diff --git a/built-in-nodes/APG.mdx b/built-in-nodes/APG.mdx
new file mode 100644
index 000000000..3e58f603d
--- /dev/null
+++ b/built-in-nodes/APG.mdx
@@ -0,0 +1,25 @@
+---
+title: "APG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the APG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "APG"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/APG/en.md)
+
+The APG (Adaptive Projected Guidance) node modifies the sampling process by adjusting how guidance is applied during diffusion. It separates the guidance vector into parallel and orthogonal components relative to the conditional output, allowing for more controlled image generation. The node provides parameters to scale the guidance, normalize its magnitude, and apply momentum for smoother transitions between diffusion steps.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | Required | - | - | The diffusion model to apply adaptive projected guidance to |
+| `eta` | FLOAT | Required | 1.0 | -10.0 to 10.0 | Controls the scale of the parallel guidance vector. Default CFG behavior at a setting of 1. |
+| `norm_threshold` | FLOAT | Required | 5.0 | 0.0 to 50.0 | Normalize guidance vector to this value, normalization disable at a setting of 0. |
+| `momentum` | FLOAT | Required | 0.0 | -5.0 to 1.0 | Controls a running average of guidance during diffusion, disabled at a setting of 0. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | Returns the modified model with adaptive projected guidance applied to its sampling process |
diff --git a/built-in-nodes/AddNoise.mdx b/built-in-nodes/AddNoise.mdx
new file mode 100644
index 000000000..8cfbea7f6
--- /dev/null
+++ b/built-in-nodes/AddNoise.mdx
@@ -0,0 +1,31 @@
+---
+title: "AddNoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AddNoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AddNoise"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddNoise/en.md)
+
+# AddNoise
+
+This node adds controlled noise to a latent image using specified noise parameters and sigma values. It processes the input through the model's sampling system to apply noise scaling appropriate for the given sigma range.
+
+## How It Works
+
+The node takes a latent image and applies noise to it based on the provided noise generator and sigma values. It first checks if there are any sigmas provided - if not, it returns the original latent image unchanged. The node then uses the model's sampling system to process the latent image and apply scaled noise. The noise scaling is determined by the difference between the first and last sigma values when multiple sigmas are provided, or by the single sigma value when only one is available. Empty latent images (containing only zeros) are not shifted during processing. The final output is a new latent representation with the applied noise, with any NaN or infinite values converted to zeros for stability.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | Required | - | - | The model containing sampling parameters and processing functions |
+| `noise` | NOISE | Required | - | - | The noise generator that produces the base noise pattern |
+| `sigmas` | SIGMAS | Required | - | - | Sigma values controlling the noise scaling intensity |
+| `latent_image` | LATENT | Required | - | - | The input latent representation to which noise will be added |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | The modified latent representation with added noise |
diff --git a/built-in-nodes/AddTextPrefix.mdx b/built-in-nodes/AddTextPrefix.mdx
new file mode 100644
index 000000000..45fd17a81
--- /dev/null
+++ b/built-in-nodes/AddTextPrefix.mdx
@@ -0,0 +1,23 @@
+---
+title: "AddTextPrefix - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AddTextPrefix node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AddTextPrefix"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextPrefix/en.md)
+
+The Add Text Prefix node modifies text by adding a specified string to the beginning of each input text. It takes the text and a prefix as input, then returns the combined result.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | Yes | | The text to which the prefix will be added. |
+| `prefix` | STRING | No | | The string to add to the beginning of the text (default: ""). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `text` | STRING | The resulting text with the prefix added to the front. |
diff --git a/built-in-nodes/AddTextSuffix.mdx b/built-in-nodes/AddTextSuffix.mdx
new file mode 100644
index 000000000..18d93db6d
--- /dev/null
+++ b/built-in-nodes/AddTextSuffix.mdx
@@ -0,0 +1,23 @@
+---
+title: "AddTextSuffix - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AddTextSuffix node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AddTextSuffix"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextSuffix/en.md)
+
+This node appends a specified suffix to the end of an input text string. It takes the original text and the suffix as inputs, then returns the combined result.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | Yes | | The original text to which the suffix will be added. |
+| `suffix` | STRING | No | | The suffix to add to the text (default: ""). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `text` | STRING | The resulting text after the suffix has been appended. |
diff --git a/built-in-nodes/AdjustBrightness.mdx b/built-in-nodes/AdjustBrightness.mdx
new file mode 100644
index 000000000..ec3e3343d
--- /dev/null
+++ b/built-in-nodes/AdjustBrightness.mdx
@@ -0,0 +1,23 @@
+---
+title: "AdjustBrightness - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AdjustBrightness node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AdjustBrightness"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustBrightness/en.md)
+
+The Adjust Brightness node modifies the brightness of an input image. It works by multiplying each pixel's value by a specified factor, then ensuring the resulting values stay within a valid range. A factor of 1.0 leaves the image unchanged, values below 1.0 make it darker, and values above 1.0 make it brighter.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to adjust. |
+| `factor` | FLOAT | No | 0.0 - 2.0 | Brightness factor. 1.0 = no change, <1.0 = darker, >1.0 = brighter. (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The output image with adjusted brightness. |
diff --git a/built-in-nodes/AdjustContrast.mdx b/built-in-nodes/AdjustContrast.mdx
new file mode 100644
index 000000000..9de77370d
--- /dev/null
+++ b/built-in-nodes/AdjustContrast.mdx
@@ -0,0 +1,23 @@
+---
+title: "AdjustContrast - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AdjustContrast node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AdjustContrast"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustContrast/en.md)
+
+The Adjust Contrast node modifies the contrast level of an input image. It works by adjusting the difference between the light and dark areas of the image. A factor of 1.0 leaves the image unchanged, values below 1.0 reduce contrast, and values above 1.0 increase it.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to have its contrast adjusted. |
+| `factor` | FLOAT | No | 0.0 - 2.0 | Contrast factor. 1.0 = no change, <1.0 = less contrast, >1.0 = more contrast. (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resulting image with adjusted contrast. |
diff --git a/built-in-nodes/AlignYourStepsScheduler.mdx b/built-in-nodes/AlignYourStepsScheduler.mdx
new file mode 100644
index 000000000..75a0cb165
--- /dev/null
+++ b/built-in-nodes/AlignYourStepsScheduler.mdx
@@ -0,0 +1,24 @@
+---
+title: "AlignYourStepsScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AlignYourStepsScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AlignYourStepsScheduler"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AlignYourStepsScheduler/en.md)
+
+The AlignYourStepsScheduler node generates sigma values for the denoising process based on different model types. It calculates appropriate noise levels for each step of the sampling process and adjusts the total number of steps according to the denoise parameter. This helps align the sampling steps with the specific requirements of different diffusion models.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model_type` | STRING | COMBO | - | SD1, SDXL, SVD | Specifies the type of model to use for sigma calculation |
+| `steps` | INT | INT | 10 | 1-10000 | The total number of sampling steps to generate |
+| `denoise` | FLOAT | FLOAT | 1.0 | 0.0-1.0 | Controls how much to denoise the image, where 1.0 uses all steps and lower values use fewer steps |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | Returns the calculated sigma values for the denoising process |
diff --git a/built-in-nodes/AudioAdjustVolume.mdx b/built-in-nodes/AudioAdjustVolume.mdx
new file mode 100644
index 000000000..c8d71106b
--- /dev/null
+++ b/built-in-nodes/AudioAdjustVolume.mdx
@@ -0,0 +1,23 @@
+---
+title: "AudioAdjustVolume - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioAdjustVolume node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioAdjustVolume"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioAdjustVolume/en.md)
+
+The AudioAdjustVolume node modifies the loudness of audio by applying volume adjustments in decibels. It takes an audio input and applies a gain factor based on the specified volume level, where positive values increase volume and negative values decrease it. The node returns the modified audio with the same sample rate as the original.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `audio` | AUDIO | required | - | - | The audio input to be processed |
+| `volume` | INT | required | 1.0 | -100 to 100 | Volume adjustment in decibels (dB). 0 = no change, +6 = double, -6 = half, etc |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The processed audio with adjusted volume level |
diff --git a/built-in-nodes/AudioConcat.mdx b/built-in-nodes/AudioConcat.mdx
new file mode 100644
index 000000000..10f872ed0
--- /dev/null
+++ b/built-in-nodes/AudioConcat.mdx
@@ -0,0 +1,24 @@
+---
+title: "AudioConcat - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioConcat node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioConcat"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioConcat/en.md)
+
+The AudioConcat node combines two audio inputs by joining them together. It takes two audio inputs and connects them in the order you specify, either placing the second audio before or after the first audio. The node automatically handles different audio formats by converting mono audio to stereo and matching sample rates between the two inputs.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `audio1` | AUDIO | required | - | - | The first audio input to be concatenated |
+| `audio2` | AUDIO | required | - | - | The second audio input to be concatenated |
+| `direction` | COMBO | required | after | ['after', 'before'] | Whether to append audio2 after or before audio1 |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | The combined audio containing both input audio files joined together |
diff --git a/built-in-nodes/AudioEncoderEncode.mdx b/built-in-nodes/AudioEncoderEncode.mdx
new file mode 100644
index 000000000..2a43bc81a
--- /dev/null
+++ b/built-in-nodes/AudioEncoderEncode.mdx
@@ -0,0 +1,23 @@
+---
+title: "AudioEncoderEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioEncoderEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioEncoderEncode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioEncoderEncode/en.md)
+
+The AudioEncoderEncode node processes audio data by encoding it using an audio encoder model. It takes audio input and converts it into an encoded representation that can be used for further processing in the conditioning pipeline. This node transforms raw audio waveforms into a format suitable for audio-based machine learning applications.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `audio_encoder` | AUDIO_ENCODER | Required | - | - | The audio encoder model used to process the audio input |
+| `audio` | AUDIO | Required | - | - | The audio data containing waveform and sample rate information |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | AUDIO_ENCODER_OUTPUT | The encoded audio representation generated by the audio encoder |
diff --git a/built-in-nodes/AudioEncoderLoader.mdx b/built-in-nodes/AudioEncoderLoader.mdx
new file mode 100644
index 000000000..d5feb06cf
--- /dev/null
+++ b/built-in-nodes/AudioEncoderLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "AudioEncoderLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioEncoderLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioEncoderLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioEncoderLoader/en.md)
+
+The AudioEncoderLoader node loads audio encoder models from your available audio encoder files. It takes an audio encoder filename as input and returns a loaded audio encoder model that can be used for audio processing tasks in your workflow.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `audio_encoder_name` | STRING | COMBO | - | Available audio encoder files | Selects which audio encoder model file to load from your audio_encoders folder |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio_encoder` | AUDIO_ENCODER | Returns the loaded audio encoder model for use in audio processing workflows |
diff --git a/built-in-nodes/AudioEqualizer3Band.mdx b/built-in-nodes/AudioEqualizer3Band.mdx
new file mode 100644
index 000000000..6938b8a2d
--- /dev/null
+++ b/built-in-nodes/AudioEqualizer3Band.mdx
@@ -0,0 +1,31 @@
+---
+title: "AudioEqualizer3Band - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioEqualizer3Band node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioEqualizer3Band"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioEqualizer3Band/en.md)
+
+The Audio Equalizer (3-Band) node allows you to adjust the bass, mid, and treble frequencies of an audio waveform. It applies three separate filters: a low shelf for bass, a peaking filter for mids, and a high shelf for treble. Each band can be independently controlled with gain, frequency, and bandwidth settings.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The input audio data containing the waveform and sample rate. |
+| `low_gain_dB` | FLOAT | No | -24.0 to 24.0 | Gain for Low frequencies (Bass). Positive values boost, negative values cut. (default: 0.0) |
+| `low_freq` | INT | No | 20 to 500 | Cutoff frequency for Low shelf filter in Hertz (Hz). (default: 100) |
+| `mid_gain_dB` | FLOAT | No | -24.0 to 24.0 | Gain for Mid frequencies. Positive values boost, negative values cut. (default: 0.0) |
+| `mid_freq` | INT | No | 200 to 4000 | Center frequency for the Mid peaking filter in Hertz (Hz). (default: 1000) |
+| `mid_q` | FLOAT | No | 0.1 to 10.0 | Q factor (bandwidth) for the Mid peaking filter. Lower values create a wider band, higher values create a narrower band. (default: 0.707) |
+| `high_gain_dB` | FLOAT | No | -24.0 to 24.0 | Gain for High frequencies (Treble). Positive values boost, negative values cut. (default: 0.0) |
+| `high_freq` | INT | No | 1000 to 15000 | Cutoff frequency for High shelf filter in Hertz (Hz). (default: 5000) |
+
+**Note:** The `low_gain_dB`, `mid_gain_dB`, and `high_gain_dB` parameters are only applied when their value is not zero. If a gain is set to 0.0, the corresponding filter stage is skipped.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The processed audio data with the equalization applied, containing the modified waveform and the original sample rate. |
diff --git a/built-in-nodes/AudioMerge.mdx b/built-in-nodes/AudioMerge.mdx
new file mode 100644
index 000000000..32293f8b4
--- /dev/null
+++ b/built-in-nodes/AudioMerge.mdx
@@ -0,0 +1,24 @@
+---
+title: "AudioMerge - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioMerge node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioMerge"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioMerge/en.md)
+
+The AudioMerge node combines two audio tracks by overlaying their waveforms. It automatically matches the sample rates of both audio inputs and adjusts their lengths to be equal before merging. The node provides several mathematical methods for combining the audio signals and ensures the output remains within acceptable volume levels.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `audio1` | AUDIO | required | - | - | First audio input to merge |
+| `audio2` | AUDIO | required | - | - | Second audio input to merge |
+| `merge_method` | COMBO | required | - | ["add", "mean", "subtract", "multiply"] | The method used to combine the audio waveforms. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | The merged audio output containing the combined waveform and sample rate |
diff --git a/built-in-nodes/AutogrowNamesTestNode.mdx b/built-in-nodes/AutogrowNamesTestNode.mdx
new file mode 100644
index 000000000..d38c68369
--- /dev/null
+++ b/built-in-nodes/AutogrowNamesTestNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "AutogrowNamesTestNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AutogrowNamesTestNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AutogrowNamesTestNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AutogrowNamesTestNode/en.md)
+
+This node is a test for the Autogrow input feature. It takes a dynamic number of float inputs, each labeled with a specific name, and combines their values into a single comma-separated string.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `autogrow` | FLOAT | Yes | N/A | A dynamic input group. You can add multiple float inputs, each with a pre-defined name from the list: "a", "b", or "c". The node will accept any combination of these named inputs. |
+
+**Note:** The `autogrow` input is dynamic. You can add or remove individual float inputs (named "a", "b", or "c") as needed for your workflow. The node processes all provided values.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | A single string containing the values from all provided float inputs, joined together with commas. |
diff --git a/built-in-nodes/AutogrowPrefixTestNode.mdx b/built-in-nodes/AutogrowPrefixTestNode.mdx
new file mode 100644
index 000000000..49d3dcaa1
--- /dev/null
+++ b/built-in-nodes/AutogrowPrefixTestNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "AutogrowPrefixTestNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AutogrowPrefixTestNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AutogrowPrefixTestNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AutogrowPrefixTestNode/en.md)
+
+The AutogrowPrefixTestNode is a logic node designed to test the autogrow input feature. It accepts a dynamic number of float inputs, combines their values into a comma-separated string, and outputs that string.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `autogrow` | AUTOGROW | Yes | 1 to 10 inputs | A dynamic input group that can accept between 1 and 10 float values. Each input in the group is a FLOAT type. |
+
+**Note:** The `autogrow` input is a special dynamic input. You can add multiple float inputs to this group, up to a maximum of 10. The node will process all provided values.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | A single string containing all the input float values, separated by commas. |
diff --git a/built-in-nodes/BasicGuider.mdx b/built-in-nodes/BasicGuider.mdx
new file mode 100644
index 000000000..56232060a
--- /dev/null
+++ b/built-in-nodes/BasicGuider.mdx
@@ -0,0 +1,23 @@
+---
+title: "BasicGuider - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BasicGuider node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BasicGuider"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BasicGuider/en.md)
+
+The BasicGuider node creates a simple guidance mechanism for the sampling process. It takes a model and conditioning data as inputs and produces a guider object that can be used to guide the generation process during sampling. This node provides the fundamental guidance functionality needed for controlled generation.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | required | - | - | The model to be used for guidance |
+| `conditioning` | CONDITIONING | required | - | - | The conditioning data that guides the generation process |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `GUIDER` | GUIDER | A guider object that can be used during the sampling process to guide generation |
diff --git a/built-in-nodes/BasicScheduler.mdx b/built-in-nodes/BasicScheduler.mdx
index ac4928595..1f837863a 100755
--- a/built-in-nodes/BasicScheduler.mdx
+++ b/built-in-nodes/BasicScheduler.mdx
@@ -1,10 +1,10 @@
 ---
 title: "BasicScheduler - ComfyUI Built-in Node Documentation"
-description: "The BasicScheduler node is used to compute a sequence of sigma values for diffusion models based on the provided scheduler, model, and denoising parameters."
+description: "Complete documentation for the BasicScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
 sidebarTitle: "BasicScheduler"
 icon: "circle"
+mode: wide
 ---
-
 The `BasicScheduler` node is designed to compute a sequence of sigma values for diffusion models based on the provided scheduler, model, and denoising parameters. It dynamically adjusts the total number of steps based on the denoise factor to fine-tune the diffusion process, providing precise "recipes" for different stages in advanced sampling processes that require fine control (such as multi-stage sampling).
 
 ## Inputs
diff --git a/built-in-nodes/BatchImagesMasksLatentsNode.mdx b/built-in-nodes/BatchImagesMasksLatentsNode.mdx
new file mode 100644
index 000000000..2b5b252f2
--- /dev/null
+++ b/built-in-nodes/BatchImagesMasksLatentsNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "BatchImagesMasksLatentsNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BatchImagesMasksLatentsNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BatchImagesMasksLatentsNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchImagesMasksLatentsNode/en.md)
+
+The Batch Images/Masks/Latents node combines multiple inputs of the same type into a single batch. It automatically detects whether the inputs are images, masks, or latent representations and uses the appropriate batching method. This is useful for preparing multiple items for processing by nodes that accept batched inputs.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `inputs` | IMAGE, MASK, or LATENT | Yes | 1 to 50 inputs | A dynamic list of inputs to be combined into a batch. You can add between 1 and 50 items. All items must be of the same type (all images, all masks, or all latents). |
+
+**Note:** The node automatically determines the data type (IMAGE, MASK, or LATENT) based on the first item in the `inputs` list. All subsequent items must match this type. The node will fail if you try to mix different data types.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE, MASK, or LATENT | A single batched output. The data type matches the input type (batched IMAGE, batched MASK, or batched LATENT). |
diff --git a/built-in-nodes/BatchImagesNode.mdx b/built-in-nodes/BatchImagesNode.mdx
new file mode 100644
index 000000000..13cdf1b5b
--- /dev/null
+++ b/built-in-nodes/BatchImagesNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "BatchImagesNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BatchImagesNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BatchImagesNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchImagesNode/en.md)
+
+The Batch Images node combines multiple individual images into a single batch. It takes a variable number of image inputs and outputs them as one batched image tensor, allowing them to be processed together in subsequent nodes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | 2 to 50 inputs | A dynamic list of image inputs. You can add between 2 and 50 images to be combined into a batch. The node interface allows you to add more image input slots as needed. |
+
+**Note:** You must connect at least two images for the node to function. The first input slot is always required, and you can add more using the "+" button that appears in the node interface.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | A single batched image tensor containing all the input images stacked together. |
diff --git a/built-in-nodes/BatchLatentsNode.mdx b/built-in-nodes/BatchLatentsNode.mdx
new file mode 100644
index 000000000..88e5a6c23
--- /dev/null
+++ b/built-in-nodes/BatchLatentsNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "BatchLatentsNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BatchLatentsNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BatchLatentsNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchLatentsNode/en.md)
+
+The Batch Latents node combines multiple latent inputs into a single batch. It takes a variable number of latent samples and merges them along the batch dimension, allowing them to be processed together in subsequent nodes. This is useful for generating or processing multiple images in a single operation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `latents` | LATENT | Yes | N/A | The first latent sample to be included in the batch. |
+| `latent_2` to `latent_50` | LATENT | No | N/A | Additional latent samples to be included in the batch. You can add between 2 and 50 latent inputs in total. |
+
+**Note:** You must provide at least two latent inputs for the node to function. The node will automatically create input slots as you connect more latents, up to a maximum of 50.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | LATENT | A single latent output containing all the input latents combined into one batch. |
diff --git a/built-in-nodes/BatchMasksNode.mdx b/built-in-nodes/BatchMasksNode.mdx
new file mode 100644
index 000000000..e5fb92a47
--- /dev/null
+++ b/built-in-nodes/BatchMasksNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "BatchMasksNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BatchMasksNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BatchMasksNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchMasksNode/en.md)
+
+The Batch Masks node combines multiple individual mask inputs into a single batch. It takes a variable number of mask inputs and outputs them as a single batched mask tensor, allowing for batch processing of masks in subsequent nodes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `mask_0` | MASK | Yes | - | The first mask input. |
+| `mask_1` | MASK | Yes | - | The second mask input. |
+| `mask_2` to `mask_49` | MASK | No | - | Additional optional mask inputs. The node can accept a minimum of 2 and a maximum of 50 masks in total. |
+
+**Note:** This node uses an autogrow input template. You must connect at least two masks (`mask_0` and `mask_1`). You can add up to 48 more optional mask inputs (`mask_2` through `mask_49`) for a total of 50 masks. All connected masks will be combined into a single batch.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | MASK | A single batched mask containing all the input masks stacked together. |
diff --git a/built-in-nodes/BetaSamplingScheduler.mdx b/built-in-nodes/BetaSamplingScheduler.mdx
new file mode 100644
index 000000000..b112702c8
--- /dev/null
+++ b/built-in-nodes/BetaSamplingScheduler.mdx
@@ -0,0 +1,25 @@
+---
+title: "BetaSamplingScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BetaSamplingScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BetaSamplingScheduler"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BetaSamplingScheduler/en.md)
+
+The BetaSamplingScheduler node generates a sequence of noise levels (sigmas) for the sampling process using a beta scheduling algorithm. It takes a model and configuration parameters to create a customized noise schedule that controls the denoising process during image generation. This scheduler allows fine-tuning of the noise reduction trajectory through alpha and beta parameters.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | Required | - | - | The model used for sampling, which provides the model sampling object |
+| `steps` | INT | Required | 20 | 1-10000 | The number of sampling steps to generate sigmas for |
+| `alpha` | FLOAT | Required | 0.6 | 0.0-50.0 | Alpha parameter for the beta scheduler, controlling the scheduling curve |
+| `beta` | FLOAT | Required | 0.6 | 0.0-50.0 | Beta parameter for the beta scheduler, controlling the scheduling curve |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `SIGMAS` | SIGMAS | A sequence of noise levels (sigmas) used for the sampling process |
diff --git a/built-in-nodes/BriaImageEditNode.mdx b/built-in-nodes/BriaImageEditNode.mdx
new file mode 100644
index 000000000..98ee5ff60
--- /dev/null
+++ b/built-in-nodes/BriaImageEditNode.mdx
@@ -0,0 +1,38 @@
+---
+title: "BriaImageEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BriaImageEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BriaImageEditNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaImageEditNode/en.md)
+
+The Bria FIBO Image Edit node allows you to modify an existing image using a text instruction. It sends the image and your prompt to the Bria API, which uses the FIBO model to generate a new, edited version of the image based on your request. You can also provide a mask to limit the edits to a specific area.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"FIBO"` | The model version to use for image editing. |
+| `image` | IMAGE | Yes | - | The input image you want to edit. |
+| `prompt` | STRING | No | - | The text instruction describing how to edit the image (default: empty). |
+| `negative_prompt` | STRING | No | - | Text describing what you do not want to appear in the edited image (default: empty). |
+| `structured_prompt` | STRING | No | - | A string containing the structured edit prompt in JSON format. Use this instead of the usual prompt for precise, programmatic control (default: empty). |
+| `seed` | INT | Yes | 1 to 2147483647 | A number used to initialize the random generation, ensuring reproducible results (default: 1). |
+| `guidance_scale` | FLOAT | Yes | 3.0 to 5.0 | Controls how closely the generated image follows the prompt. A higher value results in stronger adherence (default: 3.0). |
+| `steps` | INT | Yes | 20 to 50 | The number of denoising steps the model will perform (default: 50). |
+| `moderation` | DYNAMICCOMBO | Yes | `"true"`<br />`"false"` | Enables or disables content moderation. Selecting `"true"` reveals additional moderation options. |
+| `mask` | MASK | No | - | An optional mask image. If provided, edits will only be applied to the masked areas of the image. |
+
+**Important Constraints:**
+
+* You must provide at least one of the `prompt` or `structured_prompt` inputs. They cannot both be empty.
+* Exactly one input `image` is required.
+* When the `moderation` parameter is set to `"true"`, three additional boolean inputs become available: `prompt_content_moderation`, `visual_input_moderation`, and `visual_output_moderation`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The edited image returned by the Bria API. |
+| `structured_prompt` | STRING | The structured prompt that was used or generated during the editing process. |
diff --git a/built-in-nodes/BriaRemoveImageBackground.mdx b/built-in-nodes/BriaRemoveImageBackground.mdx
new file mode 100644
index 000000000..6c4129f94
--- /dev/null
+++ b/built-in-nodes/BriaRemoveImageBackground.mdx
@@ -0,0 +1,28 @@
+---
+title: "BriaRemoveImageBackground - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BriaRemoveImageBackground node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BriaRemoveImageBackground"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaRemoveImageBackground/en.md)
+
+This node removes the background from an image using the Bria RMBG 2.0 service. It sends the image to an external API for processing and returns the result with the background removed.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image from which the background will be removed. |
+| `moderation` | COMBO | No | `"false"`<br />`"true"` | Moderation settings. When set to `"true"`, additional moderation options become available. |
+| `visual_input_moderation` | BOOLEAN | No | - | Enables visual content moderation on the input image. This parameter is only available when `moderation` is set to `"true"`. Default: `False`. |
+| `visual_output_moderation` | BOOLEAN | No | - | Enables visual content moderation on the output image. This parameter is only available when `moderation` is set to `"true"`. Default: `True`. |
+| `seed` | INT | No | 0 to 2147483647 | A seed value that controls whether the node should re-run. The results are non-deterministic regardless of the seed value. Default: `0`. |
+
+**Note:** The `visual_input_moderation` and `visual_output_moderation` parameters are dependent on the `moderation` parameter. They are only active and required if `moderation` is set to `"true"`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The processed image with its background removed. |
diff --git a/built-in-nodes/BriaRemoveVideoBackground.mdx b/built-in-nodes/BriaRemoveVideoBackground.mdx
new file mode 100644
index 000000000..140fbcc31
--- /dev/null
+++ b/built-in-nodes/BriaRemoveVideoBackground.mdx
@@ -0,0 +1,26 @@
+---
+title: "BriaRemoveVideoBackground - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BriaRemoveVideoBackground node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BriaRemoveVideoBackground"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaRemoveVideoBackground/en.md)
+
+This node removes the background from a video using the Bria AI service. It processes the input video and replaces the original background with a solid color of your choice. The operation is performed via an external API, and the result is returned as a new video file.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | N/A | The input video file from which the background will be removed. |
+| `background_color` | STRING | Yes | `"Black"`<br />`"White"`<br />`"Gray"`<br />`"Red"`<br />`"Green"`<br />`"Blue"`<br />`"Yellow"`<br />`"Cyan"`<br />`"Magenta"`<br />`"Orange"` | The solid color to use as the new background for the output video. |
+| `seed` | INT | No | 0 to 2147483647 | A seed value that controls whether the node should re-run. The results are non-deterministic regardless of the seed value. (default: 0) |
+
+**Note:** The input video must have a duration of 60 seconds or less.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The processed video file with the background removed and replaced by the selected color. |
diff --git a/built-in-nodes/ByteDanceFirstLastFrameNode.mdx b/built-in-nodes/ByteDanceFirstLastFrameNode.mdx
new file mode 100644
index 000000000..6cd117f0e
--- /dev/null
+++ b/built-in-nodes/ByteDanceFirstLastFrameNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "ByteDanceFirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceFirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceFirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceFirstLastFrameNode/en.md)
+
+This node generates a video using a text prompt along with first and last frame images. It takes your description and the two key frames to create a complete video sequence that transitions between them. The node provides various options to control the video's resolution, aspect ratio, duration, and other generation parameters.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | COMBO | combo | seedance_1_lite | seedance_1_lite | Model name |
+| `prompt` | STRING | string | - | - | The text prompt used to generate the video. |
+| `first_frame` | IMAGE | image | - | - | First frame to be used for the video. |
+| `last_frame` | IMAGE | image | - | - | Last frame to be used for the video. |
+| `resolution` | COMBO | combo | - | 480p, 720p, 1080p | The resolution of the output video. |
+| `aspect_ratio` | COMBO | combo | - | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | The aspect ratio of the output video. |
+| `duration` | INT | slider | 5 | 3-12 | The duration of the output video in seconds. |
+| `seed` | INT | number | 0 | 0-2147483647 | Seed to use for generation. (optional) |
+| `camera_fixed` | BOOLEAN | boolean | False | - | Specifies whether to fix the camera. The platform appends an instruction to fix the camera to your prompt, but does not guarantee the actual effect. (optional) |
+| `watermark` | BOOLEAN | boolean | True | - | Whether to add an "AI generated" watermark to the video. (optional) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/ByteDanceImageEditNode.mdx b/built-in-nodes/ByteDanceImageEditNode.mdx
new file mode 100644
index 000000000..e4bbe8021
--- /dev/null
+++ b/built-in-nodes/ByteDanceImageEditNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "ByteDanceImageEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceImageEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceImageEditNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageEditNode/en.md)
+
+The ByteDance Image Edit node allows you to modify images using ByteDance's AI models through an API. You provide an input image and a text prompt describing the desired changes, and the node processes the image according to your instructions. The node handles the API communication automatically and returns the edited image.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | COMBO | seededit_3 | Image2ImageModelName options | Model name |
+| `image` | IMAGE | IMAGE | - | - | The base image to edit |
+| `prompt` | STRING | STRING | "" | - | Instruction to edit image |
+| `seed` | INT | INT | 0 | 0-2147483647 | Seed to use for generation |
+| `guidance_scale` | FLOAT | FLOAT | 5.5 | 1.0-10.0 | Higher value makes the image follow the prompt more closely |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | Whether to add an "AI generated" watermark to the image |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The edited image returned from the ByteDance API |
diff --git a/built-in-nodes/ByteDanceImageNode.mdx b/built-in-nodes/ByteDanceImageNode.mdx
new file mode 100644
index 000000000..f661cbe90
--- /dev/null
+++ b/built-in-nodes/ByteDanceImageNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "ByteDanceImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageNode/en.md)
+
+The ByteDance Image node generates images using ByteDance models through an API based on text prompts. It allows you to select different models, specify image dimensions, and control various generation parameters like seed and guidance scale. The node connects to ByteDance's image generation service and returns the created image.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | COMBO | seedream_3 | Text2ImageModelName options | Model name |
+| `prompt` | STRING | STRING | - | - | The text prompt used to generate the image |
+| `size_preset` | STRING | COMBO | - | RECOMMENDED_PRESETS labels | Pick a recommended size. Select Custom to use the width and height below |
+| `width` | INT | INT | 1024 | 512-2048 (step 64) | Custom width for image. Value is working only if `size_preset` is set to `Custom` |
+| `height` | INT | INT | 1024 | 512-2048 (step 64) | Custom height for image. Value is working only if `size_preset` is set to `Custom` |
+| `seed` | INT | INT | 0 | 0-2147483647 (step 1) | Seed to use for generation (optional) |
+| `guidance_scale` | FLOAT | FLOAT | 2.5 | 1.0-10.0 (step 0.01) | Higher value makes the image follow the prompt more closely (optional) |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | Whether to add an "AI generated" watermark to the image (optional) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The generated image from the ByteDance API |
diff --git a/built-in-nodes/ByteDanceImageReferenceNode.mdx b/built-in-nodes/ByteDanceImageReferenceNode.mdx
new file mode 100644
index 000000000..676bf29d1
--- /dev/null
+++ b/built-in-nodes/ByteDanceImageReferenceNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "ByteDanceImageReferenceNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceImageReferenceNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceImageReferenceNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageReferenceNode/en.md)
+
+The ByteDance Image Reference Node generates videos using a text prompt and one to four reference images. It sends the images and prompt to an external API service that creates a video matching your description while incorporating the visual style and content from your reference images. The node provides various controls for video resolution, aspect ratio, duration, and other generation parameters.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | COMBO | seedance_1_lite | seedance_1_lite | Model name |
+| `prompt` | STRING | STRING | - | - | The text prompt used to generate the video. |
+| `images` | IMAGE | IMAGE | - | - | One to four images. |
+| `resolution` | STRING | COMBO | - | 480p, 720p | The resolution of the output video. |
+| `aspect_ratio` | STRING | COMBO | - | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | The aspect ratio of the output video. |
+| `duration` | INT | INT | 5 | 3-12 | The duration of the output video in seconds. |
+| `seed` | INT | INT | 0 | 0-2147483647 | Seed to use for generation. |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | Whether to add an "AI generated" watermark to the video. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file based on the input prompt and reference images. |
diff --git a/built-in-nodes/ByteDanceImageToVideoNode.mdx b/built-in-nodes/ByteDanceImageToVideoNode.mdx
new file mode 100644
index 000000000..6364246a9
--- /dev/null
+++ b/built-in-nodes/ByteDanceImageToVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "ByteDanceImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageToVideoNode/en.md)
+
+The ByteDance Image to Video node generates videos using ByteDance models through an API based on an input image and text prompt. It takes a starting image frame and creates a video sequence that follows the provided description. The node offers various customization options for video resolution, aspect ratio, duration, and other generation parameters.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | STRING | COMBO | seedance_1_pro | Image2VideoModelName options | Model name |
+| `prompt` | STRING | STRING | - | - | The text prompt used to generate the video. |
+| `image` | IMAGE | IMAGE | - | - | First frame to be used for the video. |
+| `resolution` | STRING | COMBO | - | ["480p", "720p", "1080p"] | The resolution of the output video. |
+| `aspect_ratio` | STRING | COMBO | - | ["adaptive", "16:9", "4:3", "1:1", "3:4", "9:16", "21:9"] | The aspect ratio of the output video. |
+| `duration` | INT | INT | 5 | 3-12 | The duration of the output video in seconds. |
+| `seed` | INT | INT | 0 | 0-2147483647 | Seed to use for generation. |
+| `camera_fixed` | BOOLEAN | BOOLEAN | False | - | Specifies whether to fix the camera. The platform appends an instruction to fix the camera to your prompt, but does not guarantee the actual effect. |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | Whether to add an "AI generated" watermark to the video. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file based on the input image and prompt parameters. |
diff --git a/built-in-nodes/ByteDanceSeedreamNode.mdx b/built-in-nodes/ByteDanceSeedreamNode.mdx
new file mode 100644
index 000000000..81046383e
--- /dev/null
+++ b/built-in-nodes/ByteDanceSeedreamNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "ByteDanceSeedreamNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceSeedreamNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceSeedreamNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedreamNode/en.md)
+
+The ByteDance Seedream 4 node provides unified text-to-image generation and precise single-sentence editing capabilities at up to 4K resolution. It can create new images from text prompts or edit existing images using text instructions. The node supports both single image generation and sequential generation of multiple related images.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | COMBO | "seedream-4-0-250828" | ["seedream-4-0-250828"] | Model name |
+| `prompt` | STRING | STRING | "" | - | Text prompt for creating or editing an image. |
+| `image` | IMAGE | IMAGE | - | - | Input image(s) for image-to-image generation. List of 1-10 images for single or multi-reference generation. |
+| `size_preset` | STRING | COMBO | First preset from RECOMMENDED_PRESETS_SEEDREAM_4 | All labels from RECOMMENDED_PRESETS_SEEDREAM_4 | Pick a recommended size. Select Custom to use the width and height below. |
+| `width` | INT | INT | 2048 | 1024-4096 (step 64) | Custom width for image. Value is working only if `size_preset` is set to `Custom` |
+| `height` | INT | INT | 2048 | 1024-4096 (step 64) | Custom height for image. Value is working only if `size_preset` is set to `Custom` |
+| `sequential_image_generation` | STRING | COMBO | "disabled" | ["disabled", "auto"] | Group image generation mode. 'disabled' generates a single image. 'auto' lets the model decide whether to generate multiple related images (e.g., story scenes, character variations). |
+| `max_images` | INT | INT | 1 | 1-15 | Maximum number of images to generate when sequential_image_generation='auto'. Total images (input + generated) cannot exceed 15. |
+| `seed` | INT | INT | 0 | 0-2147483647 | Seed to use for generation. |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | Whether to add an "AI generated" watermark to the image. |
+| `fail_on_partial` | BOOLEAN | BOOLEAN | True | - | If enabled, abort execution if any requested images are missing or return an error. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | Generated image(s) based on the input parameters and prompt |
diff --git a/built-in-nodes/ByteDanceTextToVideoNode.mdx b/built-in-nodes/ByteDanceTextToVideoNode.mdx
new file mode 100644
index 000000000..050483ed3
--- /dev/null
+++ b/built-in-nodes/ByteDanceTextToVideoNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "ByteDanceTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceTextToVideoNode/en.md)
+
+The ByteDance Text to Video node generates videos using ByteDance models through an API based on text prompts. It takes a text description and various video settings as input, then creates a video that matches the provided specifications. The node handles the API communication and returns the generated video as output.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | STRING | Combo | seedance_1_pro | Text2VideoModelName options | Model name |
+| `prompt` | STRING | String | - | - | The text prompt used to generate the video. |
+| `resolution` | STRING | Combo | - | ["480p", "720p", "1080p"] | The resolution of the output video. |
+| `aspect_ratio` | STRING | Combo | - | ["16:9", "4:3", "1:1", "3:4", "9:16", "21:9"] | The aspect ratio of the output video. |
+| `duration` | INT | Int | 5 | 3-12 | The duration of the output video in seconds. |
+| `seed` | INT | Int | 0 | 0-2147483647 | Seed to use for generation. (Optional) |
+| `camera_fixed` | BOOLEAN | Boolean | False | - | Specifies whether to fix the camera. The platform appends an instruction to fix the camera to your prompt, but does not guarantee the actual effect. (Optional) |
+| `watermark` | BOOLEAN | Boolean | True | - | Whether to add an "AI generated" watermark to the video. (Optional) |
+
+**Parameter Constraints:**
+
+- The `prompt` parameter must contain at least 1 character after whitespace removal
+- The `prompt` parameter cannot contain the following text parameters: "resolution", "ratio", "duration", "seed", "camerafixed", "watermark"
+- The `duration` parameter is limited to values between 3 and 12 seconds
+- The `seed` parameter accepts values from 0 to 2,147,483,647
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/CFGGuider.mdx b/built-in-nodes/CFGGuider.mdx
new file mode 100644
index 000000000..5812b726d
--- /dev/null
+++ b/built-in-nodes/CFGGuider.mdx
@@ -0,0 +1,25 @@
+---
+title: "CFGGuider - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CFGGuider node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CFGGuider"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGGuider/en.md)
+
+The CFGGuider node creates a guidance system for controlling the sampling process in image generation. It takes a model along with positive and negative conditioning inputs, then applies a classifier-free guidance scale to steer the generation toward desired content while avoiding unwanted elements. This node outputs a guider object that can be used by sampling nodes to control the image generation direction.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | Required | - | - | The model to be used for guidance |
+| `positive` | CONDITIONING | Required | - | - | The positive conditioning that guides the generation toward desired content |
+| `negative` | CONDITIONING | Required | - | - | The negative conditioning that steers the generation away from unwanted content |
+| `cfg` | FLOAT | Required | 8.0 | 0.0 - 100.0 | The classifier-free guidance scale that controls how strongly the conditioning influences the generation |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `GUIDER` | GUIDER | A guider object that can be passed to sampling nodes to control the generation process |
diff --git a/built-in-nodes/CFGNorm.mdx b/built-in-nodes/CFGNorm.mdx
new file mode 100644
index 000000000..24daa28c5
--- /dev/null
+++ b/built-in-nodes/CFGNorm.mdx
@@ -0,0 +1,23 @@
+---
+title: "CFGNorm - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CFGNorm node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CFGNorm"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGNorm/en.md)
+
+The CFGNorm node applies a normalization technique to the classifier-free guidance (CFG) process in diffusion models. It adjusts the scale of the denoised prediction by comparing the norms of the conditional and unconditional outputs, then applies a strength multiplier to control the effect. This helps stabilize the generation process by preventing extreme values in the guidance scaling.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | required | - | - | The diffusion model to apply CFG normalization to |
+| `strength` | FLOAT | required | 1.0 | 0.0 - 100.0 | Controls the intensity of the normalization effect applied to the CFG scaling |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | Returns the modified model with CFG normalization applied to its sampling process |
diff --git a/built-in-nodes/CFGZeroStar.mdx b/built-in-nodes/CFGZeroStar.mdx
new file mode 100644
index 000000000..be36c0077
--- /dev/null
+++ b/built-in-nodes/CFGZeroStar.mdx
@@ -0,0 +1,22 @@
+---
+title: "CFGZeroStar - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CFGZeroStar node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CFGZeroStar"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGZeroStar/en.md)
+
+The CFGZeroStar node applies a specialized guidance scaling technique to diffusion models. It modifies the classifier-free guidance process by calculating an optimized scale factor based on the difference between conditional and unconditional predictions. This approach adjusts the final output to provide enhanced control over the generation process while maintaining model stability.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | required | - | - | The diffusion model to be modified with the CFGZeroStar guidance scaling technique |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | The modified model with CFGZeroStar guidance scaling applied |
diff --git a/built-in-nodes/CLIPAdd.mdx b/built-in-nodes/CLIPAdd.mdx
new file mode 100644
index 000000000..834c61de5
--- /dev/null
+++ b/built-in-nodes/CLIPAdd.mdx
@@ -0,0 +1,23 @@
+---
+title: "CLIPAdd - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPAdd node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPAdd"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPAdd/en.md)
+
+The CLIPAdd node combines two CLIP models by merging their key patches. It creates a copy of the first CLIP model and then adds most of the key patches from the second model, excluding position IDs and logit scale parameters. This allows you to blend features from different CLIP models while preserving the structure of the first model.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip1` | CLIP | Required | - | - | The primary CLIP model that will be used as the base for merging |
+| `clip2` | CLIP | Required | - | - | The secondary CLIP model that provides additional patches to be added |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | Returns a merged CLIP model combining features from both input models |
diff --git a/built-in-nodes/CLIPAttentionMultiply.mdx b/built-in-nodes/CLIPAttentionMultiply.mdx
new file mode 100644
index 000000000..448610855
--- /dev/null
+++ b/built-in-nodes/CLIPAttentionMultiply.mdx
@@ -0,0 +1,26 @@
+---
+title: "CLIPAttentionMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPAttentionMultiply"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPAttentionMultiply/en.md)
+
+The CLIPAttentionMultiply node allows you to adjust the attention mechanism in CLIP models by applying multiplication factors to different components of the self-attention layers. It works by modifying the query, key, value, and output projection weights and biases in the CLIP model's attention mechanism. This experimental node creates a modified copy of the input CLIP model with the specified scaling factors applied.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip` | CLIP | required | - | - | The CLIP model to modify |
+| `q` | FLOAT | required | 1.0 | 0.0 - 10.0 | Multiplication factor for query projection weights and biases |
+| `k` | FLOAT | required | 1.0 | 0.0 - 10.0 | Multiplication factor for key projection weights and biases |
+| `v` | FLOAT | required | 1.0 | 0.0 - 10.0 | Multiplication factor for value projection weights and biases |
+| `out` | FLOAT | required | 1.0 | 0.0 - 10.0 | Multiplication factor for output projection weights and biases |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | Returns a modified CLIP model with the specified attention scaling factors applied |
diff --git a/built-in-nodes/CLIPMergeAdd.mdx b/built-in-nodes/CLIPMergeAdd.mdx
new file mode 100644
index 000000000..7f685e6c1
--- /dev/null
+++ b/built-in-nodes/CLIPMergeAdd.mdx
@@ -0,0 +1,23 @@
+---
+title: "CLIPMergeAdd - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPMergeAdd node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPMergeAdd"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPMergeAdd/en.md)
+
+The CLIPMergeAdd node combines two CLIP models by adding patches from the second model to the first model. It creates a copy of the first CLIP model and selectively incorporates key patches from the second model, excluding position IDs and logit scale parameters. This allows you to merge CLIP model components while preserving the structure of the base model.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip1` | CLIP | Yes | - | The base CLIP model that will be cloned and used as the foundation for merging |
+| `clip2` | CLIP | Yes | - | The secondary CLIP model that provides key patches to be added to the base model |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | A merged CLIP model containing the base model structure with added patches from the secondary model |
diff --git a/built-in-nodes/CLIPMergeSubtract.mdx b/built-in-nodes/CLIPMergeSubtract.mdx
new file mode 100644
index 000000000..a885eb6c5
--- /dev/null
+++ b/built-in-nodes/CLIPMergeSubtract.mdx
@@ -0,0 +1,26 @@
+---
+title: "CLIPMergeSubtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPMergeSubtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPMergeSubtract"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPMergeSubtract/en.md)
+
+The CLIPMergeSubtract node performs model merging by subtracting the weights of one CLIP model from another. It creates a new CLIP model by cloning the first model and then subtracting the key patches from the second model, with an adjustable multiplier to control the subtraction strength. This allows for fine-tuned model blending by removing specific characteristics from the base model.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip1` | CLIP | Yes | - | The base CLIP model that will be cloned and modified |
+| `clip2` | CLIP | Yes | - | The CLIP model whose key patches will be subtracted from the base model |
+| `multiplier` | FLOAT | Yes | -10.0 to 10.0 | Controls the strength of the subtraction operation (default: 1.0) |
+
+**Note:** The node excludes `.position_ids` and `.logit_scale` parameters from the subtraction operation, regardless of the multiplier value.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `clip` | CLIP | The resulting CLIP model after subtracting the second model's weights from the first |
diff --git a/built-in-nodes/CLIPSubtract.mdx b/built-in-nodes/CLIPSubtract.mdx
new file mode 100644
index 000000000..45f2f7275
--- /dev/null
+++ b/built-in-nodes/CLIPSubtract.mdx
@@ -0,0 +1,24 @@
+---
+title: "CLIPSubtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPSubtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPSubtract"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPSubtract/en.md)
+
+The CLIPSubtract node performs a subtraction operation between two CLIP models. It takes the first CLIP model as a base and subtracts the key patches from the second CLIP model, with an optional multiplier to control the subtraction strength. This allows for fine-tuned model blending by removing specific characteristics from one model using another.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip1` | CLIP | Required | - | - | The base CLIP model that will be modified |
+| `clip2` | CLIP | Required | - | - | The CLIP model whose key patches will be subtracted from the base model |
+| `multiplier` | FLOAT | Required | 1.0 | -10.0 to 10.0, step 0.01 | Controls the strength of the subtraction operation |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | The resulting CLIP model after the subtraction operation |
diff --git a/built-in-nodes/CLIPTextEncodeControlnet.mdx b/built-in-nodes/CLIPTextEncodeControlnet.mdx
new file mode 100644
index 000000000..cd5328fc5
--- /dev/null
+++ b/built-in-nodes/CLIPTextEncodeControlnet.mdx
@@ -0,0 +1,26 @@
+---
+title: "CLIPTextEncodeControlnet - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeControlnet node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeControlnet"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeControlnet/en.md)
+
+The CLIPTextEncodeControlnet node processes text input using a CLIP model and combines it with existing conditioning data to create enhanced conditioning output for controlnet applications. It tokenizes the input text, encodes it through the CLIP model, and adds the resulting embeddings to the provided conditioning data as cross-attention controlnet parameters.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip` | CLIP | Required | - | - | The CLIP model used for text tokenization and encoding |
+| `conditioning` | CONDITIONING | Required | - | - | Existing conditioning data to be enhanced with controlnet parameters |
+| `text` | STRING | Multiline, Dynamic Prompts | - | - | Text input to be processed by the CLIP model |
+
+**Note:** This node requires both `clip` and `conditioning` inputs to function properly. The `text` input supports dynamic prompts and multiline text for flexible text processing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | Enhanced conditioning data with added controlnet cross-attention parameters |
diff --git a/built-in-nodes/CLIPTextEncodeHiDream.mdx b/built-in-nodes/CLIPTextEncodeHiDream.mdx
new file mode 100644
index 000000000..d2473725c
--- /dev/null
+++ b/built-in-nodes/CLIPTextEncodeHiDream.mdx
@@ -0,0 +1,28 @@
+---
+title: "CLIPTextEncodeHiDream - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeHiDream node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeHiDream"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeHiDream/en.md)
+
+The CLIPTextEncodeHiDream node processes multiple text inputs using different language models and combines them into a single conditioning output. It tokenizes text from four different sources (CLIP-L, CLIP-G, T5-XXL, and LLaMA) and encodes them using a scheduled encoding approach. This allows for more sophisticated text conditioning by leveraging multiple language models simultaneously.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip` | CLIP | Required Input | - | - | The CLIP model used for tokenization and encoding |
+| `clip_l` | STRING | Multiline Text | - | - | Text input for CLIP-L model processing |
+| `clip_g` | STRING | Multiline Text | - | - | Text input for CLIP-G model processing |
+| `t5xxl` | STRING | Multiline Text | - | - | Text input for T5-XXL model processing |
+| `llama` | STRING | Multiline Text | - | - | Text input for LLaMA model processing |
+
+**Note:** All text inputs support dynamic prompts and multiline text entry. The node requires all four text parameters to be provided for proper functioning, as each contributes to the final conditioning output through the scheduled encoding process.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The combined conditioning output from all processed text inputs |
diff --git a/built-in-nodes/CLIPTextEncodeKandinsky5.mdx b/built-in-nodes/CLIPTextEncodeKandinsky5.mdx
new file mode 100644
index 000000000..254a85fec
--- /dev/null
+++ b/built-in-nodes/CLIPTextEncodeKandinsky5.mdx
@@ -0,0 +1,24 @@
+---
+title: "CLIPTextEncodeKandinsky5 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeKandinsky5 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeKandinsky5"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeKandinsky5/en.md)
+
+The CLIPTextEncodeKandinsky5 node prepares text prompts for use with the Kandinsky 5 model. It takes two separate text inputs, tokenizes them using a provided CLIP model, and combines them into a single conditioning output. This output is used to guide the image generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | | The CLIP model used to tokenize and encode the text prompts. |
+| `clip_l` | STRING | Yes | | The primary text prompt. This input supports multiline text and dynamic prompts. |
+| `qwen25_7b` | STRING | Yes | | A secondary text prompt. This input supports multiline text and dynamic prompts. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The combined conditioning data generated from both text prompts, ready to be fed into a Kandinsky 5 model for image generation. |
diff --git a/built-in-nodes/CLIPTextEncodeLumina2.mdx b/built-in-nodes/CLIPTextEncodeLumina2.mdx
new file mode 100644
index 000000000..18a1bbea7
--- /dev/null
+++ b/built-in-nodes/CLIPTextEncodeLumina2.mdx
@@ -0,0 +1,26 @@
+---
+title: "CLIPTextEncodeLumina2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeLumina2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeLumina2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeLumina2/en.md)
+
+The CLIP Text Encode for Lumina2 node encodes a system prompt and a user prompt using a CLIP model into an embedding that can guide the diffusion model to generate specific images. It combines a pre-defined system prompt with your custom text prompt and processes them through the CLIP model to create conditioning data for image generation.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `system_prompt` | STRING | COMBO | - | "superior", "alignment" | Lumina2 provide two types of system prompts: Superior: You are an assistant designed to generate superior images with the superior degree of image-text alignment based on textual prompts or user prompts. Alignment: You are an assistant designed to generate high-quality images with the highest degree of image-text alignment based on textual prompts. |
+| `user_prompt` | STRING | STRING | - | - | The text to be encoded. |
+| `clip` | CLIP | CLIP | - | - | The CLIP model used for encoding the text. |
+
+**Note:** The `clip` input is required and cannot be None. If the clip input is invalid, the node will raise an error indicating that the checkpoint may not contain a valid CLIP or text encoder model.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | A conditioning containing the embedded text used to guide the diffusion model. |
diff --git a/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx b/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx
new file mode 100644
index 000000000..28846f442
--- /dev/null
+++ b/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx
@@ -0,0 +1,25 @@
+---
+title: "CLIPTextEncodePixArtAlpha - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodePixArtAlpha node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodePixArtAlpha"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodePixArtAlpha/en.md)
+
+Encodes text and sets the resolution conditioning for PixArt Alpha. This node processes text input and adds width and height information to create conditioning data specifically for PixArt Alpha models. It does not apply to PixArt Sigma models.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `width` | INT | Input | 1024 | 0 to MAX_RESOLUTION | The width dimension for resolution conditioning |
+| `height` | INT | Input | 1024 | 0 to MAX_RESOLUTION | The height dimension for resolution conditioning |
+| `text` | STRING | Input | - | - | Text input to be encoded, supports multiline input and dynamic prompts |
+| `clip` | CLIP | Input | - | - | CLIP model used for tokenization and encoding |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | Encoded conditioning data with text tokens and resolution information |
diff --git a/built-in-nodes/CLIPTextEncodeSD3.mdx b/built-in-nodes/CLIPTextEncodeSD3.mdx
new file mode 100644
index 000000000..0ab57099f
--- /dev/null
+++ b/built-in-nodes/CLIPTextEncodeSD3.mdx
@@ -0,0 +1,32 @@
+---
+title: "CLIPTextEncodeSD3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeSD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeSD3"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeSD3/en.md)
+
+The CLIPTextEncodeSD3 node processes text inputs for Stable Diffusion 3 models by encoding multiple text prompts using different CLIP models. It handles three separate text inputs (clip_g, clip_l, and t5xxl) and provides options for managing empty text padding. The node ensures proper token alignment between different text inputs and returns conditioning data suitable for SD3 generation pipelines.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip` | CLIP | Required | - | - | The CLIP model used for text encoding |
+| `clip_l` | STRING | Multiline, Dynamic Prompts | - | - | Text input for the local CLIP model |
+| `clip_g` | STRING | Multiline, Dynamic Prompts | - | - | Text input for the global CLIP model |
+| `t5xxl` | STRING | Multiline, Dynamic Prompts | - | - | Text input for the T5-XXL model |
+| `empty_padding` | COMBO | Selection | - | ["none", "empty_prompt"] | Controls how empty text inputs are handled |
+
+**Parameter Constraints:**
+
+- When `empty_padding` is set to "none", empty text inputs for `clip_g`, `clip_l`, or `t5xxl` will result in empty token lists instead of padding
+- The node automatically balances token lengths between `clip_l` and `clip_g` inputs by padding the shorter one with empty tokens when lengths differ
+- All text inputs support dynamic prompts and multiline text entry
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The encoded text conditioning data ready for use in SD3 generation pipelines |
diff --git a/built-in-nodes/Canny.mdx b/built-in-nodes/Canny.mdx
index 86153878d..6fcf9877f 100755
--- a/built-in-nodes/Canny.mdx
+++ b/built-in-nodes/Canny.mdx
@@ -1,10 +1,10 @@
 ---
 title: "Canny - ComfyUI Built-in Node Documentation"
-description: "The Canny node used to extract edge lines from photos."
+description: "Complete documentation for the Canny node in ComfyUI. Learn its inputs, outputs, parameters and usage."
 sidebarTitle: "Canny"
 icon: "circle"
+mode: wide
 ---
-
 Extract all edge lines from photos, like using a pen to outline a photo, drawing out the contours and detail boundaries of objects.
 
 ## Working Principle
@@ -35,9 +35,9 @@ The final output is a black and white image, where white parts are detected edge
 
 ## Parameter Comparison
 
-![Original Image](/images/built-in-nodes/canny/input.webp)
+![Original Image](/images/built-in-nodes/Canny/input.webp)
 
-![Parameter Comparison](/images/built-in-nodes/canny/compare.webp)
+![Parameter Comparison](/images/built-in-nodes/Canny/compare.webp)
 
 **Common Issues:**
 
diff --git a/built-in-nodes/CaseConverter.mdx b/built-in-nodes/CaseConverter.mdx
new file mode 100644
index 000000000..995420642
--- /dev/null
+++ b/built-in-nodes/CaseConverter.mdx
@@ -0,0 +1,23 @@
+---
+title: "CaseConverter - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CaseConverter node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CaseConverter"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CaseConverter/en.md)
+
+The Case Converter node transforms text strings into different letter case formats. It takes an input string and converts it based on the selected mode, producing an output string with the specified case formatting applied. The node supports four different case conversion options to modify the capitalization of your text.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `string` | STRING | String | - | - | The text string to be converted to a different case format |
+| `mode` | STRING | Combo | - | ["UPPERCASE", "lowercase", "Capitalize", "Title Case"] | The case conversion mode to apply: UPPERCASE converts all letters to uppercase, lowercase converts all letters to lowercase, Capitalize capitalizes only the first letter, Title Case capitalizes the first letter of each word |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The input string converted to the specified case format |
diff --git a/built-in-nodes/CenterCropImages.mdx b/built-in-nodes/CenterCropImages.mdx
new file mode 100644
index 000000000..40aea881b
--- /dev/null
+++ b/built-in-nodes/CenterCropImages.mdx
@@ -0,0 +1,24 @@
+---
+title: "CenterCropImages - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CenterCropImages node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CenterCropImages"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CenterCropImages/en.md)
+
+The Center Crop Images node crops an image from its center to a specified width and height. It calculates the central region of the input image and extracts a rectangular area of the defined dimensions. If the requested crop size is larger than the image, the crop will be constrained to the image's boundaries.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be cropped. |
+| `width` | INT | No | 1 to 8192 | The width of the crop area (default: 512). |
+| `height` | INT | No | 1 to 8192 | The height of the crop area (default: 512). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resulting image after the center crop operation. |
diff --git a/built-in-nodes/CheckpointLoader.mdx b/built-in-nodes/CheckpointLoader.mdx
new file mode 100644
index 000000000..e4f8e68db
--- /dev/null
+++ b/built-in-nodes/CheckpointLoader.mdx
@@ -0,0 +1,29 @@
+---
+title: "CheckpointLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CheckpointLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CheckpointLoader/en.md)
+
+The CheckpointLoader node loads a pre-trained model checkpoint along with its configuration file. It takes a configuration file and a checkpoint file as inputs and returns the loaded model components including the main model, CLIP model, and VAE model for use in the workflow.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `config_name` | STRING | COMBO | - | Available config files | The configuration file that defines the model architecture and settings |
+| `ckpt_name` | STRING | COMBO | - | Available checkpoint files | The checkpoint file containing the trained model weights and parameters |
+
+**Note:** This node requires both a configuration file and a checkpoint file to be selected. The configuration file must match the architecture of the checkpoint file being loaded.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | The loaded main model component ready for inference |
+| `CLIP` | CLIP | The loaded CLIP model component for text encoding |
+| `VAE` | VAE | The loaded VAE model component for image encoding and decoding |
+
+**Important Note:** This node has been marked as deprecated and may be removed in future versions. Consider using alternative loading nodes for new workflows.
diff --git a/built-in-nodes/CheckpointLoaderSimple.mdx b/built-in-nodes/CheckpointLoaderSimple.mdx
index 68f7d6cd2..1c2740095 100755
--- a/built-in-nodes/CheckpointLoaderSimple.mdx
+++ b/built-in-nodes/CheckpointLoaderSimple.mdx
@@ -1,10 +1,10 @@
 ---
 title: "CheckpointLoaderSimple - ComfyUI Built-in Node Documentation"
-description: "The CheckpointLoaderSimple node is used to load model files from specified locations and decompose them into three core components: the main model, text encoder, and image encoder/decoder."
+description: "Complete documentation for the CheckpointLoaderSimple node in ComfyUI. Learn its inputs, outputs, parameters and usage."
 sidebarTitle: "CheckpointLoaderSimple"
 icon: "circle"
+mode: wide
 ---
-
 This is a model loader node that loads model files from specified locations and decomposes them into three core components: the main model, text encoder, and image encoder/decoder.
 
 This node automatically detects all model files in the `ComfyUI/models/checkpoints` folder, as well as additional paths configured in your `extra_model_paths.yaml` file.
diff --git a/built-in-nodes/CheckpointSave.mdx b/built-in-nodes/CheckpointSave.mdx
index 2d4c292fc..8252921a8 100755
--- a/built-in-nodes/CheckpointSave.mdx
+++ b/built-in-nodes/CheckpointSave.mdx
@@ -1,10 +1,10 @@
 ---
 title: "CheckpointSave - ComfyUI Built-in Node Documentation"
-description: "The CheckpointSave node is used to save the complete Stable Diffusion model (including UNet, CLIP, and VAE components) as a **.safetensors** format checkpoint file."
+description: "Complete documentation for the CheckpointSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
 sidebarTitle: "CheckpointSave"
 icon: "circle"
+mode: wide
 ---
-
 The `Save Checkpoint` node is designed to save a complete Stable Diffusion model (including UNet, CLIP, and VAE components) as a **.safetensors** format checkpoint file.
 
 The Save Checkpoint is primarily used in model merging workflows. After creating a new merged model through nodes like `ModelMergeSimple`, `ModelMergeBlocks`, etc., you can use this node to save the result as a reusable checkpoint file.
diff --git a/built-in-nodes/ChromaRadianceOptions.mdx b/built-in-nodes/ChromaRadianceOptions.mdx
new file mode 100644
index 000000000..75935862b
--- /dev/null
+++ b/built-in-nodes/ChromaRadianceOptions.mdx
@@ -0,0 +1,28 @@
+---
+title: "ChromaRadianceOptions - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ChromaRadianceOptions node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ChromaRadianceOptions"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ChromaRadianceOptions/en.md)
+
+The ChromaRadianceOptions node allows you to configure advanced settings for the Chroma Radiance model. It wraps an existing model and applies specific options during the denoising process based on sigma values, enabling fine-tuned control over NeRF tile size and other radiance-related parameters.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | Required | - | - | The model to apply Chroma Radiance options to |
+| `preserve_wrapper` | BOOLEAN | Optional | True | - | When enabled, will delegate to an existing model function wrapper if it exists. Generally should be left enabled. |
+| `start_sigma` | FLOAT | Optional | 1.0 | 0.0 - 1.0 | First sigma that these options will be in effect. |
+| `end_sigma` | FLOAT | Optional | 0.0 | 0.0 - 1.0 | Last sigma that these options will be in effect. |
+| `nerf_tile_size` | INT | Optional | -1 | -1 and above | Allows overriding the default NeRF tile size. -1 means use the default (32). 0 means use non-tiling mode (may require a lot of VRAM). |
+
+**Note:** The Chroma Radiance options only take effect when the current sigma value falls between `end_sigma` and `start_sigma` (inclusive). The `nerf_tile_size` parameter is only applied when set to 0 or higher values.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with Chroma Radiance options applied |
diff --git a/built-in-nodes/ClipLoader.mdx b/built-in-nodes/ClipLoader.mdx
index 3206d29fb..ebc321f6c 100755
--- a/built-in-nodes/ClipLoader.mdx
+++ b/built-in-nodes/ClipLoader.mdx
@@ -1,10 +1,10 @@
 ---
-title: "ClipLoader - ComfyUI Built-in Node Documentation"
-description: "The ClipLoader node is used to load CLIP text encoder models independently."
-sidebarTitle: "ClipLoader"
+title: "CLIPLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPLoader"
 icon: "circle"
+mode: wide
 ---
-
 This node is primarily used for loading CLIP text encoder models independently.
 The model files can be detected in the following paths:
 
diff --git a/built-in-nodes/ClipMergeSimple.mdx b/built-in-nodes/ClipMergeSimple.mdx
index c97e4d0af..ee926f122 100755
--- a/built-in-nodes/ClipMergeSimple.mdx
+++ b/built-in-nodes/ClipMergeSimple.mdx
@@ -1,10 +1,10 @@
 ---
-title: "ClipMergeSimple - ComfyUI Built-in Node Documentation"
-description: "The ClipMergeSimple node is used to combine two CLIP text encoder models based on a specified ratio."
-sidebarTitle: "ClipMergeSimple"
+title: "CLIPMergeSimple - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPMergeSimple node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPMergeSimple"
 icon: "circle"
+mode: wide
 ---
-
 `CLIPMergeSimple` is an advanced model merging node used to combine two CLIP text encoder models based on a specified ratio.
 
 This node specializes in merging two CLIP models based on a specified ratio, effectively blending their characteristics. It selectively applies patches from one model to another, excluding specific components like position IDs and logit scale, to create a hybrid model that combines features from both source models.
diff --git a/built-in-nodes/ClipSave.mdx b/built-in-nodes/ClipSave.mdx
index d4c6a0a15..5c8cc7e0b 100755
--- a/built-in-nodes/ClipSave.mdx
+++ b/built-in-nodes/ClipSave.mdx
@@ -1,10 +1,10 @@
 ---
-title: "ClipSave - ComfyUI Built-in Node Documentation"
-description: "The ClipSave node is used to save CLIP text encoder models in SafeTensors format."
-sidebarTitle: "ClipSave"
+title: "CLIPSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPSave"
 icon: "circle"
+mode: wide
 ---
-
 The `CLIPSave` node is designed for saving CLIP text encoder models in SafeTensors format. This node is part of advanced model merging workflows and is typically used in conjunction with nodes like `CLIPMergeSimple` and `CLIPMergeAdd`. The saved files use the SafeTensors format to ensure security and compatibility.
 
 ## Inputs
diff --git a/built-in-nodes/ClipSetLastLayer.mdx b/built-in-nodes/ClipSetLastLayer.mdx
index c12947a59..ec8d15554 100755
--- a/built-in-nodes/ClipSetLastLayer.mdx
+++ b/built-in-nodes/ClipSetLastLayer.mdx
@@ -1,10 +1,10 @@
 ---
-title: "ClipSetLastLayer - ComfyUI Built-in Node Documentation"
-description: "The ClipSetLastLayer node is used to control the processing depth of CLIP models."
-sidebarTitle: "ClipSetLastLayer"
+title: "CLIPSetLastLayer - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPSetLastLayer node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPSetLastLayer"
 icon: "circle"
+mode: wide
 ---
-
 `CLIP Set Last Layer` is a core node in ComfyUI for controlling the processing depth of CLIP models. It allows users to precisely control where the CLIP text encoder stops processing, affecting both the depth of text understanding and the style of generated images.
 
 Imagine the CLIP model as a 24-layer intelligent brain:
diff --git a/built-in-nodes/ClipTextEncode.mdx b/built-in-nodes/ClipTextEncode.mdx
index 1b3e3e926..3c67dfe8f 100755
--- a/built-in-nodes/ClipTextEncode.mdx
+++ b/built-in-nodes/ClipTextEncode.mdx
@@ -1,54 +1,72 @@
 ---
-title: "ClipTextEncode - ComfyUI Built-in Node Documentation"
-description: "The ClipTextEncode node is used to convert text prompts into AI-understandable 'language' for image generation."
-sidebarTitle: "ClipTextEncode"
+title: "CLIPTextEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncode"
 icon: "circle"
+mode: wide
 ---
+`CLIP Text Encode (CLIPTextEncode)` acts as a translator, converting your text descriptions into a format that AI can understand. This helps the AI interpret your input and generate the desired image.
 
-`CLIP Text Encode (CLIPTextEncode)` acts like a translator, converting your creative text prompts into a special "language" that AI can understand, helping the AI accurately interpret what kind of image you want to create.
-
-Imagine communicating with a foreign artist - you need a translator to help accurately convey the artwork you want. This node acts as that translator, using the CLIP model (an AI model trained on vast amounts of image-text pairs) to understand your text descriptions and convert them into "instructions" that the AI art model can understand.
+Think of it as communicating with an artist who speaks a different language. The CLIP model, trained on vast image-text pairs, bridges this gap by converting your descriptions into "instructions" that the AI model can follow.
 
 ## Inputs
 
 | Parameter | Data Type | Input Method | Default | Range | Description |
 |-----------|-----------|--------------|---------|--------|-------------|
-| text | STRING | Text Input | Empty | Any text | Like detailed instructions to an artist, enter your image description here. Supports multi-line text for detailed descriptions. |
-| clip | CLIP | Model Selection | None | Loaded CLIP models | Like choosing a specific translator, different CLIP models are like different translators with slightly different understandings of artistic styles. |
+| text | STRING | Text Input | Empty | Any text | Enter the description (prompt) for the image you want to create. Supports multi-line input for detailed descriptions. |
+| clip | CLIP | Model Selection | None | Loaded CLIP models | Select the CLIP model to use when translating your description into instructions for the AI model. |
 
 ## Outputs
 
 | Output Name | Data Type | Description |
 |-------------|-----------|-------------|
-| CONDITIONING | CONDITIONING | These are the translated "painting instructions" containing detailed creative guidance that the AI model can understand. These instructions tell the AI model how to create an image matching your description. |
-
-## Usage Tips
-
-1. **Basic Text Prompt Usage**
-   - Write detailed descriptions like you're writing a short essay
-   - More specific descriptions lead to more accurate results
-   - Use English commas to separate different descriptive elements
-
-2. **Special Feature: Using Embedding Models**
-   - Embedding models are like preset art style packages that can quickly apply specific artistic effects
-   - Currently supports .safetensors, .pt, and .bin file formats, and you don't necessarily need to use the complete model name
-   - How to use:
-     1. Place the embedding model file (in .pt format) in the `ComfyUI/models/embeddings` folder
-     2. Use `embedding:model_name` in your text
-     Example: If you have a model called `EasyNegative.pt`, you can use it like this:
-
-     ```
-     a beautiful landscape, embedding:EasyNegative, high quality
-     ```
-
-3. **Prompt Weight Adjustment**
-   - Use parentheses to adjust the importance of certain descriptions
-   - For example: `(beautiful:1.2)` will make the "beautiful" feature more prominent
-   - Regular parentheses `()` have a default weight of 1.1
-   - Use keyboard shortcuts `ctrl + up/down arrow` to quickly adjust weights
-   - The weight adjustment step size can be modified in settings
-
-4. **Important Notes**
-   - Ensure the CLIP model is properly loaded
-   - Use positive and clear text descriptions
-   - When using embedding models, make sure the file name is correct and compatible with your current main model's architecture
+| CONDITIONING | CONDITIONING | The processed "instructions" of your description that guide the AI model when generating an image. |
+
+## Prompt Features
+
+### Embedding Models
+
+Embedding models allow you to apply specific artistic effects or styles. Supported formats include `.safetensors`, `.pt`, and `.bin`. To use an embedding model:
+
+1. Place the file in the `ComfyUI/models/embeddings` folder.
+2. Reference it in your text using `embedding:model_name`.
+
+Example: If you have a model named `EasyNegative.pt` in your `ComfyUI/models/embeddings` folder, then you can use it like this:
+
+```
+worst quality, embedding:EasyNegative, bad quality
+```
+
+**IMPORTANT**: When using embedding models, verify that the file name matches and is compatible with your model's architecture. For example an embedding designed for SD1.5 will not work correctly for a SDXL model.
+
+### Prompt Weight Adjustment
+
+You can adjust the importance of certain parts of your description using parentheses. For example:
+
+- `(beautiful:1.2)` increases the weight of "beautiful".
+- `(beautiful:0.8)` decrease the weight of "beautiful".
+- Plain parentheses `(beautiful)` will apply a default weight of 1.1.
+
+You can use the keyboard shortcuts `ctrl + up/down arrow` to quickly adjust weights. The weight adjustment step size can be modified in the settings.
+
+If you want to include literal parentheses in your prompt without changing the weight, you can escape them using a backslash e.g. `\(word\)`.
+
+### Wildcard/Dynamic Prompts
+
+Use `{}` to create dynamic prompts. For example, `{day|night|morning}` will randomly select one option each time the prompt is processed.
+
+If you want to include literal curly braces in your prompt without triggering dynamic behavior, you can escape them using a backslash e.g. `\{word\}`.
+
+### Comments in Prompts
+
+You can add comments that are excluded from the prompt by using:
+
+- `//` to comment out a single line.
+- `/* */` to comment out a section or multiple lines.
+
+Example:
+
+```
+// this line is excluded from the prompt.
+a beautiful landscape, /* this part is ignored */ high quality
+```
diff --git a/built-in-nodes/ClipTextEncodeFlux.mdx b/built-in-nodes/ClipTextEncodeFlux.mdx
index 31ef456d9..97d6099d6 100644
--- a/built-in-nodes/ClipTextEncodeFlux.mdx
+++ b/built-in-nodes/ClipTextEncodeFlux.mdx
@@ -1,13 +1,14 @@
 ---
-title: "ClipTextEncodeFlux - ComfyUI Built-in Node Documentation"
-description: "The ClipTextEncodeFlux node is used to encode text prompts into Flux-compatible conditioning embeddings."
-sidebarTitle: "ClipTextEncodeFlux"
+title: "CLIPTextEncodeFlux - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeFlux node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeFlux"
 icon: "circle"
+mode: wide
 ---
-
 `CLIPTextEncodeFlux` is an advanced text encoding node in ComfyUI, specifically designed for the Flux architecture. It uses a dual-encoder mechanism (CLIP-L and T5XXL) to process both structured keywords and detailed natural language descriptions, providing the Flux model with more accurate and comprehensive text understanding for improved text-to-image generation quality.
 
 This node is based on a dual-encoder collaboration mechanism:
+
 1. The `clip_l` input is processed by the CLIP-L encoder, extracting style, theme, and other keyword features—ideal for concise descriptions.
 2. The `t5xxl` input is processed by the T5XXL encoder, which excels at understanding complex and detailed natural language scene descriptions.
 3. The outputs from both encoders are fused, and combined with the `guidance` parameter to generate unified conditioning embeddings (`CONDITIONING`) for downstream Flux sampler nodes, controlling how closely the generated content matches the text description.
diff --git a/built-in-nodes/ClipTextEncodeHunyuanDit.mdx b/built-in-nodes/ClipTextEncodeHunyuanDit.mdx
index a46b0b0d3..ab2b8cf73 100644
--- a/built-in-nodes/ClipTextEncodeHunyuanDit.mdx
+++ b/built-in-nodes/ClipTextEncodeHunyuanDit.mdx
@@ -1,10 +1,10 @@
 ---
-title: "ClipTextEncodeHunyuanDit - ComfyUI Built-in Node Documentation"
-description: "The ClipTextEncodeHunyuanDit node is used to encode text prompts into HunyuanDiT-compatible conditioning embeddings."
-sidebarTitle: "ClipTextEncodeHunyuanDit"
+title: "CLIPTextEncodeHunyuanDiT - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeHunyuanDiT node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeHunyuanDiT"
 icon: "circle"
+mode: wide
 ---
-
 The `CLIPTextEncodeHunyuanDiT` node's main function is to convert input text into a form that the model can understand. It is an advanced conditioning node specifically designed for the dual text encoder architecture of the HunyuanDiT model.
 Its primary role is like a translator, converting our text descriptions into "machine language" that the AI model can understand. The `bert` and `mt5xl` inputs prefer different types of prompt inputs.
 
diff --git a/built-in-nodes/ClipTextEncodeSdxl.mdx b/built-in-nodes/ClipTextEncodeSdxl.mdx
index c9c773ee2..970e6d841 100755
--- a/built-in-nodes/ClipTextEncodeSdxl.mdx
+++ b/built-in-nodes/ClipTextEncodeSdxl.mdx
@@ -1,10 +1,10 @@
 ---
-title: "ClipTextEncodeSdxl - ComfyUI Built-in Node Documentation"
-description: "The ClipTextEncodeSdxl node is used to encode text prompts into SDXL-compatible conditioning embeddings."
-sidebarTitle: "ClipTextEncodeSdxl"
+title: "CLIPTextEncodeSDXL - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeSDXL node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeSDXL"
 icon: "circle"
+mode: wide
 ---
-
 This node is designed to encode text input using a CLIP model specifically customized for the SDXL architecture. It uses a dual encoder system (CLIP-L and CLIP-G) to process text descriptions, resulting in more accurate image generation.
 
 ## Inputs
diff --git a/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx b/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx
index 71da2a005..2b85ac8d2 100755
--- a/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx
+++ b/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx
@@ -1,10 +1,10 @@
 ---
-title: "ClipTextEncodeSdxlRefiner - ComfyUI Built-in Node Documentation"
-description: "The ClipTextEncodeSdxlRefiner node is used to encode text prompts into SDXL Refiner-compatible conditioning embeddings."
-sidebarTitle: "ClipTextEncodeSdxlRefiner"
+title: "CLIPTextEncodeSDXLRefiner - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeSDXLRefiner node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeSDXLRefiner"
 icon: "circle"
+mode: wide
 ---
-
 This node is specifically designed for the SDXL Refiner model to convert text prompts into conditioning information by incorporating aesthetic scores and dimensional information to enhance the conditions for generation tasks, thereby improving the final refinement effect. It acts like a professional art director, not only conveying your creative intent but also injecting precise aesthetic standards and specification requirements into the work.
 
 ## About SDXL Refiner
@@ -16,6 +16,7 @@ SDXL Refiner is a specialized refinement model that focuses on enhancing image d
 3. Finally, it focuses on processing high-frequency image details to improve overall quality
 
 Refiner can be used in two ways:
+
 - As a standalone refinement step for post-processing images generated by the base model
 - As part of an expert integration system, taking over processing during the low-noise phase of generation
 
diff --git a/built-in-nodes/ClipVisionEncode.mdx b/built-in-nodes/ClipVisionEncode.mdx
index a8ed957a8..49d2c398a 100755
--- a/built-in-nodes/ClipVisionEncode.mdx
+++ b/built-in-nodes/ClipVisionEncode.mdx
@@ -1,10 +1,10 @@
 ---
-title: "ClipVisionEncode - ComfyUI Built-in Node Documentation"
-description: "The ClipVisionEncode node is used to encode input images into visual feature vectors through the CLIP Vision model."
-sidebarTitle: "ClipVisionEncode"
+title: "CLIPVisionEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPVisionEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPVisionEncode"
 icon: "circle"
+mode: wide
 ---
-
 The `CLIP Vision Encode` node is an image encoding node in ComfyUI, used to convert input images into visual feature vectors through the CLIP Vision model. This node is an important bridge connecting image and text understanding, and is widely used in various AI image generation and processing workflows.
 
 **Node Functionality**
@@ -28,6 +28,7 @@ The `CLIP Vision Encode` node is an image encoding node in ComfyUI, used to conv
 | CLIP_VISION_OUTPUT  | CLIP_VISION_OUTPUT | Encoded visual features    |
 
 This output object contains:
+
 - `last_hidden_state`: The last hidden state
 - `image_embeds`: Image embedding vector
 - `penultimate_hidden_states`: The penultimate hidden state
diff --git a/built-in-nodes/ClipVisionLoader.mdx b/built-in-nodes/ClipVisionLoader.mdx
index a299ed6b4..193420f0a 100755
--- a/built-in-nodes/ClipVisionLoader.mdx
+++ b/built-in-nodes/ClipVisionLoader.mdx
@@ -1,10 +1,10 @@
 ---
-title: "Load CLIP Vision - ComfyUI Built-in Node Documentation"
-description: "The Load CLIP Vision node is used to load CLIP Vision models from the `ComfyUI/models/clip_vision` folder."
-sidebarTitle: "Load CLIP Vision"
+title: "CLIPVisionLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPVisionLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPVisionLoader"
 icon: "circle"
+mode: wide
 ---
-
 This node automatically detects models located in the `ComfyUI/models/clip_vision` folder, as well as any additional model paths configured in the `extra_model_paths.yaml` file. If you add models after starting ComfyUI, please **refresh the ComfyUI interface** to ensure the latest model files are listed.
 
 ## Inputs
diff --git a/built-in-nodes/ColorToRGBInt.mdx b/built-in-nodes/ColorToRGBInt.mdx
new file mode 100644
index 000000000..e1bb87191
--- /dev/null
+++ b/built-in-nodes/ColorToRGBInt.mdx
@@ -0,0 +1,24 @@
+---
+title: "ColorToRGBInt - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ColorToRGBInt node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ColorToRGBInt"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ColorToRGBInt/en.md)
+
+The ColorToRGBInt node converts a color specified in a hexadecimal format into a single integer value. It takes a color string like `#FF5733` and calculates the corresponding RGB integer by combining the red, green, and blue components.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `color` | STRING | Yes | N/A | A color value in the hexadecimal format `#RRGGBB`. |
+
+**Note:** The input `color` string must be exactly 7 characters long and start with a `#` symbol, followed by six hexadecimal digits (e.g., `#FF0000` for red). The node will raise an error if the format is incorrect.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `rgb_int` | INT | The calculated RGB integer value. This is derived from the formula: `(Red * 65536) + (Green * 256) + Blue`. |
diff --git a/built-in-nodes/CombineHooks.mdx b/built-in-nodes/CombineHooks.mdx
new file mode 100644
index 000000000..a18a7c825
--- /dev/null
+++ b/built-in-nodes/CombineHooks.mdx
@@ -0,0 +1,25 @@
+---
+title: "CombineHooks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CombineHooks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CombineHooks"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CombineHooks/en.md)
+
+The Combine Hooks [2] node merges two hook groups into a single combined hook group. It takes two optional hook inputs and combines them using ComfyUI's hook combination functionality. This allows you to consolidate multiple hook configurations for streamlined processing.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `hooks_A` | HOOKS | Optional | None | - | First hook group to combine |
+| `hooks_B` | HOOKS | Optional | None | - | Second hook group to combine |
+
+**Note:** Both inputs are optional, but at least one hook group must be provided for the node to function. If only one hook group is provided, it will be returned unchanged.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `hooks` | HOOKS | Combined hook group containing all hooks from both input groups |
diff --git a/built-in-nodes/CombineHooksEight.mdx b/built-in-nodes/CombineHooksEight.mdx
new file mode 100644
index 000000000..3090548b7
--- /dev/null
+++ b/built-in-nodes/CombineHooksEight.mdx
@@ -0,0 +1,31 @@
+---
+title: "CombineHooksEight - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CombineHooksEight node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CombineHooksEight"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CombineHooksEight/en.md)
+
+The Combine Hooks [8] node merges up to eight different hook groups into a single combined hook group. It takes multiple hook inputs and combines them using ComfyUI's hook combination functionality. This allows you to consolidate multiple hook configurations for streamlined processing in advanced workflows.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `hooks_A` | HOOKS | optional | None | - | First hook group to combine |
+| `hooks_B` | HOOKS | optional | None | - | Second hook group to combine |
+| `hooks_C` | HOOKS | optional | None | - | Third hook group to combine |
+| `hooks_D` | HOOKS | optional | None | - | Fourth hook group to combine |
+| `hooks_E` | HOOKS | optional | None | - | Fifth hook group to combine |
+| `hooks_F` | HOOKS | optional | None | - | Sixth hook group to combine |
+| `hooks_G` | HOOKS | optional | None | - | Seventh hook group to combine |
+| `hooks_H` | HOOKS | optional | None | - | Eighth hook group to combine |
+
+**Note:** All input parameters are optional. The node will combine only the hook groups that are provided, ignoring any that are left empty. You can provide anywhere from one to eight hook groups for combination.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `HOOKS` | HOOKS | A single combined hook group containing all the provided hook configurations |
diff --git a/built-in-nodes/CombineHooksFour.mdx b/built-in-nodes/CombineHooksFour.mdx
new file mode 100644
index 000000000..6a5382b37
--- /dev/null
+++ b/built-in-nodes/CombineHooksFour.mdx
@@ -0,0 +1,27 @@
+---
+title: "CombineHooksFour - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CombineHooksFour node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CombineHooksFour"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CombineHooksFour/en.md)
+
+The Combine Hooks [4] node merges up to four separate hook groups into a single combined hook group. It takes any combination of the four available hook inputs and combines them using ComfyUI's hook combination system. This allows you to consolidate multiple hook configurations for streamlined processing in advanced workflows.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `hooks_A` | HOOKS | optional | None | - | First hook group to combine |
+| `hooks_B` | HOOKS | optional | None | - | Second hook group to combine |
+| `hooks_C` | HOOKS | optional | None | - | Third hook group to combine |
+| `hooks_D` | HOOKS | optional | None | - | Fourth hook group to combine |
+
+**Note:** All four hook inputs are optional. The node will combine only the hook groups that are provided, and will return an empty hook group if no inputs are connected.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `HOOKS` | HOOKS | Combined hook group containing all provided hook configurations |
diff --git a/built-in-nodes/ComboOptionTestNode.mdx b/built-in-nodes/ComboOptionTestNode.mdx
new file mode 100644
index 000000000..45943ff9c
--- /dev/null
+++ b/built-in-nodes/ComboOptionTestNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "ComboOptionTestNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ComboOptionTestNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ComboOptionTestNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComboOptionTestNode/en.md)
+
+The ComboOptionTestNode is a logic node designed to test and pass through combo box selections. It takes two combo box inputs, each with a predefined set of options, and outputs the selected values directly without modification.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `combo` | COMBO | Yes | `"option1"`<br />`"option2"`<br />`"option3"` | The first selection from a set of three test options. |
+| `combo2` | COMBO | Yes | `"option4"`<br />`"option5"`<br />`"option6"` | The second selection from a different set of three test options. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output_1` | COMBO | Outputs the value selected from the first combo box (`combo`). |
+| `output_2` | COMBO | Outputs the value selected from the second combo box (`combo2`). |
diff --git a/built-in-nodes/ComfySoftSwitchNode.mdx b/built-in-nodes/ComfySoftSwitchNode.mdx
new file mode 100644
index 000000000..8d6303a35
--- /dev/null
+++ b/built-in-nodes/ComfySoftSwitchNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "ComfySoftSwitchNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ComfySoftSwitchNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ComfySoftSwitchNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfySoftSwitchNode/en.md)
+
+The Soft Switch node selects between two possible input values based on a boolean condition. It outputs the value from the `on_true` input when the `switch` is true, and the value from the `on_false` input when the `switch` is false. This node is designed to be lazy, meaning it only evaluates the input that is needed based on the switch state.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `switch` | BOOLEAN | Yes | | The boolean condition that determines which input to pass through. When true, the `on_true` input is selected. When false, the `on_false` input is selected. |
+| `on_false` | MATCH_TYPE | No | | The value to output when the `switch` condition is false. This input is optional, but at least one of `on_false` or `on_true` must be connected. |
+| `on_true` | MATCH_TYPE | No | | The value to output when the `switch` condition is true. This input is optional, but at least one of `on_false` or `on_true` must be connected. |
+
+**Note:** The `on_false` and `on_true` inputs must be of the same data type, as defined by the node's internal template. At least one of these two inputs must be connected for the node to function.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | MATCH_TYPE | The selected value. It will match the data type of the connected `on_false` or `on_true` input. |
diff --git a/built-in-nodes/ComfySwitchNode.mdx b/built-in-nodes/ComfySwitchNode.mdx
new file mode 100644
index 000000000..ef4103dae
--- /dev/null
+++ b/built-in-nodes/ComfySwitchNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "ComfySwitchNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ComfySwitchNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ComfySwitchNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfySwitchNode/en.md)
+
+The Switch node selects between two possible inputs based on a boolean condition. It outputs the `on_true` input when the `switch` is enabled, and the `on_false` input when the `switch` is disabled. This allows you to create conditional logic and choose different data paths in your workflow.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `switch` | BOOLEAN | Yes | | A boolean condition that determines which input to pass through. When enabled (true), the `on_true` input is selected. When disabled (false), the `on_false` input is selected. |
+| `on_false` | MATCH_TYPE | No | | The data to be passed to the output when the `switch` is disabled (false). This input is only required when the `switch` is false. |
+| `on_true` | MATCH_TYPE | No | | The data to be passed to the output when the `switch` is enabled (true). This input is only required when the `switch` is true. |
+
+**Note on Input Requirements:** The `on_false` and `on_true` inputs are conditionally required. The node will request the `on_true` input only when the `switch` is true, and the `on_false` input only when the `switch` is false. Both inputs must be of the same data type.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | MATCH_TYPE | The selected data. This will be the value from the `on_true` input if the `switch` is true, or the value from the `on_false` input if the `switch` is false. |
diff --git a/built-in-nodes/ConditioningAverage.mdx b/built-in-nodes/ConditioningAverage.mdx
new file mode 100644
index 000000000..4b11f8a53
--- /dev/null
+++ b/built-in-nodes/ConditioningAverage.mdx
@@ -0,0 +1,33 @@
+---
+title: "ConditioningAverage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningAverage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningAverage"
+icon: "circle"
+mode: wide
+---
+The `ConditioningAverage` node is used to blend two different sets of conditioning (such as text prompts) according to a specified weight, generating a new conditioning vector that lies between the two. By adjusting the weight parameter, you can flexibly control the influence of each conditioning on the final result. This is especially suitable for prompt interpolation, style fusion, and other advanced use cases.
+
+As shown below, by adjusting the strength of `conditioning_to`, you can output a result between the two conditionings.
+
+![example](/images/built-in-nodes/ConditioningAverage/example.webp)
+
+## Inputs
+
+| Parameter               | Comfy dtype    | Description |
+|------------------------|---------------|-------------|
+| `conditioning_to`      | `CONDITIONING`| The target conditioning vector, serving as the main base for the weighted average. |
+| `conditioning_from`    | `CONDITIONING`| The source conditioning vector, which will be blended into the target according to a certain weight. |
+| `conditioning_to_strength` | `FLOAT`    | The strength of the target conditioning, range 0.0-1.0, default 1.0, step 0.01. |
+
+## Outputs
+
+| Parameter        | Comfy dtype    | Description |
+|------------------|---------------|-------------|
+| `conditioning`   | `CONDITIONING`| The resulting conditioning vector after blending, reflecting the weighted average. |
+
+## Typical Use Cases
+
+- **Prompt Interpolation:** Smoothly transition between two different text prompts, generating content with intermediate style or semantics.
+- **Style Fusion:** Combine different artistic styles or semantic conditions to create novel effects.
+- **Strength Adjustment:** Precisely control the influence of a particular conditioning on the result by adjusting the weight.
+- **Creative Exploration:** Explore diverse generative effects by mixing different prompts.
diff --git a/built-in-nodes/ConditioningCombine.mdx b/built-in-nodes/ConditioningCombine.mdx
new file mode 100644
index 000000000..c3a312697
--- /dev/null
+++ b/built-in-nodes/ConditioningCombine.mdx
@@ -0,0 +1,35 @@
+---
+title: "ConditioningCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningCombine"
+icon: "circle"
+mode: wide
+---
+This node combines two conditioning inputs into a single output, effectively merging their information. The two conditions are combined using list concatenation.
+
+## Inputs
+
+| Parameter Name       | Data Type          | Description |
+|----------------------|--------------------|-------------|
+| `conditioning_1`     | `CONDITIONING`     | The first conditioning input to be combined. It has equal importance with `conditioning_2` in the combination process. |
+| `conditioning_2`     | `CONDITIONING`     | The second conditioning input to be combined. It has equal importance with `conditioning_1` in the combination process. |
+
+## Outputs
+
+| Parameter Name       | Data Type          | Description |
+|----------------------|--------------------|-------------|
+| `conditioning`       | `CONDITIONING`     | The result of combining `conditioning_1` and `conditioning_2`, encapsulating the merged information. |
+
+## Usage Scenarios
+
+Compare the two groups below: the left side uses the ConditioningCombine node, while the right side shows normal output.
+
+![Compare](/images/built-in-nodes/ConditioningCombine/compare.jpg)
+
+In this example, the two conditions used in `Conditioning Combine` have equivalent importance. Therefore, you can use different text encodings for image style, subject features, etc., allowing the prompt features to be output more completely. The second prompt uses the combined complete prompt, but semantic understanding may encode completely different conditions.
+
+Using this node, you can achieve:
+
+- Basic text merging: Connect the outputs of two `CLIP Text Encode` nodes to the two input ports of `Conditioning Combine`
+- Complex prompt combination: Combine positive and negative prompts, or separately encode main descriptions and style descriptions before merging
+- Conditional chain combination: Multiple `Conditioning Combine` nodes can be used in series to achieve gradual combination of multiple conditions
diff --git a/built-in-nodes/ConditioningConcat.mdx b/built-in-nodes/ConditioningConcat.mdx
new file mode 100644
index 000000000..00b5f91e9
--- /dev/null
+++ b/built-in-nodes/ConditioningConcat.mdx
@@ -0,0 +1,21 @@
+---
+title: "ConditioningConcat - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningConcat node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningConcat"
+icon: "circle"
+mode: wide
+---
+The ConditioningConcat node is designed to concatenate conditioning vectors, specifically merging the 'conditioning_from' vector into the 'conditioning_to' vector. This operation is fundamental in scenarios where the conditioning information from two sources needs to be combined into a single, unified representation.
+
+## Inputs
+
+| Parameter             | Comfy dtype        | Description |
+|-----------------------|--------------------|-------------|
+| `conditioning_to`     | `CONDITIONING`     | Represents the primary set of conditioning vectors to which the 'conditioning_from' vectors will be concatenated. It serves as the base for the concatenation process. |
+| `conditioning_from`   | `CONDITIONING`     | Consists of conditioning vectors that are to be concatenated to the 'conditioning_to' vectors. This parameter allows for additional conditioning information to be integrated into the existing set. |
+
+## Outputs
+
+| Parameter            | Comfy dtype        | Description |
+|----------------------|--------------------|-------------|
+| `conditioning`       | `CONDITIONING`     | The output is a unified set of conditioning vectors, resulting from the concatenation of 'conditioning_from' vectors into the 'conditioning_to' vectors. |
diff --git a/built-in-nodes/ConditioningSetArea.mdx b/built-in-nodes/ConditioningSetArea.mdx
new file mode 100644
index 000000000..824ec35e9
--- /dev/null
+++ b/built-in-nodes/ConditioningSetArea.mdx
@@ -0,0 +1,25 @@
+---
+title: "ConditioningSetArea - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetArea node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetArea"
+icon: "circle"
+mode: wide
+---
+This node is designed to modify the conditioning information by setting specific areas within the conditioning context. It allows for the precise spatial manipulation of conditioning elements, enabling targeted adjustments and enhancements based on specified dimensions and strength.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `CONDITIONING` | CONDITIONING | The conditioning data to be modified. It serves as the base for applying spatial adjustments. |
+| `width`   | `INT`      | Specifies the width of the area to be set within the conditioning context, influencing the horizontal scope of the adjustment. |
+| `height`  | `INT`      | Determines the height of the area to be set, affecting the vertical extent of the conditioning modification. |
+| `x`       | `INT`      | The horizontal starting point of the area to be set, positioning the adjustment within the conditioning context. |
+| `y`       | `INT`      | The vertical starting point for the area adjustment, establishing its position within the conditioning context. |
+| `strength`| `FLOAT`    | Defines the intensity of the conditioning modification within the specified area, allowing for nuanced control over the adjustment's impact. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `CONDITIONING` | CONDITIONING | The modified conditioning data, reflecting the specified area settings and adjustments. |
diff --git a/built-in-nodes/ConditioningSetAreaPercentage.mdx b/built-in-nodes/ConditioningSetAreaPercentage.mdx
new file mode 100644
index 000000000..57e3c1c0a
--- /dev/null
+++ b/built-in-nodes/ConditioningSetAreaPercentage.mdx
@@ -0,0 +1,25 @@
+---
+title: "ConditioningSetAreaPercentage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetAreaPercentage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetAreaPercentage"
+icon: "circle"
+mode: wide
+---
+The ConditioningSetAreaPercentage node specializes in adjusting the area of influence for conditioning elements based on percentage values. It allows for the specification of the area's dimensions and position as percentages of the total image size, alongside a strength parameter to modulate the intensity of the conditioning effect.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `CONDITIONING` | CONDITIONING | Represents the conditioning elements to be modified, serving as the foundation for applying area and strength adjustments. |
+| `width`   | `FLOAT`     | Specifies the width of the area as a percentage of the total image width, influencing how much of the image the conditioning affects horizontally. |
+| `height`  | `FLOAT`     | Determines the height of the area as a percentage of the total image height, affecting the vertical extent of the conditioning's influence. |
+| `x`       | `FLOAT`     | Indicates the horizontal starting point of the area as a percentage of the total image width, positioning the conditioning effect. |
+| `y`       | `FLOAT`     | Specifies the vertical starting point of the area as a percentage of the total image height, positioning the conditioning effect. |
+| `strength`| `FLOAT`     | Controls the intensity of the conditioning effect within the specified area, allowing for fine-tuning of its impact. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `CONDITIONING` | CONDITIONING | Returns the modified conditioning elements with updated area and strength parameters, ready for further processing or application. |
diff --git a/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx b/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx
new file mode 100644
index 000000000..80591b692
--- /dev/null
+++ b/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx
@@ -0,0 +1,29 @@
+---
+title: "ConditioningSetAreaPercentageVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetAreaPercentageVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetAreaPercentageVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetAreaPercentageVideo/en.md)
+
+The ConditioningSetAreaPercentageVideo node modifies conditioning data by defining a specific area and temporal region for video generation. It allows you to set the position, size, and duration of the area where the conditioning will be applied using percentage values relative to the overall dimensions. This is useful for focusing the generation on specific parts of a video sequence.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `conditioning` | CONDITIONING | Required | - | - | The conditioning data to be modified |
+| `width` | FLOAT | Required | 1.0 | 0.0 - 1.0 | The width of the area as a percentage of the total width |
+| `height` | FLOAT | Required | 1.0 | 0.0 - 1.0 | The height of the area as a percentage of the total height |
+| `temporal` | FLOAT | Required | 1.0 | 0.0 - 1.0 | The temporal duration of the area as a percentage of the total video length |
+| `x` | FLOAT | Required | 0.0 | 0.0 - 1.0 | The horizontal starting position of the area as a percentage |
+| `y` | FLOAT | Required | 0.0 | 0.0 - 1.0 | The vertical starting position of the area as a percentage |
+| `z` | FLOAT | Required | 0.0 | 0.0 - 1.0 | The temporal starting position of the area as a percentage of the video timeline |
+| `strength` | FLOAT | Required | 1.0 | 0.0 - 10.0 | The strength multiplier applied to the conditioning within the defined area |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | The modified conditioning data with the specified area and strength settings applied |
diff --git a/built-in-nodes/ConditioningSetAreaStrength.mdx b/built-in-nodes/ConditioningSetAreaStrength.mdx
new file mode 100644
index 000000000..41f88d94e
--- /dev/null
+++ b/built-in-nodes/ConditioningSetAreaStrength.mdx
@@ -0,0 +1,21 @@
+---
+title: "ConditioningSetAreaStrength - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetAreaStrength node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetAreaStrength"
+icon: "circle"
+mode: wide
+---
+This node is designed to modify the strength attribute of a given conditioning set, allowing for the adjustment of the influence or intensity of the conditioning on the generation process.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `CONDITIONING` | CONDITIONING | The conditioning set to be modified, representing the current state of conditioning that influences the generation process. |
+| `strength` | `FLOAT` | The strength value to be applied to the conditioning set, dictating the intensity of its influence. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `CONDITIONING` | CONDITIONING | The modified conditioning set with updated strength values for each element. |
diff --git a/built-in-nodes/ConditioningSetDefaultAndCombine.mdx b/built-in-nodes/ConditioningSetDefaultAndCombine.mdx
new file mode 100644
index 000000000..56d8943c5
--- /dev/null
+++ b/built-in-nodes/ConditioningSetDefaultAndCombine.mdx
@@ -0,0 +1,24 @@
+---
+title: "ConditioningSetDefaultAndCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetDefaultAndCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetDefaultAndCombine"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetDefaultAndCombine/en.md)
+
+This node combines conditioning data with default conditioning data using a hook-based system. It takes a primary conditioning input and a default conditioning input, then merges them according to the specified hook configuration. The result is a single conditioning output that incorporates both sources.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `cond` | CONDITIONING | Required | - | - | The primary conditioning input to be processed |
+| `cond_DEFAULT` | CONDITIONING | Required | - | - | The default conditioning data to be combined with the primary conditioning |
+| `hooks` | HOOKS | Optional | - | - | Optional hook configuration that controls how the conditioning data is processed and combined |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The combined conditioning data resulting from merging the primary and default conditioning inputs |
diff --git a/built-in-nodes/ConditioningSetMask.mdx b/built-in-nodes/ConditioningSetMask.mdx
new file mode 100644
index 000000000..c46ce576f
--- /dev/null
+++ b/built-in-nodes/ConditioningSetMask.mdx
@@ -0,0 +1,25 @@
+---
+title: "ConditioningSetMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetMask"
+icon: "circle"
+mode: wide
+---
+This node is designed to modify the conditioning of a generative model by applying a mask with a specified strength to certain areas. It allows for targeted adjustments within the conditioning, enabling more precise control over the generation process.
+
+## Inputs
+
+### Required
+
+| Parameter     | Data Type | Description |
+|---------------|--------------|-------------|
+| `CONDITIONING` | CONDITIONING | The conditioning data to be modified. It serves as the basis for applying the mask and strength adjustments. |
+| `mask`        | `MASK`       | A mask tensor that specifies the areas within the conditioning to be modified. |
+| `strength`    | `FLOAT`      | The strength of the mask's effect on the conditioning, allowing for fine-tuning of the applied modifications. |
+| `set_cond_area` | COMBO[STRING] | Determines whether the mask's effect is applied to the default area or bounded by the mask itself, offering flexibility in targeting specific regions. |
+
+## Outputs
+
+| Parameter     | Data Type | Description |
+|---------------|--------------|-------------|
+| `CONDITIONING` | CONDITIONING | The modified conditioning data, with the mask and strength adjustments applied. |
diff --git a/built-in-nodes/ConditioningSetProperties.mdx b/built-in-nodes/ConditioningSetProperties.mdx
new file mode 100644
index 000000000..277be556d
--- /dev/null
+++ b/built-in-nodes/ConditioningSetProperties.mdx
@@ -0,0 +1,29 @@
+---
+title: "ConditioningSetProperties - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetProperties node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetProperties"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetProperties/en.md)
+
+The ConditioningSetProperties node modifies the properties of conditioning data by adjusting strength, area settings, and applying optional masks or timestep ranges. It allows you to control how conditioning influences the generation process by setting specific parameters that affect the application of conditioning data during image generation.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `cond_NEW` | CONDITIONING | Required | - | - | The conditioning data to modify |
+| `strength` | FLOAT | Required | 1.0 | 0.0-10.0 | Controls the intensity of the conditioning effect |
+| `set_cond_area` | STRING | Required | default | ["default", "mask bounds"] | Determines how the conditioning area is applied |
+| `mask` | MASK | Optional | - | - | Optional mask to restrict where conditioning is applied |
+| `hooks` | HOOKS | Optional | - | - | Optional hook functions for custom processing |
+| `timesteps` | TIMESTEPS_RANGE | Optional | - | - | Optional timestep range to limit when conditioning is active |
+
+**Note:** When a `mask` is provided, the `set_cond_area` parameter can be set to "mask bounds" to restrict conditioning application to the masked region only.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The modified conditioning data with updated properties |
diff --git a/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx b/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx
new file mode 100644
index 000000000..b8bcfa176
--- /dev/null
+++ b/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx
@@ -0,0 +1,30 @@
+---
+title: "ConditioningSetPropertiesAndCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetPropertiesAndCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetPropertiesAndCombine"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetPropertiesAndCombine/en.md)
+
+The ConditioningSetPropertiesAndCombine node modifies conditioning data by applying properties from a new conditioning input to an existing conditioning input. It combines the two conditioning sets while controlling the strength of the new conditioning and specifying how the conditioning area should be applied.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `cond` | CONDITIONING | Required | - | - | The original conditioning data to be modified |
+| `cond_NEW` | CONDITIONING | Required | - | - | The new conditioning data providing properties to apply |
+| `strength` | FLOAT | Required | 1.0 | 0.0 - 10.0 | Controls the intensity of the new conditioning properties |
+| `set_cond_area` | STRING | Required | default | ["default", "mask bounds"] | Determines how the conditioning area is applied |
+| `mask` | MASK | Optional | - | - | Optional mask to define specific areas for conditioning |
+| `hooks` | HOOKS | Optional | - | - | Optional hook functions for custom processing |
+| `timesteps` | TIMESTEPS_RANGE | Optional | - | - | Optional timestep range for controlling when conditioning is applied |
+
+**Note:** When `mask` is provided, the `set_cond_area` parameter can use "mask bounds" to constrain the conditioning application to the masked regions.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The combined conditioning data with modified properties |
diff --git a/built-in-nodes/ConditioningSetTimestepRange.mdx b/built-in-nodes/ConditioningSetTimestepRange.mdx
new file mode 100644
index 000000000..df760702c
--- /dev/null
+++ b/built-in-nodes/ConditioningSetTimestepRange.mdx
@@ -0,0 +1,22 @@
+---
+title: "ConditioningSetTimestepRange - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetTimestepRange node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetTimestepRange"
+icon: "circle"
+mode: wide
+---
+This node is designed to adjust the temporal aspect of conditioning by setting a specific range of timesteps. It allows for the precise control over the start and end points of the conditioning process, enabling more targeted and efficient generation.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | The conditioning input represents the current state of the generation process, which this node modifies by setting a specific range of timesteps. |
+| `start` | `FLOAT` | The start parameter specifies the beginning of the timestep range as a percentage of the total generation process, allowing for fine-tuned control over when the conditioning effects begin. |
+| `end` | `FLOAT` | The end parameter defines the endpoint of the timestep range as a percentage, enabling precise control over the duration and conclusion of the conditioning effects. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | The output is the modified conditioning with the specified timestep range applied, ready for further processing or generation. |
diff --git a/built-in-nodes/ConditioningStableAudio.mdx b/built-in-nodes/ConditioningStableAudio.mdx
new file mode 100644
index 000000000..016295bbb
--- /dev/null
+++ b/built-in-nodes/ConditioningStableAudio.mdx
@@ -0,0 +1,26 @@
+---
+title: "ConditioningStableAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningStableAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningStableAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningStableAudio/en.md)
+
+The ConditioningStableAudio node adds timing information to both positive and negative conditioning inputs for audio generation. It sets the start time and total duration parameters that help control when and how long audio content should be generated. This node modifies existing conditioning data by appending audio-specific timing metadata.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The positive conditioning input to be modified with audio timing information |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning input to be modified with audio timing information |
+| `seconds_start` | FLOAT | Yes | 0.0 to 1000.0 | The starting time in seconds for audio generation (default: 0.0) |
+| `seconds_total` | FLOAT | Yes | 0.0 to 1000.0 | The total duration in seconds for audio generation (default: 47.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The modified positive conditioning with audio timing information applied |
+| `negative` | CONDITIONING | The modified negative conditioning with audio timing information applied |
diff --git a/built-in-nodes/ConditioningTimestepsRange.mdx b/built-in-nodes/ConditioningTimestepsRange.mdx
new file mode 100644
index 000000000..0e1c19a31
--- /dev/null
+++ b/built-in-nodes/ConditioningTimestepsRange.mdx
@@ -0,0 +1,25 @@
+---
+title: "ConditioningTimestepsRange - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningTimestepsRange node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningTimestepsRange"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningTimestepsRange/en.md)
+
+The ConditioningTimestepsRange node creates three distinct timestep ranges for controlling when conditioning effects are applied during the generation process. It takes start and end percentage values and divides the entire timestep range (0.0 to 1.0) into three segments: the main range between the specified percentages, the range before the start percentage, and the range after the end percentage.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `start_percent` | FLOAT | Yes | 0.0 - 1.0 | The starting percentage of the timestep range (default: 0.0) |
+| `end_percent` | FLOAT | Yes | 0.0 - 1.0 | The ending percentage of the timestep range (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `TIMESTEPS_RANGE` | TIMESTEPS_RANGE | The main timestep range defined by start_percent and end_percent |
+| `BEFORE_RANGE` | TIMESTEPS_RANGE | The timestep range from 0.0 to start_percent |
+| `AFTER_RANGE` | TIMESTEPS_RANGE | The timestep range from end_percent to 1.0 |
diff --git a/built-in-nodes/ConditioningZeroOut.mdx b/built-in-nodes/ConditioningZeroOut.mdx
new file mode 100644
index 000000000..ef0836741
--- /dev/null
+++ b/built-in-nodes/ConditioningZeroOut.mdx
@@ -0,0 +1,20 @@
+---
+title: "ConditioningZeroOut - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningZeroOut node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningZeroOut"
+icon: "circle"
+mode: wide
+---
+This node zeroes out specific elements within the conditioning data structure, effectively neutralizing their influence in subsequent processing steps. It's designed for advanced conditioning operations where direct manipulation of the conditioning's internal representation is required.
+
+## Inputs
+
+| Parameter | Comfy dtype                | Description |
+|-----------|----------------------------|-------------|
+| `CONDITIONING` | CONDITIONING | The conditioning data structure to be modified. This node zeroes out the 'pooled_output' elements within each conditioning entry, if present. |
+
+## Outputs
+
+| Parameter | Comfy dtype                | Description |
+|-----------|----------------------------|-------------|
+| `CONDITIONING` | CONDITIONING | The modified conditioning data structure, with 'pooled_output' elements set to zero where applicable. |
diff --git a/built-in-nodes/ContextWindowsManual.mdx b/built-in-nodes/ContextWindowsManual.mdx
new file mode 100644
index 000000000..92b942735
--- /dev/null
+++ b/built-in-nodes/ContextWindowsManual.mdx
@@ -0,0 +1,35 @@
+---
+title: "ContextWindowsManual - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ContextWindowsManual node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ContextWindowsManual"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ContextWindowsManual/en.md)
+
+The Context Windows (Manual) node allows you to manually configure context windows for models during sampling. It creates overlapping context segments with specified length, overlap, and scheduling patterns to process data in manageable chunks while maintaining continuity between segments.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply context windows to during sampling. |
+| `context_length` | INT | No | 1+ | The length of the context window (default: 16). |
+| `context_overlap` | INT | No | 0+ | The overlap of the context window (default: 4). |
+| `context_schedule` | COMBO | No | `STATIC_STANDARD`<br />`UNIFORM_STANDARD`<br />`UNIFORM_LOOPED`<br />`BATCHED` | The stride of the context window. |
+| `context_stride` | INT | No | 1+ | The stride of the context window; only applicable to uniform schedules (default: 1). |
+| `closed_loop` | BOOLEAN | No | - | Whether to close the context window loop; only applicable to looped schedules (default: False). |
+| `fuse_method` | COMBO | No | `PYRAMID`<br />`LIST_STATIC` | The method to use to fuse the context windows (default: PYRAMID). |
+| `dim` | INT | No | 0-5 | The dimension to apply the context windows to (default: 0). |
+
+**Parameter Constraints:**
+
+- `context_stride` is only used when uniform schedules are selected
+- `closed_loop` is only applicable to looped schedules
+- `dim` must be between 0 and 5 inclusive
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The model with context windows applied during sampling. |
diff --git a/built-in-nodes/ControlNetApply.mdx b/built-in-nodes/ControlNetApply.mdx
new file mode 100644
index 000000000..e84c19b96
--- /dev/null
+++ b/built-in-nodes/ControlNetApply.mdx
@@ -0,0 +1,28 @@
+---
+title: "ControlNetApply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetApply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetApply"
+icon: "circle"
+mode: wide
+---
+Using controlNet requires preprocessing of input images. Since ComfyUI initial nodes do not come with preprocessors and controlNet models, please first install ControlNet preprocessors [download preprocessors here](https://github.com/Fannovel16/comfy_controlnet_preprocessors) and corresponding controlNet models.
+
+## Inputs
+
+| Parameter | Data Type | Function |
+| --- | --- | --- |
+| `positive` | `CONDITIONING` | Positive conditioning data, from CLIP Text Encoder or other conditioning inputs |
+| `negative` | `CONDITIONING` | Negative conditioning data, from CLIP Text Encoder or other conditioning inputs |
+| `control_net` | `CONTROL_NET` | The controlNet model to apply, typically input from ControlNet Loader |
+| `image` | `IMAGE` | Image for controlNet application, needs to be processed by preprocessor |
+| `vae` | `VAE` | Vae model input |
+| `strength` | `FLOAT` | Controls the strength of network adjustments, value range 0~10. Recommended values between 0.5~1.5 are reasonable. Lower values allow more model freedom, higher values impose stricter constraints. Too high values may result in strange images. You can test and adjust this value to fine-tune the control network's influence. |
+| `start_percent` | `FLOAT` | Value 0.000~1.000, determines when to start applying controlNet as a percentage, e.g., 0.2 means ControlNet guidance will start influencing image generation at 20% of the diffusion process |
+| `end_percent` | `FLOAT` | Value 0.000~1.000, determines when to stop applying controlNet as a percentage, e.g., 0.8 means ControlNet guidance will stop influencing image generation at 80% of the diffusion process |
+
+### Outputs
+
+| Parameter | Data Type | Function |
+| --- | --- | --- |
+| `positive` | `CONDITIONING` | Positive conditioning data processed by ControlNet, can be output to next ControlNet or K Sampler nodes |
+| `negative` | `CONDITIONING` | Negative conditioning data processed by ControlNet, can be output to next ControlNet or K Sampler nodes |
diff --git a/built-in-nodes/ControlNetApplyAdvanced.mdx b/built-in-nodes/ControlNetApplyAdvanced.mdx
new file mode 100644
index 000000000..c33a2e176
--- /dev/null
+++ b/built-in-nodes/ControlNetApplyAdvanced.mdx
@@ -0,0 +1,27 @@
+---
+title: "ControlNetApplyAdvanced - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetApplyAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetApplyAdvanced"
+icon: "circle"
+mode: wide
+---
+This node applies advanced control net transformations to conditioning data based on an image and a control net model. It allows for fine-tuned adjustments of the control net's influence over the generated content, enabling more precise and varied modifications to the conditioning.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `positive` | `CONDITIONING` | The positive conditioning data to which the control net transformations will be applied. It represents the desired attributes or features to enhance or maintain in the generated content. |
+| `negative` | `CONDITIONING` | The negative conditioning data, representing attributes or features to diminish or remove from the generated content. The control net transformations are applied to this data as well, allowing for a balanced adjustment of the content's characteristics. |
+| `control_net` | `CONTROL_NET` | The control net model is crucial for defining the specific adjustments and enhancements to the conditioning data. It interprets the reference image and strength parameters to apply transformations, significantly influencing the final output by modifying attributes in both positive and negative conditioning data. |
+| `image` | `IMAGE` | The image serving as a reference for the control net transformations. It influences the adjustments made by the control net to the conditioning data, guiding the enhancement or suppression of specific features. |
+| `strength` | `FLOAT` | A scalar value determining the intensity of the control net's influence on the conditioning data. Higher values result in more pronounced adjustments. |
+| `start_percent` | `FLOAT` | The starting percentage of the control net's effect, allowing for gradual application of transformations over a specified range. |
+| `end_percent` | `FLOAT` | The ending percentage of the control net's effect, defining the range over which the transformations are applied. This enables more nuanced control over the adjustment process. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `positive` | `CONDITIONING` | The modified positive conditioning data after the application of control net transformations, reflecting the enhancements made based on the input parameters. |
+| `negative` | `CONDITIONING` | The modified negative conditioning data after the application of control net transformations, reflecting the suppression or removal of specific features based on the input parameters. |
diff --git a/built-in-nodes/ControlNetApplySD3.mdx b/built-in-nodes/ControlNetApplySD3.mdx
new file mode 100644
index 000000000..aa5b25cce
--- /dev/null
+++ b/built-in-nodes/ControlNetApplySD3.mdx
@@ -0,0 +1,32 @@
+---
+title: "ControlNetApplySD3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetApplySD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetApplySD3"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetApplySD3/en.md)
+
+This node applies ControlNet guidance to Stable Diffusion 3 conditioning. It takes positive and negative conditioning inputs along with a ControlNet model and image, then applies the control guidance with adjustable strength and timing parameters to influence the generation process.
+
+**Note:** This node has been marked as deprecated and may be removed in future versions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The positive conditioning to apply ControlNet guidance to |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning to apply ControlNet guidance to |
+| `control_net` | CONTROL_NET | Yes | - | The ControlNet model to use for guidance |
+| `vae` | VAE | Yes | - | The VAE model used in the process |
+| `image` | IMAGE | Yes | - | The input image that ControlNet will use as guidance |
+| `strength` | FLOAT | Yes | 0.0 - 10.0 | The strength of the ControlNet effect (default: 1.0) |
+| `start_percent` | FLOAT | Yes | 0.0 - 1.0 | The starting point in the generation process where ControlNet begins to apply (default: 0.0) |
+| `end_percent` | FLOAT | Yes | 0.0 - 1.0 | The ending point in the generation process where ControlNet stops applying (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The modified positive conditioning with ControlNet guidance applied |
+| `negative` | CONDITIONING | The modified negative conditioning with ControlNet guidance applied |
diff --git a/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx b/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx
new file mode 100644
index 000000000..8bc8b95b1
--- /dev/null
+++ b/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx
@@ -0,0 +1,33 @@
+---
+title: "ControlNetInpaintingAliMamaApply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetInpaintingAliMamaApply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetInpaintingAliMamaApply"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetInpaintingAliMamaApply/en.md)
+
+The ControlNetInpaintingAliMamaApply node applies ControlNet conditioning for inpainting tasks by combining positive and negative conditioning with a control image and mask. It processes the input image and mask to create modified conditioning that guides the generation process, allowing for precise control over which areas of the image are inpainted. The node supports strength adjustment and timing controls to fine-tune the ControlNet's influence during different stages of the generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The positive conditioning that guides the generation toward desired content |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning that guides the generation away from unwanted content |
+| `control_net` | CONTROL_NET | Yes | - | The ControlNet model that provides additional control over the generation |
+| `vae` | VAE | Yes | - | The VAE (Variational Autoencoder) used for encoding and decoding images |
+| `image` | IMAGE | Yes | - | The input image that serves as control guidance for the ControlNet |
+| `mask` | MASK | Yes | - | The mask that defines which areas of the image should be inpainted |
+| `strength` | FLOAT | Yes | 0.0 to 10.0 | The strength of the ControlNet effect (default: 1.0) |
+| `start_percent` | FLOAT | Yes | 0.0 to 1.0 | The starting point (as percentage) of when ControlNet influence begins during generation (default: 0.0) |
+| `end_percent` | FLOAT | Yes | 0.0 to 1.0 | The ending point (as percentage) of when ControlNet influence stops during generation (default: 1.0) |
+
+**Note:** When the ControlNet has `concat_mask` enabled, the mask is inverted and applied to the image before processing, and the mask is included in the extra concatenation data sent to the ControlNet.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The modified positive conditioning with ControlNet applied for inpainting |
+| `negative` | CONDITIONING | The modified negative conditioning with ControlNet applied for inpainting |
diff --git a/built-in-nodes/ControlNetLoader.mdx b/built-in-nodes/ControlNetLoader.mdx
new file mode 100644
index 000000000..1516c3e09
--- /dev/null
+++ b/built-in-nodes/ControlNetLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "ControlNetLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetLoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/controlnet` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+The ControlNetLoader node is designed to load a ControlNet model from a specified path. It plays a crucial role in initializing ControlNet models, which are essential for applying control mechanisms over generated content or modifying existing content based on control signals.
+
+## Inputs
+
+| Field             | Comfy dtype       | Description                                                                       |
+|-------------------|-------------------|-----------------------------------------------------------------------------------|
+| `control_net_name`| `COMBO[STRING]`    | Specifies the name of the ControlNet model to be loaded, used to locate the model file within a predefined directory structure. |
+
+## Outputs
+
+| Field          | Comfy dtype   | Description                                                              |
+|----------------|---------------|--------------------------------------------------------------------------|
+| `control_net`  | `CONTROL_NET` | Returns the loaded ControlNet model, ready for use in controlling or modifying content generation processes. |
diff --git a/built-in-nodes/ConvertStringToComboNode.mdx b/built-in-nodes/ConvertStringToComboNode.mdx
new file mode 100644
index 000000000..dad6b1a7d
--- /dev/null
+++ b/built-in-nodes/ConvertStringToComboNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "ConvertStringToComboNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConvertStringToComboNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConvertStringToComboNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertStringToComboNode/en.md)
+
+The Convert String to Combo node takes a text string as input and converts it into a Combo data type. This allows you to use a text value as a selection for other nodes that require a Combo input. It simply passes the string value through unchanged but changes its data type.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | N/A | The text string to be converted into a Combo type. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | COMBO | The input string, now formatted as a Combo data type. |
diff --git a/built-in-nodes/CosmosImageToVideoLatent.mdx b/built-in-nodes/CosmosImageToVideoLatent.mdx
new file mode 100644
index 000000000..fb539e505
--- /dev/null
+++ b/built-in-nodes/CosmosImageToVideoLatent.mdx
@@ -0,0 +1,30 @@
+---
+title: "CosmosImageToVideoLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CosmosImageToVideoLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CosmosImageToVideoLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CosmosImageToVideoLatent/en.md)
+
+The CosmosImageToVideoLatent node creates video latent representations from input images. It generates a blank video latent and optionally encodes start and/or end images into the beginning and/or end frames of the video sequence. When images are provided, it also creates corresponding noise masks to indicate which parts of the latent should be preserved during generation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `vae` | VAE | Yes | - | The VAE model used for encoding images into latent space |
+| `width` | INT | No | 16 to MAX_RESOLUTION | The width of the output video in pixels (default: 1280) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | The height of the output video in pixels (default: 704) |
+| `length` | INT | No | 1 to MAX_RESOLUTION | The number of frames in the video sequence (default: 121) |
+| `batch_size` | INT | No | 1 to 4096 | The number of latent batches to generate (default: 1) |
+| `start_image` | IMAGE | No | - | Optional image to encode at the beginning of the video sequence |
+| `end_image` | IMAGE | No | - | Optional image to encode at the end of the video sequence |
+
+**Note:** When neither `start_image` nor `end_image` are provided, the node returns a blank latent without any noise mask. When either image is provided, the corresponding sections of the latent are encoded and masked accordingly.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `latent` | LATENT | The generated video latent representation with optional encoded images and corresponding noise masks |
diff --git a/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx b/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx
new file mode 100644
index 000000000..ae31c3ba0
--- /dev/null
+++ b/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx
@@ -0,0 +1,31 @@
+---
+title: "CosmosPredict2ImageToVideoLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CosmosPredict2ImageToVideoLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CosmosPredict2ImageToVideoLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CosmosPredict2ImageToVideoLatent/en.md)
+
+The CosmosPredict2ImageToVideoLatent node creates video latent representations from images for video generation. It can generate a blank video latent or incorporate start and end images to create video sequences with specified dimensions and duration. The node handles the encoding of images into the appropriate latent space format for video processing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `vae` | VAE | Yes | - | The VAE model used for encoding images into latent space |
+| `width` | INT | No | 16 to MAX_RESOLUTION | The width of the output video in pixels (default: 848, must be divisible by 16) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | The height of the output video in pixels (default: 480, must be divisible by 16) |
+| `length` | INT | No | 1 to MAX_RESOLUTION | The number of frames in the video sequence (default: 93, step: 4) |
+| `batch_size` | INT | No | 1 to 4096 | The number of video sequences to generate (default: 1) |
+| `start_image` | IMAGE | No | - | Optional starting image for the video sequence |
+| `end_image` | IMAGE | No | - | Optional ending image for the video sequence |
+
+**Note:** When neither `start_image` nor `end_image` are provided, the node generates a blank video latent. When images are provided, they are encoded and positioned at the beginning and/or end of the video sequence with appropriate masking.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | The generated video latent representation containing the encoded video sequence |
+| `noise_mask` | LATENT | A mask indicating which parts of the latent should be preserved during generation |
diff --git a/built-in-nodes/CreateHookKeyframe.mdx b/built-in-nodes/CreateHookKeyframe.mdx
new file mode 100644
index 000000000..60bb0bb00
--- /dev/null
+++ b/built-in-nodes/CreateHookKeyframe.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateHookKeyframe - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookKeyframe node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookKeyframe"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframe/en.md)
+
+The Create Hook Keyframe node allows you to define specific points in a generation process where hook behavior changes. It creates keyframes that modify the strength of hooks at particular percentages of the generation progress, and these keyframes can be chained together to create complex scheduling patterns.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `strength_mult` | FLOAT | Yes | -20.0 to 20.0 | Multiplier for hook strength at this keyframe (default: 1.0) |
+| `start_percent` | FLOAT | Yes | 0.0 to 1.0 | The percentage point in the generation process where this keyframe takes effect (default: 0.0) |
+| `prev_hook_kf` | HOOK_KEYFRAMES | No | - | Optional previous hook keyframe group to add this keyframe to |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `HOOK_KF` | HOOK_KEYFRAMES | A group of hook keyframes including the newly created keyframe |
diff --git a/built-in-nodes/CreateHookKeyframesFromFloats.mdx b/built-in-nodes/CreateHookKeyframesFromFloats.mdx
new file mode 100644
index 000000000..8bc999454
--- /dev/null
+++ b/built-in-nodes/CreateHookKeyframesFromFloats.mdx
@@ -0,0 +1,28 @@
+---
+title: "CreateHookKeyframesFromFloats - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookKeyframesFromFloats node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookKeyframesFromFloats"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesFromFloats/en.md)
+
+This node creates hook keyframes from a list of floating-point strength values, distributing them evenly between specified start and end percentages. It generates a sequence of keyframes where each strength value is assigned to a specific percentage position in the animation timeline. The node can either create a new keyframe group or add to an existing one, with an option to print the generated keyframes for debugging purposes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `floats_strength` | FLOATS | Yes | -1 to ∞ | A single float value or list of float values representing strength values for the keyframes (default: -1) |
+| `start_percent` | FLOAT | Yes | 0.0 to 1.0 | The starting percentage position for the first keyframe in the timeline (default: 0.0) |
+| `end_percent` | FLOAT | Yes | 0.0 to 1.0 | The ending percentage position for the last keyframe in the timeline (default: 1.0) |
+| `print_keyframes` | BOOLEAN | Yes | True/False | When enabled, prints the generated keyframe information to the console (default: False) |
+| `prev_hook_kf` | HOOK_KEYFRAMES | No | - | An existing hook keyframe group to add the new keyframes to, or creates a new group if not provided |
+
+**Note:** The `floats_strength` parameter accepts either a single float value or an iterable list of floats. The keyframes are distributed linearly between `start_percent` and `end_percent` based on the number of strength values provided.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `HOOK_KF` | HOOK_KEYFRAMES | A hook keyframe group containing the newly created keyframes, either as a new group or appended to the input keyframe group |
diff --git a/built-in-nodes/CreateHookKeyframesInterpolated.mdx b/built-in-nodes/CreateHookKeyframesInterpolated.mdx
new file mode 100644
index 000000000..203226f3a
--- /dev/null
+++ b/built-in-nodes/CreateHookKeyframesInterpolated.mdx
@@ -0,0 +1,29 @@
+---
+title: "CreateHookKeyframesInterpolated - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookKeyframesInterpolated node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookKeyframesInterpolated"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesInterpolated/en.md)
+
+Creates a sequence of hook keyframes with interpolated strength values between a start and end point. The node generates multiple keyframes that smoothly transition the strength parameter across a specified percentage range of the generation process, using various interpolation methods to control the transition curve.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `strength_start` | FLOAT | Yes | 0.0 - 10.0 | The starting strength value for the interpolation sequence (default: 1.0) |
+| `strength_end` | FLOAT | Yes | 0.0 - 10.0 | The ending strength value for the interpolation sequence (default: 1.0) |
+| `interpolation` | COMBO | Yes | Multiple options available | The interpolation method used to transition between strength values |
+| `start_percent` | FLOAT | Yes | 0.0 - 1.0 | The starting percentage position in the generation process (default: 0.0) |
+| `end_percent` | FLOAT | Yes | 0.0 - 1.0 | The ending percentage position in the generation process (default: 1.0) |
+| `keyframes_count` | INT | Yes | 2 - 100 | The number of keyframes to generate in the interpolation sequence (default: 5) |
+| `print_keyframes` | BOOLEAN | Yes | True/False | Whether to print generated keyframe information to the log (default: False) |
+| `prev_hook_kf` | HOOK_KEYFRAMES | No | - | Optional previous hook keyframes group to append to |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `HOOK_KF` | HOOK_KEYFRAMES | The generated hook keyframes group containing the interpolated sequence |
diff --git a/built-in-nodes/CreateHookLora.mdx b/built-in-nodes/CreateHookLora.mdx
new file mode 100644
index 000000000..3c3933d54
--- /dev/null
+++ b/built-in-nodes/CreateHookLora.mdx
@@ -0,0 +1,30 @@
+---
+title: "CreateHookLora - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookLora node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookLora"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookLora/en.md)
+
+The Create Hook LoRA node generates hook objects for applying LoRA (Low-Rank Adaptation) modifications to models. It loads a specified LoRA file and creates hooks that can adjust model and CLIP strengths, then combines these hooks with any existing hooks passed to it. The node efficiently manages LoRA loading by caching previously loaded LoRA files to avoid redundant operations.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `lora_name` | STRING | Yes | Multiple options available | The name of the LoRA file to load from the loras directory |
+| `strength_model` | FLOAT | Yes | -20.0 to 20.0 | The strength multiplier for model adjustments (default: 1.0) |
+| `strength_clip` | FLOAT | Yes | -20.0 to 20.0 | The strength multiplier for CLIP adjustments (default: 1.0) |
+| `prev_hooks` | HOOKS | No | N/A | Optional existing hook group to combine with the new LoRA hooks |
+
+**Parameter Constraints:**
+
+- If both `strength_model` and `strength_clip` are set to 0, the node will skip creating new LoRA hooks and return the existing hooks unchanged
+- The node caches the last loaded LoRA file to optimize performance when the same LoRA is used repeatedly
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `HOOKS` | HOOKS | A hook group containing the combined LoRA hooks and any previous hooks |
diff --git a/built-in-nodes/CreateHookLoraModelOnly.mdx b/built-in-nodes/CreateHookLoraModelOnly.mdx
new file mode 100644
index 000000000..b66a25673
--- /dev/null
+++ b/built-in-nodes/CreateHookLoraModelOnly.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateHookLoraModelOnly - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookLoraModelOnly node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookLoraModelOnly"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookLoraModelOnly/en.md)
+
+This node creates a LoRA (Low-Rank Adaptation) hook that applies only to the model component, allowing you to modify model behavior without affecting the CLIP component. It loads a LoRA file and applies it with a specified strength to the model while keeping the CLIP component unchanged. The node can be chained with previous hooks to create complex modification pipelines.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `lora_name` | STRING | Yes | Multiple options available | The name of the LoRA file to load from the loras folder |
+| `strength_model` | FLOAT | Yes | -20.0 to 20.0 | The strength multiplier for applying the LoRA to the model component (default: 1.0) |
+| `prev_hooks` | HOOKS | No | - | Optional previous hooks to chain with this hook |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `hooks` | HOOKS | The created LoRA hook that can be applied to model processing |
diff --git a/built-in-nodes/CreateHookModelAsLora.mdx b/built-in-nodes/CreateHookModelAsLora.mdx
new file mode 100644
index 000000000..8e64ffa01
--- /dev/null
+++ b/built-in-nodes/CreateHookModelAsLora.mdx
@@ -0,0 +1,32 @@
+---
+title: "CreateHookModelAsLora - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookModelAsLora node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookModelAsLora"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookModelAsLora/en.md)
+
+This node creates a hook model as a LoRA (Low-Rank Adaptation) by loading checkpoint weights and applying strength adjustments to both the model and CLIP components. It allows you to apply LoRA-style modifications to existing models through a hook-based approach, enabling fine-tuning and adaptation without permanent model changes. The node can combine with previous hooks and caches loaded weights for efficiency.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `ckpt_name` | COMBO | Yes | Multiple options available | The checkpoint file to load weights from (select from available checkpoints) |
+| `strength_model` | FLOAT | Yes | -20.0 to 20.0 | The strength multiplier applied to the model weights (default: 1.0) |
+| `strength_clip` | FLOAT | Yes | -20.0 to 20.0 | The strength multiplier applied to the CLIP weights (default: 1.0) |
+| `prev_hooks` | HOOKS | No | - | Optional previous hooks to combine with the newly created LoRA hooks |
+
+**Parameter Constraints:**
+
+- The `ckpt_name` parameter loads checkpoints from the available checkpoints folder
+- Both strength parameters accept values from -20.0 to 20.0 with 0.01 step increments
+- When `prev_hooks` is not provided, the node creates a new hook group
+- The node caches loaded weights to avoid reloading the same checkpoint multiple times
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `HOOKS` | HOOKS | The created LoRA hooks, combined with any previous hooks if provided |
diff --git a/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx b/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx
new file mode 100644
index 000000000..31a4124e9
--- /dev/null
+++ b/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateHookModelAsLoraModelOnly - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookModelAsLoraModelOnly node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookModelAsLoraModelOnly"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookModelAsLoraModelOnly/en.md)
+
+This node creates a hook that applies a LoRA (Low-Rank Adaptation) model to modify only the model component of a neural network. It loads a checkpoint file and applies it with a specified strength to the model while leaving the CLIP component unchanged. This is an experimental node that extends the functionality of the base CreateHookModelAsLora class.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `ckpt_name` | STRING | Yes | Multiple options available | The checkpoint file to load as a LoRA model. Available options depend on the checkpoints folder contents. |
+| `strength_model` | FLOAT | Yes | -20.0 to 20.0 | The strength multiplier for applying the LoRA to the model component (default: 1.0) |
+| `prev_hooks` | HOOKS | No | - | Optional previous hooks to chain with this hook |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `hooks` | HOOKS | The created hook group containing the LoRA model modification |
diff --git a/built-in-nodes/CreateList.mdx b/built-in-nodes/CreateList.mdx
new file mode 100644
index 000000000..3b7a28d48
--- /dev/null
+++ b/built-in-nodes/CreateList.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateList - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateList node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateList"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateList/en.md)
+
+The Create List node combines multiple inputs into a single, sequential list. It takes any number of inputs of the same data type and concatenates them in the order they are connected. This node is useful for preparing batches of data, such as images or text, to be processed by other nodes in a workflow.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `input_*` | Varies | Yes | Any | A variable number of input slots. You can add more inputs by clicking the plus (+) icon. All inputs must be of the same data type (e.g., all IMAGE or all STRING). |
+
+**Note:** The node will automatically create new input slots as you connect items. All connected inputs must share the same data type for the node to function correctly.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `list` | Varies | A single list containing all the items from the connected inputs, concatenated in the order they were provided. The output data type matches the input data type. |
diff --git a/built-in-nodes/CreateVideo.mdx b/built-in-nodes/CreateVideo.mdx
new file mode 100644
index 000000000..be00154d5
--- /dev/null
+++ b/built-in-nodes/CreateVideo.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateVideo/en.md)
+
+The Create Video node generates a video file from a sequence of images. You can specify the playback speed using frames per second and optionally add audio to the video. The node combines your images into a video format that can be played back with the specified frame rate.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | The images to create a video from. |
+| `fps` | FLOAT | Yes | 1.0 - 120.0 | The frames per second for the video playback speed (default: 30.0). |
+| `audio` | AUDIO | No | - | The audio to add to the video. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file containing the input images and optional audio. |
diff --git a/built-in-nodes/CropMask.mdx b/built-in-nodes/CropMask.mdx
new file mode 100644
index 000000000..4bd21801d
--- /dev/null
+++ b/built-in-nodes/CropMask.mdx
@@ -0,0 +1,24 @@
+---
+title: "CropMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CropMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CropMask"
+icon: "circle"
+mode: wide
+---
+The CropMask node is designed for cropping a specified area from a given mask. It allows users to define the region of interest by specifying coordinates and dimensions, effectively extracting a portion of the mask for further processing or analysis.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | MASK        | The mask input represents the mask image to be cropped. It is essential for defining the area to be extracted based on the specified coordinates and dimensions. |
+| `x`       | INT         | The x coordinate specifies the starting point on the horizontal axis from which the cropping should begin. |
+| `y`       | INT         | The y coordinate determines the starting point on the vertical axis for the cropping operation. |
+| `width`   | INT         | Width defines the horizontal extent of the crop area from the starting point. |
+| `height`  | INT         | Height specifies the vertical extent of the crop area from the starting point. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | MASK        | The output is a cropped mask, which is a portion of the original mask defined by the specified coordinates and dimensions. |
diff --git a/built-in-nodes/CustomCombo.mdx b/built-in-nodes/CustomCombo.mdx
new file mode 100644
index 000000000..cfc47fa03
--- /dev/null
+++ b/built-in-nodes/CustomCombo.mdx
@@ -0,0 +1,24 @@
+---
+title: "CustomCombo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CustomCombo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CustomCombo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CustomCombo/en.md)
+
+The Custom Combo node allows you to create a custom dropdown menu with your own list of text options. It is a frontend-focused node that provides a backend representation to ensure compatibility within your workflow. When you select an option from the dropdown, the node outputs that text as a string.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `choice` | COMBO | Yes | User-defined | The text option selected from the custom dropdown. The list of available options is defined by the user in the node's frontend interface. |
+
+**Note:** The validation for this node's input is intentionally disabled. This allows you to define any custom text options you want in the frontend without the backend checking if your selection is from a predefined list.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The text string of the option selected from the custom combo box. |
diff --git a/built-in-nodes/DCTestNode.mdx b/built-in-nodes/DCTestNode.mdx
new file mode 100644
index 000000000..63e51b1f9
--- /dev/null
+++ b/built-in-nodes/DCTestNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "DCTestNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DCTestNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DCTestNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DCTestNode/en.md)
+
+The DCTestNode is a logic node that returns different types of data based on a user's selection from a dynamic combo box. It acts as a conditional router, where the chosen option determines which input field is active and what type of value the node will output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `combo` | COMBO | Yes | `"option1"`<br />`"option2"`<br />`"option3"`<br />`"option4"` | The main selection that determines which input field is active and what the node will output. |
+| `string` | STRING | No | - | A text input field. This field is only active and required when `combo` is set to `"option1"`. |
+| `integer` | INT | No | - | A whole number input field. This field is only active and required when `combo` is set to `"option2"`. |
+| `image` | IMAGE | No | - | An image input field. This field is only active and required when `combo` is set to `"option3"`. |
+| `subcombo` | COMBO | No | `"opt1"`<br />`"opt2"` | A secondary selection that appears when `combo` is set to `"option4"`. It determines which nested input fields are active. |
+| `float_x` | FLOAT | No | - | A decimal number input. This field is only active and required when `combo` is set to `"option4"` and `subcombo` is set to `"opt1"`. |
+| `float_y` | FLOAT | No | - | A decimal number input. This field is only active and required when `combo` is set to `"option4"` and `subcombo` is set to `"opt1"`. |
+| `mask1` | MASK | No | - | A mask input field. This field is only active when `combo` is set to `"option4"` and `subcombo` is set to `"opt2"`. It is optional. |
+
+**Parameter Constraints:**
+
+* The `combo` parameter controls the visibility and requirement of all other input fields. Only the inputs associated with the selected `combo` option will be shown and are required (except for `mask1` which is optional).
+* When `combo` is set to `"option4"`, the `subcombo` parameter becomes required and controls a second set of nested inputs (`float_x`/`float_y` or `mask1`).
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | ANYTYPE | The output depends on the selected `combo` option. It can be a STRING (`"option1"`), an INT (`"option2"`), an IMAGE (`"option3"`), or a string representation of the `subcombo` dictionary (`"option4"`). |
diff --git a/built-in-nodes/DeprecatedCheckpointLoader.mdx b/built-in-nodes/DeprecatedCheckpointLoader.mdx
new file mode 100644
index 000000000..de462d9a6
--- /dev/null
+++ b/built-in-nodes/DeprecatedCheckpointLoader.mdx
@@ -0,0 +1,23 @@
+---
+title: "DeprecatedCheckpointLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DeprecatedCheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DeprecatedCheckpointLoader"
+icon: "circle"
+mode: wide
+---
+The CheckpointLoader node is designed for advanced loading operations, specifically to load model checkpoints along with their configurations. It facilitates the retrieval of model components necessary for initializing and running generative models, including configurations and checkpoints from specified directories.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|--------------|-------------|
+| `config_name` | COMBO[STRING] | Specifies the name of the configuration file to be used. This is crucial for determining the model's parameters and settings, affecting the model's behavior and performance. |
+| `ckpt_name`  | COMBO[STRING] | Indicates the name of the checkpoint file to be loaded. This directly influences the state of the model being initialized, impacting its initial weights and biases. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | Represents the primary model loaded from the checkpoint, ready for further operations or inference. |
+| `clip`    | CLIP      | Provides the CLIP model component, if available and requested, loaded from the checkpoint. |
+| `vae`     | VAE       | Delivers the VAE model component, if available and requested, loaded from the checkpoint. |
diff --git a/built-in-nodes/DeprecatedDiffusersLoader.mdx b/built-in-nodes/DeprecatedDiffusersLoader.mdx
new file mode 100644
index 000000000..dde50e8e1
--- /dev/null
+++ b/built-in-nodes/DeprecatedDiffusersLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "DeprecatedDiffusersLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DeprecatedDiffusersLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DeprecatedDiffusersLoader"
+icon: "circle"
+mode: wide
+---
+The DiffusersLoader node is designed for loading models from the diffusers library, specifically handling the loading of UNet, CLIP, and VAE models based on provided model paths. It facilitates the integration of these models into the ComfyUI framework, enabling advanced functionalities such as text-to-image generation, image manipulation, and more.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|--------------|-------------|
+| `model_path` | COMBO[STRING] | Specifies the path to the model to be loaded. This path is crucial as it determines which model will be utilized for subsequent operations, affecting the output and capabilities of the node. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The loaded UNet model, which is part of the output tuple. This model is essential for image synthesis and manipulation tasks within the ComfyUI framework. |
+| `clip`    | CLIP      | The loaded CLIP model, included in the output tuple if requested. This model enables advanced text and image understanding and manipulation capabilities. |
+| `vae`     | VAE       | The loaded VAE model, included in the output tuple if requested. This model is crucial for tasks involving latent space manipulation and image generation. |
diff --git a/built-in-nodes/DiffControlNetLoader.mdx b/built-in-nodes/DiffControlNetLoader.mdx
new file mode 100644
index 000000000..d64cc9881
--- /dev/null
+++ b/built-in-nodes/DiffControlNetLoader.mdx
@@ -0,0 +1,23 @@
+---
+title: "DiffControlNetLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DiffControlNetLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DiffControlNetLoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/controlnet` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+The DiffControlNetLoader node is designed for loading differential control networks, which are specialized models that can modify the behavior of another model based on control net specifications. This node allows for the dynamic adjustment of model behaviors by applying differential control nets, facilitating the creation of customized model outputs.
+
+## Inputs
+
+| Field               | Comfy dtype       | Description                                                                                 |
+|---------------------|-------------------|---------------------------------------------------------------------------------------------|
+| `model`             | `MODEL`           | The base model to which the differential control net will be applied, allowing for customization of the model's behavior. |
+| `control_net_name`  | `COMBO[STRING]`    | Identifies the specific differential control net to be loaded and applied to the base model for modifying its behavior. |
+
+## Outputs
+
+| Field          | Comfy dtype   | Description                                                                   |
+|----------------|---------------|-------------------------------------------------------------------------------|
+| `control_net`  | `CONTROL_NET` | A differential control net that has been loaded and is ready to be applied to a base model for behavior modification. |
diff --git a/built-in-nodes/DifferentialDiffusion.mdx b/built-in-nodes/DifferentialDiffusion.mdx
new file mode 100644
index 000000000..612f033cc
--- /dev/null
+++ b/built-in-nodes/DifferentialDiffusion.mdx
@@ -0,0 +1,23 @@
+---
+title: "DifferentialDiffusion - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DifferentialDiffusion node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DifferentialDiffusion"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DifferentialDiffusion/en.md)
+
+The Differential Diffusion node modifies the denoising process by applying a binary mask based on timestep thresholds. It creates a mask that blends between the original denoise mask and a threshold-based binary mask, allowing controlled adjustment of the diffusion process strength.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to modify |
+| `strength` | FLOAT | No | 0.0 - 1.0 | Controls the blending strength between the original denoise mask and the binary threshold mask (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified diffusion model with updated denoise mask function |
diff --git a/built-in-nodes/DiffusersLoader.mdx b/built-in-nodes/DiffusersLoader.mdx
new file mode 100644
index 000000000..c01c8cc2b
--- /dev/null
+++ b/built-in-nodes/DiffusersLoader.mdx
@@ -0,0 +1,24 @@
+---
+title: "DiffusersLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DiffusersLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DiffusersLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DiffusersLoader/en.md)
+
+The DiffusersLoader node loads pre-trained models from the diffusers format. It searches for valid diffusers model directories containing a model_index.json file and loads them as MODEL, CLIP, and VAE components for use in the pipeline. This node is part of the deprecated loaders category and provides compatibility with Hugging Face diffusers models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_path` | STRING | Yes | Multiple options available<br />(auto-populated from diffusers folders) | The path to the diffusers model directory to load. The node automatically scans for valid diffusers models in the configured diffusers folders and lists available options. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | The loaded model component from the diffusers format |
+| `CLIP` | CLIP | The loaded CLIP model component from the diffusers format |
+| `VAE` | VAE | The loaded VAE (Variational Autoencoder) component from the diffusers format |
diff --git a/built-in-nodes/DisableNoise.mdx b/built-in-nodes/DisableNoise.mdx
new file mode 100644
index 000000000..3a454ed23
--- /dev/null
+++ b/built-in-nodes/DisableNoise.mdx
@@ -0,0 +1,22 @@
+---
+title: "DisableNoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DisableNoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DisableNoise"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DisableNoise/en.md)
+
+The DisableNoise node provides an empty noise configuration that can be used to disable noise generation in sampling processes. It returns a special noise object that contains no noise data, allowing other nodes to skip noise-related operations when connected to this output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| *No input parameters* | - | - | - | This node does not require any input parameters. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `NOISE` | NOISE | Returns an empty noise configuration that can be used to disable noise generation in sampling processes. |
diff --git a/built-in-nodes/DualCFGGuider.mdx b/built-in-nodes/DualCFGGuider.mdx
new file mode 100644
index 000000000..f8a308445
--- /dev/null
+++ b/built-in-nodes/DualCFGGuider.mdx
@@ -0,0 +1,28 @@
+---
+title: "DualCFGGuider - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DualCFGGuider node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DualCFGGuider"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DualCFGGuider/en.md)
+
+The DualCFGGuider node creates a guidance system for dual classifier-free guidance sampling. It combines two positive conditioning inputs with one negative conditioning input, applying different guidance scales to each conditioning pair to control the influence of each prompt on the generated output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to use for guidance |
+| `cond1` | CONDITIONING | Yes | - | The first positive conditioning input |
+| `cond2` | CONDITIONING | Yes | - | The second positive conditioning input |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning input |
+| `cfg_conds` | FLOAT | Yes | 0.0 - 100.0 | Guidance scale for the first positive conditioning (default: 8.0) |
+| `cfg_cond2_negative` | FLOAT | Yes | 0.0 - 100.0 | Guidance scale for the second positive and negative conditioning (default: 8.0) |
+| `style` | COMBO | Yes | "regular"<br />"nested" | The guidance style to apply (default: "regular") |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `GUIDER` | GUIDER | A configured guidance system ready for use with sampling |
diff --git a/built-in-nodes/DualCLIPLoader.mdx b/built-in-nodes/DualCLIPLoader.mdx
new file mode 100644
index 000000000..1b1d59b42
--- /dev/null
+++ b/built-in-nodes/DualCLIPLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "DualCLIPLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DualCLIPLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DualCLIPLoader"
+icon: "circle"
+mode: wide
+---
+The DualCLIPLoader node is designed for loading two CLIP models simultaneously, facilitating operations that require the integration or comparison of features from both models.
+
+This node will detect models located in the `ComfyUI/models/text_encoders` folder.
+
+## Inputs
+
+| Parameter    | Comfy dtype     | Description                                                                                                                                                                                     |
+| ------------ | --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `clip_name1` | COMBO[STRING] | Specifies the name of the first CLIP model to be loaded. This parameter is crucial for identifying and retrieving the correct model from a predefined list of available CLIP models.            |
+| `clip_name2` | COMBO[STRING] | Specifies the name of the second CLIP model to be loaded. This parameter enables the loading of a second distinct CLIP model for comparative or integrative analysis alongside the first model. |
+| `type`       | `option`        | Choose from "sdxl", "sd3", "flux" to adapt to different models.                                                                                                                                 |
+
+* The order of loading does not affect the output effect
+
+## Outputs
+
+| Parameter | Data Type | Description                                                                                                           |
+| --------- | ----------- | --------------------------------------------------------------------------------------------------------------------- |
+| `clip`    | CLIP      | The output is a combined CLIP model that integrates the features or functionalities of the two specified CLIP models. |
diff --git a/built-in-nodes/EasyCache.mdx b/built-in-nodes/EasyCache.mdx
new file mode 100644
index 000000000..58c755d19
--- /dev/null
+++ b/built-in-nodes/EasyCache.mdx
@@ -0,0 +1,26 @@
+---
+title: "EasyCache - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EasyCache node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EasyCache"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EasyCache/en.md)
+
+The EasyCache node implements a native caching system for models to improve performance by reusing previously computed steps during the sampling process. It adds EasyCache functionality to a model with configurable thresholds for when to start and stop using the cache during the sampling timeline.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to add EasyCache to. |
+| `reuse_threshold` | FLOAT | No | 0.0 - 3.0 | The threshold for reusing cached steps (default: 0.2). |
+| `start_percent` | FLOAT | No | 0.0 - 1.0 | The relative sampling step to begin use of EasyCache (default: 0.15). |
+| `end_percent` | FLOAT | No | 0.0 - 1.0 | The relative sampling step to end use of EasyCache (default: 0.95). |
+| `verbose` | BOOLEAN | No | - | Whether to log verbose information (default: False). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The model with EasyCache functionality added. |
diff --git a/built-in-nodes/ElevenLabsAudioIsolation.mdx b/built-in-nodes/ElevenLabsAudioIsolation.mdx
new file mode 100644
index 000000000..64e7cff80
--- /dev/null
+++ b/built-in-nodes/ElevenLabsAudioIsolation.mdx
@@ -0,0 +1,22 @@
+---
+title: "ElevenLabsAudioIsolation - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsAudioIsolation node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsAudioIsolation"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsAudioIsolation/en.md)
+
+The ElevenLabs Voice Isolation node removes background noise from an audio file, isolating the vocals or speech. It sends the audio to the ElevenLabs API for processing and returns the cleaned audio.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | | Audio to process for background noise removal. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The processed audio with background noise removed. |
diff --git a/built-in-nodes/ElevenLabsInstantVoiceClone.mdx b/built-in-nodes/ElevenLabsInstantVoiceClone.mdx
new file mode 100644
index 000000000..3820b3e2f
--- /dev/null
+++ b/built-in-nodes/ElevenLabsInstantVoiceClone.mdx
@@ -0,0 +1,25 @@
+---
+title: "ElevenLabsInstantVoiceClone - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsInstantVoiceClone node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsInstantVoiceClone"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsInstantVoiceClone/en.md)
+
+The ElevenLabs Instant Voice Clone node creates a new, unique voice model by analyzing 1 to 8 audio recordings of a person's voice. It sends these samples to the ElevenLabs API, which processes them to generate a voice clone that can be used for text-to-speech synthesis.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio_*` | AUDIO | Yes | 1 to 8 files | Audio recordings for voice cloning. You must provide between 1 and 8 audio files. |
+| `remove_background_noise` | BOOLEAN | No | True / False | Remove background noise from voice samples using audio isolation. (default: False) |
+
+**Note:** You must provide at least one audio file, and you can provide up to eight. The node will automatically create input slots for the audio files you add.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `voice` | ELEVENLABS_VOICE | The unique identifier for the newly created cloned voice model. This output can be connected to other ElevenLabs text-to-speech nodes. |
diff --git a/built-in-nodes/ElevenLabsSpeechToSpeech.mdx b/built-in-nodes/ElevenLabsSpeechToSpeech.mdx
new file mode 100644
index 000000000..39ed4e53b
--- /dev/null
+++ b/built-in-nodes/ElevenLabsSpeechToSpeech.mdx
@@ -0,0 +1,28 @@
+---
+title: "ElevenLabsSpeechToSpeech - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsSpeechToSpeech node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsSpeechToSpeech"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToSpeech/en.md)
+
+The ElevenLabs Speech to Speech node transforms an input audio file from one voice to another. It uses the ElevenLabs API to convert speech while preserving the original content and emotional tone of the audio.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `voice` | CUSTOM | Yes | - | Target voice for the transformation. Connect from Voice Selector or Instant Voice Clone. |
+| `audio` | AUDIO | Yes | - | Source audio to transform. |
+| `stability` | FLOAT | No | 0.0 - 1.0 | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech (default: 0.5). |
+| `model` | DYNAMICCOMBO | No | `eleven_multilingual_sts_v2`<br />`eleven_english_sts_v2` | Model to use for speech-to-speech transformation. Each option provides a specific set of voice settings (similarity_boost, style, use_speaker_boost, speed). |
+| `output_format` | COMBO | No | `"mp3_44100_192"`<br />`"opus_48000_192"` | Audio output format (default: "mp3_44100_192"). |
+| `seed` | INT | No | 0 - 4294967295 | Seed for reproducibility (default: 0). |
+| `remove_background_noise` | BOOLEAN | No | - | Remove background noise from input audio using audio isolation (default: False). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The transformed audio file in the specified output format. |
diff --git a/built-in-nodes/ElevenLabsSpeechToText.mdx b/built-in-nodes/ElevenLabsSpeechToText.mdx
new file mode 100644
index 000000000..5461ea0d0
--- /dev/null
+++ b/built-in-nodes/ElevenLabsSpeechToText.mdx
@@ -0,0 +1,35 @@
+---
+title: "ElevenLabsSpeechToText - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsSpeechToText node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsSpeechToText"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToText/en.md)
+
+The ElevenLabs Speech to Text node transcribes audio files into text. It uses ElevenLabs' API to convert spoken words into a written transcript, supporting features like automatic language detection, identifying different speakers, and tagging non-speech sounds like music or laughter.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | Audio to transcribe. |
+| `model` | COMBO | Yes | `"scribe_v2"` | Model to use for transcription. Selecting this model reveals additional parameters. |
+| `tag_audio_events` | BOOLEAN | No | - | Annotate sounds like (laughter), (music), etc. in transcript. This parameter is revealed when the `"scribe_v2"` model is selected. (default: False) |
+| `diarize` | BOOLEAN | No | - | Annotate which speaker is talking. This parameter is revealed when the `"scribe_v2"` model is selected. (default: False) |
+| `diarization_threshold` | FLOAT | No | 0.1 - 0.4 | Speaker separation sensitivity. Lower values are more sensitive to speaker changes. This parameter is revealed when the `"scribe_v2"` model is selected and `diarize` is enabled. (default: 0.22) |
+| `temperature` | FLOAT | No | 0.0 - 2.0 | Randomness control. 0.0 uses model default. Higher values increase randomness. This parameter is revealed when the `"scribe_v2"` model is selected. (default: 0.0) |
+| `timestamps_granularity` | COMBO | No | `"word"`<br />`"character"`<br />`"none"` | Timing precision for transcript words. This parameter is revealed when the `"scribe_v2"` model is selected. (default: "word") |
+| `language_code` | STRING | No | - | ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection. (default: "") |
+| `num_speakers` | INT | No | 0 - 32 | Maximum number of speakers to predict. Set to 0 for automatic detection. (default: 0) |
+| `seed` | INT | No | 0 - 2147483647 | Seed for reproducibility (determinism not guaranteed). (default: 1) |
+
+**Note:** The `num_speakers` parameter cannot be set to a value greater than 0 when the `diarize` option is enabled. You must either disable `diarize` or set `num_speakers` to 0.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `text` | STRING | The transcribed text from the audio. |
+| `language_code` | STRING | The detected language code of the audio. |
+| `words_json` | STRING | A JSON-formatted string containing detailed word-level information, including timestamps and speaker labels if enabled. |
diff --git a/built-in-nodes/ElevenLabsTextToDialogue.mdx b/built-in-nodes/ElevenLabsTextToDialogue.mdx
new file mode 100644
index 000000000..d54b46100
--- /dev/null
+++ b/built-in-nodes/ElevenLabsTextToDialogue.mdx
@@ -0,0 +1,30 @@
+---
+title: "ElevenLabsTextToDialogue - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsTextToDialogue node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsTextToDialogue"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToDialogue/en.md)
+
+The ElevenLabs Text to Dialogue node generates a multi-speaker audio dialogue from text. It allows you to create a conversation by specifying different text lines and distinct voices for each participant. The node sends the dialogue request to the ElevenLabs API and returns the generated audio.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `stability` | FLOAT | No | 0.0 - 1.0 | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech. (default: 0.5) |
+| `apply_text_normalization` | COMBO | No | `"auto"`<br />`"on"`<br />`"off"` | Text normalization mode. 'auto' lets the system decide, 'on' always applies normalization, 'off' skips it. |
+| `model` | COMBO | No | `"eleven_v3"` | Model to use for dialogue generation. |
+| `inputs` | DYNAMICCOMBO | Yes | `"1"`<br />`"2"`<br />`"3"`<br />`"4"`<br />`"5"`<br />`"6"`<br />`"7"`<br />`"8"`<br />`"9"`<br />`"10"` | Number of dialogue entries. Selecting a number will generate that many text and voice input fields. |
+| `language_code` | STRING | No | - | ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection. (default: empty) |
+| `seed` | INT | No | 0 - 4294967295 | Seed for reproducibility. (default: 1) |
+| `output_format` | COMBO | No | `"mp3_44100_192"`<br />`"opus_48000_192"` | Audio output format. |
+
+**Note:** The `inputs` parameter is dynamic. When you select a number (e.g., "3"), the node will display three corresponding `text` and `voice` input fields (e.g., `text1`, `voice1`, `text2`, `voice2`, `text3`, `voice3`). Each `text` field must contain at least one character.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The generated multi-speaker dialogue audio in the selected output format. |
diff --git a/built-in-nodes/ElevenLabsTextToSoundEffects.mdx b/built-in-nodes/ElevenLabsTextToSoundEffects.mdx
new file mode 100644
index 000000000..aa82f60ed
--- /dev/null
+++ b/built-in-nodes/ElevenLabsTextToSoundEffects.mdx
@@ -0,0 +1,30 @@
+---
+title: "ElevenLabsTextToSoundEffects - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsTextToSoundEffects node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsTextToSoundEffects"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToSoundEffects/en.md)
+
+The ElevenLabs Text to Sound Effects node generates audio sound effects from a text description. It uses the ElevenLabs API to create sound effects based on your prompt, allowing you to control the duration, looping behavior, and how closely the sound follows the text.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | Yes | N/A | Text description of the sound effect to generate. This is a required field. |
+| `model` | COMBO | Yes | `"eleven_sfx_v2"` | Model to use for sound effect generation. Selecting this model reveals additional parameters: `duration` (default: 5.0, range: 0.5 to 30.0 seconds), `loop` (default: False), and `prompt_influence` (default: 0.3, range: 0.0 to 1.0). |
+| `output_format` | COMBO | Yes | `"mp3_44100_192"`<br />`"opus_48000_192"` | Audio output format. |
+
+**Parameter Details:**
+
+* **`model["duration"]`**: Duration of the generated sound in seconds. Default is 5.0, with a minimum of 0.5 and a maximum of 30.0.
+* **`model["loop"]`**: When enabled, creates a smoothly looping sound effect. Default is False.
+* **`model["prompt_influence"]`**: Controls how closely the generation follows the text prompt. Higher values make the sound follow the text more closely. Default is 0.3, with a range from 0.0 to 1.0.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The generated sound effect audio file. |
diff --git a/built-in-nodes/ElevenLabsTextToSpeech.mdx b/built-in-nodes/ElevenLabsTextToSpeech.mdx
new file mode 100644
index 000000000..464a44d2b
--- /dev/null
+++ b/built-in-nodes/ElevenLabsTextToSpeech.mdx
@@ -0,0 +1,42 @@
+---
+title: "ElevenLabsTextToSpeech - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsTextToSpeech node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsTextToSpeech"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToSpeech/en.md)
+
+The ElevenLabs Text to Speech node converts written text into spoken audio using the ElevenLabs API. It allows you to select a specific voice and fine-tune various speech characteristics like stability, speed, and style to generate a customized audio output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `voice` | CUSTOM | Yes | N/A | Voice to use for speech synthesis. Connect from Voice Selector or Instant Voice Clone. |
+| `text` | STRING | Yes | N/A | The text to convert to speech. |
+| `stability` | FLOAT | No | 0.0 - 1.0 | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech (default: 0.5). |
+| `apply_text_normalization` | COMBO | No | `"auto"`<br />`"on"`<br />`"off"` | Text normalization mode. 'auto' lets the system decide, 'on' always applies normalization, 'off' skips it. |
+| `model` | DYNAMICCOMBO | No | `"eleven_multilingual_v2"`<br />`"eleven_v3"` | Model to use for text-to-speech. Selecting a model reveals its specific parameters. |
+| `language_code` | STRING | No | N/A | ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection (default: ""). |
+| `seed` | INT | No | 0 - 2147483647 | Seed for reproducibility (determinism not guaranteed) (default: 1). |
+| `output_format` | COMBO | No | `"mp3_44100_192"`<br />`"opus_48000_192"` | Audio output format. |
+
+**Model-Specific Parameters:**
+When the `model` parameter is set to `"eleven_multilingual_v2"`, the following additional parameters become available:
+
+* `speed`: Speech speed. 1.0 is normal, &lt;1.0 slower, >1.0 faster (default: 1.0, range: 0.7 - 1.3).
+* `similarity_boost`: Similarity boost. Higher values make the voice more similar to the original (default: 0.75, range: 0.0 - 1.0).
+* `use_speaker_boost`: Boost similarity to the original speaker voice (default: False).
+* `style`: Style exaggeration. Higher values increase stylistic expression but may reduce stability (default: 0.0, range: 0.0 - 0.2).
+
+When the `model` parameter is set to `"eleven_v3"`, the following additional parameters become available:
+
+* `speed`: Speech speed. 1.0 is normal, &lt;1.0 slower, >1.0 faster (default: 1.0, range: 0.7 - 1.3).
+* `similarity_boost`: Similarity boost. Higher values make the voice more similar to the original (default: 0.75, range: 0.0 - 1.0).
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The generated audio from the text-to-speech conversion. |
diff --git a/built-in-nodes/ElevenLabsVoiceSelector.mdx b/built-in-nodes/ElevenLabsVoiceSelector.mdx
new file mode 100644
index 000000000..bde82990c
--- /dev/null
+++ b/built-in-nodes/ElevenLabsVoiceSelector.mdx
@@ -0,0 +1,22 @@
+---
+title: "ElevenLabsVoiceSelector - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsVoiceSelector node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsVoiceSelector"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsVoiceSelector/en.md)
+
+The ElevenLabs Voice Selector node allows you to choose a specific voice from a predefined list of ElevenLabs text-to-speech voices. It takes a voice name as input and outputs the corresponding voice identifier needed for audio generation. This node simplifies the process of selecting a compatible voice for use with other ElevenLabs audio nodes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `voice` | STRING | Yes | `"Adam"`<br />`"Antoni"`<br />`"Arnold"`<br />`"Bella"`<br />`"Domi"`<br />`"Elli"`<br />`"Josh"`<br />`"Rachel"`<br />`"Sam"` | Choose a voice from the predefined ElevenLabs voices. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `voice` | STRING | The unique identifier for the selected ElevenLabs voice, which can be passed to other nodes for text-to-speech generation. |
diff --git a/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx b/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx
new file mode 100644
index 000000000..fcdc8c16c
--- /dev/null
+++ b/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx
@@ -0,0 +1,23 @@
+---
+title: "EmptyAceStep1.5LatentAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyAceStep1.5LatentAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyAceStep1.5LatentAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyAceStep1.5LatentAudio/en.md)
+
+The Empty Ace Step 1.5 Latent Audio node creates an empty latent tensor designed for audio processing. It generates a silent audio latent of a specified duration and batch size, which can be used as a starting point for audio generation workflows in ComfyUI. The node calculates the latent length based on the input seconds and a fixed sample rate.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `seconds` | FLOAT | No | 1.0 - 1000.0 | The duration of the audio to generate, in seconds (default: 120.0). |
+| `batch_size` | INT | No | 1 - 4096 | The number of latent images in the batch (default: 1). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | An empty latent tensor representing silent audio, with a type identifier of "audio". |
diff --git a/built-in-nodes/EmptyAceStepLatentAudio.mdx b/built-in-nodes/EmptyAceStepLatentAudio.mdx
new file mode 100644
index 000000000..8010953cf
--- /dev/null
+++ b/built-in-nodes/EmptyAceStepLatentAudio.mdx
@@ -0,0 +1,23 @@
+---
+title: "EmptyAceStepLatentAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyAceStepLatentAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyAceStepLatentAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyAceStepLatentAudio/en.md)
+
+The EmptyAceStepLatentAudio node creates empty latent audio samples of a specified duration. It generates a batch of silent audio latents with zeros, where the length is calculated based on the input seconds and audio processing parameters. This node is useful for initializing audio processing workflows that require latent representations.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `seconds` | FLOAT | No | 1.0 - 1000.0 | The duration of the audio in seconds (default: 120.0) |
+| `batch_size` | INT | No | 1 - 4096 | The number of latent images in the batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | LATENT | Returns empty latent audio samples with zeros |
diff --git a/built-in-nodes/EmptyAudio.mdx b/built-in-nodes/EmptyAudio.mdx
new file mode 100644
index 000000000..a3fed3279
--- /dev/null
+++ b/built-in-nodes/EmptyAudio.mdx
@@ -0,0 +1,24 @@
+---
+title: "EmptyAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyAudio/en.md)
+
+The EmptyAudio node generates a silent audio clip with specified duration, sample rate, and channel configuration. It creates a waveform containing all zeros, producing complete silence for the given duration. This node is useful for creating placeholder audio or generating silent segments in audio workflows.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `duration` | FLOAT | Yes | 0.0 to 1.8446744073709552e+19 | Duration of the empty audio clip in seconds (default: 60.0) |
+| `sample_rate` | INT | Yes | - | Sample rate of the empty audio clip (default: 44100) |
+| `channels` | INT | Yes | 1 to 2 | Number of audio channels (1 for mono, 2 for stereo) (default: 2) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | The generated silent audio clip containing waveform data and sample rate information |
diff --git a/built-in-nodes/EmptyChromaRadianceLatentImage.mdx b/built-in-nodes/EmptyChromaRadianceLatentImage.mdx
new file mode 100644
index 000000000..808890eed
--- /dev/null
+++ b/built-in-nodes/EmptyChromaRadianceLatentImage.mdx
@@ -0,0 +1,24 @@
+---
+title: "EmptyChromaRadianceLatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyChromaRadianceLatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyChromaRadianceLatentImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyChromaRadianceLatentImage/en.md)
+
+The EmptyChromaRadianceLatentImage node creates a blank latent image with specified dimensions for use in chroma radiance workflows. It generates a tensor filled with zeros that serves as a starting point for latent space operations. The node allows you to define the width, height, and batch size of the empty latent image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | The width of the latent image in pixels (default: 1024, must be divisible by 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | The height of the latent image in pixels (default: 1024, must be divisible by 16) |
+| `batch_size` | INT | No | 1 to 4096 | The number of latent images to generate in a batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | The generated empty latent image tensor with specified dimensions |
diff --git a/built-in-nodes/EmptyCosmosLatentVideo.mdx b/built-in-nodes/EmptyCosmosLatentVideo.mdx
new file mode 100644
index 000000000..a02518c76
--- /dev/null
+++ b/built-in-nodes/EmptyCosmosLatentVideo.mdx
@@ -0,0 +1,25 @@
+---
+title: "EmptyCosmosLatentVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyCosmosLatentVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyCosmosLatentVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyCosmosLatentVideo/en.md)
+
+The EmptyCosmosLatentVideo node creates an empty latent video tensor with specified dimensions. It generates a zero-filled latent representation that can be used as a starting point for video generation workflows, with configurable width, height, length, and batch size parameters.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | The width of the latent video in pixels (default: 1280, must be divisible by 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | The height of the latent video in pixels (default: 704, must be divisible by 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | The number of frames in the latent video (default: 121) |
+| `batch_size` | INT | No | 1 to 4096 | The number of latent videos to generate in a batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | The generated empty latent video tensor with zero values |
diff --git a/built-in-nodes/EmptyFlux2LatentImage.mdx b/built-in-nodes/EmptyFlux2LatentImage.mdx
new file mode 100644
index 000000000..d3ee25e21
--- /dev/null
+++ b/built-in-nodes/EmptyFlux2LatentImage.mdx
@@ -0,0 +1,26 @@
+---
+title: "EmptyFlux2LatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyFlux2LatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyFlux2LatentImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyFlux2LatentImage/en.md)
+
+The EmptyFlux2LatentImage node creates a blank, empty latent representation. It generates a tensor filled with zeros, which serves as a starting point for the Flux model's denoising process. The dimensions of the latent are determined by the input width and height, scaled down by a factor of 16.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 16 to 8192 | The width of the final image to generate. The latent width will be this value divided by 16. The default value is 1024. |
+| `height` | INT | Yes | 16 to 8192 | The height of the final image to generate. The latent height will be this value divided by 16. The default value is 1024. |
+| `batch_size` | INT | No | 1 to 4096 | The number of latent samples to generate in a single batch. The default value is 1. |
+
+**Note:** The `width` and `height` inputs must be divisible by 16, as the node internally divides them by this factor to create the latent dimensions.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | A latent tensor filled with zeros. The shape is `[batch_size, 128, height // 16, width // 16]`. |
diff --git a/built-in-nodes/EmptyHunyuanImageLatent.mdx b/built-in-nodes/EmptyHunyuanImageLatent.mdx
new file mode 100644
index 000000000..a8db7d674
--- /dev/null
+++ b/built-in-nodes/EmptyHunyuanImageLatent.mdx
@@ -0,0 +1,24 @@
+---
+title: "EmptyHunyuanImageLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyHunyuanImageLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyHunyuanImageLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyHunyuanImageLatent/en.md)
+
+The EmptyHunyuanImageLatent node creates an empty latent tensor with specific dimensions for use with Hunyuan image generation models. It generates a blank starting point that can be processed through subsequent nodes in the workflow. The node allows you to specify the width, height, and batch size of the latent space.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 64 to MAX_RESOLUTION | The width of the generated latent image in pixels (default: 2048, step: 32) |
+| `height` | INT | Yes | 64 to MAX_RESOLUTION | The height of the generated latent image in pixels (default: 2048, step: 32) |
+| `batch_size` | INT | Yes | 1 to 4096 | The number of latent samples to generate in a batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | An empty latent tensor with the specified dimensions for Hunyuan image processing |
diff --git a/built-in-nodes/EmptyHunyuanLatentVideo.mdx b/built-in-nodes/EmptyHunyuanLatentVideo.mdx
new file mode 100644
index 000000000..5c47490d5
--- /dev/null
+++ b/built-in-nodes/EmptyHunyuanLatentVideo.mdx
@@ -0,0 +1,23 @@
+---
+title: "EmptyHunyuanLatentVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyHunyuanLatentVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyHunyuanLatentVideo"
+icon: "circle"
+mode: wide
+---
+The `EmptyHunyuanLatentVideo` node is similar to the `EmptyLatentImage` node. You can consider it as a blank canvas for video generation, where width, height, and length define the properties of the canvas, and the batch size determines the number of canvases to create. This node creates empty canvases ready for subsequent video generation tasks.
+
+## Inputs
+
+| Parameter    | Comfy Type | Description                                                                                |
+| ----------- | ---------- | ------------------------------------------------------------------------------------------ |
+| `width`     | `INT`      | Video width, default 848, minimum 16, maximum `nodes.MAX_RESOLUTION`, step size 16.        |
+| `height`    | `INT`      | Video height, default 480, minimum 16, maximum `nodes.MAX_RESOLUTION`, step size 16.       |
+| `length`    | `INT`      | Video length, default 25, minimum 1, maximum `nodes.MAX_RESOLUTION`, step size 4.          |
+| `batch_size`| `INT`      | Batch size, default 1, minimum 1, maximum 4096.                                           |
+
+## Outputs
+
+| Parameter | Comfy Type | Description                                                                               |
+| --------- | ---------- | ----------------------------------------------------------------------------------------- |
+| `samples` | `LATENT`   | Generated latent video samples containing zero tensors, ready for processing and generation tasks. |
diff --git a/built-in-nodes/EmptyHunyuanVideo15Latent.mdx b/built-in-nodes/EmptyHunyuanVideo15Latent.mdx
new file mode 100644
index 000000000..14876a431
--- /dev/null
+++ b/built-in-nodes/EmptyHunyuanVideo15Latent.mdx
@@ -0,0 +1,27 @@
+---
+title: "EmptyHunyuanVideo15Latent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyHunyuanVideo15Latent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyHunyuanVideo15Latent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyHunyuanVideo15Latent/en.md)
+
+This node creates an empty latent tensor specifically formatted for use with the HunyuanVideo 1.5 model. It generates a blank starting point for video generation by allocating a tensor of zeros with the correct channel count and spatial dimensions for the model's latent space.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | - | The width of the video frame in pixels. |
+| `height` | INT | Yes | - | The height of the video frame in pixels. |
+| `length` | INT | Yes | - | The number of frames in the video sequence. |
+| `batch_size` | INT | No | - | The number of video samples to generate in a batch (default: 1). |
+
+**Note:** The spatial dimensions of the generated latent tensor are calculated by dividing the input `width` and `height` by 16. The temporal dimension (frames) is calculated as `((length - 1) // 4) + 1`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | An empty latent tensor with dimensions suitable for the HunyuanVideo 1.5 model. The tensor has a shape of `[batch_size, 32, frames, height//16, width//16]`. |
diff --git a/built-in-nodes/EmptyImage.mdx b/built-in-nodes/EmptyImage.mdx
new file mode 100644
index 000000000..327509e9e
--- /dev/null
+++ b/built-in-nodes/EmptyImage.mdx
@@ -0,0 +1,56 @@
+---
+title: "EmptyImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyImage"
+icon: "circle"
+mode: wide
+---
+## Function Description
+
+The EmptyImage node is used to create blank images with specified dimensions and colors. It can generate solid-color background images, commonly used as starting points or background images for image processing workflows.
+
+## Working Principle
+
+Just like a painter preparing a blank canvas before starting to create, the EmptyImage node provides you with a "digital canvas". You can specify the canvas size (width and height), choose the base color of the canvas, and even prepare multiple canvases of the same specifications at once. This node is like an intelligent art supply store that can create standardized canvases that perfectly meet your size and color requirements.
+
+## Inputs
+
+| Parameter Name | Data Type | Description |
+|----------------|-----------|-------------|
+| `width` | INT | Sets the width of the generated image (in pixels), determining the horizontal dimensions of the canvas |
+| `height` | INT | Sets the height of the generated image (in pixels), determining the vertical dimensions of the canvas |
+| `batch_size` | INT | The number of images to generate at once, used for batch creation of images with the same specifications |
+| `color` | INT | The background color of the image. You can input hexadecimal color settings, which will be automatically converted to decimal |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The generated blank image tensor, formatted as [batch_size, height, width, 3], containing RGB three color channels |
+
+## Common Color Reference Values
+
+Since the current color input for this node is not user-friendly, with all color values being converted to decimal, here are some common color values that can be used directly for quick application.
+
+| Color Name | Hexadecimal Value |
+|------------|-------------------|
+| Black      | 0x000000         |
+| White      | 0xFFFFFF         |
+| Red        | 0xFF0000         |
+| Green      | 0x00FF00         |
+| Blue       | 0x0000FF         |
+| Yellow     | 0xFFFF00         |
+| Cyan       | 0x00FFFF         |
+| Magenta    | 0xFF00FF         |
+| Orange     | 0xFF8000         |
+| Purple     | 0x8000FF         |
+| Pink       | 0xFF80C0         |
+| Brown      | 0x8B4513         |
+| Dark Gray  | 0x404040         |
+| Light Gray | 0xC0C0C0         |
+| Navy Blue  | 0x000080         |
+| Dark Green | 0x008000         |
+| Dark Red   | 0x800000         |
+| Gold       | 0xFFD700         |
+| Silver     | 0xC0C0C0         |
+| Beige      | 0xF5F5DC         |
diff --git a/built-in-nodes/EmptyLTXVLatentVideo.mdx b/built-in-nodes/EmptyLTXVLatentVideo.mdx
new file mode 100644
index 000000000..029f9a26d
--- /dev/null
+++ b/built-in-nodes/EmptyLTXVLatentVideo.mdx
@@ -0,0 +1,25 @@
+---
+title: "EmptyLTXVLatentVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyLTXVLatentVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyLTXVLatentVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyLTXVLatentVideo/en.md)
+
+The EmptyLTXVLatentVideo node creates an empty latent tensor for video processing. It generates a blank starting point with specified dimensions that can be used as input for video generation workflows. The node produces a zero-filled latent representation with the configured width, height, length, and batch size.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 64 to MAX_RESOLUTION | The width of the latent video tensor (default: 768, step: 32) |
+| `height` | INT | Yes | 64 to MAX_RESOLUTION | The height of the latent video tensor (default: 512, step: 32) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | The number of frames in the latent video (default: 97, step: 8) |
+| `batch_size` | INT | No | 1 to 4096 | The number of latent videos to generate in a batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | The generated empty latent tensor with zero values in the specified dimensions |
diff --git a/built-in-nodes/EmptyLatentAudio.mdx b/built-in-nodes/EmptyLatentAudio.mdx
new file mode 100644
index 000000000..27d387a28
--- /dev/null
+++ b/built-in-nodes/EmptyLatentAudio.mdx
@@ -0,0 +1,23 @@
+---
+title: "EmptyLatentAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyLatentAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyLatentAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyLatentAudio/en.md)
+
+The EmptyLatentAudio node creates empty latent tensors for audio processing. It generates a blank audio latent representation with specified duration and batch size, which can be used as input for audio generation or processing workflows. The node calculates the appropriate latent dimensions based on the audio duration and sample rate.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `seconds` | FLOAT | Yes | 1.0 - 1000.0 | The duration of the audio in seconds (default: 47.6) |
+| `batch_size` | INT | Yes | 1 - 4096 | The number of latent images in the batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | Returns an empty latent tensor for audio processing with specified duration and batch size |
diff --git a/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx b/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx
new file mode 100644
index 000000000..8bd24cb4c
--- /dev/null
+++ b/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx
@@ -0,0 +1,23 @@
+---
+title: "EmptyLatentHunyuan3Dv2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyLatentHunyuan3Dv2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyLatentHunyuan3Dv2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyLatentHunyuan3Dv2/en.md)
+
+The EmptyLatentHunyuan3Dv2 node creates blank latent tensors specifically formatted for Hunyuan3Dv2 3D generation models. It generates empty latent spaces with the correct dimensions and structure required by the Hunyuan3Dv2 architecture, allowing you to start 3D generation workflows from scratch. The node produces latent tensors filled with zeros that serve as the foundation for subsequent 3D generation processes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `resolution` | INT | Yes | 1 - 8192 | The resolution dimension for the latent space (default: 3072) |
+| `batch_size` | INT | Yes | 1 - 4096 | The number of latent images in the batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | Returns a latent tensor containing empty samples formatted for Hunyuan3Dv2 3D generation |
diff --git a/built-in-nodes/EmptyLatentImage.mdx b/built-in-nodes/EmptyLatentImage.mdx
new file mode 100644
index 000000000..422ab635d
--- /dev/null
+++ b/built-in-nodes/EmptyLatentImage.mdx
@@ -0,0 +1,22 @@
+---
+title: "EmptyLatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyLatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyLatentImage"
+icon: "circle"
+mode: wide
+---
+The `EmptyLatentImage` node is designed to generate a blank latent space representation with specified dimensions and batch size. This node serves as a foundational step in generating or manipulating images in latent space, providing a starting point for further image synthesis or modification processes.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `width`   | `INT`       | Specifies the width of the latent image to be generated. This parameter directly influences the spatial dimensions of the resulting latent representation. |
+| `height`  | `INT`       | Determines the height of the latent image to be generated. This parameter is crucial for defining the spatial dimensions of the latent space representation. |
+| `batch_size` | `INT` | Controls the number of latent images to be generated in a single batch. This allows for the generation of multiple latent representations simultaneously, facilitating batch processing. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a tensor representing a batch of blank latent images, serving as a base for further image generation or manipulation in latent space. |
diff --git a/built-in-nodes/EmptyMochiLatentVideo.mdx b/built-in-nodes/EmptyMochiLatentVideo.mdx
new file mode 100644
index 000000000..1ee19e086
--- /dev/null
+++ b/built-in-nodes/EmptyMochiLatentVideo.mdx
@@ -0,0 +1,27 @@
+---
+title: "EmptyMochiLatentVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyMochiLatentVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyMochiLatentVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyMochiLatentVideo/en.md)
+
+The EmptyMochiLatentVideo node creates an empty latent video tensor with specified dimensions. It generates a zero-filled latent representation that can be used as a starting point for video generation workflows. The node allows you to define the width, height, length, and batch size for the latent video tensor.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | The width of the latent video in pixels (default: 848, must be divisible by 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | The height of the latent video in pixels (default: 480, must be divisible by 16) |
+| `length` | INT | Yes | 7 to MAX_RESOLUTION | The number of frames in the latent video (default: 25) |
+| `batch_size` | INT | No | 1 to 4096 | The number of latent videos to generate in a batch (default: 1) |
+
+**Note:** The actual latent dimensions are calculated as width/8 and height/8, and the temporal dimension is calculated as ((length - 1) // 6) + 1.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | An empty latent video tensor with the specified dimensions, containing all zeros |
diff --git a/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx b/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx
new file mode 100644
index 000000000..52ca4e02f
--- /dev/null
+++ b/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx
@@ -0,0 +1,27 @@
+---
+title: "EmptyQwenImageLayeredLatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyQwenImageLayeredLatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyQwenImageLayeredLatentImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyQwenImageLayeredLatentImage/en.md)
+
+The Empty Qwen Image Layered Latent node creates a blank, multi-layered latent representation for use with Qwen image models. It generates a tensor filled with zeros, structured with a specified number of layers, batch size, and spatial dimensions. This empty latent serves as a starting point for subsequent image generation or manipulation workflows.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | The width of the latent image to create. The value must be divisible by 16. (default: 640) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | The height of the latent image to create. The value must be divisible by 16. (default: 640) |
+| `layers` | INT | Yes | 0 to MAX_RESOLUTION | The number of additional layers to add to the latent structure. This defines the depth of the latent representation. (default: 3) |
+| `batch_size` | INT | No | 1 to 4096 | The number of latent samples to generate in a batch. (default: 1) |
+
+**Note:** The `width` and `height` parameters are internally divided by 8 to determine the spatial dimensions of the output latent tensor.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | A latent tensor filled with zeros. Its shape is `[batch_size, 16, layers + 1, height // 8, width // 8]`. |
diff --git a/built-in-nodes/EmptySD3LatentImage.mdx b/built-in-nodes/EmptySD3LatentImage.mdx
new file mode 100644
index 000000000..8571443c7
--- /dev/null
+++ b/built-in-nodes/EmptySD3LatentImage.mdx
@@ -0,0 +1,24 @@
+---
+title: "EmptySD3LatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptySD3LatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptySD3LatentImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptySD3LatentImage/en.md)
+
+The EmptySD3LatentImage node creates a blank latent image tensor specifically formatted for Stable Diffusion 3 models. It generates a tensor filled with zeros that has the correct dimensions and structure expected by SD3 pipelines. This is commonly used as a starting point for image generation workflows.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 16 to MAX_RESOLUTION (step: 16) | The width of the output latent image in pixels (default: 1024) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION (step: 16) | The height of the output latent image in pixels (default: 1024) |
+| `batch_size` | INT | Yes | 1 to 4096 | The number of latent images to generate in a batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | A latent tensor containing blank samples with SD3-compatible dimensions |
diff --git a/built-in-nodes/Epsilon Scaling.mdx b/built-in-nodes/Epsilon Scaling.mdx
new file mode 100644
index 000000000..c461474ba
--- /dev/null
+++ b/built-in-nodes/Epsilon Scaling.mdx	
@@ -0,0 +1,23 @@
+---
+title: "Epsilon Scaling - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Epsilon Scaling node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Epsilon Scaling"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon%20Scaling/en.md)
+
+This node implements the Epsilon Scaling method from the research paper "Elucidating the Exposure Bias in Diffusion Models." It works by scaling the predicted noise during the sampling process to help reduce exposure bias, which can lead to improved quality in the generated images. This implementation uses the "uniform schedule" recommended by the paper.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to which the epsilon scaling patch will be applied. |
+| `scaling_factor` | FLOAT | No | 0.5 - 1.5 | The factor by which the predicted noise is scaled. A value greater than 1.0 reduces the noise, while a value less than 1.0 increases it (default: 1.005). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | A patched version of the input model with the epsilon scaling function applied to its sampling process. |
diff --git a/built-in-nodes/EpsilonScaling.mdx b/built-in-nodes/EpsilonScaling.mdx
new file mode 100644
index 000000000..586c00c7a
--- /dev/null
+++ b/built-in-nodes/EpsilonScaling.mdx
@@ -0,0 +1,23 @@
+---
+title: "EpsilonScaling - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EpsilonScaling node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EpsilonScaling"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EpsilonScaling/en.md)
+
+Implements the Epsilon Scaling method from the research paper "Elucidating the Exposure Bias in Diffusion Models." This method improves sample quality by scaling the predicted noise during the sampling process. It uses a uniform schedule to mitigate exposure bias in diffusion models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply epsilon scaling to |
+| `scaling_factor` | FLOAT | No | 0.5 - 1.5 | The factor used to scale the predicted noise (default: 1.005) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The model with epsilon scaling applied |
diff --git a/built-in-nodes/ExponentialScheduler.mdx b/built-in-nodes/ExponentialScheduler.mdx
new file mode 100644
index 000000000..6db3bf959
--- /dev/null
+++ b/built-in-nodes/ExponentialScheduler.mdx
@@ -0,0 +1,22 @@
+---
+title: "ExponentialScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ExponentialScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ExponentialScheduler"
+icon: "circle"
+mode: wide
+---
+The `ExponentialScheduler` node is designed to generate a sequence of sigma values following an exponential schedule for diffusion sampling processes. It provides a customizable approach to control the noise levels applied at each step of the diffusion process, allowing for fine-tuning of the sampling behavior.
+
+## Inputs
+
+| Parameter   | Data Type | Description                                                                                   |
+|-------------|-------------|---------------------------------------------------------------------------------------------|
+| `steps`     | INT         | Specifies the number of steps in the diffusion process. It influences the length of the generated sigma sequence and thus the granularity of the noise application. |
+| `sigma_max` | FLOAT       | Defines the maximum sigma value, setting the upper limit of noise intensity in the diffusion process. It plays a crucial role in determining the range of noise levels applied. |
+| `sigma_min` | FLOAT       | Sets the minimum sigma value, establishing the lower boundary of noise intensity. This parameter helps in fine-tuning the starting point of the noise application. |
+
+## Outputs
+
+| Parameter | Data Type | Description                                                                                   |
+|-----------|-------------|---------------------------------------------------------------------------------------------|
+| `sigmas`  | SIGMAS      | A sequence of sigma values generated according to the exponential schedule. These values are used to control the noise levels at each step of the diffusion process. |
diff --git a/built-in-nodes/ExtendIntermediateSigmas.mdx b/built-in-nodes/ExtendIntermediateSigmas.mdx
new file mode 100644
index 000000000..828a26d9f
--- /dev/null
+++ b/built-in-nodes/ExtendIntermediateSigmas.mdx
@@ -0,0 +1,28 @@
+---
+title: "ExtendIntermediateSigmas - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ExtendIntermediateSigmas node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ExtendIntermediateSigmas"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ExtendIntermediateSigmas/en.md)
+
+The ExtendIntermediateSigmas node takes an existing sequence of sigma values and inserts additional intermediate sigma values between them. It allows you to specify how many extra steps to add, the spacing method for interpolation, and optional start and end sigma boundaries to control where the extension occurs within the sigma sequence.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `sigmas` | SIGMAS | Yes | - | The input sigma sequence to extend with intermediate values |
+| `steps` | INT | Yes | 1-100 | Number of intermediate steps to insert between existing sigmas (default: 2) |
+| `start_at_sigma` | FLOAT | Yes | -1.0 to 20000.0 | Upper sigma boundary for extension - only extend sigmas below this value (default: -1.0, which means infinity) |
+| `end_at_sigma` | FLOAT | Yes | 0.0 to 20000.0 | Lower sigma boundary for extension - only extend sigmas above this value (default: 12.0) |
+| `spacing` | COMBO | Yes | "linear"<br />"cosine"<br />"sine" | The interpolation method for spacing the intermediate sigma values |
+
+**Note:** The node only inserts intermediate sigmas between existing sigma pairs where both the current sigma is less than or equal to `start_at_sigma` and greater than or equal to `end_at_sigma`. When `start_at_sigma` is set to -1.0, it's treated as infinity, meaning only the `end_at_sigma` lower boundary applies.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | The extended sigma sequence with additional intermediate values inserted |
diff --git a/built-in-nodes/FeatherMask.mdx b/built-in-nodes/FeatherMask.mdx
new file mode 100644
index 000000000..9d5d101b0
--- /dev/null
+++ b/built-in-nodes/FeatherMask.mdx
@@ -0,0 +1,24 @@
+---
+title: "FeatherMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FeatherMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FeatherMask"
+icon: "circle"
+mode: wide
+---
+The `FeatherMask` node applies a feathering effect to the edges of a given mask, smoothly transitioning the mask's edges by adjusting their opacity based on specified distances from each edge. This creates a softer, more blended edge effect.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|--------------|-------------|
+| `mask`    | MASK         | The mask to which the feathering effect will be applied. It determines the area of the image that will be affected by the feathering. |
+| `left`    | INT          | Specifies the distance from the left edge within which the feathering effect will be applied. |
+| `top`     | INT          | Specifies the distance from the top edge within which the feathering effect will be applied. |
+| `right`   | INT          | Specifies the distance from the right edge within which the feathering effect will be applied. |
+| `bottom`  | INT          | Specifies the distance from the bottom edge within which the feathering effect will be applied. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|--------------|-------------|
+| `mask`    | MASK         | The output is a modified version of the input mask with a feathering effect applied to its edges. |
diff --git a/built-in-nodes/FlipSigmas.mdx b/built-in-nodes/FlipSigmas.mdx
new file mode 100644
index 000000000..bcea11bb9
--- /dev/null
+++ b/built-in-nodes/FlipSigmas.mdx
@@ -0,0 +1,20 @@
+---
+title: "FlipSigmas - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FlipSigmas node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FlipSigmas"
+icon: "circle"
+mode: wide
+---
+The `FlipSigmas` node is designed to manipulate the sequence of sigma values used in diffusion models by reversing their order and ensuring the first value is non-zero if originally zero. This operation is crucial for adapting the noise levels in reverse order, facilitating the generation process in models that operate by gradually reducing noise from data.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `sigmas`  | `SIGMAS`    | The 'sigmas' parameter represents the sequence of sigma values to be flipped. This sequence is crucial for controlling the noise levels applied during the diffusion process, and flipping it is essential for the reverse generation process. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `sigmas`  | `SIGMAS`    | The output is the modified sequence of sigma values, flipped and adjusted to ensure the first value is non-zero if originally zero, ready for use in subsequent diffusion model operations. |
diff --git a/built-in-nodes/Flux2Scheduler.mdx b/built-in-nodes/Flux2Scheduler.mdx
new file mode 100644
index 000000000..96af31ad0
--- /dev/null
+++ b/built-in-nodes/Flux2Scheduler.mdx
@@ -0,0 +1,24 @@
+---
+title: "Flux2Scheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Flux2Scheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Flux2Scheduler"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Flux2Scheduler/en.md)
+
+The Flux2Scheduler node generates a sequence of noise levels (sigmas) for the denoising process, specifically tailored for the Flux model. It calculates a schedule based on the number of denoising steps and the dimensions of the target image, which influences the progression of noise removal during image generation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `steps` | INT | Yes | 1 to 4096 | The number of denoising steps to perform. A higher value typically leads to more detailed results but takes longer to process (default: 20). |
+| `width` | INT | Yes | 16 to 16384 | The width of the image to be generated, in pixels. This value influences the noise schedule calculation (default: 1024). |
+| `height` | INT | Yes | 16 to 16384 | The height of the image to be generated, in pixels. This value influences the noise schedule calculation (default: 1024). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | A sequence of noise level values (sigmas) that define the denoising schedule for the sampler. |
diff --git a/built-in-nodes/FluxDisableGuidance.mdx b/built-in-nodes/FluxDisableGuidance.mdx
new file mode 100644
index 000000000..34270515d
--- /dev/null
+++ b/built-in-nodes/FluxDisableGuidance.mdx
@@ -0,0 +1,22 @@
+---
+title: "FluxDisableGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxDisableGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxDisableGuidance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxDisableGuidance/en.md)
+
+This node completely disables the guidance embed functionality for Flux and similar models. It takes conditioning data as input and removes the guidance component by setting it to None, effectively turning off guidance-based conditioning for the generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | Yes | - | The conditioning data to process and remove guidance from |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | The modified conditioning data with guidance disabled |
diff --git a/built-in-nodes/FluxGuidance.mdx b/built-in-nodes/FluxGuidance.mdx
new file mode 100644
index 000000000..972b5741d
--- /dev/null
+++ b/built-in-nodes/FluxGuidance.mdx
@@ -0,0 +1,19 @@
+---
+title: "FluxGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxGuidance"
+icon: "circle"
+mode: wide
+---
+## Inputs
+
+| Parameter | Data Type | Description |
+|----------------|-----------|-------------|
+| conditioning | CONDITIONING | Input conditioning data, typically from previous encoding or processing steps |
+| guidance | FLOAT | Controls the influence of text prompts on image generation, adjustable range from 0.0 to 100.0 |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|----------------|-----------|-------------|
+| CONDITIONING | CONDITIONING | Updated conditioning data, containing the new guidance value |
diff --git a/built-in-nodes/FluxKontextImageScale.mdx b/built-in-nodes/FluxKontextImageScale.mdx
new file mode 100644
index 000000000..93f808a2b
--- /dev/null
+++ b/built-in-nodes/FluxKontextImageScale.mdx
@@ -0,0 +1,44 @@
+---
+title: "FluxKontextImageScale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxKontextImageScale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxKontextImageScale"
+icon: "circle"
+mode: wide
+---
+This node scales the input image to an optimal size used during Flux Kontext model training using the Lanczos algorithm, based on the input image's aspect ratio. This node is particularly useful when inputting large-sized images, as oversized inputs may lead to degraded model output quality or issues such as multiple subjects appearing in the output.
+
+## Inputs
+
+| Parameter Name | Data Type | Input Type | Default Value | Value Range | Description |
+|----------------|-----------|------------|---------------|-------------|-------------|
+| `image` | IMAGE | Required | - | - | Input image to be resized |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | Resized image |
+
+## Preset Size List
+
+The following is a list of standard sizes used during model training. The node will select the size closest to the input image's aspect ratio:
+
+| Width | Height | Aspect Ratio |
+|-------|--------|--------------|
+| 672   | 1568   | 0.429       |
+| 688   | 1504   | 0.457       |
+| 720   | 1456   | 0.494       |
+| 752   | 1392   | 0.540       |
+| 800   | 1328   | 0.603       |
+| 832   | 1248   | 0.667       |
+| 880   | 1184   | 0.743       |
+| 944   | 1104   | 0.855       |
+| 1024  | 1024   | 1.000       |
+| 1104  | 944    | 1.170       |
+| 1184  | 880    | 1.345       |
+| 1248  | 832    | 1.500       |
+| 1328  | 800    | 1.660       |
+| 1392  | 752    | 1.851       |
+| 1456  | 720    | 2.022       |
+| 1504  | 688    | 2.186       |
+| 1568  | 672    | 2.333       |
diff --git a/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx b/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx
new file mode 100644
index 000000000..aff51d8df
--- /dev/null
+++ b/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx
@@ -0,0 +1,23 @@
+---
+title: "FluxKontextMultiReferenceLatentMethod - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxKontextMultiReferenceLatentMethod node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxKontextMultiReferenceLatentMethod"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxKontextMultiReferenceLatentMethod/en.md)
+
+The FluxKontextMultiReferenceLatentMethod node modifies conditioning data by setting a specific reference latents method. It appends the chosen method to the conditioning input, which affects how reference latents are processed in subsequent generation steps. This node is marked as experimental and is part of the Flux conditioning system.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | Yes | - | The conditioning data to be modified with the reference latents method |
+| `reference_latents_method` | STRING | Yes | `"offset"`<br />`"index"`<br />`"uxo/uno"` | The method to use for reference latents processing. If "uxo" or "uso" is selected, it will be converted to "uxo" |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | The modified conditioning data with the reference latents method applied |
diff --git a/built-in-nodes/FluxProCannyNode.mdx b/built-in-nodes/FluxProCannyNode.mdx
new file mode 100644
index 000000000..e89897c98
--- /dev/null
+++ b/built-in-nodes/FluxProCannyNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "FluxProCannyNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProCannyNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProCannyNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProCannyNode/en.md)
+
+Generate image using a control image (canny). This node takes a control image and generates a new image based on the provided prompt while following the edge structure detected in the control image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `control_image` | IMAGE | Yes | - | The input image used for canny edge detection control |
+| `prompt` | STRING | No | - | Prompt for the image generation (default: empty string) |
+| `prompt_upsampling` | BOOLEAN | No | - | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False) |
+| `canny_low_threshold` | FLOAT | No | 0.01 - 0.99 | Low threshold for Canny edge detection; ignored if skip_processing is True (default: 0.1) |
+| `canny_high_threshold` | FLOAT | No | 0.01 - 0.99 | High threshold for Canny edge detection; ignored if skip_processing is True (default: 0.4) |
+| `skip_preprocessing` | BOOLEAN | No | - | Whether to skip preprocessing; set to True if control_image already is canny-fied, False if it is a raw image. (default: False) |
+| `guidance` | FLOAT | No | 1 - 100 | Guidance strength for the image generation process (default: 30) |
+| `steps` | INT | No | 15 - 50 | Number of steps for the image generation process (default: 50) |
+| `seed` | INT | No | 0 - 18446744073709551615 | The random seed used for creating the noise. (default: 0) |
+
+**Note:** When `skip_preprocessing` is set to True, the `canny_low_threshold` and `canny_high_threshold` parameters are ignored since the control image is assumed to already be processed as a canny edge image.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | The generated image based on the control image and prompt |
diff --git a/built-in-nodes/FluxProDepthNode.mdx b/built-in-nodes/FluxProDepthNode.mdx
new file mode 100644
index 000000000..0fc7aee7e
--- /dev/null
+++ b/built-in-nodes/FluxProDepthNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "FluxProDepthNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProDepthNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProDepthNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProDepthNode/en.md)
+
+This node generates images using a depth control image as guidance. It takes a control image and a text prompt, then creates a new image that follows both the depth information from the control image and the description in the prompt. The node connects to an external API to perform the image generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `control_image` | IMAGE | Yes | - | The depth control image used to guide the image generation |
+| `prompt` | STRING | No | - | Prompt for the image generation (default: empty string) |
+| `prompt_upsampling` | BOOLEAN | No | - | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False) |
+| `skip_preprocessing` | BOOLEAN | No | - | Whether to skip preprocessing; set to True if control_image already is depth-ified, False if it is a raw image. (default: False) |
+| `guidance` | FLOAT | No | 1-100 | Guidance strength for the image generation process (default: 15) |
+| `steps` | INT | No | 15-50 | Number of steps for the image generation process (default: 50) |
+| `seed` | INT | No | 0-18446744073709551615 | The random seed used for creating the noise. (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | The generated image based on the depth control image and prompt |
diff --git a/built-in-nodes/FluxProExpandNode.mdx b/built-in-nodes/FluxProExpandNode.mdx
new file mode 100644
index 000000000..024f61f6e
--- /dev/null
+++ b/built-in-nodes/FluxProExpandNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "FluxProExpandNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProExpandNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProExpandNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProExpandNode/en.md)
+
+Outpaints image based on prompt. This node expands an image by adding pixels to the top, bottom, left, and right sides while generating new content that matches the provided text description.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be expanded |
+| `prompt` | STRING | No | - | Prompt for the image generation (default: "") |
+| `prompt_upsampling` | BOOLEAN | No | - | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False) |
+| `top` | INT | No | 0-2048 | Number of pixels to expand at the top of the image (default: 0) |
+| `bottom` | INT | No | 0-2048 | Number of pixels to expand at the bottom of the image (default: 0) |
+| `left` | INT | No | 0-2048 | Number of pixels to expand at the left of the image (default: 0) |
+| `right` | INT | No | 0-2048 | Number of pixels to expand at the right of the image (default: 0) |
+| `guidance` | FLOAT | No | 1.5-100 | Guidance strength for the image generation process (default: 60) |
+| `steps` | INT | No | 15-50 | Number of steps for the image generation process (default: 50) |
+| `seed` | INT | No | 0-18446744073709551615 | The random seed used for creating the noise. (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The expanded output image |
diff --git a/built-in-nodes/FluxProFillNode.mdx b/built-in-nodes/FluxProFillNode.mdx
new file mode 100644
index 000000000..7b4267ecf
--- /dev/null
+++ b/built-in-nodes/FluxProFillNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "FluxProFillNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProFillNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProFillNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProFillNode/en.md)
+
+Inpaints image based on mask and prompt. This node uses the Flux.1 model to fill in masked areas of an image according to the provided text description, generating new content that matches the surrounding image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be inpainted |
+| `mask` | MASK | Yes | - | The mask defining which areas of the image should be filled |
+| `prompt` | STRING | No | - | Prompt for the image generation (default: empty string) |
+| `prompt_upsampling` | BOOLEAN | No | - | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: false) |
+| `guidance` | FLOAT | No | 1.5-100 | Guidance strength for the image generation process (default: 60) |
+| `steps` | INT | No | 15-50 | Number of steps for the image generation process (default: 50) |
+| `seed` | INT | No | 0-18446744073709551615 | The random seed used for creating the noise. (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | The generated image with the masked areas filled according to the prompt |
diff --git a/built-in-nodes/FluxProImageNode.mdx b/built-in-nodes/FluxProImageNode.mdx
new file mode 100644
index 000000000..0bf085566
--- /dev/null
+++ b/built-in-nodes/FluxProImageNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "FluxProImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProImageNode/en.md)
+
+Generates images synchronously based on prompt and resolution. This node creates images using the Flux 1.1 Pro model by sending requests to an API endpoint and waiting for the complete response before returning the generated image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: empty string) |
+| `prompt_upsampling` | BOOLEAN | Yes | - | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False) |
+| `width` | INT | Yes | 256-1440 | Image width in pixels (default: 1024, step: 32) |
+| `height` | INT | Yes | 256-1440 | Image height in pixels (default: 768, step: 32) |
+| `seed` | INT | Yes | 0-18446744073709551615 | The random seed used for creating the noise. (default: 0) |
+| `image_prompt` | IMAGE | No | - | Optional reference image to guide the generation |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image returned from the API |
diff --git a/built-in-nodes/FluxProUltraImageNode.mdx b/built-in-nodes/FluxProUltraImageNode.mdx
new file mode 100644
index 000000000..f441b4544
--- /dev/null
+++ b/built-in-nodes/FluxProUltraImageNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "FluxProUltraImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProUltraImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProUltraImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProUltraImageNode/en.md)
+
+Generates images using Flux Pro 1.1 Ultra via API based on prompt and resolution. This node connects to an external service to create images according to your text description and specified dimensions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: empty string) |
+| `prompt_upsampling` | BOOLEAN | No | - | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False) |
+| `seed` | INT | No | 0 to 18446744073709551615 | The random seed used for creating the noise. (default: 0) |
+| `aspect_ratio` | STRING | No | - | Aspect ratio of image; must be between 1:4 and 4:1. (default: "16:9") |
+| `raw` | BOOLEAN | No | - | When True, generate less processed, more natural-looking images. (default: False) |
+| `image_prompt` | IMAGE | No | - | Optional reference image to guide generation |
+| `image_prompt_strength` | FLOAT | No | 0.0 to 1.0 | Blend between the prompt and the image prompt. (default: 0.1) |
+
+**Note:** The `aspect_ratio` parameter must be between 1:4 and 4:1. When `image_prompt` is provided, `image_prompt_strength` becomes active and controls how much the reference image influences the final output.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | The generated image from Flux Pro 1.1 Ultra |
diff --git a/built-in-nodes/FreSca.mdx b/built-in-nodes/FreSca.mdx
new file mode 100644
index 000000000..f1068104f
--- /dev/null
+++ b/built-in-nodes/FreSca.mdx
@@ -0,0 +1,25 @@
+---
+title: "FreSca - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FreSca node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FreSca"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FreSca/en.md)
+
+The FreSca node applies frequency-dependent scaling to guidance during the sampling process. It separates the guidance signal into low-frequency and high-frequency components using Fourier filtering, then applies different scaling factors to each frequency range before recombining them. This allows for more nuanced control over how guidance affects different aspects of the generated output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply frequency scaling to |
+| `scale_low` | FLOAT | No | 0-10 | Scaling factor for low-frequency components (default: 1.0) |
+| `scale_high` | FLOAT | No | 0-10 | Scaling factor for high-frequency components (default: 1.25) |
+| `freq_cutoff` | INT | No | 1-10000 | Number of frequency indices around center to consider as low-frequency (default: 20) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with frequency-dependent scaling applied to its guidance function |
diff --git a/built-in-nodes/FreeU.mdx b/built-in-nodes/FreeU.mdx
new file mode 100644
index 000000000..04a4f6764
--- /dev/null
+++ b/built-in-nodes/FreeU.mdx
@@ -0,0 +1,26 @@
+---
+title: "FreeU - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FreeU node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FreeU"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FreeU/en.md)
+
+The FreeU node applies frequency-domain modifications to a model's output blocks to enhance image generation quality. It works by scaling different channel groups and applying Fourier filtering to specific feature maps, allowing for fine-tuned control over the model's behavior during the generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply FreeU modifications to |
+| `b1` | FLOAT | Yes | 0.0 - 10.0 | Backbone scaling factor for model_channels × 4 features (default: 1.1) |
+| `b2` | FLOAT | Yes | 0.0 - 10.0 | Backbone scaling factor for model_channels × 2 features (default: 1.2) |
+| `s1` | FLOAT | Yes | 0.0 - 10.0 | Skip connection scaling factor for model_channels × 4 features (default: 0.9) |
+| `s2` | FLOAT | Yes | 0.0 - 10.0 | Skip connection scaling factor for model_channels × 2 features (default: 0.2) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with FreeU patches applied |
diff --git a/built-in-nodes/FreeU_V2.mdx b/built-in-nodes/FreeU_V2.mdx
new file mode 100644
index 000000000..d64a420bd
--- /dev/null
+++ b/built-in-nodes/FreeU_V2.mdx
@@ -0,0 +1,26 @@
+---
+title: "FreeU_V2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FreeU_V2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FreeU_V2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FreeU_V2/en.md)
+
+The FreeU_V2 node applies a frequency-based enhancement to diffusion models by modifying the U-Net architecture. It scales different feature channels using configurable parameters to improve image generation quality without requiring additional training. The node works by patching the model's output blocks to apply scaling factors to specific channel dimensions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to apply FreeU enhancement to |
+| `b1` | FLOAT | Yes | 0.0 - 10.0 | Backbone feature scaling factor for the first block (default: 1.3) |
+| `b2` | FLOAT | Yes | 0.0 - 10.0 | Backbone feature scaling factor for the second block (default: 1.4) |
+| `s1` | FLOAT | Yes | 0.0 - 10.0 | Skip feature scaling factor for the first block (default: 0.9) |
+| `s2` | FLOAT | Yes | 0.0 - 10.0 | Skip feature scaling factor for the second block (default: 0.2) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The enhanced diffusion model with FreeU modifications applied |
diff --git a/built-in-nodes/GITSScheduler.mdx b/built-in-nodes/GITSScheduler.mdx
new file mode 100644
index 000000000..aa77f08ae
--- /dev/null
+++ b/built-in-nodes/GITSScheduler.mdx
@@ -0,0 +1,26 @@
+---
+title: "GITSScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GITSScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GITSScheduler"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GITSScheduler/en.md)
+
+The GITSScheduler node generates noise schedule sigmas for the GITS (Generative Iterative Time Steps) sampling method. It calculates sigma values based on a coefficient parameter and number of steps, with an optional denoising factor that can reduce the total steps used. The node uses pre-defined noise levels and interpolation to create the final sigma schedule.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `coeff` | FLOAT | Yes | 0.80 - 1.50 | The coefficient value that controls the noise schedule curve (default: 1.20) |
+| `steps` | INT | Yes | 2 - 1000 | The total number of sampling steps to generate sigmas for (default: 10) |
+| `denoise` | FLOAT | Yes | 0.0 - 1.0 | Denoising factor that reduces the number of steps used (default: 1.0) |
+
+**Note:** When `denoise` is set to 0.0, the node returns an empty tensor. When `denoise` is less than 1.0, the actual number of steps used is calculated as `round(steps * denoise)`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | The generated sigma values for the noise schedule |
diff --git a/built-in-nodes/GLIGENLoader.mdx b/built-in-nodes/GLIGENLoader.mdx
new file mode 100644
index 000000000..1219617f2
--- /dev/null
+++ b/built-in-nodes/GLIGENLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "GLIGENLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GLIGENLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GLIGENLoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/gligen` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+The `GLIGENLoader` node is designed for loading GLIGEN models, which are specialized generative models. It facilitates the process of retrieving and initializing these models from specified paths, making them ready for further generative tasks.
+
+## Inputs
+
+| Field       | Comfy dtype       | Description                                                                       |
+|-------------|-------------------|-----------------------------------------------------------------------------------|
+| `gligen_name`| `COMBO[STRING]`    | The name of the GLIGEN model to be loaded, specifying which model file to retrieve and load, crucial for the initialization of the GLIGEN model. |
+
+## Outputs
+
+| Field    | Data Type | Description                                                              |
+|----------|-------------|--------------------------------------------------------------------------|
+| `gligen` | `GLIGEN`    | The loaded GLIGEN model, ready for use in generative tasks, representing the fully initialized model loaded from the specified path. |
diff --git a/built-in-nodes/GLIGENTextBoxApply.mdx b/built-in-nodes/GLIGENTextBoxApply.mdx
new file mode 100644
index 000000000..8da0d27eb
--- /dev/null
+++ b/built-in-nodes/GLIGENTextBoxApply.mdx
@@ -0,0 +1,27 @@
+---
+title: "GLIGENTextBoxApply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GLIGENTextBoxApply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GLIGENTextBoxApply"
+icon: "circle"
+mode: wide
+---
+The `GLIGENTextBoxApply` node is designed to integrate text-based conditioning into a generative model's input, specifically by applying text box parameters and encoding them using a CLIP model. This process enriches the conditioning with spatial and textual information, facilitating more precise and context-aware generation.
+
+## Inputs
+
+| Parameter            | Comfy dtype        | Description |
+|----------------------|--------------------|-------------|
+| `conditioning_to`     | `CONDITIONING`     | Specifies the initial conditioning input to which the text box parameters and encoded text information will be appended. It plays a crucial role in determining the final output by integrating new conditioning data. |
+| `clip`               | `CLIP`             | The CLIP model used for encoding the provided text into a format that can be utilized by the generative model. It's essential for converting textual information into a compatible conditioning format. |
+| `gligen_textbox_model` | `GLIGEN`         | Represents the specific GLIGEN model configuration to be used for generating the text box. It's crucial for ensuring that the text box is generated according to the desired specifications. |
+| `text`               | `STRING`           | The text content to be encoded and integrated into the conditioning. It provides the semantic information that guides the generative model. |
+| `width`              | `INT`              | The width of the text box in pixels. It defines the spatial dimension of the text box within the generated image. |
+| `height`             | `INT`              | The height of the text box in pixels. Similar to width, it defines the spatial dimension of the text box within the generated image. |
+| `x`                  | `INT`              | The x-coordinate of the top-left corner of the text box within the generated image. It specifies the text box's position horizontally. |
+| `y`                  | `INT`              | The y-coordinate of the top-left corner of the text box within the generated image. It specifies the text box's position vertically. |
+
+## Outputs
+
+| Parameter            | Comfy dtype        | Description |
+|----------------------|--------------------|-------------|
+| `conditioning`        | `CONDITIONING`     | The enriched conditioning output, which includes the original conditioning data along with the newly appended text box parameters and encoded text information. It's used to guide the generative model in producing context-aware outputs. |
diff --git a/built-in-nodes/GLSLShader.mdx b/built-in-nodes/GLSLShader.mdx
new file mode 100644
index 000000000..9d56bcbc5
--- /dev/null
+++ b/built-in-nodes/GLSLShader.mdx
@@ -0,0 +1,38 @@
+---
+title: "GLSLShader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GLSLShader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GLSLShader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GLSLShader/en.md)
+
+The GLSL Shader node applies custom GLSL ES fragment shader code to input images. It allows you to write shader programs that can process multiple images and accept uniform parameters (floats and integers) to create complex visual effects. The output size can be determined by the first input image or set manually.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `fragment_shader` | STRING | Yes | N/A | GLSL fragment shader source code (GLSL ES 3.00 / WebGL 2.0 compatible). Default: A basic shader that outputs the first input image. |
+| `size_mode` | COMBO | Yes | `"from_input"`<br />`"custom"` | Output size: 'from_input' uses first input image dimensions, 'custom' allows manual size. |
+| `width` | INT | No | 1 to 16384 | The width of the output image when `size_mode` is set to `"custom"`. Default: 512. |
+| `height` | INT | No | 1 to 16384 | The height of the output image when `size_mode` is set to `"custom"`. Default: 512. |
+| `images` | IMAGE | Yes | 1 to 8 images | Input images to be processed by the shader. Images are available as `u_image0` to `u_image7` (sampler2D) in the shader code. |
+| `floats` | FLOAT | No | 0 to 8 floats | Floating-point uniform values for the shader. Floats are available as `u_float0` to `u_float7` in the shader code. Default: 0.0. |
+| `ints` | INT | No | 0 to 8 integers | Integer uniform values for the shader. Ints are available as `u_int0` to `u_int7` in the shader code. Default: 0. |
+
+**Notes:**
+
+* The `width` and `height` parameters are only required and visible when `size_mode` is set to `"custom"`.
+* At least one input image is required.
+* The shader code always has access to a `u_resolution` (vec2) uniform containing the output dimensions.
+* A maximum of 8 input images, 8 float uniforms, and 8 integer uniforms can be provided.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE0` | IMAGE | The first output image from the shader. Available via `layout(location = 0) out vec4 fragColor0` in the shader code. |
+| `IMAGE1` | IMAGE | The second output image from the shader. Available via `layout(location = 1) out vec4 fragColor1` in the shader code. |
+| `IMAGE2` | IMAGE | The third output image from the shader. Available via `layout(location = 2) out vec4 fragColor2` in the shader code. |
+| `IMAGE3` | IMAGE | The fourth output image from the shader. Available via `layout(location = 3) out vec4 fragColor3` in the shader code. |
diff --git a/built-in-nodes/GeminiImage.mdx b/built-in-nodes/GeminiImage.mdx
new file mode 100644
index 000000000..a1df014f9
--- /dev/null
+++ b/built-in-nodes/GeminiImage.mdx
@@ -0,0 +1,29 @@
+---
+title: "GeminiImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImage/en.md)
+
+The GeminiImage node generates text and image responses from Google's Gemini AI models. It allows you to provide multimodal inputs including text prompts, images, and files to create coherent text and image outputs. The node handles all API communication and response parsing with the latest Gemini models.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `prompt` | STRING | required | "" | - | Text prompt for generation |
+| `model` | COMBO | required | gemini_2_5_flash_image_preview | Available Gemini models<br />Options extracted from GeminiImageModel enum | The Gemini model to use for generating responses. |
+| `seed` | INT | required | 42 | 0 to 18446744073709551615 | When seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. |
+| `images` | IMAGE | optional | None | - | Optional image(s) to use as context for the model. To include multiple images, you can use the Batch Images node. |
+| `files` | GEMINI_INPUT_FILES | optional | None | - | Optional file(s) to use as context for the model. Accepts inputs from the Gemini Generate Content Input Files node. |
+
+**Note:** The node includes hidden parameters (`auth_token`, `comfy_api_key`, `unique_id`) that are automatically handled by the system and do not require user input.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The generated image response from the Gemini model |
+| `STRING` | STRING | The generated text response from the Gemini model |
diff --git a/built-in-nodes/GeminiImage2Node.mdx b/built-in-nodes/GeminiImage2Node.mdx
new file mode 100644
index 000000000..e7dbf2956
--- /dev/null
+++ b/built-in-nodes/GeminiImage2Node.mdx
@@ -0,0 +1,36 @@
+---
+title: "GeminiImage2Node - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiImage2Node node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiImage2Node"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImage2Node/en.md)
+
+The GeminiImage2Node generates or edits images using Google's Vertex AI Gemini model. It sends a text prompt and optional reference images or files to the API and returns the generated image and/or a text description.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | N/A | Text prompt describing the image to generate or the edits to apply. Include any constraints, styles, or details the model should follow. |
+| `model` | COMBO | Yes | `"gemini-3-pro-image-preview"` | The specific Gemini model to use for generation. |
+| `seed` | INT | Yes | 0 to 18446744073709551615 | When fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Changing the model or other settings can cause variations even with the same seed. Default: 42. |
+| `aspect_ratio` | COMBO | Yes | `"auto"`<br />`"1:1"`<br />`"2:3"`<br />`"3:2"`<br />`"3:4"`<br />`"4:3"`<br />`"4:5"`<br />`"5:4"`<br />`"9:16"`<br />`"16:9"`<br />`"21:9"` | The desired aspect ratio for the output image. If set to 'auto', it matches your input image's aspect ratio; if no image is provided, a 16:9 square is usually generated. Default: "auto". |
+| `resolution` | COMBO | Yes | `"1K"`<br />`"2K"`<br />`"4K"` | Target output resolution. For 2K/4K the native Gemini upscaler is used. |
+| `response_modalities` | COMBO | Yes | `"IMAGE+TEXT"`<br />`"IMAGE"` | Choose 'IMAGE' for image-only output, or 'IMAGE+TEXT' to return both the generated image and a text response. |
+| `images` | IMAGE | No | N/A | Optional reference image(s). To include multiple images, use the Batch Images node (up to 14). |
+| `files` | CUSTOM | No | N/A | Optional file(s) to use as context for the model. Accepts inputs from the Gemini Generate Content Input Files node. |
+| `system_prompt` | STRING | No | N/A | Foundational instructions that dictate an AI's behavior. Default: A pre-defined system prompt for image generation. |
+
+**Constraints:**
+
+* The `images` input supports a maximum of 14 images. If more are provided, an error will be raised.
+* The `files` input must be connected to a node that outputs the `GEMINI_INPUT_FILES` data type.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The image generated or edited by the Gemini model. |
+| `string` | STRING | The text response from the model. This output will be empty if `response_modalities` is set to "IMAGE". |
diff --git a/built-in-nodes/GeminiImageNode.mdx b/built-in-nodes/GeminiImageNode.mdx
new file mode 100644
index 000000000..982e51136
--- /dev/null
+++ b/built-in-nodes/GeminiImageNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "GeminiImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImage/en.md)
+
+The GeminiImage node generates text and image responses from Google's Gemini AI models. It allows you to provide multimodal inputs including text prompts, images, and files to create coherent text and image outputs. The node handles all API communication and response parsing with the latest Gemini models.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `prompt` | STRING | required | "" | - | Text prompt for generation |
+| `model` | COMBO | required | gemini_2_5_flash_image_preview | Available Gemini models<br />Options extracted from GeminiImageModel enum | The Gemini model to use for generating responses |
+| `seed` | INT | required | 42 | 0 to 18446744073709551615 | When seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used |
+| `images` | IMAGE | optional | None | - | Optional image(s) to use as context for the model. To include multiple images, you can use the Batch Images node |
+| `files` | GEMINI_INPUT_FILES | optional | None | - | Optional file(s) to use as context for the model. Accepts inputs from the Gemini Generate Content Input Files node |
+
+*Note: The node includes hidden parameters (`auth_token`, `comfy_api_key`, `unique_id`) that are automatically handled by the system and do not require user input.*
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The generated image response from the Gemini model |
+| `STRING` | STRING | The generated text response from the Gemini model |
diff --git a/built-in-nodes/GeminiInputFiles.mdx b/built-in-nodes/GeminiInputFiles.mdx
new file mode 100644
index 000000000..eb415a02a
--- /dev/null
+++ b/built-in-nodes/GeminiInputFiles.mdx
@@ -0,0 +1,25 @@
+---
+title: "GeminiInputFiles - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiInputFiles node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiInputFiles"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiInputFiles/en.md)
+
+Loads and formats input files for use with the Gemini API. This node allows users to include text (.txt) and PDF (.pdf) files as input context for the Gemini model. Files are converted to the appropriate format required by the API and can be chained together to include multiple files in a single request.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `file` | COMBO | Yes | Multiple options available | Input files to include as context for the model. Only accepts text (.txt) and PDF (.pdf) files for now. Files must be smaller than the maximum input file size limit. |
+| `GEMINI_INPUT_FILES` | GEMINI_INPUT_FILES | No | N/A | An optional additional file(s) to batch together with the file loaded from this node. Allows chaining of input files so that a single message can include multiple input files. |
+
+**Note:** The `file` parameter only displays text (.txt) and PDF (.pdf) files that are smaller than the maximum input file size limit. Files are automatically filtered and sorted by name.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `GEMINI_INPUT_FILES` | GEMINI_INPUT_FILES | Formatted file data ready for use with Gemini LLM nodes, containing the loaded file content in the appropriate API format. |
diff --git a/built-in-nodes/GeminiNode.mdx b/built-in-nodes/GeminiNode.mdx
new file mode 100644
index 000000000..72d9199a5
--- /dev/null
+++ b/built-in-nodes/GeminiNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "GeminiNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiNode/en.md)
+
+This node allows users to interact with Google's Gemini AI models to generate text responses. You can provide multiple types of inputs including text, images, audio, video, and files as context for the model to generate more relevant and meaningful responses. The node handles all API communication and response parsing automatically.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text inputs to the model, used to generate a response. You can include detailed instructions, questions, or context for the model. Default: empty string. |
+| `model` | COMBO | Yes | `gemini-2.0-flash-exp`<br />`gemini-2.0-flash-thinking-exp`<br />`gemini-2.5-pro-exp`<br />`gemini-2.0-flash`<br />`gemini-2.0-flash-thinking`<br />`gemini-2.5-pro`<br />`gemini-2.0-flash-lite`<br />`gemini-1.5-flash`<br />`gemini-1.5-flash-8b`<br />`gemini-1.5-pro`<br />`gemini-1.0-pro` | The Gemini model to use for generating responses. Default: gemini-2.5-pro. |
+| `seed` | INT | Yes | 0 to 18446744073709551615 | When seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. Default: 42. |
+| `images` | IMAGE | No | - | Optional image(s) to use as context for the model. To include multiple images, you can use the Batch Images node. Default: None. |
+| `audio` | AUDIO | No | - | Optional audio to use as context for the model. Default: None. |
+| `video` | VIDEO | No | - | Optional video to use as context for the model. Default: None. |
+| `files` | GEMINI_INPUT_FILES | No | - | Optional file(s) to use as context for the model. Accepts inputs from the Gemini Generate Content Input Files node. Default: None. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `STRING` | STRING | The text response generated by the Gemini model. |
diff --git a/built-in-nodes/GenerateTracks.mdx b/built-in-nodes/GenerateTracks.mdx
new file mode 100644
index 000000000..fa9203167
--- /dev/null
+++ b/built-in-nodes/GenerateTracks.mdx
@@ -0,0 +1,38 @@
+---
+title: "GenerateTracks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GenerateTracks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GenerateTracks"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GenerateTracks/en.md)
+
+The `GenerateTracks` node creates multiple parallel motion paths for video generation. It defines a primary path from a start point to an end point, then generates a set of tracks that run parallel to this path, spaced evenly apart. You can control the shape of the path (straight line or Bezier curve), the speed of movement along it, and which frames the tracks are visible in.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 16 - 4096 | The width of the video frame in pixels. The default value is 832. |
+| `height` | INT | Yes | 16 - 4096 | The height of the video frame in pixels. The default value is 480. |
+| `start_x` | FLOAT | Yes | 0.0 - 1.0 | Normalized X coordinate (0-1) for start position. The default value is 0.0. |
+| `start_y` | FLOAT | Yes | 0.0 - 1.0 | Normalized Y coordinate (0-1) for start position. The default value is 0.0. |
+| `end_x` | FLOAT | Yes | 0.0 - 1.0 | Normalized X coordinate (0-1) for end position. The default value is 1.0. |
+| `end_y` | FLOAT | Yes | 0.0 - 1.0 | Normalized Y coordinate (0-1) for end position. The default value is 1.0. |
+| `num_frames` | INT | Yes | 1 - 1024 | The total number of frames for which to generate track positions. The default value is 81. |
+| `num_tracks` | INT | Yes | 1 - 100 | The number of parallel tracks to generate. The default value is 5. |
+| `track_spread` | FLOAT | Yes | 0.0 - 1.0 | Normalized distance between tracks. Tracks are spread perpendicular to the motion direction. The default value is 0.025. |
+| `bezier` | BOOLEAN | Yes | True / False | Enable Bezier curve path using the mid point as control point. The default value is False. |
+| `mid_x` | FLOAT | Yes | 0.0 - 1.0 | Normalized X control point for Bezier curve. Only used when 'bezier' is enabled. The default value is 0.5. |
+| `mid_y` | FLOAT | Yes | 0.0 - 1.0 | Normalized Y control point for Bezier curve. Only used when 'bezier' is enabled. The default value is 0.5. |
+| `interpolation` | COMBO | Yes | `"linear"`<br />`"ease_in"`<br />`"ease_out"`<br />`"ease_in_out"`<br />`"constant"` | Controls the timing/speed of movement along the path. The default value is "linear". |
+| `track_mask` | MASK | No | - | Optional mask to indicate visible frames. |
+
+**Note:** The `mid_x` and `mid_y` parameters are only used when the `bezier` parameter is set to `True`. When `bezier` is `False`, the path is a straight line from the start to the end point.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `TRACKS` | TRACKS | A tracks object containing the generated path coordinates and visibility information for all tracks across all frames. |
+| `track_length` | INT | The number of frames for which tracks were generated, matching the input `num_frames`. |
diff --git a/built-in-nodes/GetImageSize.mdx b/built-in-nodes/GetImageSize.mdx
new file mode 100644
index 000000000..5c462e418
--- /dev/null
+++ b/built-in-nodes/GetImageSize.mdx
@@ -0,0 +1,25 @@
+---
+title: "GetImageSize - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GetImageSize node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GetImageSize"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetImageSize/en.md)
+
+The GetImageSize node extracts the dimensions and batch information from an input image. It returns the width, height, and batch size of the image while also displaying this information as progress text on the node interface. The original image data passes through unchanged.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image from which to extract size information |
+| `unique_id` | UNIQUE_ID | No | - | Internal identifier used for displaying progress information |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `width` | INT | The width of the input image in pixels |
+| `height` | INT | The height of the input image in pixels |
+| `batch_size` | INT | The number of images in the batch |
diff --git a/built-in-nodes/GetVideoComponents.mdx b/built-in-nodes/GetVideoComponents.mdx
new file mode 100644
index 000000000..525f66d6b
--- /dev/null
+++ b/built-in-nodes/GetVideoComponents.mdx
@@ -0,0 +1,24 @@
+---
+title: "GetVideoComponents - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GetVideoComponents node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GetVideoComponents"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetVideoComponents/en.md)
+
+The Get Video Components node extracts all the main elements from a video file. It separates the video into individual frames, extracts the audio track, and provides the video's framerate information. This allows you to work with each component independently for further processing or analysis.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | - | The video to extract components from. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `images` | IMAGE | The individual frames extracted from the video as separate images. |
+| `audio` | AUDIO | The audio track extracted from the video. |
+| `fps` | FLOAT | The framerate of the video in frames per second. |
diff --git a/built-in-nodes/GrokImageEditNode.mdx b/built-in-nodes/GrokImageEditNode.mdx
new file mode 100644
index 000000000..56889679d
--- /dev/null
+++ b/built-in-nodes/GrokImageEditNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "GrokImageEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrokImageEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrokImageEditNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokImageEditNode/en.md)
+
+The Grok Image Edit node modifies an existing image based on a text prompt. It uses the Grok API to generate one or more new images that are variations of the input, guided by your description.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"grok-imagine-image-beta"` | The specific AI model to use for image editing. |
+| `image` | IMAGE | Yes | | The input image to be edited. Only one image is supported. |
+| `prompt` | STRING | Yes | | The text prompt used to generate the edited image. |
+| `resolution` | COMBO | Yes | `"1K"` | The resolution for the output image. |
+| `number_of_images` | INT | No | 1 to 10 | Number of edited images to generate (default: 1). |
+| `seed` | INT | No | 0 to 2147483647 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0). |
+
+**Note:** The `image` input must contain exactly one image. Providing multiple images will cause an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The edited image(s) generated by the node. If `number_of_images` is greater than 1, the outputs are concatenated into a batch. |
diff --git a/built-in-nodes/GrokImageNode.mdx b/built-in-nodes/GrokImageNode.mdx
new file mode 100644
index 000000000..97c2c65d3
--- /dev/null
+++ b/built-in-nodes/GrokImageNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "GrokImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrokImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrokImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokImageNode/en.md)
+
+The Grok Image node generates one or more images based on a text description using the Grok AI model. It sends your prompt to an external service and returns the generated images as tensors that can be used in your workflow.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"grok-imagine-image-beta"` | The specific Grok model to use for image generation. |
+| `prompt` | STRING | Yes | N/A | The text prompt used to generate the image. This description guides the AI on what to create. |
+| `aspect_ratio` | COMBO | Yes | `"1:1"`<br />`"2:3"`<br />`"3:2"`<br />`"3:4"`<br />`"4:3"`<br />`"9:16"`<br />`"16:9"`<br />`"9:19.5"`<br />`"19.5:9"`<br />`"9:20"`<br />`"20:9"`<br />`"1:2"`<br />`"2:1"` | The desired width-to-height ratio for the generated image. |
+| `number_of_images` | INT | No | 1 to 10 | Number of images to generate (default: 1). |
+| `seed` | INT | No | 0 to 2147483647 | A seed value to determine if the node should re-run. The actual image results are nondeterministic and will vary even with the same seed (default: 0). |
+
+**Note:** The `seed` parameter is primarily used to control when the node re-executes within a workflow. Due to the nature of the external AI service, the generated images will not be reproducible or identical across runs, even with an identical seed.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image or a batch of images. If `number_of_images` is 1, a single image tensor is returned. If greater than 1, a batch of image tensors is returned. |
diff --git a/built-in-nodes/GrokVideoEditNode.mdx b/built-in-nodes/GrokVideoEditNode.mdx
new file mode 100644
index 000000000..cf68c16f7
--- /dev/null
+++ b/built-in-nodes/GrokVideoEditNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "GrokVideoEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrokVideoEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrokVideoEditNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoEditNode/en.md)
+
+This node uses the Grok API to edit an existing video based on a text prompt. It uploads your video, sends a request to the AI model to modify it according to your description, and returns the newly generated video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"grok-imagine-video-beta"` | The AI model to use for video editing. |
+| `prompt` | STRING | Yes | N/A | Text description of the desired video. |
+| `video` | VIDEO | Yes | N/A | The input video to be edited. Maximum supported duration is 8.7 seconds and 50MB file size. |
+| `seed` | INT | No | 0 to 2147483647 | A seed value to determine if the node should re-run. The actual results are nondeterministic regardless of the seed value (default: 0). |
+
+**Constraints:**
+
+* The input `video` must be between 1 and 8.7 seconds in duration.
+* The input `video` file size must not exceed 50MB.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The edited video generated by the AI model. |
diff --git a/built-in-nodes/GrokVideoNode.mdx b/built-in-nodes/GrokVideoNode.mdx
new file mode 100644
index 000000000..71f6ab66f
--- /dev/null
+++ b/built-in-nodes/GrokVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "GrokVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrokVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrokVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoNode/en.md)
+
+The Grok Video node generates a short video from a text description. It can create a video from scratch using a prompt or animate a single input image based on a prompt. The node sends a request to an external API and returns the generated video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"grok-imagine-video-beta"` | The model to use for video generation. |
+| `prompt` | STRING | Yes | - | Text description of the desired video. |
+| `resolution` | COMBO | Yes | `"480p"`<br />`"720p"` | The resolution of the output video. |
+| `aspect_ratio` | COMBO | Yes | `"auto"`<br />`"16:9"`<br />`"4:3"`<br />`"3:2"`<br />`"1:1"`<br />`"2:3"`<br />`"3:4"`<br />`"9:16"` | The aspect ratio of the output video. |
+| `duration` | INT | Yes | 1 to 15 | The duration of the output video in seconds (default: 6). |
+| `seed` | INT | Yes | 0 to 2147483647 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0). |
+| `image` | IMAGE | No | - | An optional input image to animate. |
+
+**Note:** If an `image` is provided, only one image is supported. Providing multiple images will cause an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video. |
diff --git a/built-in-nodes/GrowMask.mdx b/built-in-nodes/GrowMask.mdx
new file mode 100644
index 000000000..9bd3cf816
--- /dev/null
+++ b/built-in-nodes/GrowMask.mdx
@@ -0,0 +1,22 @@
+---
+title: "GrowMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrowMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrowMask"
+icon: "circle"
+mode: wide
+---
+The `GrowMask` node is designed to modify the size of a given mask, either expanding or contracting it, while optionally applying a tapered effect to the corners. This functionality is crucial for dynamically adjusting mask boundaries in image processing tasks, allowing for more flexible and precise control over the area of interest.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | MASK        | The input mask to be modified. This parameter is central to the node's operation, serving as the base upon which the mask is either expanded or contracted. |
+| `expand`  | INT         | Determines the magnitude and direction of the mask modification. Positive values cause the mask to expand, while negative values lead to contraction. This parameter directly influences the final size of the mask. |
+| `tapered_corners` | BOOLEAN    | A boolean flag that, when set to True, applies a tapered effect to the corners of the mask during modification. This option allows for smoother transitions and visually appealing results. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | MASK        | The modified mask after applying the specified expansion/contraction and optional tapered corners effect. |
diff --git a/built-in-nodes/HitPawGeneralImageEnhance.mdx b/built-in-nodes/HitPawGeneralImageEnhance.mdx
new file mode 100644
index 000000000..71048a2b6
--- /dev/null
+++ b/built-in-nodes/HitPawGeneralImageEnhance.mdx
@@ -0,0 +1,27 @@
+---
+title: "HitPawGeneralImageEnhance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HitPawGeneralImageEnhance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HitPawGeneralImageEnhance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HitPawGeneralImageEnhance/en.md)
+
+This node enhances low-resolution images by upscaling them to super-resolution, removing artifacts and noise. It uses an external API to process the image and can automatically adjust the input size to stay within processing limits. The maximum allowed output size is 4 megapixels.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | STRING | Yes | `"generative_portrait"`<br />`"generative"` | The enhancement model to use. |
+| `image` | IMAGE | Yes | - | The input image to be enhanced. |
+| `upscale_factor` | INT | Yes | `1`<br />`2`<br />`4` | The factor by which to upscale the image's dimensions. |
+| `auto_downscale` | BOOLEAN | No | - | Automatically downscale input image if output would exceed the limit. (default: `False`) |
+
+**Note:** The node will raise an error if the calculated output size (input height × upscale_factor × input width × upscale_factor) exceeds 4,000,000 pixels (4MP) and `auto_downscale` is disabled. When `auto_downscale` is enabled, the node will attempt to downscale the input image to fit within the limit before applying the requested upscale factor.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The enhanced and upscaled output image. |
diff --git a/built-in-nodes/HitPawVideoEnhance.mdx b/built-in-nodes/HitPawVideoEnhance.mdx
new file mode 100644
index 000000000..826d30230
--- /dev/null
+++ b/built-in-nodes/HitPawVideoEnhance.mdx
@@ -0,0 +1,29 @@
+---
+title: "HitPawVideoEnhance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HitPawVideoEnhance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HitPawVideoEnhance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HitPawVideoEnhance/en.md)
+
+The HitPaw Video Enhance node uses an external API to improve the quality of videos. It upscales low-resolution videos to a higher resolution, removes visual artifacts, and reduces noise. The processing cost is calculated per second of the input video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | DYNAMIC COMBO | Yes | Multiple options available | The AI model to use for video enhancement. Selecting a model reveals a nested `resolution` parameter. |
+| `model.resolution` | COMBO | Yes | `"original"`<br />`"720p"`<br />`"1080p"`<br />`"2k/qhd"`<br />`"4k/uhd"`<br />`"8k"` | The target resolution for the enhanced video. Some options may be unavailable depending on the selected `model`. |
+| `video` | VIDEO | Yes | N/A | The input video file to be enhanced. |
+
+**Constraints:**
+
+* The input `video` must be between 0.5 seconds and 60 minutes (3600 seconds) in duration.
+* The selected `resolution` must be larger than the input video's dimensions. If the video is square, the selected resolution must be larger than its width/height. For non-square videos, the selected resolution must be larger than the video's shorter dimension. If the target resolution is smaller, an error will be raised. Choose `"original"` to keep the input video's resolution.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The enhanced video file. |
diff --git a/built-in-nodes/Hunyuan3Dv2Conditioning.mdx b/built-in-nodes/Hunyuan3Dv2Conditioning.mdx
new file mode 100644
index 000000000..9f3e26ba7
--- /dev/null
+++ b/built-in-nodes/Hunyuan3Dv2Conditioning.mdx
@@ -0,0 +1,23 @@
+---
+title: "Hunyuan3Dv2Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Hunyuan3Dv2Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Hunyuan3Dv2Conditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2Conditioning/en.md)
+
+The Hunyuan3Dv2Conditioning node processes CLIP vision output to generate conditioning data for video models. It extracts the last hidden state embeddings from the vision output and creates both positive and negative conditioning pairs. The positive conditioning uses the actual embeddings while the negative conditioning uses zero-valued embeddings of the same shape.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip_vision_output` | CLIP_VISION_OUTPUT | Yes | - | The output from a CLIP vision model containing visual embeddings |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning data containing the CLIP vision embeddings |
+| `negative` | CONDITIONING | Negative conditioning data containing zero-valued embeddings matching the positive embeddings shape |
diff --git a/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx b/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx
new file mode 100644
index 000000000..5f2be73ca
--- /dev/null
+++ b/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx
@@ -0,0 +1,28 @@
+---
+title: "Hunyuan3Dv2ConditioningMultiView - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Hunyuan3Dv2ConditioningMultiView node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Hunyuan3Dv2ConditioningMultiView"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2ConditioningMultiView/en.md)
+
+The Hunyuan3Dv2ConditioningMultiView node processes multi-view CLIP vision embeddings for 3D video generation. It takes optional front, left, back, and right view embeddings and combines them with positional encoding to create conditioning data for video models. The node outputs both positive conditioning from the combined embeddings and negative conditioning with zero values.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `front` | CLIP_VISION_OUTPUT | No | - | CLIP vision output for the front view |
+| `left` | CLIP_VISION_OUTPUT | No | - | CLIP vision output for the left view |
+| `back` | CLIP_VISION_OUTPUT | No | - | CLIP vision output for the back view |
+| `right` | CLIP_VISION_OUTPUT | No | - | CLIP vision output for the right view |
+
+**Note:** At least one view input must be provided for the node to function. The node will only process views that contain valid CLIP vision output data.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning containing the combined multi-view embeddings with positional encoding |
+| `negative` | CONDITIONING | Negative conditioning with zero values for contrastive learning |
diff --git a/built-in-nodes/HunyuanImageToVideo.mdx b/built-in-nodes/HunyuanImageToVideo.mdx
new file mode 100644
index 000000000..7da9c219c
--- /dev/null
+++ b/built-in-nodes/HunyuanImageToVideo.mdx
@@ -0,0 +1,36 @@
+---
+title: "HunyuanImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanImageToVideo/en.md)
+
+The HunyuanImageToVideo node converts images into video latent representations using the Hunyuan video model. It takes conditioning inputs and optional starting images to generate video latents that can be further processed by video generation models. The node supports different guidance types for controlling how the starting image influences the video generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning input for guiding the video generation |
+| `vae` | VAE | Yes | - | VAE model used for encoding images into latent space |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Width of the output video in pixels (default: 848, step: 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Height of the output video in pixels (default: 480, step: 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames in the output video (default: 53, step: 4) |
+| `batch_size` | INT | Yes | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `guidance_type` | COMBO | Yes | "v1 (concat)"<br />"v2 (replace)"<br />"custom" | Method for incorporating the starting image into video generation |
+| `start_image` | IMAGE | No | - | Optional starting image to initialize the video generation |
+
+**Note:** When `start_image` is provided, the node uses different guidance methods based on the selected `guidance_type`:
+
+- "v1 (concat)": Concatenates the image latent with the video latent
+- "v2 (replace)": Replaces initial video frames with the image latent
+- "custom": Uses the image as a reference latent for guidance
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Modified positive conditioning with image guidance applied when start_image is provided |
+| `latent` | LATENT | Video latent representation ready for further processing by video generation models |
diff --git a/built-in-nodes/HunyuanRefinerLatent.mdx b/built-in-nodes/HunyuanRefinerLatent.mdx
new file mode 100644
index 000000000..2e6f89e7f
--- /dev/null
+++ b/built-in-nodes/HunyuanRefinerLatent.mdx
@@ -0,0 +1,27 @@
+---
+title: "HunyuanRefinerLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanRefinerLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanRefinerLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanRefinerLatent/en.md)
+
+The HunyuanRefinerLatent node processes conditioning and latent inputs for refinement operations. It applies noise augmentation to both positive and negative conditioning while incorporating latent image data, and generates a new latent output with specific dimensions for further processing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The positive conditioning input to be processed |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning input to be processed |
+| `latent` | LATENT | Yes | - | The latent representation input |
+| `noise_augmentation` | FLOAT | Yes | 0.0 - 1.0 | The amount of noise augmentation to apply (default: 0.10) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The processed positive conditioning with applied noise augmentation and latent image concatenation |
+| `negative` | CONDITIONING | The processed negative conditioning with applied noise augmentation and latent image concatenation |
+| `latent` | LATENT | A new latent output with dimensions [batch_size, 32, height, width, channels] |
diff --git a/built-in-nodes/HunyuanVideo15ImageToVideo.mdx b/built-in-nodes/HunyuanVideo15ImageToVideo.mdx
new file mode 100644
index 000000000..52db38591
--- /dev/null
+++ b/built-in-nodes/HunyuanVideo15ImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "HunyuanVideo15ImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanVideo15ImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanVideo15ImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15ImageToVideo/en.md)
+
+The HunyuanVideo15ImageToVideo node prepares conditioning and latent space data for video generation based on the HunyuanVideo 1.5 model. It creates an initial latent representation for a video sequence and can optionally integrate a starting image or a CLIP vision output to guide the generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The positive conditioning prompts that describe what the video should contain. |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning prompts that describe what the video should avoid. |
+| `vae` | VAE | Yes | - | The VAE (Variational Autoencoder) model used to encode the starting image into the latent space. |
+| `width` | INT | No | 16 to MAX_RESOLUTION | The width of the output video frames in pixels. Must be divisible by 16. (default: 848) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | The height of the output video frames in pixels. Must be divisible by 16. (default: 480) |
+| `length` | INT | No | 1 to MAX_RESOLUTION | The total number of frames in the video sequence. (default: 33) |
+| `batch_size` | INT | No | 1 to 4096 | The number of video sequences to generate in a single batch. (default: 1) |
+| `start_image` | IMAGE | No | - | An optional starting image to initialize the video generation. If provided, it is encoded and used to condition the first frames. |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | No | - | Optional CLIP vision embeddings to provide additional visual conditioning for the generation. |
+
+**Note:** When a `start_image` is provided, it is automatically resized to match the specified `width` and `height` using bilinear interpolation. The first `length` frames of the image batch are used. The encoded image is then added to both the `positive` and `negative` conditioning as a `concat_latent_image` with a corresponding `concat_mask`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The modified positive conditioning, which may now include the encoded starting image or CLIP vision output. |
+| `negative` | CONDITIONING | The modified negative conditioning, which may now include the encoded starting image or CLIP vision output. |
+| `latent` | LATENT | An empty latent tensor with dimensions configured for the specified batch size, video length, width, and height. |
diff --git a/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx b/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx
new file mode 100644
index 000000000..4666ff658
--- /dev/null
+++ b/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx
@@ -0,0 +1,29 @@
+---
+title: "HunyuanVideo15LatentUpscaleWithModel - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanVideo15LatentUpscaleWithModel node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanVideo15LatentUpscaleWithModel"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15LatentUpscaleWithModel/en.md)
+
+The Hunyuan Video 15 Latent Upscale With Model node increases the resolution of a latent image representation. It first upscales the latent samples to a specified size using a chosen interpolation method, then refines the upscaled result using a specialized Hunyuan Video 1.5 upscale model to improve quality.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | LATENT_UPSCALE_MODEL | Yes | N/A | The Hunyuan Video 1.5 latent upscale model used to refine the upscaled samples. |
+| `samples` | LATENT | Yes | N/A | The latent image representation to be upscaled. |
+| `upscale_method` | COMBO | No | `"nearest-exact"`<br />`"bilinear"`<br />`"area"`<br />`"bicubic"`<br />`"bislerp"` | The interpolation algorithm used for the initial upscaling step (default: `"bilinear"`). |
+| `width` | INT | No | 0 to 16384 | The target width for the upscaled latent, in pixels. A value of 0 will calculate the width automatically based on the target height and the original aspect ratio. The final output width will be a multiple of 16 (default: 1280). |
+| `height` | INT | No | 0 to 16384 | The target height for the upscaled latent, in pixels. A value of 0 will calculate the height automatically based on the target width and the original aspect ratio. The final output height will be a multiple of 16 (default: 720). |
+| `crop` | COMBO | No | `"disabled"`<br />`"center"` | Determines how the upscaled latent is cropped to fit the target dimensions. |
+
+**Note on Dimensions:** If both `width` and `height` are set to 0, the node returns the input `samples` unchanged. If only one dimension is set to 0, the other dimension is calculated to preserve the original aspect ratio. The final dimensions are always adjusted to be at least 64 pixels and are divisible by 16.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | The upscaled and model-refined latent image representation. |
diff --git a/built-in-nodes/HunyuanVideo15SuperResolution.mdx b/built-in-nodes/HunyuanVideo15SuperResolution.mdx
new file mode 100644
index 000000000..a33bd2e9e
--- /dev/null
+++ b/built-in-nodes/HunyuanVideo15SuperResolution.mdx
@@ -0,0 +1,32 @@
+---
+title: "HunyuanVideo15SuperResolution - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanVideo15SuperResolution node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanVideo15SuperResolution"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15SuperResolution/en.md)
+
+The HunyuanVideo15SuperResolution node prepares conditioning data for a video super-resolution process. It takes a latent representation of a video and, optionally, a starting image, and packages them along with noise augmentation and CLIP vision data into a format that can be used by a model to generate a higher-resolution output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | N/A | The positive conditioning input to be modified with latent and augmentation data. |
+| `negative` | CONDITIONING | Yes | N/A | The negative conditioning input to be modified with latent and augmentation data. |
+| `vae` | VAE | No | N/A | The VAE used to encode the optional `start_image`. Required if `start_image` is provided. |
+| `start_image` | IMAGE | No | N/A | An optional starting image to guide the super-resolution. If provided, it will be upscaled and encoded into the conditioning latent. |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | No | N/A | Optional CLIP vision embeddings to add to the conditioning. |
+| `latent` | LATENT | Yes | N/A | The input latent video representation that will be incorporated into the conditioning. |
+| `noise_augmentation` | FLOAT | No | 0.0 - 1.0 | The strength of noise augmentation to apply to the conditioning (default: 0.70). |
+
+**Note:** If you provide a `start_image`, you must also connect a `vae` for it to be encoded. The `start_image` will be automatically upscaled to match the dimensions implied by the input `latent`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The modified positive conditioning, now containing the concatenated latent, noise augmentation, and optional CLIP vision data. |
+| `negative` | CONDITIONING | The modified negative conditioning, now containing the concatenated latent, noise augmentation, and optional CLIP vision data. |
+| `latent` | LATENT | The input latent is passed through unchanged. |
diff --git a/built-in-nodes/HyperTile.mdx b/built-in-nodes/HyperTile.mdx
new file mode 100644
index 000000000..524d920d5
--- /dev/null
+++ b/built-in-nodes/HyperTile.mdx
@@ -0,0 +1,26 @@
+---
+title: "HyperTile - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HyperTile node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HyperTile"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HyperTile/en.md)
+
+The HyperTile node applies a tiling technique to the attention mechanism in diffusion models to optimize memory usage during image generation. It divides the latent space into smaller tiles and processes them separately, then reassembles the results. This allows for working with larger image sizes without running out of memory.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to apply the HyperTile optimization to |
+| `tile_size` | INT | No | 1-2048 | The target tile size for processing (default: 256) |
+| `swap_size` | INT | No | 1-128 | Controls how the tiles are rearranged during processing (default: 2) |
+| `max_depth` | INT | No | 0-10 | Maximum depth level to apply tiling (default: 0) |
+| `scale_depth` | BOOLEAN | No | - | Whether to scale tile size based on depth level (default: False) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with HyperTile optimization applied |
diff --git a/built-in-nodes/HypernetworkLoader.mdx b/built-in-nodes/HypernetworkLoader.mdx
new file mode 100644
index 000000000..4e54d676e
--- /dev/null
+++ b/built-in-nodes/HypernetworkLoader.mdx
@@ -0,0 +1,24 @@
+---
+title: "HypernetworkLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HypernetworkLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HypernetworkLoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/hypernetworks` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+The HypernetworkLoader node is designed to enhance or modify the capabilities of a given model by applying a hypernetwork. It loads a specified hypernetwork and applies it to the model, potentially altering its behavior or performance based on the strength parameter. This process allows for dynamic adjustments to the model's architecture or parameters, enabling more flexible and adaptive AI systems.
+
+## Inputs
+
+| Field                 | Comfy dtype       | Description                                                                                  |
+|-----------------------|-------------------|----------------------------------------------------------------------------------------------|
+| `model`               | `MODEL`           | The base model to which the hypernetwork will be applied, determining the architecture to be enhanced or modified. |
+| `hypernetwork_name`  | `COMBO[STRING]`   | The name of the hypernetwork to be loaded and applied to the model, impacting the model's modified behavior or performance. |
+| `strength`            | `FLOAT`           | A scalar adjusting the intensity of the hypernetwork's effect on the model, allowing fine-tuning of the alterations. |
+
+## Outputs
+
+| Field   | Data Type | Description                                                              |
+|---------|-------------|--------------------------------------------------------------------------|
+| `model` | `MODEL`     | The modified model after the hypernetwork has been applied, showcasing the impact of the hypernetwork on the original model. |
diff --git a/built-in-nodes/IdeogramV1.mdx b/built-in-nodes/IdeogramV1.mdx
new file mode 100644
index 000000000..6f99bb362
--- /dev/null
+++ b/built-in-nodes/IdeogramV1.mdx
@@ -0,0 +1,30 @@
+---
+title: "IdeogramV1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the IdeogramV1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "IdeogramV1"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV1/en.md)
+
+The IdeogramV1 node generates images using the Ideogram V1 model through an API. It takes text prompts and various generation settings to create one or more images based on your input. The node supports different aspect ratios and generation modes to customize the output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: empty) |
+| `turbo` | BOOLEAN | Yes | - | Whether to use turbo mode (faster generation, potentially lower quality) (default: False) |
+| `aspect_ratio` | COMBO | No | "1:1"<br />"16:9"<br />"9:16"<br />"4:3"<br />"3:4"<br />"3:2"<br />"2:3" | The aspect ratio for image generation (default: "1:1") |
+| `magic_prompt_option` | COMBO | No | "AUTO"<br />"ON"<br />"OFF" | Determine if MagicPrompt should be used in generation (default: "AUTO") |
+| `seed` | INT | No | 0-2147483647 | Random seed value for generation (default: 0) |
+| `negative_prompt` | STRING | No | - | Description of what to exclude from the image (default: empty) |
+| `num_images` | INT | No | 1-8 | Number of images to generate (default: 1) |
+
+**Note:** The `num_images` parameter has a maximum limit of 8 images per generation request.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image(s) from the Ideogram V1 model |
diff --git a/built-in-nodes/IdeogramV2.mdx b/built-in-nodes/IdeogramV2.mdx
new file mode 100644
index 000000000..e4e7a040d
--- /dev/null
+++ b/built-in-nodes/IdeogramV2.mdx
@@ -0,0 +1,32 @@
+---
+title: "IdeogramV2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the IdeogramV2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "IdeogramV2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV2/en.md)
+
+The Ideogram V2 node generates images using the Ideogram V2 AI model. It takes text prompts and various generation settings to create images through an API service. The node supports different aspect ratios, resolutions, and style options to customize the output images.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: empty string) |
+| `turbo` | BOOLEAN | No | - | Whether to use turbo mode (faster generation, potentially lower quality) (default: False) |
+| `aspect_ratio` | COMBO | No | "1:1"<br />"16:9"<br />"9:16"<br />"4:3"<br />"3:4"<br />"3:2"<br />"2:3" | The aspect ratio for image generation. Ignored if resolution is not set to AUTO. (default: "1:1") |
+| `resolution` | COMBO | No | "Auto"<br />"1024x1024"<br />"1152x896"<br />"896x1152"<br />"1216x832"<br />"832x1216"<br />"1344x768"<br />"768x1344"<br />"1536x640"<br />"640x1536" | The resolution for image generation. If not set to AUTO, this overrides the aspect_ratio setting. (default: "Auto") |
+| `magic_prompt_option` | COMBO | No | "AUTO"<br />"ON"<br />"OFF" | Determine if MagicPrompt should be used in generation (default: "AUTO") |
+| `seed` | INT | No | 0-2147483647 | Random seed for generation (default: 0) |
+| `style_type` | COMBO | No | "AUTO"<br />"GENERAL"<br />"REALISTIC"<br />"DESIGN"<br />"RENDER_3D"<br />"ANIME" | Style type for generation (V2 only) (default: "NONE") |
+| `negative_prompt` | STRING | No | - | Description of what to exclude from the image (default: empty string) |
+| `num_images` | INT | No | 1-8 | Number of images to generate (default: 1) |
+
+**Note:** When `resolution` is not set to "Auto", it overrides the `aspect_ratio` setting. The `num_images` parameter has a maximum limit of 8 images per generation.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image(s) from the Ideogram V2 model |
diff --git a/built-in-nodes/IdeogramV3.mdx b/built-in-nodes/IdeogramV3.mdx
new file mode 100644
index 000000000..2e1ca6484
--- /dev/null
+++ b/built-in-nodes/IdeogramV3.mdx
@@ -0,0 +1,41 @@
+---
+title: "IdeogramV3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the IdeogramV3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "IdeogramV3"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV3/en.md)
+
+The Ideogram V3 node generates images using the Ideogram V3 model. It supports both regular image generation from text prompts and image editing when both an image and mask are provided. The node offers various controls for aspect ratio, resolution, generation speed, and optional character reference images.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the image generation or editing (default: empty) |
+| `image` | IMAGE | No | - | Optional reference image for image editing |
+| `mask` | MASK | No | - | Optional mask for inpainting (white areas will be replaced) |
+| `aspect_ratio` | COMBO | No | "1:1"<br />"16:9"<br />"9:16"<br />"4:3"<br />"3:4"<br />"3:2"<br />"2:3" | The aspect ratio for image generation. Ignored if resolution is not set to Auto (default: "1:1") |
+| `resolution` | COMBO | No | "Auto"<br />"1024x1024"<br />"1152x896"<br />"896x1152"<br />"1216x832"<br />"832x1216"<br />"1344x768"<br />"768x1344"<br />"1536x640"<br />"640x1536" | The resolution for image generation. If not set to Auto, this overrides the aspect_ratio setting (default: "Auto") |
+| `magic_prompt_option` | COMBO | No | "AUTO"<br />"ON"<br />"OFF" | Determine if MagicPrompt should be used in generation (default: "AUTO") |
+| `seed` | INT | No | 0-2147483647 | Random seed for generation (default: 0) |
+| `num_images` | INT | No | 1-8 | Number of images to generate (default: 1) |
+| `rendering_speed` | COMBO | No | "DEFAULT"<br />"TURBO"<br />"QUALITY" | Controls the trade-off between generation speed and quality (default: "DEFAULT") |
+| `character_image` | IMAGE | No | - | Image to use as character reference |
+| `character_mask` | MASK | No | - | Optional mask for character reference image |
+
+**Parameter Constraints:**
+
+- When both `image` and `mask` are provided, the node switches to editing mode
+- If only one of `image` or `mask` is provided, an error will occur
+- `character_mask` requires `character_image` to be present
+- The `aspect_ratio` parameter is ignored when `resolution` is not set to "Auto"
+- White areas in the mask will be replaced during inpainting
+- Character mask and character image must be the same size
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated or edited image(s) |
diff --git a/built-in-nodes/ImageAddNoise.mdx b/built-in-nodes/ImageAddNoise.mdx
new file mode 100644
index 000000000..bd184deca
--- /dev/null
+++ b/built-in-nodes/ImageAddNoise.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageAddNoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageAddNoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageAddNoise"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageAddNoise/en.md)
+
+The ImageAddNoise node adds random noise to an input image. It uses a specified random seed to generate consistent noise patterns and allows controlling the intensity of the noise effect. The resulting image maintains the same dimensions as the input but with added visual texture.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to which noise will be added |
+| `seed` | INT | Yes | 0 to 18446744073709551615 | The random seed used for creating the noise (default: 0) |
+| `strength` | FLOAT | Yes | 0.0 to 1.0 | Controls the intensity of the noise effect (default: 0.5) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The output image with added noise applied |
diff --git a/built-in-nodes/ImageBatch.mdx b/built-in-nodes/ImageBatch.mdx
new file mode 100644
index 000000000..cf3db21e3
--- /dev/null
+++ b/built-in-nodes/ImageBatch.mdx
@@ -0,0 +1,21 @@
+---
+title: "ImageBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageBatch"
+icon: "circle"
+mode: wide
+---
+The `ImageBatch` node is designed for combining two images into a single batch. If the dimensions of the images do not match, it automatically rescales the second image to match the first one's dimensions before combining them.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image1`  | `IMAGE`     | The first image to be combined into the batch. It serves as the reference for the dimensions to which the second image will be adjusted if necessary. |
+| `image2`  | `IMAGE`     | The second image to be combined into the batch. It is automatically rescaled to match the dimensions of the first image if they differ. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The combined batch of images, with the second image rescaled to match the first one's dimensions if needed. |
diff --git a/built-in-nodes/ImageBlend.mdx b/built-in-nodes/ImageBlend.mdx
new file mode 100644
index 000000000..608e23c83
--- /dev/null
+++ b/built-in-nodes/ImageBlend.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageBlend - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageBlend node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageBlend"
+icon: "circle"
+mode: wide
+---
+The `ImageBlend` node is designed to blend two images together based on a specified blending mode and blend factor. It supports various blending modes such as normal, multiply, screen, overlay, soft light, and difference, allowing for versatile image manipulation and compositing techniques. This node is essential for creating composite images by adjusting the visual interaction between two image layers.
+
+## Inputs
+
+| Field         | Data Type | Description                                                                       |
+|---------------|-------------|-----------------------------------------------------------------------------------|
+| `image1`      | `IMAGE`     | The first image to be blended. It serves as the base layer for the blending operation. |
+| `image2`      | `IMAGE`     | The second image to be blended. Depending on the blend mode, it modifies the appearance of the first image. |
+| `blend_factor`| `FLOAT`     | Determines the weight of the second image in the blend. A higher blend factor gives more prominence to the second image in the resulting blend. |
+| `blend_mode`  | COMBO[STRING] | Specifies the method of blending the two images. Supports modes like normal, multiply, screen, overlay, soft light, and difference, each producing a unique visual effect. |
+
+## Outputs
+
+| Field | Data Type | Description                                                              |
+|-------|-------------|--------------------------------------------------------------------------|
+| `image`| `IMAGE`     | The resulting image after blending the two input images according to the specified blend mode and factor. |
diff --git a/built-in-nodes/ImageBlur.mdx b/built-in-nodes/ImageBlur.mdx
new file mode 100644
index 000000000..3b9f313be
--- /dev/null
+++ b/built-in-nodes/ImageBlur.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageBlur - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageBlur node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageBlur"
+icon: "circle"
+mode: wide
+---
+The `ImageBlur` node applies a Gaussian blur to an image, allowing for the softening of edges and reduction of detail and noise. It provides control over the intensity and spread of the blur through parameters.
+
+## Inputs
+
+| Field          | Data Type | Description                                                                   |
+|----------------|-------------|-------------------------------------------------------------------------------|
+| `image`        | `IMAGE`     | The input image to be blurred. This is the primary target for the blur effect. |
+| `blur_radius`  | `INT`       | Determines the radius of the blur effect. A larger radius results in a more pronounced blur. |
+| `sigma`        | `FLOAT`     | Controls the spread of the blur. A higher sigma value means the blur will affect a wider area around each pixel. |
+
+## Outputs
+
+| Field | Data Type | Description                                                              |
+|-------|-------------|--------------------------------------------------------------------------|
+| `image`| `IMAGE`     | The output is the blurred version of the input image, with the degree of blur determined by the input parameters. |
diff --git a/built-in-nodes/ImageColorToMask.mdx b/built-in-nodes/ImageColorToMask.mdx
new file mode 100644
index 000000000..4233cbeec
--- /dev/null
+++ b/built-in-nodes/ImageColorToMask.mdx
@@ -0,0 +1,21 @@
+---
+title: "ImageColorToMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageColorToMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageColorToMask"
+icon: "circle"
+mode: wide
+---
+The `ImageColorToMask` node is designed to convert a specified color in an image to a mask. It processes an image and a target color, generating a mask where the specified color is highlighted, facilitating operations like color-based segmentation or object isolation.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The 'image' parameter represents the input image to be processed. It is crucial for determining the areas of the image that match the specified color to be converted into a mask. |
+| `color`   | `INT`       | The 'color' parameter specifies the target color in the image to be converted into a mask. It plays a key role in identifying the specific color areas to be highlighted in the resulting mask. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | `MASK`      | The output is a mask highlighting the areas of the input image that match the specified color. This mask can be used for further image processing tasks, such as segmentation or object isolation. |
diff --git a/built-in-nodes/ImageCompare.mdx b/built-in-nodes/ImageCompare.mdx
new file mode 100644
index 000000000..9068028a0
--- /dev/null
+++ b/built-in-nodes/ImageCompare.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageCompare - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageCompare node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageCompare"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageCompare/en.md)
+
+The Image Compare node provides a visual interface to compare two images side-by-side using a draggable slider. It is designed as an output node, meaning it does not pass data to other nodes but instead displays the images directly in the user interface for inspection.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image_a` | IMAGE | No | - | The first image to compare. |
+| `image_b` | IMAGE | No | - | The second image to compare. |
+| `compare_view` | IMAGECOMPARE | Yes | - | The control that enables the slider comparison view in the UI. |
+
+**Note:** This node is an output node. While `image_a` and `image_b` are optional, at least one image must be provided for the node to have a visible effect. The node will display an empty area for any image input that is not connected.
+
+## Outputs
+
+This node is an output node and does not produce any data outputs for use in other nodes. Its function is to display the provided images in the ComfyUI interface.
diff --git a/built-in-nodes/ImageCompositeMasked.mdx b/built-in-nodes/ImageCompositeMasked.mdx
new file mode 100644
index 000000000..bc048ec51
--- /dev/null
+++ b/built-in-nodes/ImageCompositeMasked.mdx
@@ -0,0 +1,25 @@
+---
+title: "ImageCompositeMasked - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageCompositeMasked node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageCompositeMasked"
+icon: "circle"
+mode: wide
+---
+The `ImageCompositeMasked` node is designed for compositing images, allowing for the overlay of a source image onto a destination image at specified coordinates, with optional resizing and masking.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `destination` | `IMAGE` | The destination image onto which the source image will be composited. It serves as the background for the composite operation. |
+| `source` | `IMAGE` | The source image to be composited onto the destination image. This image can optionally be resized to fit the destination image's dimensions. |
+| `x` | `INT` | The x-coordinate in the destination image where the top-left corner of the source image will be placed. |
+| `y` | `INT` | The y-coordinate in the destination image where the top-left corner of the source image will be placed. |
+| `resize_source` | `BOOLEAN` | A boolean flag indicating whether the source image should be resized to match the destination image's dimensions. |
+| `mask` | `MASK` | An optional mask that specifies which parts of the source image should be composited onto the destination image. This allows for more complex compositing operations, such as blending or partial overlays. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image` | `IMAGE` | The resulting image after the compositing operation, which combines elements of both t
diff --git a/built-in-nodes/ImageCrop.mdx b/built-in-nodes/ImageCrop.mdx
new file mode 100644
index 000000000..c27e854df
--- /dev/null
+++ b/built-in-nodes/ImageCrop.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageCrop - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageCrop node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageCrop"
+icon: "circle"
+mode: wide
+---
+The `ImageCrop` node is designed for cropping images to a specified width and height starting from a given x and y coordinate. This functionality is essential for focusing on specific regions of an image or for adjusting the image size to meet certain requirements.
+
+## Inputs
+
+| Field | Data Type | Description                                                                                   |
+|-------|-------------|-----------------------------------------------------------------------------------------------|
+| `image` | `IMAGE` | The input image to be cropped. This parameter is crucial as it defines the source image from which a region will be extracted based on the specified dimensions and coordinates. |
+| `width` | `INT` | Specifies the width of the cropped image. This parameter determines how wide the resulting cropped image will be. |
+| `height` | `INT` | Specifies the height of the cropped image. This parameter determines the height of the resulting cropped image. |
+| `x` | `INT` | The x-coordinate of the top-left corner of the cropping area. This parameter sets the starting point for the width dimension of the crop. |
+| `y` | `INT` | The y-coordinate of the top-left corner of the cropping area. This parameter sets the starting point for the height dimension of the crop. |
+
+## Outputs
+
+| Field | Data Type | Description                                                                   |
+|-------|-------------|-------------------------------------------------------------------------------|
+| `image` | `IMAGE` | The cropped image as a result of the cropping operation. This output is significant for further processing or analysis of the specified image region. |
diff --git a/built-in-nodes/ImageCropV2.mdx b/built-in-nodes/ImageCropV2.mdx
new file mode 100644
index 000000000..779e17236
--- /dev/null
+++ b/built-in-nodes/ImageCropV2.mdx
@@ -0,0 +1,25 @@
+---
+title: "ImageCropV2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageCropV2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageCropV2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageCropV2/en.md)
+
+The Image Crop node extracts a rectangular section from an input image. You define the region to keep by specifying its top-left corner coordinates and its width and height. The node then returns the cropped portion of the original image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | N/A | The input image to be cropped. |
+| `crop_region` | BOUNDINGBOX | Yes | N/A | Defines the rectangular area to extract from the image. It is specified by `x` (horizontal start), `y` (vertical start), `width`, and `height`. If the defined region extends beyond the image's borders, it will be automatically adjusted to fit within the image dimensions. |
+
+**Note on Region Constraints:** The crop region is automatically constrained to stay within the bounds of the input image. If the specified `x` or `y` coordinate is greater than the image's width or height, it will be set to the maximum valid position. The resulting crop width and height will be adjusted so the region does not exceed the image's edges.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The cropped section of the original input image. |
diff --git a/built-in-nodes/ImageDeduplication.mdx b/built-in-nodes/ImageDeduplication.mdx
new file mode 100644
index 000000000..4a7af5776
--- /dev/null
+++ b/built-in-nodes/ImageDeduplication.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageDeduplication - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageDeduplication node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageDeduplication"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageDeduplication/en.md)
+
+This node removes duplicate or very similar images from a batch. It works by creating a perceptual hash for each image—a simple numerical fingerprint based on its visual content—and then comparing them. Images whose hashes are more similar than a set threshold are considered duplicates and filtered out.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | The batch of images to process for deduplication. |
+| `similarity_threshold` | FLOAT | No | 0.0 - 1.0 | Similarity threshold (0-1). Higher means more similar. Images above this threshold are considered duplicates. (default: 0.95) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `images` | IMAGE | The filtered list of images with duplicates removed. |
diff --git a/built-in-nodes/ImageFlip.mdx b/built-in-nodes/ImageFlip.mdx
new file mode 100644
index 000000000..ceecf7c7a
--- /dev/null
+++ b/built-in-nodes/ImageFlip.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageFlip - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageFlip node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageFlip"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageFlip/en.md)
+
+The ImageFlip node flips images along different axes. It can flip images vertically along the x-axis or horizontally along the y-axis. The node uses torch.flip operations to perform the flipping based on the selected method.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be flipped |
+| `flip_method` | STRING | Yes | "x-axis: vertically"<br />"y-axis: horizontally" | The flipping direction to apply |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The flipped output image |
diff --git a/built-in-nodes/ImageFromBatch.mdx b/built-in-nodes/ImageFromBatch.mdx
new file mode 100644
index 000000000..10e7e72d1
--- /dev/null
+++ b/built-in-nodes/ImageFromBatch.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageFromBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageFromBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageFromBatch"
+icon: "circle"
+mode: wide
+---
+The `ImageFromBatch` node is designed for extracting a specific segment of images from a batch based on the provided index and length. It allows for more granular control over the batched images, enabling operations on individual or subsets of images within a larger batch.
+
+## Inputs
+
+| Field          | Data Type | Description                                                                           |
+|----------------|-------------|---------------------------------------------------------------------------------------|
+| `image`        | `IMAGE`     | The batch of images from which a segment will be extracted. This parameter is crucial for specifying the source batch. |
+| `batch_index`  | `INT`       | The starting index within the batch from which the extraction begins. It determines the initial position of the segment to be extracted from the batch. |
+| `length`       | `INT`       | The number of images to extract from the batch starting from the batch_index. This parameter defines the size of the segment to be extracted. |
+
+## Outputs
+
+| Field | Data Type | Description                                                                                   |
+|-------|-------------|-----------------------------------------------------------------------------------------------|
+| `image` | `IMAGE`    | The extracted segment of images from the specified batch. This output represents a subset of the original batch, determined by the batch_index and length parameters. |
diff --git a/built-in-nodes/ImageGrid.mdx b/built-in-nodes/ImageGrid.mdx
new file mode 100644
index 000000000..396c594e5
--- /dev/null
+++ b/built-in-nodes/ImageGrid.mdx
@@ -0,0 +1,26 @@
+---
+title: "ImageGrid - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageGrid node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageGrid"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageGrid/en.md)
+
+The Image Grid node combines multiple images into a single, organized grid or collage. It takes a list of images and arranges them into a specified number of columns, resizing each image to fit a defined cell size and adding optional padding between them. The result is a single, new image containing all the input images in a grid layout.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | A list of images to be arranged into the grid. The node requires at least one image to function. |
+| `columns` | INT | No | 1 - 20 | The number of columns in the grid (default: 4). |
+| `cell_width` | INT | No | 32 - 2048 | The width, in pixels, of each cell in the grid (default: 256). |
+| `cell_height` | INT | No | 32 - 2048 | The height, in pixels, of each cell in the grid (default: 256). |
+| `padding` | INT | No | 0 - 50 | The amount of padding, in pixels, to place between images in the grid (default: 4). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The single output image containing all the input images arranged in a grid. |
diff --git a/built-in-nodes/ImageInvert.mdx b/built-in-nodes/ImageInvert.mdx
new file mode 100644
index 000000000..825788bc4
--- /dev/null
+++ b/built-in-nodes/ImageInvert.mdx
@@ -0,0 +1,20 @@
+---
+title: "ImageInvert - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageInvert node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageInvert"
+icon: "circle"
+mode: wide
+---
+The `ImageInvert` node is designed to invert the colors of an image, effectively transforming each pixel's color value to its complementary color on the color wheel. This operation is useful for creating negative images or for visual effects that require color inversion.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The 'image' parameter represents the input image to be inverted. It is crucial for specifying the target image whose colors are to be inverted, affecting the node's execution and the visual outcome of the inversion process. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The output is an inverted version of the input image, with each pixel's color value transformed to its complementary color. |
diff --git a/built-in-nodes/ImageOnlyCheckpointLoader.mdx b/built-in-nodes/ImageOnlyCheckpointLoader.mdx
new file mode 100644
index 000000000..0dafd000b
--- /dev/null
+++ b/built-in-nodes/ImageOnlyCheckpointLoader.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageOnlyCheckpointLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageOnlyCheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageOnlyCheckpointLoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/checkpoints` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+This node specializes in loading checkpoints specifically for image-based models within video generation workflows. It efficiently retrieves and configures the necessary components from a given checkpoint, focusing on image-related aspects of the model.
+
+## Inputs
+
+| Field      | Data Type | Description                                                                       |
+|------------|-------------|-----------------------------------------------------------------------------------|
+| `ckpt_name`| COMBO[STRING] | Specifies the name of the checkpoint to load, crucial for identifying and retrieving the correct checkpoint file from a predefined list. |
+
+## Outputs
+
+| Field     | Data Type | Description                                                                                   |
+|-----------|-------------|-----------------------------------------------------------------------------------------------|
+| `model`   | MODEL     | Returns the main model loaded from the checkpoint, configured for image processing within video generation contexts. |
+| `clip_vision` | `CLIP_VISION` | Provides the CLIP vision component from the checkpoint, tailored for image understanding and feature extraction. |
+| `vae`     | VAE       | Delivers the Variational Autoencoder (VAE) component, essential for image manipulation and generation tasks. |
diff --git a/built-in-nodes/ImageOnlyCheckpointSave.mdx b/built-in-nodes/ImageOnlyCheckpointSave.mdx
new file mode 100644
index 000000000..96bb7b79c
--- /dev/null
+++ b/built-in-nodes/ImageOnlyCheckpointSave.mdx
@@ -0,0 +1,27 @@
+---
+title: "ImageOnlyCheckpointSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageOnlyCheckpointSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageOnlyCheckpointSave"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageOnlyCheckpointSave/en.md)
+
+The ImageOnlyCheckpointSave node saves a checkpoint file containing a model, CLIP vision encoder, and VAE. It creates a safetensors file with the specified filename prefix and stores it in the output directory. This node is specifically designed for saving image-related model components together in a single checkpoint file.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to be saved in the checkpoint |
+| `clip_vision` | CLIP_VISION | Yes | - | The CLIP vision encoder to be saved in the checkpoint |
+| `vae` | VAE | Yes | - | The VAE (Variational Autoencoder) to be saved in the checkpoint |
+| `filename_prefix` | STRING | Yes | - | The prefix for the output filename (default: "checkpoints/ComfyUI") |
+| `prompt` | PROMPT | No | - | Hidden parameter for workflow prompt data |
+| `extra_pnginfo` | EXTRA_PNGINFO | No | - | Hidden parameter for additional PNG metadata |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| - | - | This node does not return any outputs |
diff --git a/built-in-nodes/ImagePadForOutpaint.mdx b/built-in-nodes/ImagePadForOutpaint.mdx
new file mode 100644
index 000000000..52f5fec9c
--- /dev/null
+++ b/built-in-nodes/ImagePadForOutpaint.mdx
@@ -0,0 +1,26 @@
+---
+title: "ImagePadForOutpaint - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImagePadForOutpaint node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImagePadForOutpaint"
+icon: "circle"
+mode: wide
+---
+This node is designed for preparing images for the outpainting process by adding padding around them. It adjusts the image dimensions to ensure compatibility with outpainting algorithms, facilitating the generation of extended image areas beyond the original boundaries.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The 'image' input is the primary image to be prepared for outpainting, serving as the base for padding operations. |
+| `left`    | `INT`       | Specifies the amount of padding to add to the left side of the image, influencing the expanded area for outpainting. |
+| `top`     | `INT`       | Determines the amount of padding to add to the top of the image, affecting the vertical expansion for outpainting. |
+| `right`   | `INT`       | Defines the amount of padding to add to the right side of the image, impacting the horizontal expansion for outpainting. |
+| `bottom`  | `INT`       | Indicates the amount of padding to add to the bottom of the image, contributing to the vertical expansion for outpainting. |
+| `feathering` | `INT` | Controls the smoothness of the transition between the original image and the added padding, enhancing the visual integration for outpainting. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The output 'image' represents the padded image, ready for the outpainting process. |
+| `mask`    | `MASK`      | The output 'mask' indicates the areas of the original image and the added padding, useful for guiding the outpainting algorithms. |
diff --git a/built-in-nodes/ImageQuantize.mdx b/built-in-nodes/ImageQuantize.mdx
new file mode 100644
index 000000000..17fa240aa
--- /dev/null
+++ b/built-in-nodes/ImageQuantize.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageQuantize - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageQuantize node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageQuantize"
+icon: "circle"
+mode: wide
+---
+The ImageQuantize node is designed to reduce the number of colors in an image to a specified number, optionally applying dithering techniques to maintain visual quality. This process is useful for creating palette-based images or reducing the color complexity for certain applications.
+
+## Inputs
+
+| Field   | Data Type | Description                                                                       |
+|---------|-------------|-----------------------------------------------------------------------------------|
+| `image` | `IMAGE`     | The input image tensor to be quantized. It affects the node's execution by being the primary data upon which color reduction is performed. |
+| `colors`| `INT`       | Specifies the number of colors to reduce the image to. It directly influences the quantization process by determining the color palette size. |
+| `dither`| COMBO[STRING] | Determines the dithering technique to be applied during quantization, affecting the visual quality and appearance of the output image. |
+
+## Outputs
+
+| Field | Data Type | Description                                                                   |
+|-------|-------------|-------------------------------------------------------------------------------|
+| `image`| `IMAGE`     | The quantized version of the input image, with reduced color complexity and optionally dithered to maintain visual quality. |
diff --git a/built-in-nodes/ImageRGBToYUV.mdx b/built-in-nodes/ImageRGBToYUV.mdx
new file mode 100644
index 000000000..79f120e1f
--- /dev/null
+++ b/built-in-nodes/ImageRGBToYUV.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageRGBToYUV - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageRGBToYUV node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageRGBToYUV"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageRGBToYUV/en.md)
+
+The ImageRGBToYUV node converts RGB color images to the YUV color space. It takes an RGB image as input and separates it into three distinct channels: Y (luminance), U (blue projection), and V (red projection). Each output channel is returned as a separate grayscale image representing the corresponding YUV component.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input RGB image to be converted to YUV color space |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `Y` | IMAGE | The luminance (brightness) component of the YUV color space |
+| `U` | IMAGE | The blue projection component of the YUV color space |
+| `V` | IMAGE | The red projection component of the YUV color space |
diff --git a/built-in-nodes/ImageRotate.mdx b/built-in-nodes/ImageRotate.mdx
new file mode 100644
index 000000000..d8e8b7704
--- /dev/null
+++ b/built-in-nodes/ImageRotate.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageRotate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageRotate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageRotate"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageRotate/en.md)
+
+The ImageRotate node rotates an input image by specified angles. It supports four rotation options: no rotation, 90 degrees clockwise, 180 degrees, and 270 degrees clockwise. The rotation is performed using efficient tensor operations that maintain the image data integrity.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be rotated |
+| `rotation` | STRING | Yes | "none"<br />"90 degrees"<br />"180 degrees"<br />"270 degrees" | The rotation angle to apply to the image |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The rotated output image |
diff --git a/built-in-nodes/ImageScale.mdx b/built-in-nodes/ImageScale.mdx
new file mode 100644
index 000000000..502bfcb76
--- /dev/null
+++ b/built-in-nodes/ImageScale.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageScale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageScale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageScale"
+icon: "circle"
+mode: wide
+---
+The ImageScale node is designed for resizing images to specific dimensions, offering a selection of upscale methods and the ability to crop the resized image. It abstracts the complexity of image upscaling and cropping, providing a straightforward interface for modifying image dimensions according to user-defined parameters.
+
+## Inputs
+
+| Parameter       | Data Type | Description                                                                           |
+|-----------------|-------------|---------------------------------------------------------------------------------------|
+| `image`         | `IMAGE`     | The input image to be upscaled. This parameter is central to the node's operation, serving as the primary data upon which resizing transformations are applied. The quality and dimensions of the output image are directly influenced by the original image's properties. |
+| `upscale_method`| COMBO[STRING] | Specifies the method used for upscaling the image. The choice of method can affect the quality and characteristics of the upscaled image, influencing the visual fidelity and potential artifacts in the resized output. |
+| `width`         | `INT`       | The target width for the upscaled image. This parameter directly influences the dimensions of the output image, determining the horizontal scale of the resizing operation. |
+| `height`        | `INT`       | The target height for the upscaled image. This parameter directly influences the dimensions of the output image, determining the vertical scale of the resizing operation. |
+| `crop`          | COMBO[STRING] | Determines whether and how the upscaled image should be cropped, offering options for disabled cropping or center cropping. This affects the final composition of the image by potentially removing edges to fit the specified dimensions. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The upscaled (and optionally cropped) image, ready for further processing or visualization. |
diff --git a/built-in-nodes/ImageScaleBy.mdx b/built-in-nodes/ImageScaleBy.mdx
new file mode 100644
index 000000000..d4e24ea89
--- /dev/null
+++ b/built-in-nodes/ImageScaleBy.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageScaleBy - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageScaleBy node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageScaleBy"
+icon: "circle"
+mode: wide
+---
+The ImageScaleBy node is designed for upscaling images by a specified scale factor using various interpolation methods. It allows for the adjustment of the image size in a flexible manner, catering to different upscaling needs.
+
+## Inputs
+
+| Parameter       | Data Type | Description                                                                 |
+|-----------------|-------------|----------------------------------------------------------------------------|
+| `image`         | `IMAGE`     | The input image to be upscaled. This parameter is crucial as it provides the base image that will undergo the upscaling process. |
+| `upscale_method`| COMBO[STRING] | Specifies the interpolation method to be used for upscaling. The choice of method can affect the quality and characteristics of the upscaled image. |
+| `scale_by`      | `FLOAT`     | The factor by which the image will be upscaled. This determines the increase in size of the output image relative to the input image. |
+
+## Outputs
+
+| Parameter | Data Type | Description                                                   |
+|-----------|-------------|---------------------------------------------------------------|
+| `image`   | `IMAGE`     | The upscaled image, which is larger than the input image according to the specified scale factor and interpolation method. |
diff --git a/built-in-nodes/ImageScaleToMaxDimension.mdx b/built-in-nodes/ImageScaleToMaxDimension.mdx
new file mode 100644
index 000000000..959282927
--- /dev/null
+++ b/built-in-nodes/ImageScaleToMaxDimension.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageScaleToMaxDimension - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageScaleToMaxDimension node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageScaleToMaxDimension"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageScaleToMaxDimension/en.md)
+
+The ImageScaleToMaxDimension node resizes images to fit within a specified maximum dimension while maintaining the original aspect ratio. It calculates whether the image is portrait or landscape oriented, then scales the larger dimension to match the target size while proportionally adjusting the smaller dimension. The node supports multiple upscaling methods for different quality and performance requirements.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be scaled |
+| `upscale_method` | STRING | Yes | "area"<br />"lanczos"<br />"bilinear"<br />"nearest-exact"<br />"bicubic" | The interpolation method used for scaling the image |
+| `largest_size` | INT | Yes | 0 to 16384 | The maximum dimension for the scaled image (default: 512) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The scaled image with the largest dimension matching the specified size |
diff --git a/built-in-nodes/ImageScaleToTotalPixels.mdx b/built-in-nodes/ImageScaleToTotalPixels.mdx
new file mode 100644
index 000000000..e7bd84678
--- /dev/null
+++ b/built-in-nodes/ImageScaleToTotalPixels.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageScaleToTotalPixels - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageScaleToTotalPixels node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageScaleToTotalPixels"
+icon: "circle"
+mode: wide
+---
+The ImageScaleToTotalPixels node is designed for resizing images to a specified total number of pixels while maintaining the aspect ratio. It provides various methods for upscaling the image to achieve the desired pixel count.
+
+## Inputs
+
+| Parameter       | Data Type | Description                                                                |
+|-----------------|-------------|----------------------------------------------------------------------------|
+| `image`         | `IMAGE`     | The input image to be upscaled to the specified total number of pixels.    |
+| `upscale_method`| COMBO[STRING] | The method used for upscaling the image. It affects the quality and characteristics of the upscaled image. |
+| `megapixels`    | `FLOAT`     | The target size of the image in megapixels. This determines the total number of pixels in the upscaled image. |
+
+## Outputs
+
+| Parameter | Data Type | Description                                                           |
+|-----------|-------------|-----------------------------------------------------------------------|
+| `image`   | `IMAGE`     | The upscaled image with the specified total number of pixels, maintaining the original aspect ratio. |
diff --git a/built-in-nodes/ImageSharpen.mdx b/built-in-nodes/ImageSharpen.mdx
new file mode 100644
index 000000000..3a45e5ea4
--- /dev/null
+++ b/built-in-nodes/ImageSharpen.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageSharpen - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageSharpen node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageSharpen"
+icon: "circle"
+mode: wide
+---
+The ImageSharpen node enhances the clarity of an image by accentuating its edges and details. It applies a sharpening filter to the image, which can be adjusted in intensity and radius, thereby making the image appear more defined and crisp.
+
+## Inputs
+
+| Field          | Data Type | Description                                                                                   |
+|----------------|-------------|-----------------------------------------------------------------------------------------------|
+| `image`        | `IMAGE`     | The input image to be sharpened. This parameter is crucial as it determines the base image on which the sharpening effect will be applied. |
+| `sharpen_radius`| `INT`       | Defines the radius of the sharpening effect. A larger radius means that more pixels around the edge will be affected, leading to a more pronounced sharpening effect. |
+| `sigma`        | `FLOAT`     | Controls the spread of the sharpening effect. A higher sigma value results in a smoother transition at the edges, while a lower sigma makes the sharpening more localized. |
+| `alpha`        | `FLOAT`     | Adjusts the intensity of the sharpening effect. Higher alpha values result in a stronger sharpening effect. |
+
+## Outputs
+
+| Field | Data Type | Description                                                              |
+|-------|-------------|--------------------------------------------------------------------------|
+| `image`| `IMAGE`     | The sharpened image, with enhanced edges and details, ready for further processing or display. |
diff --git a/built-in-nodes/ImageStitch.mdx b/built-in-nodes/ImageStitch.mdx
new file mode 100644
index 000000000..b08173c7e
--- /dev/null
+++ b/built-in-nodes/ImageStitch.mdx
@@ -0,0 +1,59 @@
+---
+title: "ImageStitch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageStitch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageStitch"
+icon: "circle"
+mode: wide
+---
+This node allows you to stitch two images together in a specified direction (up, down, left, right), with support for size matching and spacing between images.
+
+## Inputs
+
+| Parameter Name | Data Type | Input Type | Default | Range | Description |
+|---------------|-----------|-------------|---------|--------|-------------|
+| `image1` | IMAGE | Required | - | - | The first image to be stitched |
+| `image2` | IMAGE | Optional | None | - | The second image to be stitched, if not provided returns only the first image |
+| `direction` | STRING | Required | right | right/down/left/up | The direction to stitch the second image: right, down, left, or up |
+| `match_image_size` | BOOLEAN | Required | True | True/False | Whether to resize the second image to match the dimensions of the first image |
+| `spacing_width` | INT | Required | 0 | 0-1024 | Width of spacing between images, must be an even number |
+| `spacing_color` | STRING | Required | white | white/black/red/green/blue | Color of the spacing between stitched images |
+
+> For `spacing_color`, when using colors other than "white/black", if `match_image_size` is set to `false`, the padding area will be filled with black
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The stitched image |
+
+## Workflow Example
+
+In the workflow below, we use 3 input images of different sizes as examples:
+
+- image1: 500x300
+- image2: 400x250
+- image3: 300x300
+
+![workflow](/images/built-in-nodes/ImageStitch/workflow.webp)
+
+**First Image Stitch Node**
+
+- `match_image_size`: false, images will be stitched at their original sizes
+- `direction`: up, `image2` will be placed above `image1`
+- `spacing_width`: 20
+- `spacing_color`: black
+
+Output image 1:
+
+![output1](/images/built-in-nodes/ImageStitch/output-1.webp)
+
+**Second Image Stitch Node**
+
+- `match_image_size`: true, the second image will be scaled to match the height or width of the first image
+- `direction`: right, `image3` will appear on the right side
+- `spacing_width`: 20
+- `spacing_color`: white
+
+Output image 2:
+
+![output2](/images/built-in-nodes/ImageStitch/output-2.webp)
diff --git a/built-in-nodes/ImageToMask.mdx b/built-in-nodes/ImageToMask.mdx
new file mode 100644
index 000000000..6a541f210
--- /dev/null
+++ b/built-in-nodes/ImageToMask.mdx
@@ -0,0 +1,21 @@
+---
+title: "ImageToMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageToMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageToMask"
+icon: "circle"
+mode: wide
+---
+The ImageToMask node is designed to convert an image into a mask based on a specified color channel. It allows for the extraction of mask layers corresponding to the red, green, blue, or alpha channels of an image, facilitating operations that require channel-specific masking or processing.
+
+## Inputs
+
+| Parameter   | Data Type | Description                                                                                                          |
+|-------------|-------------|----------------------------------------------------------------------------------------------------------------------|
+| `image`     | `IMAGE`     | The 'image' parameter represents the input image from which a mask will be generated based on the specified color channel. It plays a crucial role in determining the content and characteristics of the resulting mask. |
+| `channel`   | COMBO[STRING] | The 'channel' parameter specifies which color channel (red, green, blue, or alpha) of the input image should be used to generate the mask. This choice directly influences the mask's appearance and which parts of the image are highlighted or masked out. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | `MASK`      | The output 'mask' is a binary or grayscale representation of the specified color channel from the input image, useful for further image processing or masking operations. |
diff --git a/built-in-nodes/ImageUpscaleWithModel.mdx b/built-in-nodes/ImageUpscaleWithModel.mdx
new file mode 100644
index 000000000..61b20344e
--- /dev/null
+++ b/built-in-nodes/ImageUpscaleWithModel.mdx
@@ -0,0 +1,21 @@
+---
+title: "ImageUpscaleWithModel - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageUpscaleWithModel node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageUpscaleWithModel"
+icon: "circle"
+mode: wide
+---
+This node is designed for upscaling images using a specified upscale model. It efficiently manages the upscaling process by adjusting the image to the appropriate device, optimizing memory usage, and applying the upscale model in a tiled manner to prevent potential out-of-memory errors.
+
+## Inputs
+
+| Parameter         | Comfy dtype       | Description                                                                 |
+|-------------------|-------------------|----------------------------------------------------------------------------|
+| `upscale_model`   | `UPSCALE_MODEL`   | The upscale model to be used for upscaling the image. It is crucial for defining the upscaling algorithm and its parameters. |
+| `image`           | `IMAGE`           | The image to be upscaled. This input is essential for determining the source content that will undergo the upscaling process. |
+
+## Outputs
+
+| Parameter | Data Type | Description                                        |
+|-----------|-------------|----------------------------------------------------|
+| `image`   | `IMAGE`     | The upscaled image, processed by the upscale model. This output is the result of the upscaling operation, showcasing the enhanced resolution or quality. |
diff --git a/built-in-nodes/ImageYUVToRGB.mdx b/built-in-nodes/ImageYUVToRGB.mdx
new file mode 100644
index 000000000..e91eeec3c
--- /dev/null
+++ b/built-in-nodes/ImageYUVToRGB.mdx
@@ -0,0 +1,26 @@
+---
+title: "ImageYUVToRGB - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageYUVToRGB node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageYUVToRGB"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageYUVToRGB/en.md)
+
+The ImageYUVToRGB node converts YUV color space images to RGB color space. It takes three separate input images representing the Y (luma), U (blue projection), and V (red projection) channels and combines them into a single RGB image using color space conversion.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `Y` | IMAGE | Yes | - | The Y (luminance) channel input image |
+| `U` | IMAGE | Yes | - | The U (blue projection) channel input image |
+| `V` | IMAGE | Yes | - | The V (red projection) channel input image |
+
+**Note:** All three input images (Y, U, and V) must be provided together and should have compatible dimensions for proper conversion.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The converted RGB image |
diff --git a/built-in-nodes/InpaintModelConditioning.mdx b/built-in-nodes/InpaintModelConditioning.mdx
new file mode 100644
index 000000000..15c0fd684
--- /dev/null
+++ b/built-in-nodes/InpaintModelConditioning.mdx
@@ -0,0 +1,26 @@
+---
+title: "InpaintModelConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the InpaintModelConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "InpaintModelConditioning"
+icon: "circle"
+mode: wide
+---
+The InpaintModelConditioning node is designed to facilitate the conditioning process for inpainting models, enabling the integration and manipulation of various conditioning inputs to tailor the inpainting output. It encompasses a broad range of functionalities, from loading specific model checkpoints and applying style or control net models, to encoding and combining conditioning elements, thereby serving as a comprehensive tool for customizing inpainting tasks.
+
+## Inputs
+
+| Parameter | Comfy dtype        | Description |
+|-----------|--------------------|-------------|
+| `positive`| `CONDITIONING`     | Represents the positive conditioning information or parameters that are to be applied to the inpainting model. This input is crucial for defining the context or constraints under which the inpainting operation should be performed, affecting the final output significantly. |
+| `negative`| `CONDITIONING`     | Represents the negative conditioning information or parameters that are to be applied to the inpainting model. This input is essential for specifying the conditions or contexts to avoid during the inpainting process, thereby influencing the final output. |
+| `vae`     | `VAE`              | Specifies the VAE model to be used in the conditioning process. This input is crucial for determining the specific architecture and parameters of the VAE model that will be utilized. |
+| `pixels`  | `IMAGE`            | Represents the pixel data of the image to be inpainted. This input is essential for providing the visual context necessary for the inpainting task. |
+| `mask`    | `MASK`             | Specifies the mask to be applied to the image, indicating the areas to be inpainted. This input is crucial for defining the specific regions within the image that require inpainting. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|--------------|-------------|
+| `positive`| `CONDITIONING` | The modified positive conditioning information after processing, ready to be applied to the inpainting model. This output is essential for guiding the inpainting process according to the specified positive conditions. |
+| `negative`| `CONDITIONING` | The modified negative conditioning information after processing, ready to be applied to the inpainting model. This output is essential for guiding the inpainting process according to the specified negative conditions. |
+| `latent`  | `LATENT`     | The latent representation derived from the conditioning process. This output is crucial for understanding the underlying features and characteristics of the image being inpainted. |
diff --git a/built-in-nodes/InstructPixToPixConditioning.mdx b/built-in-nodes/InstructPixToPixConditioning.mdx
new file mode 100644
index 000000000..4fc2e94ad
--- /dev/null
+++ b/built-in-nodes/InstructPixToPixConditioning.mdx
@@ -0,0 +1,29 @@
+---
+title: "InstructPixToPixConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the InstructPixToPixConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "InstructPixToPixConditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InstructPixToPixConditioning/en.md)
+
+The InstructPixToPixConditioning node prepares conditioning data for InstructPix2Pix image editing by combining positive and negative text prompts with image data. It processes input images through a VAE encoder to create latent representations and attaches these latents to both positive and negative conditioning data. The node automatically handles image dimensions by cropping to multiples of 8 pixels for compatibility with the VAE encoding process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning data containing text prompts and settings for desired image characteristics |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning data containing text prompts and settings for undesired image characteristics |
+| `vae` | VAE | Yes | - | VAE model used for encoding input images into latent representations |
+| `pixels` | IMAGE | Yes | - | Input image to be processed and encoded into latent space |
+
+**Note:** The input image dimensions are automatically adjusted by cropping to the nearest multiple of 8 pixels in both width and height to ensure compatibility with the VAE encoding process.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning data with attached latent image representation |
+| `negative` | CONDITIONING | Negative conditioning data with attached latent image representation |
+| `latent` | LATENT | Empty latent tensor with the same dimensions as the encoded image |
diff --git a/built-in-nodes/InvertBooleanNode.mdx b/built-in-nodes/InvertBooleanNode.mdx
new file mode 100644
index 000000000..bd0b522d4
--- /dev/null
+++ b/built-in-nodes/InvertBooleanNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "InvertBooleanNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the InvertBooleanNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "InvertBooleanNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InvertBooleanNode/en.md)
+
+This node takes a single boolean (true/false) input and outputs the opposite value. It performs a logical NOT operation, turning `true` into `false` and `false` into `true`.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `boolean` | BOOLEAN | Yes | `true`<br />`false` | The input boolean value to be inverted. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | BOOLEAN | The inverted boolean value. |
diff --git a/built-in-nodes/InvertMask.mdx b/built-in-nodes/InvertMask.mdx
new file mode 100644
index 000000000..84bec2201
--- /dev/null
+++ b/built-in-nodes/InvertMask.mdx
@@ -0,0 +1,20 @@
+---
+title: "InvertMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the InvertMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "InvertMask"
+icon: "circle"
+mode: wide
+---
+The InvertMask node is designed to invert the values of a given mask, effectively flipping the masked and unmasked areas. This operation is fundamental in image processing tasks where the focus of interest needs to be switched between the foreground and the background.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|--------------|-------------|
+| `mask`    | MASK         | The 'mask' parameter represents the input mask to be inverted. It is crucial for determining the areas to be flipped in the inversion process. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|--------------|-------------|
+| `mask`    | MASK         | The output is an inverted version of the input mask, with previously masked areas becoming unmasked and vice versa. |
diff --git a/built-in-nodes/JoinAudioChannels.mdx b/built-in-nodes/JoinAudioChannels.mdx
new file mode 100644
index 000000000..d269436fa
--- /dev/null
+++ b/built-in-nodes/JoinAudioChannels.mdx
@@ -0,0 +1,25 @@
+---
+title: "JoinAudioChannels - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the JoinAudioChannels node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "JoinAudioChannels"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/JoinAudioChannels/en.md)
+
+The Join Audio Channels node combines two separate mono audio inputs into a single stereo audio output. It takes a left channel and a right channel, ensures they have compatible sample rates and lengths, and merges them into a two-channel audio waveform.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio_left` | AUDIO | Yes | | The mono audio data to be used as the left channel in the resulting stereo audio. |
+| `audio_right` | AUDIO | Yes | | The mono audio data to be used as the right channel in the resulting stereo audio. |
+
+**Note:** Both input audio streams must be mono (single-channel). If they have different sample rates, the channel with the lower rate will be automatically resampled to match the higher rate. If the audio streams have different lengths, they will be trimmed to the length of the shorter one.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The resulting stereo audio, containing the joined left and right channels. |
diff --git a/built-in-nodes/JoinImageWithAlpha.mdx b/built-in-nodes/JoinImageWithAlpha.mdx
new file mode 100644
index 000000000..df6ae604d
--- /dev/null
+++ b/built-in-nodes/JoinImageWithAlpha.mdx
@@ -0,0 +1,21 @@
+---
+title: "JoinImageWithAlpha - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the JoinImageWithAlpha node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "JoinImageWithAlpha"
+icon: "circle"
+mode: wide
+---
+This node is designed for compositing operations, specifically to join an image with its corresponding alpha mask to produce a single output image. It effectively combines visual content with transparency information, enabling the creation of images where certain areas are transparent or semi-transparent.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The main visual content to be combined with an alpha mask. It represents the image without transparency information. |
+| `alpha`   | `MASK`      | The alpha mask that defines the transparency of the corresponding image. It is used to determine which parts of the image should be transparent or semi-transparent. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The output is a single image that combines the input image with the alpha mask, incorporating transparency information into the visual content. |
diff --git a/built-in-nodes/KSampler.mdx b/built-in-nodes/KSampler.mdx
new file mode 100644
index 000000000..7f1b570c8
--- /dev/null
+++ b/built-in-nodes/KSampler.mdx
@@ -0,0 +1,89 @@
+---
+title: "KSampler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KSampler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KSampler"
+icon: "circle"
+mode: wide
+---
+The KSampler works like this: it modifies the provided original latent image information based on a specific model and both positive and negative conditions.
+First, it adds noise to the original image data according to the set **seed** and **denoise strength**, then inputs the preset **Model** combined with **positive** and **negative** guidance conditions to generate the image.
+
+## Inputs
+
+| Parameter Name         | Data Type    | Required | Default | Range/Options            | Description                                                                        |
+| ---------------------- | ------------ | -------- | ------- | ------------------------ | ---------------------------------------------------------------------------------- |
+| Model                  | checkpoint   | Yes      | None    | -                        | Input model used for the denoising process                                         |
+| seed                   | Int          | Yes      | 0       | 0 ~ 18446744073709551615 | Used to generate random noise, using the same "seed" generates identical images    |
+| steps                  | Int          | Yes      | 20      | 1 ~ 10000                | Number of steps to use in denoising process, more steps mean more accurate results |
+| cfg                    | float        | Yes      | 8.0     | 0.0 ~ 100.0              | Controls how closely the generated image matches input conditions, 6-8 recommended |
+| sampler_name           | UI Option    | Yes      | None    | Multiple algorithms      | Choose sampler for denoising, affects generation speed and style                   |
+| scheduler              | UI Option    | Yes      | None    | Multiple schedulers      | Controls how noise is removed, affects generation process                          |
+| Positive               | conditioning | Yes      | None    | -                        | Positive conditions guiding denoising, what you want to appear in the image        |
+| Negative               | conditioning | Yes      | None    | -                        | Negative conditions guiding denoising, what you don't want in the image            |
+| Latent_Image           | Latent       | Yes      | None    | -                        | Latent image used for denoising                                                    |
+| denoise                | float        | No       | 1.0     | 0.0 ~ 1.0                | Determines noise removal ratio, lower values mean less connection to input image   |
+| control_after_generate | UI Option    | No       | None    | Random/Inc/Dec/Keep      | Provides ability to change seed after each prompt                                  |
+
+## Output
+
+| Parameter | Function                                   |
+| -------------- | ------------------------------------------ |
+| Latent         | Outputs the latent after sampler denoising |
+
+## Source Code
+
+[Updated on May 15, 2025]
+
+```Python
+
+def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent, denoise=1.0, disable_noise=False, start_step=None, last_step=None, force_full_denoise=False):
+    latent_image = latent["samples"]
+    latent_image = comfy.sample.fix_empty_latent_channels(model, latent_image)
+
+    if disable_noise:
+        noise = torch.zeros(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, device="cpu")
+    else:
+        batch_inds = latent["batch_index"] if "batch_index" in latent else None
+        noise = comfy.sample.prepare_noise(latent_image, seed, batch_inds)
+
+    noise_mask = None
+    if "noise_mask" in latent:
+        noise_mask = latent["noise_mask"]
+
+    callback = latent_preview.prepare_callback(model, steps)
+    disable_pbar = not comfy.utils.PROGRESS_BAR_ENABLED
+    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
+                                  denoise=denoise, disable_noise=disable_noise, start_step=start_step, last_step=last_step,
+                                  force_full_denoise=force_full_denoise, noise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
+    out = latent.copy()
+    out["samples"] = samples
+    return (out, )
+class KSampler:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "model": ("MODEL", {"tooltip": "The model used for denoising the input latent."}),
+                "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff, "control_after_generate": True, "tooltip": "The random seed used for creating the noise."}),
+                "steps": ("INT", {"default": 20, "min": 1, "max": 10000, "tooltip": "The number of steps used in the denoising process."}),
+                "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01, "tooltip": "The Classifier-Free Guidance scale balances creativity and adherence to the prompt. Higher values result in images more closely matching the prompt however too high values will negatively impact quality."}),
+                "sampler_name": (comfy.samplers.KSampler.SAMPLERS, {"tooltip": "The algorithm used when sampling, this can affect the quality, speed, and style of the generated output."}),
+                "scheduler": (comfy.samplers.KSampler.SCHEDULERS, {"tooltip": "The scheduler controls how noise is gradually removed to form the image."}),
+                "positive": ("CONDITIONING", {"tooltip": "The conditioning describing the attributes you want to include in the image."}),
+                "negative": ("CONDITIONING", {"tooltip": "The conditioning describing the attributes you want to exclude from the image."}),
+                "latent_image": ("LATENT", {"tooltip": "The latent image to denoise."}),
+                "denoise": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01, "tooltip": "The amount of denoising applied, lower values will maintain the structure of the initial image allowing for image to image sampling."}),
+            }
+        }
+
+    RETURN_TYPES = ("LATENT",)
+    OUTPUT_TOOLTIPS = ("The denoised latent.",)
+    FUNCTION = "sample"
+
+    CATEGORY = "sampling"
+    DESCRIPTION = "Uses the provided model, positive and negative conditioning to denoise the latent image."
+
+    def sample(self, model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=1.0):
+        return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
+
+```
diff --git a/built-in-nodes/KSamplerAdvanced.mdx b/built-in-nodes/KSamplerAdvanced.mdx
new file mode 100644
index 000000000..075d4a29a
--- /dev/null
+++ b/built-in-nodes/KSamplerAdvanced.mdx
@@ -0,0 +1,32 @@
+---
+title: "KSamplerAdvanced - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KSamplerAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KSamplerAdvanced"
+icon: "circle"
+mode: wide
+---
+The KSamplerAdvanced node is designed to enhance the sampling process by providing advanced configurations and techniques. It aims to offer more sophisticated options for generating samples from a model, improving upon the basic KSampler functionalities.
+
+## Inputs
+
+| Parameter             | Data Type | Description                                                                                                                                                                                                                                                                                                                                                     |
+|----------------------|-------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `model`              | MODEL       | Specifies the model from which samples are to be generated, playing a crucial role in the sampling process.                                                                                                                                                                                                                      |
+| `add_noise`          | COMBO[STRING] | Determines whether noise should be added to the sampling process, affecting the diversity and quality of the generated samples.                                                                                                                                                                                                             |
+| `noise_seed`         | INT         | Sets the seed for noise generation, ensuring reproducibility in the sampling process.                                                                                                                                                                                                                                     |
+| `steps`              | INT         | Defines the number of steps to be taken in the sampling process, impacting the detail and quality of the output.                                                                                                                                                                                                                   |
+| `cfg`                | FLOAT       | Controls the conditioning factor, influencing the direction and space of the sampling process.                                                                                                                                                                                                                                  |
+| `sampler_name`       | COMBO[STRING] | Selects the specific sampler to be used, allowing for customization of the sampling technique.                                                                                                                                                                                                                                  |
+| `scheduler`          | COMBO[STRING] | Chooses the scheduler for controlling the sampling process, affecting the progression and quality of samples.                                                                                                                                                                                                                   |
+| `positive`           | CONDITIONING | Specifies the positive conditioning to guide the sampling towards desired attributes.                                                                                                                                                                                                                                     |
+| `negative`           | CONDITIONING | Specifies the negative conditioning to steer the sampling away from certain attributes.                                                                                                                                                                                                                                     |
+| `latent_image`       | LATENT      | Provides the initial latent image to be used in the sampling process, serving as a starting point.                                                                                                                                                                                                                               |
+| `start_at_step`      | INT         | Determines the starting step of the sampling process, allowing for control over the sampling progression.                                                                                                                                                                                                                               |
+| `end_at_step`        | INT         | Sets the ending step of the sampling process, defining the scope of the sampling.                                                                                                                                                                                                                                         |
+| `return_with_leftover_noise` | COMBO[STRING] | Indicates whether to return the sample with leftover noise, affecting the final output's appearance.                                                                                                                                                                                                                               |
+
+## Outputs
+
+| Parameter   | Data Type | Description                                                                                                               |
+|-------------|-------------|------------------------------------------------------------------------------------------------------------------------------|
+| `latent`    | LATENT      | The output represents the latent image generated from the model, reflecting the applied configurations and techniques. |
diff --git a/built-in-nodes/KSamplerSelect.mdx b/built-in-nodes/KSamplerSelect.mdx
new file mode 100644
index 000000000..5244a5ef2
--- /dev/null
+++ b/built-in-nodes/KSamplerSelect.mdx
@@ -0,0 +1,20 @@
+---
+title: "KSamplerSelect - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KSamplerSelect node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KSamplerSelect"
+icon: "circle"
+mode: wide
+---
+The KSamplerSelect node is designed to select a specific sampler based on the provided sampler name. It abstracts the complexity of sampler selection, allowing users to easily switch between different sampling strategies for their tasks.
+
+## Inputs
+
+| Parameter         | Data Type | Description                                                                                      |
+|-------------------|-------------|------------------------------------------------------------------------------------------------|
+| `sampler_name`    | COMBO[STRING] | Specifies the name of the sampler to be selected. This parameter determines which sampling strategy will be used, impacting the overall sampling behavior and results. |
+
+## Outputs
+
+| Parameter   | Data Type | Description                                                                 |
+|-------------|-------------|-----------------------------------------------------------------------------|
+| `sampler`   | `SAMPLER`   | Returns the selected sampler object, ready to be used for sampling tasks. |
diff --git a/built-in-nodes/Kandinsky5ImageToVideo.mdx b/built-in-nodes/Kandinsky5ImageToVideo.mdx
new file mode 100644
index 000000000..f18005c60
--- /dev/null
+++ b/built-in-nodes/Kandinsky5ImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "Kandinsky5ImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Kandinsky5ImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Kandinsky5ImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Kandinsky5ImageToVideo/en.md)
+
+The Kandinsky5ImageToVideo node prepares conditioning and latent space data for video generation using the Kandinsky model. It creates an empty video latent tensor and can optionally encode a starting image to guide the initial frames of the generated video, modifying the positive and negative conditioning accordingly.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | N/A | The positive conditioning prompts to guide the video generation. |
+| `negative` | CONDITIONING | Yes | N/A | The negative conditioning prompts to steer the video generation away from certain concepts. |
+| `vae` | VAE | Yes | N/A | The VAE model used to encode the optional starting image into the latent space. |
+| `width` | INT | No | 16 to 8192 (step 16) | The width of the output video in pixels (default: 768). |
+| `height` | INT | No | 16 to 8192 (step 16) | The height of the output video in pixels (default: 512). |
+| `length` | INT | No | 1 to 8192 (step 4) | The number of frames in the video (default: 121). |
+| `batch_size` | INT | No | 1 to 4096 | The number of video sequences to generate simultaneously (default: 1). |
+| `start_image` | IMAGE | No | N/A | An optional starting image. If provided, it is encoded and used to replace the noisy start of the model's output latents. |
+
+**Note:** When a `start_image` is provided, it is automatically resized to match the specified `width` and `height` using bilinear interpolation. The first `length` frames of the image batch are used for encoding. The encoded latent is then injected into both the `positive` and `negative` conditioning to guide the video's initial appearance.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The modified positive conditioning, potentially updated with encoded start image data. |
+| `negative` | CONDITIONING | The modified negative conditioning, potentially updated with encoded start image data. |
+| `latent` | LATENT | An empty video latent tensor with zeros, shaped for the specified dimensions. |
+| `cond_latent` | LATENT | The clean, encoded latent representation of the provided start images. This is used internally to replace the noisy beginning of the generated video latents. |
diff --git a/built-in-nodes/KarrasScheduler.mdx b/built-in-nodes/KarrasScheduler.mdx
new file mode 100644
index 000000000..9e9ddd68a
--- /dev/null
+++ b/built-in-nodes/KarrasScheduler.mdx
@@ -0,0 +1,23 @@
+---
+title: "KarrasScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KarrasScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KarrasScheduler"
+icon: "circle"
+mode: wide
+---
+The KarrasScheduler node is designed to generate a sequence of noise levels (sigmas) based on the Karras et al. (2022) noise schedule. This scheduler is useful for controlling the diffusion process in generative models, allowing for fine-tuned adjustments to the noise levels applied at each step of the generation process.
+
+## Inputs
+
+| Parameter   | Data Type | Description                                                                                      |
+|-------------|-------------|------------------------------------------------------------------------------------------------|
+| `steps`     | INT         | Specifies the number of steps in the noise schedule, affecting the granularity of the generated sigmas sequence. |
+| `sigma_max` | FLOAT       | The maximum sigma value in the noise schedule, setting the upper bound of noise levels.                    |
+| `sigma_min` | FLOAT       | The minimum sigma value in the noise schedule, setting the lower bound of noise levels.                    |
+| `rho`       | FLOAT       | A parameter that controls the shape of the noise schedule curve, influencing how noise levels progress from sigma_min to sigma_max. |
+
+## Outputs
+
+| Parameter | Data Type | Description                                                                 |
+|-----------|-------------|-----------------------------------------------------------------------------|
+| `sigmas`  | SIGMAS      | The generated sequence of noise levels (sigmas) following the Karras et al. (2022) noise schedule. |
diff --git a/built-in-nodes/KlingCameraControlI2VNode.mdx b/built-in-nodes/KlingCameraControlI2VNode.mdx
new file mode 100644
index 000000000..04d0ac08d
--- /dev/null
+++ b/built-in-nodes/KlingCameraControlI2VNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "KlingCameraControlI2VNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingCameraControlI2VNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingCameraControlI2VNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlI2VNode/en.md)
+
+The Kling Image to Video Camera Control Node transforms still images into cinematic videos with professional camera movements. This specialized image-to-video node allows you to control virtual camera actions including zoom, rotation, pan, tilt, and first-person view while maintaining focus on your original image. Camera control is currently only supported in pro mode with the kling-v1-5 model at 5-second duration.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `start_frame` | IMAGE | Yes | - | Reference Image - URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px, aspect ratio between 1:2.5 ~ 2.5:1. Base64 should not include data:image prefix. |
+| `prompt` | STRING | Yes | - | Positive text prompt |
+| `negative_prompt` | STRING | Yes | - | Negative text prompt |
+| `cfg_scale` | FLOAT | No | 0.0-1.0 | Controls the strength of text guidance (default: 0.75) |
+| `aspect_ratio` | COMBO | No | Multiple options available | Video aspect ratio selection (default: 16:9) |
+| `camera_control` | CAMERA_CONTROL | Yes | - | Can be created using the Kling Camera Controls node. Controls the camera movement and motion during the video generation. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video output |
+| `video_id` | STRING | Unique identifier for the generated video |
+| `duration` | STRING | Duration of the generated video |
diff --git a/built-in-nodes/KlingCameraControlT2VNode.mdx b/built-in-nodes/KlingCameraControlT2VNode.mdx
new file mode 100644
index 000000000..4b79e3b2c
--- /dev/null
+++ b/built-in-nodes/KlingCameraControlT2VNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "KlingCameraControlT2VNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingCameraControlT2VNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingCameraControlT2VNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlT2VNode/en.md)
+
+Kling Text to Video Camera Control Node transforms text into cinematic videos with professional camera movements that simulate real-world cinematography. This node supports controlling virtual camera actions including zoom, rotation, pan, tilt, and first-person view while maintaining focus on your original text. The duration, mode, and model name are hard-coded because camera control is only supported in pro mode with the kling-v1-5 model at 5-second duration.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Positive text prompt |
+| `negative_prompt` | STRING | Yes | - | Negative text prompt |
+| `cfg_scale` | FLOAT | No | 0.0-1.0 | Controls how closely the output follows the prompt (default: 0.75) |
+| `aspect_ratio` | COMBO | No | "16:9"<br />"9:16"<br />"1:1"<br />"21:9"<br />"3:4"<br />"4:3" | The aspect ratio for the generated video (default: "16:9") |
+| `camera_control` | CAMERA_CONTROL | No | - | Can be created using the Kling Camera Controls node. Controls the camera movement and motion during the video generation. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video with camera control effects |
+| `video_id` | STRING | The unique identifier for the generated video |
+| `duration` | STRING | The duration of the generated video |
diff --git a/built-in-nodes/KlingCameraControls.mdx b/built-in-nodes/KlingCameraControls.mdx
new file mode 100644
index 000000000..51488deb5
--- /dev/null
+++ b/built-in-nodes/KlingCameraControls.mdx
@@ -0,0 +1,30 @@
+---
+title: "KlingCameraControls - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingCameraControls node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingCameraControls"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControls/en.md)
+
+The Kling Camera Controls node allows you to configure various camera movement and rotation parameters for creating motion control effects in video generation. It provides controls for camera positioning, rotation, and zoom to simulate different camera movements.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `camera_control_type` | COMBO | Yes | Multiple options available | Specifies the type of camera control configuration to use |
+| `horizontal_movement` | FLOAT | No | -10.0 to 10.0 | Controls camera's movement along horizontal axis (x-axis). Negative indicates left, positive indicates right (default: 0.0) |
+| `vertical_movement` | FLOAT | No | -10.0 to 10.0 | Controls camera's movement along vertical axis (y-axis). Negative indicates downward, positive indicates upward (default: 0.0) |
+| `pan` | FLOAT | No | -10.0 to 10.0 | Controls camera's rotation in vertical plane (x-axis). Negative indicates downward rotation, positive indicates upward rotation (default: 0.5) |
+| `tilt` | FLOAT | No | -10.0 to 10.0 | Controls camera's rotation in horizontal plane (y-axis). Negative indicates left rotation, positive indicates right rotation (default: 0.0) |
+| `roll` | FLOAT | No | -10.0 to 10.0 | Controls camera's rolling amount (z-axis). Negative indicates counterclockwise, positive indicates clockwise (default: 0.0) |
+| `zoom` | FLOAT | No | -10.0 to 10.0 | Controls change in camera's focal length. Negative indicates narrower field of view, positive indicates wider field of view (default: 0.0) |
+
+**Note:** At least one of the camera control parameters (`horizontal_movement`, `vertical_movement`, `pan`, `tilt`, `roll`, or `zoom`) must have a non-zero value for the configuration to be valid.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `camera_control` | CAMERA_CONTROL | Returns the configured camera control settings for use in video generation |
diff --git a/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx b/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx
new file mode 100644
index 000000000..903b9676a
--- /dev/null
+++ b/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "KlingDualCharacterVideoEffectNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingDualCharacterVideoEffectNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingDualCharacterVideoEffectNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingDualCharacterVideoEffectNode/en.md)
+
+The Kling Dual Character Video Effect Node creates videos with special effects based on the selected scene. It takes two images and positions the first image on the left side and the second image on the right side of the composite video. Different visual effects are applied depending on the chosen effect scene.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image_left` | IMAGE | Yes | - | Left side image |
+| `image_right` | IMAGE | Yes | - | Right side image |
+| `effect_scene` | COMBO | Yes | Multiple options available | The type of special effect scene to apply to the video generation |
+| `model_name` | COMBO | No | Multiple options available | The model to use for character effects (default: "kling-v1") |
+| `mode` | COMBO | No | Multiple options available | The video generation mode (default: "std") |
+| `duration` | COMBO | Yes | Multiple options available | The duration of the generated video |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video with dual character effects |
+| `duration` | STRING | The duration information of the generated video |
diff --git a/built-in-nodes/KlingFirstLastFrameNode.mdx b/built-in-nodes/KlingFirstLastFrameNode.mdx
new file mode 100644
index 000000000..ad370643d
--- /dev/null
+++ b/built-in-nodes/KlingFirstLastFrameNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "KlingFirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingFirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingFirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingFirstLastFrameNode/en.md)
+
+This node uses the Kling 3.0 model to generate a video. It creates the video based on a text prompt, a specified duration, and two provided images: a starting frame and an ending frame. The node can also generate accompanying audio for the video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | N/A | The text description that guides the video generation. Must be between 1 and 2500 characters long. |
+| `duration` | INT | No | 3 to 15 | The length of the video in seconds (default: 5). |
+| `first_frame` | IMAGE | Yes | N/A | The starting image for the video. Must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1. |
+| `end_frame` | IMAGE | Yes | N/A | The ending image for the video. Must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1. |
+| `generate_audio` | BOOLEAN | No | N/A | Controls whether to generate audio for the video (default: True). |
+| `model` | COMBO | No | `"kling-v3"` | Model and generation settings. Selecting this option reveals a nested `resolution` parameter. |
+| `model.resolution` | COMBO | No | `"1080p"`<br />`"720p"` | The resolution for the generated video. This parameter is only available when the `model` is set to `"kling-v3"`. |
+| `seed` | INT | No | 0 to 2147483647 | A number used to control whether the node should re-run. The results are non-deterministic regardless of the seed value (default: 0). |
+
+**Note:** The `first_frame` and `end_frame` images must meet the specified minimum size and aspect ratio requirements for the node to function correctly.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/KlingImage2VideoNode.mdx b/built-in-nodes/KlingImage2VideoNode.mdx
new file mode 100644
index 000000000..5cd9f8618
--- /dev/null
+++ b/built-in-nodes/KlingImage2VideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "KlingImage2VideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingImage2VideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingImage2VideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImage2VideoNode/en.md)
+
+The Kling Image to Video Node generates video content from a starting image using text prompts. It takes a reference image and creates a video sequence based on the provided positive and negative text descriptions, with various configuration options for model selection, duration, and aspect ratio.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `start_frame` | IMAGE | Yes | - | The reference image used to generate the video. |
+| `prompt` | STRING | Yes | - | Positive text prompt. |
+| `negative_prompt` | STRING | Yes | - | Negative text prompt. |
+| `model_name` | COMBO | Yes | Multiple options available | Model selection for video generation (default: "kling-v2-master"). |
+| `cfg_scale` | FLOAT | Yes | 0.0-1.0 | Configuration scale parameter (default: 0.8). |
+| `mode` | COMBO | Yes | Multiple options available | Video generation mode selection (default: std). |
+| `aspect_ratio` | COMBO | Yes | Multiple options available | Aspect ratio for the generated video (default: field_16_9). |
+| `duration` | COMBO | Yes | Multiple options available | Duration of the generated video (default: field_5). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video output. |
+| `video_id` | STRING | Unique identifier for the generated video. |
+| `duration` | STRING | Duration information for the generated video. |
diff --git a/built-in-nodes/KlingImageGenerationNode.mdx b/built-in-nodes/KlingImageGenerationNode.mdx
new file mode 100644
index 000000000..b2149a296
--- /dev/null
+++ b/built-in-nodes/KlingImageGenerationNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "KlingImageGenerationNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingImageGenerationNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingImageGenerationNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImageGenerationNode/en.md)
+
+Kling Image Generation Node generates images from text prompts with the option to use a reference image for guidance. It creates one or more images based on your text description and reference settings, then returns the generated images as output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Positive text prompt |
+| `negative_prompt` | STRING | Yes | - | Negative text prompt |
+| `image_type` | COMBO | Yes | Options from KlingImageGenImageReferenceType<br />(extracted from source code) | Image reference type selection |
+| `image_fidelity` | FLOAT | Yes | 0.0 - 1.0 | Reference intensity for user-uploaded images (default: 0.5) |
+| `human_fidelity` | FLOAT | Yes | 0.0 - 1.0 | Subject reference similarity (default: 0.45) |
+| `model_name` | COMBO | Yes | "kling-v1"<br />(and other options from KlingImageGenModelName) | Model selection for image generation (default: "kling-v1") |
+| `aspect_ratio` | COMBO | Yes | "16:9"<br />(and other options from KlingImageGenAspectRatio) | Aspect ratio for generated images (default: "16:9") |
+| `n` | INT | Yes | 1 - 9 | Number of generated images (default: 1) |
+| `image` | IMAGE | No | - | Optional reference image |
+
+**Parameter Constraints:**
+
+- The `image` parameter is optional, but when provided, the kling-v1 model does not support reference images
+- Prompt and negative prompt have maximum length limitations (MAX_PROMPT_LENGTH_IMAGE_GEN)
+- When no reference image is provided, the `image_type` parameter is automatically set to None
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | Generated image(s) based on the input parameters |
diff --git a/built-in-nodes/KlingImageToVideoWithAudio.mdx b/built-in-nodes/KlingImageToVideoWithAudio.mdx
new file mode 100644
index 000000000..f2f00cb30
--- /dev/null
+++ b/built-in-nodes/KlingImageToVideoWithAudio.mdx
@@ -0,0 +1,27 @@
+---
+title: "KlingImageToVideoWithAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingImageToVideoWithAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingImageToVideoWithAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImageToVideoWithAudio/en.md)
+
+The Kling Image(First Frame) to Video with Audio node uses the Kling AI model to generate a short video from a single starting image and a text prompt. It creates a video sequence that begins with the provided image and can optionally include AI-generated audio to accompany the visuals.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | Yes | `"kling-v2-6"` | The specific version of the Kling AI model to use for video generation. |
+| `start_frame` | IMAGE | Yes | - | The image that will serve as the first frame of the generated video. The image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1. |
+| `prompt` | STRING | Yes | - | Positive text prompt. This describes the video content you want to generate. The prompt must be between 1 and 2500 characters long. |
+| `mode` | COMBO | Yes | `"pro"` | The operational mode for the video generation. |
+| `duration` | COMBO | Yes | `5`<br />`10` | The length of the video to generate, in seconds. |
+| `generate_audio` | BOOLEAN | No | - | When enabled, the node will generate audio to accompany the video. When disabled, the video will be silent. (default: True) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The generated video file, which may include audio depending on the `generate_audio` input. |
diff --git a/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx b/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx
new file mode 100644
index 000000000..f2156449c
--- /dev/null
+++ b/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx
@@ -0,0 +1,35 @@
+---
+title: "KlingLipSyncAudioToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingLipSyncAudioToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingLipSyncAudioToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncAudioToVideoNode/en.md)
+
+Kling Lip Sync Audio to Video Node synchronizes mouth movements in a video file to match the audio content of an audio file. This node analyzes the vocal patterns in the audio and adjusts the facial movements in the video to create realistic lip-syncing. The process requires both a video containing a distinct face and an audio file with clearly distinguishable vocals.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | - | The video file containing a face to be lip-synced |
+| `audio` | AUDIO | Yes | - | The audio file containing vocals to sync with the video |
+| `voice_language` | COMBO | No | `"en"`<br />`"zh"`<br />`"es"`<br />`"fr"`<br />`"de"`<br />`"it"`<br />`"pt"`<br />`"pl"`<br />`"tr"`<br />`"ru"`<br />`"nl"`<br />`"cs"`<br />`"ar"`<br />`"ja"`<br />`"hu"`<br />`"ko"` | The language of the voice in the audio file (default: "en") |
+
+**Important Constraints:**
+
+- The audio file should not be larger than 5MB
+- The video file should not be larger than 100MB
+- Video dimensions should be between 720px and 1920px in height/width
+- Video duration should be between 2 seconds and 10 seconds
+- The audio must contain clearly distinguishable vocals
+- The video must contain a distinct face
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The processed video with lip-synced mouth movements |
+| `video_id` | STRING | The unique identifier for the processed video |
+| `duration` | STRING | The duration of the processed video |
diff --git a/built-in-nodes/KlingLipSyncTextToVideoNode.mdx b/built-in-nodes/KlingLipSyncTextToVideoNode.mdx
new file mode 100644
index 000000000..ca3e9b867
--- /dev/null
+++ b/built-in-nodes/KlingLipSyncTextToVideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "KlingLipSyncTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingLipSyncTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingLipSyncTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncTextToVideoNode/en.md)
+
+Kling Lip Sync Text to Video Node synchronizes mouth movements in a video file to match a text prompt. It takes an input video and generates a new video where the character's lip movements are aligned with the provided text. The node uses voice synthesis to create natural-looking speech synchronization.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | - | Input video file for lip synchronization |
+| `text` | STRING | Yes | - | Text Content for Lip-Sync Video Generation. Required when mode is text2video. Maximum length is 120 characters. |
+| `voice` | COMBO | No | "Melody"<br />"Bella"<br />"Aria"<br />"Ethan"<br />"Ryan"<br />"Dorothy"<br />"Nathan"<br />"Lily"<br />"Aaron"<br />"Emma"<br />"Grace"<br />"Henry"<br />"Isabella"<br />"James"<br />"Katherine"<br />"Liam"<br />"Mia"<br />"Noah"<br />"Olivia"<br />"Sophia" | Voice selection for the lip-sync audio (default: "Melody") |
+| `voice_speed` | FLOAT | No | 0.8-2.0 | Speech Rate. Valid range: 0.8~2.0, accurate to one decimal place. (default: 1) |
+
+**Video Requirements:**
+
+- Video file should not be larger than 100MB
+- Height/width should be between 720px and 1920px
+- Duration should be between 2s and 10s
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | Generated video with lip-synchronized audio |
+| `video_id` | STRING | Unique identifier for the generated video |
+| `duration` | STRING | Duration information for the generated video |
diff --git a/built-in-nodes/KlingMotionControl.mdx b/built-in-nodes/KlingMotionControl.mdx
new file mode 100644
index 000000000..6d0b0d962
--- /dev/null
+++ b/built-in-nodes/KlingMotionControl.mdx
@@ -0,0 +1,32 @@
+---
+title: "KlingMotionControl - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingMotionControl node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingMotionControl"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingMotionControl/en.md)
+
+The Kling Motion Control node generates a video by applying the motion, expressions, and camera movements from a reference video to a character defined by a reference image and a text prompt. It allows you to control whether the character's final orientation comes from the reference video or the reference image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | N/A | A text description of the desired video. Maximum length is 2500 characters. |
+| `reference_image` | IMAGE | Yes | N/A | An image of the character to animate. Minimum dimensions are 340x340 pixels. The aspect ratio must be between 1:2.5 and 2.5:1. |
+| `reference_video` | VIDEO | Yes | N/A | A motion reference video used to drive the character's movement and expression. Minimum dimensions are 340x340 pixels, maximum dimensions are 3850x3850 pixels. Duration limits depend on the `character_orientation` setting. |
+| `keep_original_sound` | BOOLEAN | No | N/A | Determines if the original audio from the reference video is kept in the output. Default is `True`. |
+| `character_orientation` | COMBO | No | `"video"`<br />`"image"` | Controls where the character's facing/orientation comes from. `"video"`: movements, expressions, camera moves, and orientation follow the motion reference video. `"image"`: movements and expressions follow the motion reference video, but the character orientation matches the reference image. |
+| `mode` | COMBO | No | `"pro"`<br />`"std"` | The generation mode to use. |
+
+**Constraints:**
+
+* The `reference_video` duration must be between 3 and 30 seconds when `character_orientation` is set to `"video"`.
+* The `reference_video` duration must be between 3 and 10 seconds when `character_orientation` is set to `"image"`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video with the character performing the motion from the reference video. |
diff --git a/built-in-nodes/KlingOmniProEditVideoNode.mdx b/built-in-nodes/KlingOmniProEditVideoNode.mdx
new file mode 100644
index 000000000..68710bc82
--- /dev/null
+++ b/built-in-nodes/KlingOmniProEditVideoNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "KlingOmniProEditVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProEditVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProEditVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProEditVideoNode/en.md)
+
+The Kling Omni Edit Video (Pro) node uses an AI model to edit an existing video based on a text description. You provide a source video and a prompt, and the node generates a new video of the same length with the requested changes. It can optionally use reference images to guide the style and keep the original audio from the source video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | Yes | `"kling-video-o1"` | The AI model to use for video editing. |
+| `prompt` | STRING | Yes | | A text prompt describing the video content. This can include both positive and negative descriptions. |
+| `video` | VIDEO | Yes | | Video for editing. The output video length will be the same. |
+| `keep_original_sound` | BOOLEAN | Yes | | Determines if the original audio from the input video is kept in the output (default: True). |
+| `reference_images` | IMAGE | No | | Up to 4 additional reference images. |
+| `resolution` | COMBO | No | `"1080p"`<br />`"720p"` | The resolution for the output video (default: "1080p"). |
+
+**Constraints and Limitations:**
+
+* The `prompt` must be between 1 and 2500 characters long.
+* The input `video` must be between 3.0 and 10.05 seconds in duration.
+* The input `video` dimensions must be between 720x720 and 2160x2160 pixels.
+* A maximum of 4 `reference_images` can be provided when a video is used.
+* Each `reference_image` must be at least 300x300 pixels.
+* Each `reference_image` must have an aspect ratio between 1:2.5 and 2.5:1.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The edited video generated by the AI model. |
diff --git a/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx b/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx
new file mode 100644
index 000000000..28d7efaed
--- /dev/null
+++ b/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx
@@ -0,0 +1,37 @@
+---
+title: "KlingOmniProFirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProFirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProFirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProFirstLastFrameNode/en.md)
+
+This node uses the Kling AI model to generate a video. It requires a starting image and a text prompt. You can optionally provide an ending image or up to six reference images to guide the video's content and style. The node processes these inputs to create a video of a specified duration and resolution.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | Yes | `"kling-video-o1"` | The specific Kling AI model to use for video generation. |
+| `prompt` | STRING | Yes | - | A text prompt describing the video content. This can include both positive and negative descriptions. |
+| `duration` | INT | Yes | 3 to 10 | The desired length of the generated video in seconds (default: 5). |
+| `first_frame` | IMAGE | Yes | - | The starting image for the video sequence. |
+| `end_frame` | IMAGE | No | - | An optional end frame for the video. This cannot be used simultaneously with `reference_images`. |
+| `reference_images` | IMAGE | No | - | Up to 6 additional reference images. |
+| `resolution` | COMBO | No | `"1080p"`<br />`"720p"` | The output resolution for the generated video (default: "1080p"). |
+
+**Important Constraints:**
+
+* The `end_frame` input cannot be used at the same time as the `reference_images` input.
+* If you do not provide an `end_frame` or any `reference_images`, the `duration` can only be set to 5 or 10 seconds.
+* All input images (`first_frame`, `end_frame`, and any `reference_images`) must have a minimum dimension of 300 pixels in both width and height.
+* The aspect ratio of all input images must be between 1:2.5 and 2.5:1.
+* A maximum of 6 images can be provided via the `reference_images` input.
+* The `prompt` text must be between 1 and 2500 characters in length.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/KlingOmniProImageNode.mdx b/built-in-nodes/KlingOmniProImageNode.mdx
new file mode 100644
index 000000000..39a564e54
--- /dev/null
+++ b/built-in-nodes/KlingOmniProImageNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "KlingOmniProImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProImageNode/en.md)
+
+The Kling Omni Image (Pro) node generates or edits images using the Kling AI model. It creates images based on a text description and allows you to provide reference images to guide the style or content. The node sends a request to an external API, which processes the task and returns the final image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+| :--- | :--- | :--- | :--- | :--- |
+| `model_name` | COMBO | Yes | `"kling-image-o1"` | The specific Kling AI model to use for image generation. |
+| `prompt` | STRING | Yes | - | A text prompt describing the image content. This can include both positive and negative descriptions. The text must be between 1 and 2500 characters long. |
+| `resolution` | COMBO | Yes | `"1K"`<br />`"2K"` | The target resolution for the generated image. |
+| `aspect_ratio` | COMBO | Yes | `"16:9"`<br />`"9:16"`<br />`"1:1"`<br />`"4:3"`<br />`"3:4"`<br />`"3:2"`<br />`"2:3"`<br />`"21:9"` | The desired aspect ratio (width to height) for the generated image. |
+| `reference_images` | IMAGE | No | - | Up to 10 additional reference images. Each image must be at least 300 pixels in both width and height, and its aspect ratio must be between 1:2.5 and 2.5:1. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+| :--- | :--- | :--- |
+| `image` | IMAGE | The final image generated or edited by the Kling AI model. |
diff --git a/built-in-nodes/KlingOmniProImageToVideoNode.mdx b/built-in-nodes/KlingOmniProImageToVideoNode.mdx
new file mode 100644
index 000000000..664153c3a
--- /dev/null
+++ b/built-in-nodes/KlingOmniProImageToVideoNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "KlingOmniProImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProImageToVideoNode/en.md)
+
+This node uses the Kling AI model to generate a video based on a text prompt and up to seven reference images. It allows you to control the video's aspect ratio, duration, and resolution. The node sends the request to an external API and returns the generated video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | Yes | `"kling-video-o1"` | The specific Kling model to use for video generation. |
+| `prompt` | STRING | Yes | - | A text prompt describing the video content. This can include both positive and negative descriptions. The text is automatically normalized and must be between 1 and 2500 characters. |
+| `aspect_ratio` | COMBO | Yes | `"16:9"`<br />`"9:16"`<br />`"1:1"` | The desired aspect ratio for the generated video. |
+| `duration` | INT | Yes | 3 to 10 | The length of the video in seconds. The value can be adjusted with a slider (default: 3). |
+| `reference_images` | IMAGE | Yes | - | Up to 7 reference images. Each image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1. |
+| `resolution` | COMBO | No | `"1080p"`<br />`"720p"` | The output resolution of the video. This parameter is optional (default: "1080p"). |
+
+**Note:** The `reference_images` input accepts a maximum of 7 images. If more are provided, the node will raise an error. Each image is validated for minimum dimensions and aspect ratio.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/KlingOmniProTextToVideoNode.mdx b/built-in-nodes/KlingOmniProTextToVideoNode.mdx
new file mode 100644
index 000000000..d4b14c2b7
--- /dev/null
+++ b/built-in-nodes/KlingOmniProTextToVideoNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "KlingOmniProTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProTextToVideoNode/en.md)
+
+This node uses the Kling AI model to generate a video from a text description. It sends your prompt to a remote API and returns the generated video. The node allows you to control the video's length, shape, and quality.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | Yes | `"kling-video-o1"` | The specific Kling model to use for video generation. |
+| `prompt` | STRING | Yes | 1 to 2500 characters | A text prompt describing the video content. This can include both positive and negative descriptions. |
+| `aspect_ratio` | COMBO | Yes | `"16:9"`<br />`"9:16"`<br />`"1:1"` | The shape or dimensions of the video to generate. |
+| `duration` | COMBO | Yes | `5`<br />`10` | The length of the video in seconds. |
+| `resolution` | COMBO | No | `"1080p"`<br />`"720p"` | The quality or pixel resolution of the video (default: `"1080p"`). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The video generated based on the provided text prompt. |
diff --git a/built-in-nodes/KlingOmniProVideoToVideoNode.mdx b/built-in-nodes/KlingOmniProVideoToVideoNode.mdx
new file mode 100644
index 000000000..91218aa5a
--- /dev/null
+++ b/built-in-nodes/KlingOmniProVideoToVideoNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "KlingOmniProVideoToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProVideoToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProVideoToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProVideoToVideoNode/en.md)
+
+This node uses the Kling AI model to generate a new video based on an input video and optional reference images. You provide a text prompt describing the desired content, and the node transforms the reference video accordingly. It can also incorporate up to four additional reference images to guide the style and content of the output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | Yes | `"kling-video-o1"` | The specific Kling model to use for video generation. |
+| `prompt` | STRING | Yes | N/A | A text prompt describing the video content. This can include both positive and negative descriptions. |
+| `aspect_ratio` | COMBO | Yes | `"16:9"`<br />`"9:16"`<br />`"1:1"` | The desired aspect ratio for the generated video. |
+| `duration` | INT | Yes | 3 to 10 | The length of the generated video in seconds (default: 3). |
+| `reference_video` | VIDEO | Yes | N/A | Video to use as a reference. |
+| `keep_original_sound` | BOOLEAN | Yes | N/A | Determines if the audio from the reference video is kept in the output (default: True). |
+| `reference_images` | IMAGE | No | N/A | Up to 4 additional reference images. |
+| `resolution` | COMBO | No | `"1080p"`<br />`"720p"` | The resolution for the generated video (default: "1080p"). |
+
+**Parameter Constraints:**
+
+* The `prompt` must be between 1 and 2500 characters long.
+* The `reference_video` must be between 3.0 and 10.05 seconds in duration.
+* The `reference_video` must have dimensions between 720x720 and 2160x2160 pixels.
+* A maximum of 4 `reference_images` can be provided. Each image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The newly generated video. |
diff --git a/built-in-nodes/KlingSingleImageVideoEffectNode.mdx b/built-in-nodes/KlingSingleImageVideoEffectNode.mdx
new file mode 100644
index 000000000..fde61e709
--- /dev/null
+++ b/built-in-nodes/KlingSingleImageVideoEffectNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "KlingSingleImageVideoEffectNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingSingleImageVideoEffectNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingSingleImageVideoEffectNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingSingleImageVideoEffectNode/en.md)
+
+The Kling Single Image Video Effect Node creates videos with different special effects based on a single reference image. It applies various visual effects and scenes to transform static images into dynamic video content. The node supports different effect scenes, model options, and video durations to achieve the desired visual outcome.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | Reference Image. URL or Base64 encoded string (without data:image prefix). File size cannot exceed 10MB, resolution not less than 300*300px, aspect ratio between 1:2.5 ~ 2.5:1 |
+| `effect_scene` | COMBO | Yes | Options from KlingSingleImageEffectsScene | The type of special effect scene to apply to the video generation |
+| `model_name` | COMBO | Yes | Options from KlingSingleImageEffectModelName | The specific model to use for generating the video effect |
+| `duration` | COMBO | Yes | Options from KlingVideoGenDuration | The length of the generated video |
+
+**Note:** The specific options for `effect_scene`, `model_name`, and `duration` are determined by the available values in their respective enum classes (KlingSingleImageEffectsScene, KlingSingleImageEffectModelName, and KlingVideoGenDuration).
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video with applied effects |
+| `video_id` | STRING | The unique identifier for the generated video |
+| `duration` | STRING | The duration of the generated video |
diff --git a/built-in-nodes/KlingStartEndFrameNode.mdx b/built-in-nodes/KlingStartEndFrameNode.mdx
new file mode 100644
index 000000000..c8bd62f18
--- /dev/null
+++ b/built-in-nodes/KlingStartEndFrameNode.mdx
@@ -0,0 +1,37 @@
+---
+title: "KlingStartEndFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingStartEndFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingStartEndFrameNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingStartEndFrameNode/en.md)
+
+Kling Start-End Frame to Video node creates a video sequence that transitions between your provided start and end images. It generates all the frames in between to produce a smooth transformation from the first frame to the last frame. This node calls the image-to-video API but only supports the input options that work with the `image_tail` request field.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `start_frame` | IMAGE | Yes | - | Reference Image - URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px, aspect ratio between 1:2.5 ~ 2.5:1. Base64 should not include data:image prefix. |
+| `end_frame` | IMAGE | Yes | - | Reference Image - End frame control. URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px. Base64 should not include data:image prefix. |
+| `prompt` | STRING | Yes | - | Positive text prompt |
+| `negative_prompt` | STRING | Yes | - | Negative text prompt |
+| `cfg_scale` | FLOAT | No | 0.0-1.0 | Controls the strength of the prompt guidance (default: 0.5) |
+| `aspect_ratio` | COMBO | No | "16:9"<br />"9:16"<br />"1:1"<br />"21:9"<br />"9:21"<br />"3:4"<br />"4:3" | The aspect ratio for the generated video (default: "16:9") |
+| `mode` | COMBO | No | Multiple options available | The configuration to use for the video generation following the format: mode / duration / model_name. (default: third option from available modes) |
+
+**Image Constraints:**
+
+- Both `start_frame` and `end_frame` must be provided and cannot exceed 10MB file size
+- Minimum resolution: 300×300 pixels for both images
+- `start_frame` aspect ratio must be between 1:2.5 and 2.5:1
+- Base64 encoded images should not include the "data:image" prefix
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video sequence |
+| `video_id` | STRING | Unique identifier for the generated video |
+| `duration` | STRING | Duration of the generated video |
diff --git a/built-in-nodes/KlingTextToVideoNode.mdx b/built-in-nodes/KlingTextToVideoNode.mdx
new file mode 100644
index 000000000..7418b7d22
--- /dev/null
+++ b/built-in-nodes/KlingTextToVideoNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "KlingTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoNode/en.md)
+
+The Kling Text to Video Node converts text descriptions into video content. It takes text prompts and generates corresponding video sequences based on the specified configuration settings. The node supports different aspect ratios and generation modes to produce videos of varying durations and quality.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Positive text prompt (default: none) |
+| `negative_prompt` | STRING | Yes | - | Negative text prompt (default: none) |
+| `cfg_scale` | FLOAT | No | 0.0-1.0 | Configuration scale value (default: 1.0) |
+| `aspect_ratio` | COMBO | No | Options from KlingVideoGenAspectRatio | Video aspect ratio setting (default: "16:9") |
+| `mode` | COMBO | No | Multiple options available | The configuration to use for the video generation following the format: mode / duration / model_name. (default: modes[4]) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video output |
+| `video_id` | STRING | Unique identifier for the generated video |
+| `duration` | STRING | Duration information for the generated video |
diff --git a/built-in-nodes/KlingTextToVideoWithAudio.mdx b/built-in-nodes/KlingTextToVideoWithAudio.mdx
new file mode 100644
index 000000000..bac1509c0
--- /dev/null
+++ b/built-in-nodes/KlingTextToVideoWithAudio.mdx
@@ -0,0 +1,27 @@
+---
+title: "KlingTextToVideoWithAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingTextToVideoWithAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingTextToVideoWithAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoWithAudio/en.md)
+
+The Kling Text to Video with Audio node generates a short video from a text description. It sends a request to the Kling AI service, which processes the prompt and returns a video file. The node can also generate accompanying audio for the video based on the text.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | Yes | `"kling-v2-6"` | The specific AI model to use for video generation. |
+| `prompt` | STRING | Yes | - | Positive text prompt. The description used to generate the video. Must be between 1 and 2500 characters. |
+| `mode` | COMBO | Yes | `"pro"` | The operational mode for the video generation. |
+| `aspect_ratio` | COMBO | Yes | `"16:9"`<br />`"9:16"`<br />`"1:1"` | The desired width-to-height ratio for the generated video. |
+| `duration` | COMBO | Yes | `5`<br />`10` | The length of the video in seconds. |
+| `generate_audio` | BOOLEAN | No | - | Controls whether audio is generated for the video. When enabled, the AI will create sound based on the prompt. (default: `True`) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/KlingVideoExtendNode.mdx b/built-in-nodes/KlingVideoExtendNode.mdx
new file mode 100644
index 000000000..198ef2ec3
--- /dev/null
+++ b/built-in-nodes/KlingVideoExtendNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "KlingVideoExtendNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingVideoExtendNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingVideoExtendNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoExtendNode/en.md)
+
+The Kling Video Extend Node allows you to extend videos created by other Kling nodes. It takes an existing video identified by its video ID and generates additional content based on your text prompts. The node works by sending your extension request to the Kling API and returning the extended video along with its new ID and duration.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | No | - | Positive text prompt for guiding the video extension |
+| `negative_prompt` | STRING | No | - | Negative text prompt for elements to avoid in the extended video |
+| `cfg_scale` | FLOAT | No | 0.0 - 1.0 | Controls the strength of prompt guidance (default: 0.5) |
+| `video_id` | STRING | Yes | - | The ID of the video to be extended. Supports videos generated by text-to-video, image-to-video, and previous video extension operations. Cannot exceed 3 minutes total duration after extension. |
+
+**Note:** The `video_id` must reference a video created by other Kling nodes, and the total duration after extension cannot exceed 3 minutes.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The extended video generated by the Kling API |
+| `video_id` | STRING | The unique identifier for the extended video |
+| `duration` | STRING | The duration of the extended video |
diff --git a/built-in-nodes/KlingVideoNode.mdx b/built-in-nodes/KlingVideoNode.mdx
new file mode 100644
index 000000000..442b67968
--- /dev/null
+++ b/built-in-nodes/KlingVideoNode.mdx
@@ -0,0 +1,42 @@
+---
+title: "KlingVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoNode/en.md)
+
+This node generates videos using the Kling V3 model. It supports two primary modes: text-to-video, where a video is created from a text description, and image-to-video, where an existing image is animated. It also offers advanced features like creating multi-segment videos with different prompts for each part (storyboards) and optionally generating accompanying audio.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `multi_shot` | COMBO | Yes | `"disabled"`<br />`"1 storyboard"`<br />`"2 storyboards"`<br />`"3 storyboards"`<br />`"4 storyboards"`<br />`"5 storyboards"`<br />`"6 storyboards"` | Controls whether to generate a single video or a series of segments with individual prompts and durations. When not "disabled," additional inputs for each storyboard's prompt and duration appear. |
+| `generate_audio` | BOOLEAN | Yes | `True` / `False` | When enabled, the node will generate audio for the video. Default is `True`. |
+| `model` | COMBO | Yes | `"kling-v3"` | The model and its associated settings. Selecting this option reveals the `resolution` and `aspect_ratio` sub-parameters. |
+| `model.resolution` | COMBO | Yes | `"1080p"`<br />`"720p"` | The resolution for the generated video. This setting is available when the `model` is set to "kling-v3". |
+| `model.aspect_ratio` | COMBO | Yes | `"16:9"`<br />`"9:16"`<br />`"1:1"` | The aspect ratio for the generated video. This setting is ignored when an image is provided for `start_frame` (image-to-video mode). Available when the `model` is set to "kling-v3". |
+| `seed` | INT | Yes | 0 to 2147483647 | A seed value for generation. Changing this value will cause the node to re-run, but the results are non-deterministic. Default is `0`. |
+| `start_frame` | IMAGE | No | - | An optional starting image. When connected, the node switches from text-to-video to image-to-video mode, animating the provided image. |
+
+**Inputs for `multi_shot` mode:**
+
+* When `multi_shot` is set to **"disabled"**, the following inputs appear:
+  * `prompt` (STRING): The main text description for the video. Required. Must be between 1 and 2500 characters.
+  * `negative_prompt` (STRING): Text describing what should not appear in the video. Optional.
+  * `duration` (INT): The length of the video in seconds. Must be between 3 and 15. Default is `5`.
+* When `multi_shot` is set to a storyboard option (e.g., `"3 storyboards"`), inputs for each storyboard segment appear (e.g., `storyboard_1_prompt`, `storyboard_1_duration`). Each prompt must be between 1 and 512 characters. The **total sum of all storyboard durations** must be between 3 and 15 seconds.
+
+**Constraints:**
+
+* The node operates in **text-to-video** mode when `start_frame` is not connected. It uses the `model.aspect_ratio` setting in this mode.
+* The node operates in **image-to-video** mode when `start_frame` is connected. The `model.aspect_ratio` setting is ignored. The input image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1.
+* In storyboard mode (`multi_shot` not "disabled"), the main `prompt` and `negative_prompt` inputs are hidden and not used.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/KlingVirtualTryOnNode.mdx b/built-in-nodes/KlingVirtualTryOnNode.mdx
new file mode 100644
index 000000000..fba17d8c7
--- /dev/null
+++ b/built-in-nodes/KlingVirtualTryOnNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "KlingVirtualTryOnNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingVirtualTryOnNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingVirtualTryOnNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVirtualTryOnNode/en.md)
+
+Kling Virtual Try On Node. Input a human image and a cloth image to try on the cloth on the human. You can merge multiple clothing item pictures into one image with a white background.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `human_image` | IMAGE | Yes | - | The human image to try clothes on |
+| `cloth_image` | IMAGE | Yes | - | The clothing image to try on the human |
+| `model_name` | STRING | Yes | `"kolors-virtual-try-on-v1"` | The virtual try-on model to use (default: "kolors-virtual-try-on-v1") |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The resulting image showing the human with the clothing item tried on |
diff --git a/built-in-nodes/LTXAVTextEncoderLoader.mdx b/built-in-nodes/LTXAVTextEncoderLoader.mdx
new file mode 100644
index 000000000..184fb6f98
--- /dev/null
+++ b/built-in-nodes/LTXAVTextEncoderLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "LTXAVTextEncoderLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXAVTextEncoderLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXAVTextEncoderLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXAVTextEncoderLoader/en.md)
+
+This node loads a specialized text encoder for the LTXV audio model. It combines a specific text encoder file with a checkpoint file to create a CLIP model that can be used for audio-related text conditioning tasks.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text_encoder` | STRING | Yes | Multiple options available | The filename of the LTXV text encoder model to load. The available options are loaded from the `text_encoders` folder. |
+| `ckpt_name` | STRING | Yes | Multiple options available | The filename of the checkpoint to load. The available options are loaded from the `checkpoints` folder. |
+| `device` | STRING | No | `"default"`<br />`"cpu"` | Specifies the device to load the model onto. Use `"cpu"` to force loading onto the CPU. The default behavior (`"default"`) uses the system's automatic device placement. |
+
+**Note:** The `text_encoder` and `ckpt_name` parameters work together. The node loads both specified files to create a single, functional CLIP model. The files must be compatible with the LTXV architecture.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `clip` | CLIP | The loaded LTXV CLIP model, ready to be used for encoding text prompts for audio generation. |
diff --git a/built-in-nodes/LTXVAddGuide.mdx b/built-in-nodes/LTXVAddGuide.mdx
new file mode 100644
index 000000000..d5aa91f29
--- /dev/null
+++ b/built-in-nodes/LTXVAddGuide.mdx
@@ -0,0 +1,32 @@
+---
+title: "LTXVAddGuide - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVAddGuide node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVAddGuide"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAddGuide/en.md)
+
+The LTXVAddGuide node adds video conditioning guidance to latent sequences by encoding input images or videos and incorporating them as keyframes into the conditioning data. It processes the input through a VAE encoder and strategically places the resulting latents at specified frame positions while updating both positive and negative conditioning with keyframe information. The node handles frame alignment constraints and allows control over the strength of the conditioning influence.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning input to be modified with keyframe guidance |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning input to be modified with keyframe guidance |
+| `vae` | VAE | Yes | - | VAE model used for encoding the input image/video frames |
+| `latent` | LATENT | Yes | - | Input latent sequence that will receive the conditioning frames |
+| `image` | IMAGE | Yes | - | Image or video to condition the latent video on. Must be 8*n + 1 frames. If the video is not 8*n + 1 frames, it will be cropped to the nearest 8*n + 1 frames. |
+| `frame_idx` | INT | No | -9999 to 9999 | Frame index to start the conditioning at. For single-frame images or videos with 1-8 frames, any frame_idx value is acceptable. For videos with 9+ frames, frame_idx must be divisible by 8, otherwise it will be rounded down to the nearest multiple of 8. Negative values are counted from the end of the video. (default: 0) |
+| `strength` | FLOAT | No | 0.0 to 1.0 | Strength of the conditioning influence, where 1.0 applies full conditioning and 0.0 applies no conditioning (default: 1.0) |
+
+**Note:** The input image/video must have a frame count following the 8*n + 1 pattern (e.g., 1, 9, 17, 25 frames). If the input exceeds this pattern, it will be automatically cropped to the nearest valid frame count.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning updated with keyframe guidance information |
+| `negative` | CONDITIONING | Negative conditioning updated with keyframe guidance information |
+| `latent` | LATENT | Latent sequence with incorporated conditioning frames and updated noise mask |
diff --git a/built-in-nodes/LTXVAudioVAEDecode.mdx b/built-in-nodes/LTXVAudioVAEDecode.mdx
new file mode 100644
index 000000000..c0951b737
--- /dev/null
+++ b/built-in-nodes/LTXVAudioVAEDecode.mdx
@@ -0,0 +1,25 @@
+---
+title: "LTXVAudioVAEDecode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVAudioVAEDecode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVAudioVAEDecode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAEDecode/en.md)
+
+The LTXV Audio VAE Decode node converts a latent representation of audio back into an audio waveform. It uses a specialized Audio VAE model to perform this decoding process, producing an audio output with a specific sample rate.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | N/A | The latent to be decoded. |
+| `audio_vae` | VAE | Yes | N/A | The Audio VAE model used for decoding the latent. |
+
+**Note:** If the provided latent is nested (contains multiple latents), the node will automatically use the last latent in the sequence for decoding.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `Audio` | AUDIO | The decoded audio waveform and its associated sample rate. |
diff --git a/built-in-nodes/LTXVAudioVAEEncode.mdx b/built-in-nodes/LTXVAudioVAEEncode.mdx
new file mode 100644
index 000000000..b1f24b0b1
--- /dev/null
+++ b/built-in-nodes/LTXVAudioVAEEncode.mdx
@@ -0,0 +1,23 @@
+---
+title: "LTXVAudioVAEEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVAudioVAEEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVAudioVAEEncode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAEEncode/en.md)
+
+The LTXV Audio VAE Encode node takes an audio input and compresses it into a smaller, latent representation using a specified Audio VAE model. This process is essential for generating or manipulating audio within a latent space workflow, as it converts raw audio data into a format that other nodes in the pipeline can understand and process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The audio to be encoded. |
+| `audio_vae` | VAE | Yes | - | The Audio VAE model to use for encoding. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `Audio Latent` | LATENT | The compressed latent representation of the input audio. The output includes the latent samples, the sample rate of the VAE model, and a type identifier. |
diff --git a/built-in-nodes/LTXVAudioVAELoader.mdx b/built-in-nodes/LTXVAudioVAELoader.mdx
new file mode 100644
index 000000000..15d25de5b
--- /dev/null
+++ b/built-in-nodes/LTXVAudioVAELoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "LTXVAudioVAELoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVAudioVAELoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVAudioVAELoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAELoader/en.md)
+
+The LTXV Audio VAE Loader node loads a pre-trained Audio Variational Autoencoder (VAE) model from a checkpoint file. It reads the specified checkpoint, loads its weights and metadata, and prepares the model for use in audio generation or processing workflows within ComfyUI.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `ckpt_name` | STRING | Yes | All files in the `checkpoints` folder.<br />*Example: `"audio_vae.safetensors"`* | Audio VAE checkpoint to load. This is a dropdown list populated with all the files found in your ComfyUI `checkpoints` directory. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `Audio VAE` | VAE | The loaded Audio Variational Autoencoder model, ready to be connected to other audio processing nodes. |
diff --git a/built-in-nodes/LTXVConcatAVLatent.mdx b/built-in-nodes/LTXVConcatAVLatent.mdx
new file mode 100644
index 000000000..2e1c1fc2e
--- /dev/null
+++ b/built-in-nodes/LTXVConcatAVLatent.mdx
@@ -0,0 +1,25 @@
+---
+title: "LTXVConcatAVLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVConcatAVLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVConcatAVLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVConcatAVLatent/en.md)
+
+The LTXVConcatAVLatent node combines a video latent representation and an audio latent representation into a single, concatenated latent output. It merges the `samples` tensors from both inputs and, if present, their `noise_mask` tensors as well, preparing them for further processing in a video generation pipeline.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video_latent` | LATENT | Yes | | The latent representation of the video data. |
+| `audio_latent` | LATENT | Yes | | The latent representation of the audio data. |
+
+**Note:** The `samples` tensors from the `video_latent` and `audio_latent` inputs are concatenated. If either input contains a `noise_mask`, it will be used; if one is missing, a mask of ones (same shape as the corresponding `samples`) is created for it. The resulting masks are then also concatenated.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `latent` | LATENT | A single latent dictionary containing the concatenated `samples` and, if applicable, the concatenated `noise_mask` from the video and audio inputs. |
diff --git a/built-in-nodes/LTXVConditioning.mdx b/built-in-nodes/LTXVConditioning.mdx
new file mode 100644
index 000000000..830e694e5
--- /dev/null
+++ b/built-in-nodes/LTXVConditioning.mdx
@@ -0,0 +1,25 @@
+---
+title: "LTXVConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVConditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVConditioning/en.md)
+
+The LTXVConditioning node adds frame rate information to both positive and negative conditioning inputs for video generation models. It takes existing conditioning data and applies the specified frame rate value to both conditioning sets, making them suitable for video model processing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The positive conditioning input that will receive the frame rate information |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning input that will receive the frame rate information |
+| `frame_rate` | FLOAT | No | 0.0 - 1000.0 | The frame rate value to apply to both conditioning sets (default: 25.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The positive conditioning with frame rate information applied |
+| `negative` | CONDITIONING | The negative conditioning with frame rate information applied |
diff --git a/built-in-nodes/LTXVCropGuides.mdx b/built-in-nodes/LTXVCropGuides.mdx
new file mode 100644
index 000000000..f0bfcbe09
--- /dev/null
+++ b/built-in-nodes/LTXVCropGuides.mdx
@@ -0,0 +1,26 @@
+---
+title: "LTXVCropGuides - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVCropGuides node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVCropGuides"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVCropGuides/en.md)
+
+The LTXVCropGuides node processes conditioning and latent inputs for video generation by removing keyframe information and adjusting the latent dimensions. It crops the latent image and noise mask to exclude keyframe sections while clearing keyframe indices from both positive and negative conditioning inputs. This prepares the data for video generation workflows that don't require keyframe guidance.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The positive conditioning input containing guidance information for generation |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning input containing guidance information for what to avoid in generation |
+| `latent` | LATENT | Yes | - | The latent representation containing image samples and noise mask data |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The processed positive conditioning with keyframe indices cleared |
+| `negative` | CONDITIONING | The processed negative conditioning with keyframe indices cleared |
+| `latent` | LATENT | The cropped latent representation with adjusted samples and noise mask |
diff --git a/built-in-nodes/LTXVEmptyLatentAudio.mdx b/built-in-nodes/LTXVEmptyLatentAudio.mdx
new file mode 100644
index 000000000..bfdac547d
--- /dev/null
+++ b/built-in-nodes/LTXVEmptyLatentAudio.mdx
@@ -0,0 +1,27 @@
+---
+title: "LTXVEmptyLatentAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVEmptyLatentAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVEmptyLatentAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVEmptyLatentAudio/en.md)
+
+The LTXV Empty Latent Audio node creates a batch of empty (zero-filled) latent audio tensors. It uses the configuration from a provided Audio VAE model to determine the correct dimensions for the latent space, such as the number of channels and frequency bins. This empty latent serves as a starting point for audio generation or manipulation workflows within ComfyUI.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `frames_number` | INT | Yes | 1 to 1000 | Number of frames. The default value is 97. |
+| `frame_rate` | INT | Yes | 1 to 1000 | Number of frames per second. The default value is 25. |
+| `batch_size` | INT | Yes | 1 to 4096 | The number of latent audio samples in the batch. The default value is 1. |
+| `audio_vae` | VAE | Yes | N/A | The Audio VAE model to get configuration from. This parameter is required. |
+
+**Note:** The `audio_vae` input is mandatory. The node will raise an error if it is not provided.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `Latent` | LATENT | An empty latent audio tensor with the structure (samples, sample_rate, type) configured to match the input Audio VAE. |
diff --git a/built-in-nodes/LTXVImgToVideo.mdx b/built-in-nodes/LTXVImgToVideo.mdx
new file mode 100644
index 000000000..4d7a84d20
--- /dev/null
+++ b/built-in-nodes/LTXVImgToVideo.mdx
@@ -0,0 +1,32 @@
+---
+title: "LTXVImgToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVImgToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVImgToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVImgToVideo/en.md)
+
+The LTXVImgToVideo node converts an input image into a video latent representation for video generation models. It takes a single image and extends it into a sequence of frames using the VAE encoder, then applies conditioning with strength control to determine how much of the original image content is preserved versus modified during video generation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning prompts for guiding the video generation |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning prompts for avoiding certain elements in the video |
+| `vae` | VAE | Yes | - | VAE model used for encoding the input image into latent space |
+| `image` | IMAGE | Yes | - | Input image to be converted into video frames |
+| `width` | INT | No | 64 to MAX_RESOLUTION | Output video width in pixels (default: 768, step: 32) |
+| `height` | INT | No | 64 to MAX_RESOLUTION | Output video height in pixels (default: 512, step: 32) |
+| `length` | INT | No | 9 to MAX_RESOLUTION | Number of frames in the generated video (default: 97, step: 8) |
+| `batch_size` | INT | No | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `strength` | FLOAT | No | 0.0 to 1.0 | Control over how much the original image is modified during video generation, where 1.0 preserves most of the original content and 0.0 allows maximum modification (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Processed positive conditioning with video frame masking applied |
+| `negative` | CONDITIONING | Processed negative conditioning with video frame masking applied |
+| `latent` | LATENT | Video latent representation containing the encoded frames and noise mask for video generation |
diff --git a/built-in-nodes/LTXVImgToVideoInplace.mdx b/built-in-nodes/LTXVImgToVideoInplace.mdx
new file mode 100644
index 000000000..c4764837e
--- /dev/null
+++ b/built-in-nodes/LTXVImgToVideoInplace.mdx
@@ -0,0 +1,28 @@
+---
+title: "LTXVImgToVideoInplace - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVImgToVideoInplace node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVImgToVideoInplace"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVImgToVideoInplace/en.md)
+
+The LTXVImgToVideoInplace node conditions a video latent representation by encoding an input image into its initial frames. It works by using a VAE to encode the image into the latent space and then blending it with the existing latent samples based on a specified strength. This allows an image to serve as a starting point or conditioning signal for video generation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `vae` | VAE | Yes | - | The VAE model used to encode the input image into the latent space. |
+| `image` | IMAGE | Yes | - | The input image to be encoded and used to condition the video latent. |
+| `latent` | LATENT | Yes | - | The target latent video representation to be modified. |
+| `strength` | FLOAT | No | 0.0 - 1.0 | Controls the blending strength of the encoded image into the latent. A value of 1.0 fully replaces the initial frames, while lower values blend them. (default: 1.0) |
+| `bypass` | BOOLEAN | No | - | Bypass the conditioning. When enabled, the node returns the input latent unchanged. (default: False) |
+
+**Note:** The `image` will be automatically resized to match the spatial dimensions required by the `vae` for encoding, based on the `latent` input's width and height.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `latent` | LATENT | The modified latent video representation. It contains the updated samples and a `noise_mask` that applies the conditioning strength to the initial frames. |
diff --git a/built-in-nodes/LTXVLatentUpsampler.mdx b/built-in-nodes/LTXVLatentUpsampler.mdx
new file mode 100644
index 000000000..a476e9921
--- /dev/null
+++ b/built-in-nodes/LTXVLatentUpsampler.mdx
@@ -0,0 +1,24 @@
+---
+title: "LTXVLatentUpsampler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVLatentUpsampler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVLatentUpsampler"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVLatentUpsampler/en.md)
+
+The LTXVLatentUpsampler node increases the spatial resolution of a video latent representation by a factor of two. It uses a specialized upscale model to process the latent data, which is first un-normalized and then re-normalized using the provided VAE's channel statistics. This node is designed for video workflows within the latent space.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | | The input latent representation of the video to be upscaled. |
+| `upscale_model` | LATENT_UPSCALE_MODEL | Yes | | The loaded model used to perform the 2x upscaling on the latent data. |
+| `vae` | VAE | Yes | | The VAE model used to un-normalize the input latents before upscaling and to normalize the output latents afterwards. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | The upscaled latent representation, with spatial dimensions doubled compared to the input. |
diff --git a/built-in-nodes/LTXVPreprocess.mdx b/built-in-nodes/LTXVPreprocess.mdx
new file mode 100644
index 000000000..1e6efeaaa
--- /dev/null
+++ b/built-in-nodes/LTXVPreprocess.mdx
@@ -0,0 +1,23 @@
+---
+title: "LTXVPreprocess - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVPreprocess node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVPreprocess"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVPreprocess/en.md)
+
+The LTXVPreprocess node applies compression preprocessing to images. It takes input images and processes them with a specified compression level, outputting the processed images with the applied compression settings.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be processed |
+| `img_compression` | INT | No | 0-100 | Amount of compression to apply on image (default: 35) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | The processed output image with applied compression |
diff --git a/built-in-nodes/LTXVScheduler.mdx b/built-in-nodes/LTXVScheduler.mdx
new file mode 100644
index 000000000..09ac3ebb5
--- /dev/null
+++ b/built-in-nodes/LTXVScheduler.mdx
@@ -0,0 +1,29 @@
+---
+title: "LTXVScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVScheduler"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVScheduler/en.md)
+
+The LTXVScheduler node generates sigma values for custom sampling processes. It calculates noise schedule parameters based on the number of tokens in the input latent and applies a sigmoid transformation to create the sampling schedule. The node can optionally stretch the resulting sigmas to match a specified terminal value.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `steps` | INT | Yes | 1-10000 | Number of sampling steps (default: 20) |
+| `max_shift` | FLOAT | Yes | 0.0-100.0 | Maximum shift value for sigma calculation (default: 2.05) |
+| `base_shift` | FLOAT | Yes | 0.0-100.0 | Base shift value for sigma calculation (default: 0.95) |
+| `stretch` | BOOLEAN | Yes | True/False | Stretch the sigmas to be in the range [terminal, 1] (default: True) |
+| `terminal` | FLOAT | Yes | 0.0-0.99 | The terminal value of the sigmas after stretching (default: 0.1) |
+| `latent` | LATENT | No | - | Optional latent input used to calculate token count for sigma adjustment |
+
+**Note:** The `latent` parameter is optional. When not provided, the node uses a default token count of 4096 for calculations.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | Generated sigma values for the sampling process |
diff --git a/built-in-nodes/LTXVSeparateAVLatent.mdx b/built-in-nodes/LTXVSeparateAVLatent.mdx
new file mode 100644
index 000000000..0dd9a7736
--- /dev/null
+++ b/built-in-nodes/LTXVSeparateAVLatent.mdx
@@ -0,0 +1,25 @@
+---
+title: "LTXVSeparateAVLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVSeparateAVLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVSeparateAVLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVSeparateAVLatent/en.md)
+
+The LTXVSeparateAVLatent node takes a combined audio-visual latent representation and splits it into two distinct parts: one for video and one for audio. It separates the samples and, if present, the noise masks from the input latent, creating two new latent objects.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `av_latent` | LATENT | Yes | N/A | The combined audio-visual latent representation to be separated. |
+
+**Note:** The input latent's `samples` tensor is expected to have at least two elements along the first dimension (batch dimension). The first element is used for the video latent, and the second element is used for the audio latent. If a `noise_mask` is present, it is split in the same way.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video_latent` | LATENT | The latent representation containing the separated video data. |
+| `audio_latent` | LATENT | The latent representation containing the separated audio data. |
diff --git a/built-in-nodes/LaplaceScheduler.mdx b/built-in-nodes/LaplaceScheduler.mdx
new file mode 100644
index 000000000..0ff8ab594
--- /dev/null
+++ b/built-in-nodes/LaplaceScheduler.mdx
@@ -0,0 +1,26 @@
+---
+title: "LaplaceScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LaplaceScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LaplaceScheduler"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LaplaceScheduler/en.md)
+
+The LaplaceScheduler node generates a sequence of sigma values following a Laplace distribution for use in diffusion sampling. It creates a schedule of noise levels that gradually decrease from a maximum to minimum value, using Laplace distribution parameters to control the progression. This scheduler is commonly used in custom sampling workflows to define the noise schedule for diffusion models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `steps` | INT | Yes | 1 to 10000 | Number of sampling steps in the schedule (default: 20) |
+| `sigma_max` | FLOAT | Yes | 0.0 to 5000.0 | Maximum sigma value at the start of the schedule (default: 14.614642) |
+| `sigma_min` | FLOAT | Yes | 0.0 to 5000.0 | Minimum sigma value at the end of the schedule (default: 0.0291675) |
+| `mu` | FLOAT | Yes | -10.0 to 10.0 | Mean parameter for the Laplace distribution (default: 0.0) |
+| `beta` | FLOAT | Yes | 0.0 to 10.0 | Scale parameter for the Laplace distribution (default: 0.5) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `SIGMAS` | SIGMAS | A sequence of sigma values following a Laplace distribution schedule |
diff --git a/built-in-nodes/LatentAdd.mdx b/built-in-nodes/LatentAdd.mdx
new file mode 100644
index 000000000..5df0acbda
--- /dev/null
+++ b/built-in-nodes/LatentAdd.mdx
@@ -0,0 +1,21 @@
+---
+title: "LatentAdd - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentAdd node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentAdd"
+icon: "circle"
+mode: wide
+---
+The LatentAdd node is designed for the addition of two latent representations. It facilitates the combination of features or characteristics encoded in these representations by performing element-wise addition.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|-------------|-------------|
+| `samples1`   | `LATENT`    | The first set of latent samples to be added. It represents one of the inputs whose features are to be combined with another set of latent samples. |
+| `samples2`   | `LATENT`    | The second set of latent samples to be added. It serves as the other input whose features are combined with the first set of latent samples through element-wise addition. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The result of the element-wise addition of two latent samples, representing a new set of latent samples that combines the features of both inputs. |
diff --git a/built-in-nodes/LatentApplyOperation.mdx b/built-in-nodes/LatentApplyOperation.mdx
new file mode 100644
index 000000000..51b6b8813
--- /dev/null
+++ b/built-in-nodes/LatentApplyOperation.mdx
@@ -0,0 +1,23 @@
+---
+title: "LatentApplyOperation - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentApplyOperation node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentApplyOperation"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentApplyOperation/en.md)
+
+The LatentApplyOperation node applies a specified operation to latent samples. It takes latent data and an operation as inputs, processes the latent samples using the provided operation, and returns the modified latent data. This node allows you to transform or manipulate latent representations in your workflow.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | - | The latent samples to be processed by the operation |
+| `operation` | LATENT_OPERATION | Yes | - | The operation to apply to the latent samples |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | LATENT | The modified latent samples after applying the operation |
diff --git a/built-in-nodes/LatentApplyOperationCFG.mdx b/built-in-nodes/LatentApplyOperationCFG.mdx
new file mode 100644
index 000000000..984949a6e
--- /dev/null
+++ b/built-in-nodes/LatentApplyOperationCFG.mdx
@@ -0,0 +1,23 @@
+---
+title: "LatentApplyOperationCFG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentApplyOperationCFG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentApplyOperationCFG"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentApplyOperationCFG/en.md)
+
+The LatentApplyOperationCFG node applies a latent operation to modify the conditioning guidance process in a model. It works by intercepting the conditioning outputs during the classifier-free guidance (CFG) sampling process and applying the specified operation to the latent representations before they are used for generation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to which the CFG operation will be applied |
+| `operation` | LATENT_OPERATION | Yes | - | The latent operation to apply during the CFG sampling process |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with the CFG operation applied to its sampling process |
diff --git a/built-in-nodes/LatentBatch.mdx b/built-in-nodes/LatentBatch.mdx
new file mode 100644
index 000000000..e9a7ca3f1
--- /dev/null
+++ b/built-in-nodes/LatentBatch.mdx
@@ -0,0 +1,21 @@
+---
+title: "LatentBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentBatch"
+icon: "circle"
+mode: wide
+---
+The LatentBatch node is designed to merge two sets of latent samples into a single batch, potentially resizing one set to match the dimensions of the other before concatenation. This operation facilitates the combination of different latent representations for further processing or generation tasks.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|-------------|-------------|
+| `samples1`   | `LATENT`    | The first set of latent samples to be merged. It plays a crucial role in determining the final shape of the merged batch. |
+| `samples2`   | `LATENT`    | The second set of latent samples to be merged. If its dimensions differ from the first set, it is resized to ensure compatibility before merging. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The merged set of latent samples, now combined into a single batch for further processing. |
diff --git a/built-in-nodes/LatentBatchSeedBehavior.mdx b/built-in-nodes/LatentBatchSeedBehavior.mdx
new file mode 100644
index 000000000..d57851ddc
--- /dev/null
+++ b/built-in-nodes/LatentBatchSeedBehavior.mdx
@@ -0,0 +1,21 @@
+---
+title: "LatentBatchSeedBehavior - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentBatchSeedBehavior node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentBatchSeedBehavior"
+icon: "circle"
+mode: wide
+---
+The LatentBatchSeedBehavior node is designed to modify the seed behavior of a batch of latent samples. It allows for either randomizing or fixing the seed across the batch, thereby influencing the generation process by either introducing variability or maintaining consistency in the generated outputs.
+
+## Inputs
+
+| Parameter       | Data Type | Description |
+|-----------------|--------------|-------------|
+| `samples`       | `LATENT`     | The 'samples' parameter represents the batch of latent samples to be processed. Its modification depends on the seed behavior chosen, affecting the consistency or variability of the generated outputs. |
+| `seed_behavior`  | COMBO[STRING] | The 'seed_behavior' parameter dictates whether the seed for the batch of latent samples should be randomized or fixed. This choice significantly impacts the generation process by either introducing variability or ensuring consistency across the batch. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a modified version of the input latent samples, with adjustments made based on the specified seed behavior. It either maintains or alters the batch index to reflect the chosen seed behavior. |
diff --git a/built-in-nodes/LatentBlend.mdx b/built-in-nodes/LatentBlend.mdx
new file mode 100644
index 000000000..35948feb4
--- /dev/null
+++ b/built-in-nodes/LatentBlend.mdx
@@ -0,0 +1,26 @@
+---
+title: "LatentBlend - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentBlend node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentBlend"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentBlend/en.md)
+
+The LatentBlend node combines two latent samples by blending them together using a specified blend factor. It takes two latent inputs and creates a new output where the first sample is weighted by the blend factor and the second sample is weighted by the inverse. If the input samples have different shapes, the second sample is automatically resized to match the first sample's dimensions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples1` | LATENT | Yes | - | The first latent sample to blend |
+| `samples2` | LATENT | Yes | - | The second latent sample to blend |
+| `blend_factor` | FLOAT | Yes | 0 to 1 | Controls the blending ratio between the two samples (default: 0.5) |
+
+**Note:** If `samples1` and `samples2` have different shapes, `samples2` will be automatically resized to match the dimensions of `samples1` using bicubic interpolation with center cropping.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `latent` | LATENT | The blended latent sample combining both input samples |
diff --git a/built-in-nodes/LatentComposite.mdx b/built-in-nodes/LatentComposite.mdx
new file mode 100644
index 000000000..5c03aeda6
--- /dev/null
+++ b/built-in-nodes/LatentComposite.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentComposite - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentComposite node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentComposite"
+icon: "circle"
+mode: wide
+---
+The LatentComposite node is designed to blend or merge two latent representations into a single output. This process is essential for creating composite images or features by combining the characteristics of the input latents in a controlled manner.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|-------------|-------------|
+| `samples_to` | `LATENT`    | The 'samples_to' latent representation where the 'samples_from' will be composited onto. It serves as the base for the composite operation. |
+| `samples_from` | `LATENT` | The 'samples_from' latent representation to be composited onto the 'samples_to'. It contributes its features or characteristics to the final composite output. |
+| `x`          | `INT`      | The x-coordinate (horizontal position) where the 'samples_from' latent will be placed on the 'samples_to'. It determines the horizontal alignment of the composite. |
+| `y`          | `INT`      | The y-coordinate (vertical position) where the 'samples_from' latent will be placed on the 'samples_to'. It determines the vertical alignment of the composite. |
+| `feather`    | `INT`      | A boolean indicating whether the 'samples_from' latent should be resized to match the 'samples_to' before compositing. This can affect the scale and proportion of the composite result. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a composite latent representation, blending the features of both 'samples_to' and 'samples_from' latents based on the specified coordinates and resizing option. |
diff --git a/built-in-nodes/LatentCompositeMasked.mdx b/built-in-nodes/LatentCompositeMasked.mdx
new file mode 100644
index 000000000..4e47c7d0e
--- /dev/null
+++ b/built-in-nodes/LatentCompositeMasked.mdx
@@ -0,0 +1,26 @@
+---
+title: "LatentCompositeMasked - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentCompositeMasked node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentCompositeMasked"
+icon: "circle"
+mode: wide
+---
+
+The LatentCompositeMasked node is designed for blending two latent representations together at specified coordinates, optionally using a mask for more controlled compositing. This node enables the creation of complex latent images by overlaying parts of one image onto another, with the ability to resize the source image for a perfect fit.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `destination` | `LATENT`    | The latent representation onto which another latent representation will be composited. Acts as the base layer for the composite operation. |
+| `source` | `LATENT`    | The latent representation to be composited onto the destination. This source layer can be resized and positioned according to the specified parameters. |
+| `x` | `INT`       | The x-coordinate in the destination latent representation where the source will be placed. Allows for precise positioning of the source layer. |
+| `y` | `INT`       | The y-coordinate in the destination latent representation where the source will be placed, enabling accurate overlay positioning. |
+| `resize_source` | `BOOLEAN` | A boolean flag indicating whether the source latent representation should be resized to match the destination's dimensions before compositing. |
+| `mask` | `MASK`     | An optional mask that can be used to control the blending of the source onto the destination. The mask defines which parts of the source will be visible in the final composite. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The resulting latent representation after compositing the source onto the destination, potentially using a mask for selective blending. |
diff --git a/built-in-nodes/LatentConcat.mdx b/built-in-nodes/LatentConcat.mdx
new file mode 100644
index 000000000..abc43e089
--- /dev/null
+++ b/built-in-nodes/LatentConcat.mdx
@@ -0,0 +1,26 @@
+---
+title: "LatentConcat - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentConcat node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentConcat"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentConcat/en.md)
+
+The LatentConcat node combines two latent samples along a specified dimension. It takes two latent inputs and concatenates them together along the chosen axis (x, y, or t dimension). The node automatically adjusts the batch size of the second input to match the first input before performing the concatenation operation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples1` | LATENT | Yes | - | The first latent sample to concatenate |
+| `samples2` | LATENT | Yes | - | The second latent sample to concatenate |
+| `dim` | COMBO | Yes | `"x"`<br />`"-x"`<br />`"y"`<br />`"-y"`<br />`"t"`<br />`"-t"` | The dimension along which to concatenate the latent samples. Positive values concatenate samples1 before samples2, negative values concatenate samples2 before samples1 |
+
+**Note:** The second latent sample (`samples2`) is automatically adjusted to match the batch size of the first latent sample (`samples1`) before concatenation.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | LATENT | The concatenated latent samples resulting from combining the two input samples along the specified dimension |
diff --git a/built-in-nodes/LatentCrop.mdx b/built-in-nodes/LatentCrop.mdx
new file mode 100644
index 000000000..ea4f291a9
--- /dev/null
+++ b/built-in-nodes/LatentCrop.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentCrop - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentCrop node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentCrop"
+icon: "circle"
+mode: wide
+---
+
+The LatentCrop node is designed to perform cropping operations on latent representations of images. It allows for the specification of the crop dimensions and position, enabling targeted modifications of the latent space.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `samples` | `LATENT`    | The 'samples' parameter represents the latent representations to be cropped. It is crucial for defining the data on which the cropping operation will be performed. |
+| `width`   | `INT`       | Specifies the width of the crop area. It directly influences the dimensions of the output latent representation. |
+| `height`  | `INT`       | Specifies the height of the crop area, affecting the size of the resulting cropped latent representation. |
+| `x`       | `INT`       | Determines the starting x-coordinate of the crop area, influencing the position of the crop within the original latent representation. |
+| `y`       | `INT`       | Determines the starting y-coordinate of the crop area, setting the position of the crop within the original latent representation. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a modified latent representation with the specified crop applied. |
diff --git a/built-in-nodes/LatentCut.mdx b/built-in-nodes/LatentCut.mdx
new file mode 100644
index 000000000..33769b219
--- /dev/null
+++ b/built-in-nodes/LatentCut.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentCut - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentCut node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentCut"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentCut/en.md)
+
+The LatentCut node extracts a specific section from latent samples along a chosen dimension. It allows you to cut out a portion of the latent representation by specifying the dimension (x, y, or t), starting position, and amount to extract. The node handles both positive and negative indexing and automatically adjusts the extraction amount to stay within the available bounds.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | - | The input latent samples to extract from |
+| `dim` | COMBO | Yes | "x"<br />"y"<br />"t" | The dimension along which to cut the latent samples |
+| `index` | INT | No | -16384 to 16384 | The starting position for the cut (default: 0). Positive values count from the start, negative values count from the end |
+| `amount` | INT | No | 1 to 16384 | The number of elements to extract along the specified dimension (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | LATENT | The extracted portion of the latent samples |
diff --git a/built-in-nodes/LatentCutToBatch.mdx b/built-in-nodes/LatentCutToBatch.mdx
new file mode 100644
index 000000000..7a11c8172
--- /dev/null
+++ b/built-in-nodes/LatentCutToBatch.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentCutToBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentCutToBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentCutToBatch"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentCutToBatch/en.md)
+
+The LatentCutToBatch node takes a latent representation and splits it along a specified dimension into multiple slices. These slices are then stacked into a new batch dimension, effectively converting a single latent sample into a batch of smaller latent samples. This is useful for processing different parts of a latent space independently.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | - | The latent representation to be split and batched. |
+| `dim` | COMBO | Yes | `"t"`<br />`"x"`<br />`"y"` | The dimension along which to cut the latent samples. `"t"` refers to the temporal dimension, `"x"` to the width, and `"y"` to the height. |
+| `slice_size` | INT | Yes | 1 to 16384 | The size of each slice to cut from the specified dimension. If the dimension's size is not perfectly divisible by this value, the remainder is discarded. (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | The resulting latent batch, containing the sliced and stacked samples. |
diff --git a/built-in-nodes/LatentFlip.mdx b/built-in-nodes/LatentFlip.mdx
new file mode 100644
index 000000000..ee078207d
--- /dev/null
+++ b/built-in-nodes/LatentFlip.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentFlip - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentFlip node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentFlip"
+icon: "circle"
+mode: wide
+---
+
+The LatentFlip node is designed to manipulate latent representations by flipping them either vertically or horizontally. This operation allows for the transformation of the latent space, potentially uncovering new variations or perspectives within the data.
+
+## Inputs
+
+| Parameter     | Data Type | Description |
+|---------------|--------------|-------------|
+| `samples`     | `LATENT`     | The 'samples' parameter represents the latent representations to be flipped. The flipping operation alters these representations, either vertically or horizontally, depending on the 'flip_method' parameter, thus transforming the data in the latent space. |
+| `flip_method` | COMBO[STRING] | The 'flip_method' parameter specifies the axis along which the latent samples will be flipped. It can be either 'x-axis: vertically' or 'y-axis: horizontally', determining the direction of the flip and thus the nature of the transformation applied to the latent representations. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a modified version of the input latent representations, having been flipped according to the specified method. This transformation can introduce new variations within the latent space. |
diff --git a/built-in-nodes/LatentFromBatch.mdx b/built-in-nodes/LatentFromBatch.mdx
new file mode 100644
index 000000000..8cf28c32b
--- /dev/null
+++ b/built-in-nodes/LatentFromBatch.mdx
@@ -0,0 +1,23 @@
+---
+title: "LatentFromBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentFromBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentFromBatch"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to extract a specific subset of latent samples from a given batch based on the specified batch index and length. It allows for selective processing of latent samples, facilitating operations on smaller segments of the batch for efficiency or targeted manipulation.
+
+## Inputs
+
+| Parameter     | Data Type | Description |
+|---------------|-------------|-------------|
+| `samples`     | `LATENT`    | The collection of latent samples from which a subset will be extracted. This parameter is crucial for determining the source batch of samples to be processed. |
+| `batch_index` | `INT`       | Specifies the starting index within the batch from which the subset of samples will begin. This parameter enables targeted extraction of samples from specific positions in the batch. |
+| `length`      | `INT`       | Defines the number of samples to be extracted from the specified starting index. This parameter controls the size of the subset to be processed, allowing for flexible manipulation of batch segments. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The extracted subset of latent samples, now available for further processing or analysis. |
diff --git a/built-in-nodes/LatentInterpolate.mdx b/built-in-nodes/LatentInterpolate.mdx
new file mode 100644
index 000000000..6bc90de2f
--- /dev/null
+++ b/built-in-nodes/LatentInterpolate.mdx
@@ -0,0 +1,23 @@
+---
+title: "LatentInterpolate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentInterpolate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentInterpolate"
+icon: "circle"
+mode: wide
+---
+
+The LatentInterpolate node is designed to perform interpolation between two sets of latent samples based on a specified ratio, blending the characteristics of both sets to produce a new, intermediate set of latent samples.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|-------------|-------------|
+| `samples1`   | `LATENT`    | The first set of latent samples to be interpolated. It serves as the starting point for the interpolation process. |
+| `samples2`   | `LATENT`    | The second set of latent samples to be interpolated. It serves as the endpoint for the interpolation process. |
+| `ratio`      | `FLOAT`     | A floating-point value that determines the weight of each set of samples in the interpolated output. A ratio of 0 produces a copy of the first set, while a ratio of 1 produces a copy of the second set. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a new set of latent samples that represent an interpolated state between the two input sets, based on the specified ratio. |
diff --git a/built-in-nodes/LatentMultiply.mdx b/built-in-nodes/LatentMultiply.mdx
new file mode 100644
index 000000000..fe2222485
--- /dev/null
+++ b/built-in-nodes/LatentMultiply.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentMultiply"
+icon: "circle"
+mode: wide
+---
+
+The LatentMultiply node is designed to scale the latent representation of samples by a specified multiplier. This operation allows for the adjustment of the intensity or magnitude of features within the latent space, enabling fine-tuning of generated content or the exploration of variations within a given latent direction.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|-------------|-------------|
+| `samples`    | `LATENT`    | The 'samples' parameter represents the latent representations to be scaled. It is crucial for defining the input data on which the multiplication operation will be performed. |
+| `multiplier` | `FLOAT`     | The 'multiplier' parameter specifies the scaling factor to be applied to the latent samples. It plays a key role in adjusting the magnitude of the latent features, allowing for nuanced control over the generated output. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a modified version of the input latent samples, scaled by the specified multiplier. This allows for the exploration of variations within the latent space by adjusting the intensity of its features. |
diff --git a/built-in-nodes/LatentOperationSharpen.mdx b/built-in-nodes/LatentOperationSharpen.mdx
new file mode 100644
index 000000000..60e5f18c4
--- /dev/null
+++ b/built-in-nodes/LatentOperationSharpen.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentOperationSharpen - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentOperationSharpen node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentOperationSharpen"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentOperationSharpen/en.md)
+
+The LatentOperationSharpen node applies a sharpening effect to latent representations using a Gaussian kernel. It works by normalizing the latent data, applying a convolution with a custom sharpening kernel, and then restoring the original luminance. This enhances the details and edges in the latent space representation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `sharpen_radius` | INT | No | 1-31 | The radius of the sharpening kernel (default: 9) |
+| `sigma` | FLOAT | No | 0.1-10.0 | The standard deviation for the Gaussian kernel (default: 1.0) |
+| `alpha` | FLOAT | No | 0.0-5.0 | The sharpening intensity factor (default: 0.1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `operation` | LATENT_OPERATION | Returns a sharpening operation that can be applied to latent data |
diff --git a/built-in-nodes/LatentOperationTonemapReinhard.mdx b/built-in-nodes/LatentOperationTonemapReinhard.mdx
new file mode 100644
index 000000000..dc4015adf
--- /dev/null
+++ b/built-in-nodes/LatentOperationTonemapReinhard.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentOperationTonemapReinhard - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentOperationTonemapReinhard node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentOperationTonemapReinhard"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentOperationTonemapReinhard/en.md)
+
+The LatentOperationTonemapReinhard node applies Reinhard tonemapping to latent vectors. This technique normalizes the latent vectors and adjusts their magnitude using a statistical approach based on mean and standard deviation, with the intensity controlled by a multiplier parameter.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `multiplier` | FLOAT | No | 0.0 to 100.0 | Controls the intensity of the tonemapping effect (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `operation` | LATENT_OPERATION | Returns a tonemapping operation that can be applied to latent vectors |
diff --git a/built-in-nodes/LatentRotate.mdx b/built-in-nodes/LatentRotate.mdx
new file mode 100644
index 000000000..d0a289968
--- /dev/null
+++ b/built-in-nodes/LatentRotate.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentRotate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentRotate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentRotate"
+icon: "circle"
+mode: wide
+---
+
+The LatentRotate node is designed to rotate latent representations of images by specified angles. It abstracts the complexity of manipulating latent space to achieve rotation effects, enabling users to easily transform images in a generative model's latent space.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `samples` | `LATENT`    | The 'samples' parameter represents the latent representations of images to be rotated. It is crucial for determining the starting point of the rotation operation. |
+| `rotation` | COMBO[STRING] | The 'rotation' parameter specifies the angle by which the latent images should be rotated. It directly influences the orientation of the resulting images. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a modified version of the input latent representations, rotated by the specified angle. |
diff --git a/built-in-nodes/LatentSubtract.mdx b/built-in-nodes/LatentSubtract.mdx
new file mode 100644
index 000000000..52851ebf6
--- /dev/null
+++ b/built-in-nodes/LatentSubtract.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentSubtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentSubtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentSubtract"
+icon: "circle"
+mode: wide
+---
+
+The LatentSubtract node is designed for subtracting one latent representation from another. This operation can be used to manipulate or modify the characteristics of generative models' outputs by effectively removing features or attributes represented in one latent space from another.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|-------------|-------------|
+| `samples1`   | `LATENT`    | The first set of latent samples to be subtracted from. It serves as the base for the subtraction operation. |
+| `samples2`   | `LATENT`    | The second set of latent samples that will be subtracted from the first set. This operation can alter the resulting generative model's output by removing attributes or features. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The result of subtracting the second set of latent samples from the first. This modified latent representation can be used for further generative tasks. |
diff --git a/built-in-nodes/LatentUpscale.mdx b/built-in-nodes/LatentUpscale.mdx
new file mode 100644
index 000000000..e2e6f9d13
--- /dev/null
+++ b/built-in-nodes/LatentUpscale.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentUpscale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentUpscale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentUpscale"
+icon: "circle"
+mode: wide
+---
+
+The LatentUpscale node is designed for upscaling latent representations of images. It allows for the adjustment of the output image's dimensions and the method of upscaling, providing flexibility in enhancing the resolution of latent images.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `samples` | `LATENT`    | The latent representation of an image to be upscaled. This parameter is crucial for determining the starting point of the upscaling process. |
+| `upscale_method` | COMBO[STRING] | Specifies the method used for upscaling the latent image. Different methods can affect the quality and characteristics of the upscaled image. |
+| `width`   | `INT`       | The desired width of the upscaled image. If set to 0, it will be calculated based on the height to maintain the aspect ratio. |
+| `height`  | `INT`       | The desired height of the upscaled image. If set to 0, it will be calculated based on the width to maintain the aspect ratio. |
+| `crop`    | COMBO[STRING] | Determines how the upscaled image should be cropped, affecting the final appearance and dimensions of the output. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The upscaled latent representation of the image, ready for further processing or generation. |
diff --git a/built-in-nodes/LatentUpscaleBy.mdx b/built-in-nodes/LatentUpscaleBy.mdx
new file mode 100644
index 000000000..677f8042b
--- /dev/null
+++ b/built-in-nodes/LatentUpscaleBy.mdx
@@ -0,0 +1,23 @@
+---
+title: "LatentUpscaleBy - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentUpscaleBy node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentUpscaleBy"
+icon: "circle"
+mode: wide
+---
+
+The LatentUpscaleBy node is designed for upscaling latent representations of images. It allows for the adjustment of the scale factor and the method of upscaling, providing flexibility in enhancing the resolution of latent samples.
+
+## Inputs
+
+| Parameter     | Data Type | Description |
+|---------------|--------------|-------------|
+| `samples`     | `LATENT`     | The latent representation of images to be upscaled. This parameter is crucial for determining the input data that will undergo the upscaling process. |
+| `upscale_method` | COMBO[STRING] | Specifies the method used for upscaling the latent samples. The choice of method can significantly affect the quality and characteristics of the upscaled output. |
+| `scale_by`    | `FLOAT`      | Determines the factor by which the latent samples are scaled. This parameter directly influences the resolution of the output, allowing for precise control over the upscaling process. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The upscaled latent representation, ready for further processing or generation tasks. This output is essential for enhancing the resolution of generated images or for subsequent model operations. |
diff --git a/built-in-nodes/LatentUpscaleModelLoader.mdx b/built-in-nodes/LatentUpscaleModelLoader.mdx
new file mode 100644
index 000000000..88a030dd3
--- /dev/null
+++ b/built-in-nodes/LatentUpscaleModelLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentUpscaleModelLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentUpscaleModelLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentUpscaleModelLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentUpscaleModelLoader/en.md)
+
+The LatentUpscaleModelLoader node loads a specialized model designed for upscaling latent representations. It reads a model file from the system's designated folder and automatically detects its type (720p, 1080p, or other) to instantiate and configure the correct internal model architecture. The loaded model is then ready to be used by other nodes for latent space super-resolution tasks.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | STRING | Yes | *All files in the `latent_upscale_models` folder* | The name of the latent upscale model file to load. The available options are dynamically populated from the files present in your ComfyUI's `latent_upscale_models` directory. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | LATENT_UPSCALE_MODEL | The loaded latent upscale model, configured and ready for use. |
diff --git a/built-in-nodes/LazyCache.mdx b/built-in-nodes/LazyCache.mdx
new file mode 100644
index 000000000..c9492617f
--- /dev/null
+++ b/built-in-nodes/LazyCache.mdx
@@ -0,0 +1,26 @@
+---
+title: "LazyCache - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LazyCache node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LazyCache"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LazyCache/en.md)
+
+LazyCache is a homebrew version of EasyCache that provides an even easier implementation. It works with any model in ComfyUI and adds caching functionality to reduce computation during sampling. While it generally performs worse than EasyCache, it can be more effective in some rare cases and offers universal compatibility.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to add LazyCache to. |
+| `reuse_threshold` | FLOAT | No | 0.0 - 3.0 | The threshold for reusing cached steps (default: 0.2). |
+| `start_percent` | FLOAT | No | 0.0 - 1.0 | The relative sampling step to begin use of LazyCache (default: 0.15). |
+| `end_percent` | FLOAT | No | 0.0 - 1.0 | The relative sampling step to end use of LazyCache (default: 0.95). |
+| `verbose` | BOOLEAN | No | - | Whether to log verbose information (default: False). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The model with LazyCache functionality added. |
diff --git a/built-in-nodes/Load3D.mdx b/built-in-nodes/Load3D.mdx
index 8668aefd4..ff1bd6ccd 100644
--- a/built-in-nodes/Load3D.mdx
+++ b/built-in-nodes/Load3D.mdx
@@ -1,10 +1,10 @@
 ---
 title: "Load3D - ComfyUI Built-in Node Documentation"
-description: "The Load3D node is a core node in ComfyUI for loading and previewing various 3D model files, supporting multi-format import and rich three-dimensional view operations."
+description: "Complete documentation for the Load3D node in ComfyUI. Learn its inputs, outputs, parameters and usage."
 sidebarTitle: "Load3D"
 icon: "circle"
+mode: wide
 ---
-
 The Load3D node is a core node for loading and processing 3D model files. When loading the node, it automatically retrieves available 3D resources from `ComfyUI/input/3d/`. You can also upload supported 3D files for preview using the upload function.
 
 **Supported Formats**
@@ -13,7 +13,7 @@ Currently, this node supports multiple 3D file formats, including `.gltf`, `.glb
 **3D Node Preferences**
 Some related preferences for 3D nodes can be configured in ComfyUI's settings menu. Please refer to the following documentation for corresponding settings:
 
-[Settings Menu - 3D](/interface/settings/3d)
+[Settings Menu](https://docs.comfy.org/interface/settings/3d)
 
 Besides regular node outputs, Load3D has lots of 3D view-related settings in the canvas menu.
 
@@ -37,12 +37,13 @@ Besides regular node outputs, Load3D has lots of 3D view-related settings in the
 | camera_info     | LOAD3D_CAMERA  | Camera information                 |
 | recording_video | VIDEO          | Recorded video (only when recording exists) |
 
-All corresponding outputs preview
-![View Operation Demo](/images/comfy_core/load3d/load3d_outputs.jpg)
+All the outputs preview:
+![View Operation Demo](/images/built-in-nodes/Load3D/load3d_outputs.webp)
 
 ## Canvas Area Description
 
 The Load3D node's Canvas area contains numerous view operations, including:
+
 - Preview view settings (grid, background color, preview view)
 - Camera control: Control FOV, camera type
 - Global illumination intensity: Adjust lighting intensity
@@ -50,7 +51,7 @@ The Load3D node's Canvas area contains numerous view operations, including:
 - Model export: Supports `GLB`, `OBJ`, `STL` formats
 - And more
 
-![Load 3D Node UI](/images/comfy_core/load3d/load3d_ui.jpg)
+![Load 3D Node UI](/images/built-in-nodes/Load3D/load3d_ui.jpg)
 
 1. Contains multiple menus and hidden menus of the Load 3D node
 2. Menu for `resizing preview window` and `canvas video recording`
@@ -60,16 +61,13 @@ The Load3D node's Canvas area contains numerous view operations, including:
 
 ### 1. View Operations
 
-<video
-  controls
-  muted
-  loop
-  playsInline
-  className="w-full aspect-video rounded-xl"
-  src="/images/comfy_core/load3d/view_operations.mp4"
-></video>
+<video controls width="640" height="360">
+  <source src="/images/built-in-nodes/Load3D/view_operations.mp4" type="video/mp4" />
+  Your browser does not support video playback.
+</video>
 
 View control operations:
+
 - Left-click + drag: Rotate the view
 - Right-click + drag: Pan the view
 - Middle wheel scroll or middle-click + drag: Zoom in/out
@@ -77,9 +75,10 @@ View control operations:
 
 ### 2. Left Menu Functions
 
-![Menu](/images/comfy_core/load3d/menu.jpg)
+![Menu](/images/built-in-nodes/Load3D/menu.webp)
 
 In the canvas, some settings are hidden in the menu. Click the menu button to expand different menus
+
 - 1. Scene: Contains preview window grid, background color, preview settings
 - 2. Model: Model rendering mode, texture materials, up direction settings
 - 3. Camera: Switch between orthographic and perspective views, and set the perspective angle size
@@ -88,9 +87,10 @@ In the canvas, some settings are hidden in the menu. Click the menu button to ex
 
 #### Scene
 
-![scene menu](/images/comfy_core/load3d/menu_scene.jpg)
+![scene menu](/images/built-in-nodes/Load3D/menu_scene.webp)
 
 The Scene menu provides some basic scene setting functions
+
 1. Show/Hide grid
 2. Set background color
 3. Click to upload a background image
@@ -98,43 +98,42 @@ The Scene menu provides some basic scene setting functions
 
 #### Model
 
-![Menu_Scene](/images/comfy_core/load3d/menu_model.jpg)
+![Menu_Scene](/images/built-in-nodes/Load3D/menu_model.webp)
 
 The Model menu provides some model-related functions
+
 1. **Up direction**: Determine which axis is the up direction for the model
 2. **Material mode**: Switch model rendering modes - Original, Normal, Wireframe, Lineart
 
 #### Camera
 
-![menu_modelmenu_camera](/images/comfy_core/load3d/menu_camera.jpg)
+![menu_modelmenu_camera](/images/built-in-nodes/Load3D/menu_camera.webp)
 
 This menu provides switching between orthographic and perspective views, and perspective angle size settings
+
 1. **Camera**: Quickly switch between orthographic and orthographic views
 2. **FOV**: Adjust FOV angle
 
 #### Light
 
-![menu_modelmenu_camera](/images/comfy_core/load3d/menu_light.jpg)
+![menu_modelmenu_camera](/images/built-in-nodes/Load3D/menu_light.webp)
 
 Through this menu, you can quickly adjust the scene's global illumination intensity
 
 #### Export
 
-![menu_export](/images/comfy_core/load3d/menu_export.jpg)
+![menu_export](/images/built-in-nodes/Load3D/menu_export.webp)
 
 This menu provides the ability to quickly convert and export model formats
 
 ### 3. Right Menu Functions
 
-<video
-  controls
-  muted
-  loop
-  playsInline
-  className="w-full aspect-video rounded-xl"
-  src="/images/comfy_core/load3d/recording.mp4"
-></video>
+<video controls width="640" height="360">
+  <source src="https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/view_operations.mp4" type="video/mp4" />
+  Your browser does not support video playback.
+</video>
 
 The right menu has two main functions:
+
 1. **Reset view ratio**: After clicking the button, the view will adjust the canvas rendering area ratio according to the set width and height
 2. **Video recording**: Allows you to record current 3D view operations as video, allows import, and can be output as `recording_video` to subsequent nodes
diff --git a/built-in-nodes/Load3DAnimation.mdx b/built-in-nodes/Load3DAnimation.mdx
new file mode 100644
index 000000000..c48f15bcb
--- /dev/null
+++ b/built-in-nodes/Load3DAnimation.mdx
@@ -0,0 +1,142 @@
+---
+title: "Load3DAnimation - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Load3DAnimation node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Load3DAnimation"
+icon: "circle"
+mode: wide
+---
+The Load3DAnimation node is a core node for loading and processing 3D model files. When loading the node, it automatically retrieves available 3D resources from `ComfyUI/input/3d/`. You can also upload supported 3D files for preview using the upload function.
+
+> - Most of the functions of this node are the same as the Load 3D node, but this node supports loading models with animations, and you can preview the corresponding animations in the node.
+> - The content of this documentation is the same as the Load3D node, because except for animation preview and playback, their capabilities are identical.
+
+**Supported Formats**
+Currently, this node supports multiple 3D file formats, including `.gltf`, `.glb`, `.obj`, `.fbx`, and `.stl`.
+
+**3D Node Preferences**
+Some related preferences for 3D nodes can be configured in ComfyUI's settings menu. Please refer to the following documentation for corresponding settings:
+
+[Settings Menu](https://docs.comfy.org/interface/settings/3d)
+
+Besides regular node outputs, Load3D has lots of 3D view-related settings in the canvas menu.
+
+## Inputs
+
+| Parameter Name | Type     | Description                     | Default | Range        |
+|---------------|----------|---------------------------------|---------|--------------|
+| model_file    | File Selection | 3D model file path, supports upload, defaults to reading model files from `ComfyUI/input/3d/` | - | Supported formats |
+| width         | INT      | Canvas rendering width          | 1024    | 1-4096      |
+| height        | INT      | Canvas rendering height         | 1024    | 1-4096      |
+
+## Outputs
+
+| Parameter Name   | Data Type      | Description                        |
+|-----------------|----------------|------------------------------------|
+| image           | IMAGE          | Canvas rendered image              |
+| mask            | MASK           | Mask containing current model position |
+| mesh_path       | STRING         | Model file path                   |
+| normal          | IMAGE          | Normal map                         |
+| lineart         | IMAGE          | Line art image output, corresponding `edge_threshold` can be adjusted in the canvas model menu |
+| camera_info     | LOAD3D_CAMERA  | Camera information                 |
+| recording_video | VIDEO          | Recorded video (only when recording exists) |
+
+All the outputs preview:
+![View Operation Demo](/images/built-in-nodes/Load3DAnimation/load3d_outputs.webp)
+
+## Canvas Area Description
+
+The Load3D node's Canvas area contains numerous view operations, including:
+
+- Preview view settings (grid, background color, preview view)
+- Camera control: Control FOV, camera type
+- Global illumination intensity: Adjust lighting intensity
+- Video recording: Record and export videos
+- Model export: Supports `GLB`, `OBJ`, `STL` formats
+- And more
+
+![Load 3D Node UI](/images/built-in-nodes/Load3DAnimation/load3d_ui.jpg)
+
+1. Contains multiple menus and hidden menus of the Load 3D node
+2. Menu for `resizing preview window` and `canvas video recording`
+3. 3D view operation axis
+4. Preview thumbnail
+5. Preview size settings, scale preview view display by setting dimensions and then resizing window
+
+### 1. View Operations
+
+<video controls width="640" height="360">
+  <source src="https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/view_operations.mp4" type="video/mp4" />
+  Your browser does not support video playback.
+</video>
+
+View control operations:
+
+- Left-click + drag: Rotate the view
+- Right-click + drag: Pan the view
+- Middle wheel scroll or middle-click + drag: Zoom in/out
+- Coordinate axis: Switch views
+
+### 2. Left Menu Functions
+
+![Menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu.webp)
+
+In the canvas, some settings are hidden in the menu. Click the menu button to expand different menus
+
+- 1. Scene: Contains preview window grid, background color, preview settings
+- 2. Model: Model rendering mode, texture materials, up direction settings
+- 3. Camera: Switch between orthographic and perspective views, and set the perspective angle size
+- 4. Light: Scene global illumination intensity
+- 5. Export: Export model to other formats (GLB, OBJ, STL)
+
+#### Scene
+
+![scene menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_scene.webp)
+
+The Scene menu provides some basic scene setting functions
+
+1. Show/Hide grid
+2. Set background color
+3. Click to upload a background image
+4. Hide the preview
+
+#### Model
+
+![Menu_Scene](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_model.webp)
+
+The Model menu provides some model-related functions
+
+1. **Up direction**: Determine which axis is the up direction for the model
+2. **Material mode**: Switch model rendering modes - Original, Normal, Wireframe, Lineart
+
+#### Camera
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_camera.webp)
+
+This menu provides switching between orthographic and perspective views, and perspective angle size settings
+
+1. **Camera**: Quickly switch between orthographic and orthographic views
+2. **FOV**: Adjust FOV angle
+
+#### Light
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_light.webp)
+
+Through this menu, you can quickly adjust the scene's global illumination intensity
+
+#### Export
+
+![menu_export](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_export.webp)
+
+This menu provides the ability to quickly convert and export model formats
+
+### 3. Right Menu Functions
+
+<video controls width="640" height="360">
+  <source src="/images/built-in-nodes/Load3DAnimation/recording.mp4" type="video/mp4" />
+  Your browser does not support video playback.
+</video>
+
+The right menu has two main functions:
+
+1. **Reset view ratio**: After clicking the button, the view will adjust the canvas rendering area ratio according to the set width and height
+2. **Video recording**: Allows you to record current 3D view operations as video, allows import, and can be output as `recording_video` to subsequent nodes
diff --git a/built-in-nodes/LoadAudio.mdx b/built-in-nodes/LoadAudio.mdx
new file mode 100644
index 000000000..9aa2e5407
--- /dev/null
+++ b/built-in-nodes/LoadAudio.mdx
@@ -0,0 +1,24 @@
+---
+title: "LoadAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadAudio/en.md)
+
+The LoadAudio node loads audio files from the input directory and converts them into a format that can be processed by other audio nodes in ComfyUI. It reads audio files and extracts both the waveform data and sample rate, making them available for downstream audio processing tasks.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | All supported audio/video files in input directory | The audio file to load from the input directory |
+
+**Note:** The node only accepts audio and video files that are present in ComfyUI's input directory. The file must exist and be accessible for successful loading.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | Audio data containing waveform and sample rate information |
diff --git a/built-in-nodes/LoadImage.mdx b/built-in-nodes/LoadImage.mdx
new file mode 100644
index 000000000..34fbefebb
--- /dev/null
+++ b/built-in-nodes/LoadImage.mdx
@@ -0,0 +1,22 @@
+---
+title: "LoadImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImage"
+icon: "circle"
+mode: wide
+---
+
+The LoadImage node is designed to load and preprocess images from a specified path. It handles image formats with multiple frames, applies necessary transformations such as rotation based on EXIF data, normalizes pixel values, and optionally generates a mask for images with an alpha channel. This node is essential for preparing images for further processing or analysis within a pipeline.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|--------------|-------------|
+| `image`   | COMBO[STRING] | The 'image' parameter specifies the identifier of the image to be loaded and processed. It is crucial for determining the path to the image file and subsequently loading the image for transformation and normalization. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The processed image, with pixel values normalized and transformations applied as necessary. It is ready for further processing or analysis. |
+| `mask`    | `MASK`      | An optional output providing a mask for the image, useful in scenarios where the image includes an alpha channel for transparency. |
diff --git a/built-in-nodes/LoadImageDataSetFromFolder.mdx b/built-in-nodes/LoadImageDataSetFromFolder.mdx
new file mode 100644
index 000000000..8b7987656
--- /dev/null
+++ b/built-in-nodes/LoadImageDataSetFromFolder.mdx
@@ -0,0 +1,22 @@
+---
+title: "LoadImageDataSetFromFolder - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageDataSetFromFolder node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageDataSetFromFolder"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageDataSetFromFolder/en.md)
+
+This node loads multiple images from a specified subfolder within ComfyUI's input directory. It scans the chosen folder for common image file types and returns them as a list, making it useful for batch processing or dataset preparation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `folder` | STRING | Yes | *Multiple options available* | The folder to load images from. The options are the subfolders present in ComfyUI's main input directory. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `images` | IMAGE | List of loaded images. The node loads all valid image files (PNG, JPG, JPEG, WEBP) found in the selected folder. |
diff --git a/built-in-nodes/LoadImageMask.mdx b/built-in-nodes/LoadImageMask.mdx
new file mode 100644
index 000000000..996e6071b
--- /dev/null
+++ b/built-in-nodes/LoadImageMask.mdx
@@ -0,0 +1,22 @@
+---
+title: "LoadImageMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageMask"
+icon: "circle"
+mode: wide
+---
+
+The LoadImageMask node is designed to load images and their associated masks from a specified path, processing them to ensure compatibility with further image manipulation or analysis tasks. It focuses on handling various image formats and conditions, such as presence of an alpha channel for masks, and prepares the images and masks for downstream processing by converting them to a standardized format.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | COMBO[STRING] | The 'image' parameter specifies the image file to be loaded and processed. It plays a crucial role in determining the output by providing the source image for mask extraction and format conversion. |
+| `channel` | COMBO[STRING] | The 'channel' parameter specifies the color channel of the image that will be used to generate the mask. This allows for flexibility in mask creation based on different color channels, enhancing the node's utility in various image processing scenarios. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | `MASK`      | This node outputs the mask generated from the specified image and channel, prepared in a standardized format suitable for further processing in image manipulation tasks. |
diff --git a/built-in-nodes/LoadImageOutput.mdx b/built-in-nodes/LoadImageOutput.mdx
new file mode 100644
index 000000000..0d826d136
--- /dev/null
+++ b/built-in-nodes/LoadImageOutput.mdx
@@ -0,0 +1,23 @@
+---
+title: "LoadImageOutput - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageOutput node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageOutput"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageOutput/en.md)
+
+The LoadImageOutput node loads images from the output folder. When you click the refresh button, it updates the list of available images and automatically selects the first one, making it easy to iterate through your generated images.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | COMBO | Yes | Multiple options available | Load an image from the output folder. Includes an upload option and refresh button to update the image list. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The loaded image from the output folder |
+| `mask` | MASK | The mask associated with the loaded image |
diff --git a/built-in-nodes/LoadImageSetFromFolderNode.mdx b/built-in-nodes/LoadImageSetFromFolderNode.mdx
new file mode 100644
index 000000000..87423af58
--- /dev/null
+++ b/built-in-nodes/LoadImageSetFromFolderNode.mdx
@@ -0,0 +1,23 @@
+---
+title: "LoadImageSetFromFolderNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageSetFromFolderNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageSetFromFolderNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageSetFromFolderNode/en.md)
+
+The LoadImageSetFromFolderNode loads multiple images from a specified folder directory for training purposes. It automatically detects common image formats and can optionally resize the images using different methods before returning them as a batch.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `folder` | STRING | Yes | Multiple options available | The folder to load images from. |
+| `resize_method` | STRING | No | "None"<br />"Stretch"<br />"Crop"<br />"Pad" | The method to use for resizing images (default: "None"). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The batch of loaded images as a single tensor. |
diff --git a/built-in-nodes/LoadImageSetNode.mdx b/built-in-nodes/LoadImageSetNode.mdx
new file mode 100644
index 000000000..ae24337d5
--- /dev/null
+++ b/built-in-nodes/LoadImageSetNode.mdx
@@ -0,0 +1,23 @@
+---
+title: "LoadImageSetNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageSetNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageSetNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageSetNode/en.md)
+
+The LoadImageSetNode loads multiple images from the input directory for batch processing and training purposes. It supports various image formats and can optionally resize the images using different methods. This node processes all selected images as a batch and returns them as a single tensor.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | Multiple image files | Select multiple images from the input directory. Supports PNG, JPG, JPEG, WEBP, BMP, GIF, JPE, APNG, TIF, and TIFF formats. Allows batch selection of images. |
+| `resize_method` | STRING | No | "None"<br />"Stretch"<br />"Crop"<br />"Pad" | Optional method to resize loaded images (default: "None"). Choose "None" to keep original sizes, "Stretch" to force resize, "Crop" to maintain aspect ratio by cropping, or "Pad" to maintain aspect ratio by adding padding. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | A tensor containing all loaded images as a batch for further processing. |
diff --git a/built-in-nodes/LoadImageTextDataSetFromFolder.mdx b/built-in-nodes/LoadImageTextDataSetFromFolder.mdx
new file mode 100644
index 000000000..cf10d8b21
--- /dev/null
+++ b/built-in-nodes/LoadImageTextDataSetFromFolder.mdx
@@ -0,0 +1,25 @@
+---
+title: "LoadImageTextDataSetFromFolder - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageTextDataSetFromFolder node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageTextDataSetFromFolder"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextDataSetFromFolder/en.md)
+
+This node loads a dataset of images and their corresponding text captions from a specified folder. It searches for image files and automatically looks for matching `.txt` files with the same base name to use as captions. The node also supports a specific folder structure where subfolders can be named with a number prefix (like `10_folder_name`) to indicate that the images inside should be repeated multiple times in the output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `folder` | COMBO | Yes | *Dynamically loaded from `folder_paths.get_input_subfolders()`* | The folder to load images from. The available options are the subdirectories within ComfyUI's input directory. |
+
+**Note:** The node expects a specific file structure. For each image file (`.png`, `.jpg`, `.jpeg`, `.webp`), it will look for a `.txt` file with the same name to use as a caption. If a caption file is not found, an empty string is used. The node also supports a special structure where a subfolder's name begins with a number and an underscore (e.g., `5_cats`), which will cause all images inside that subfolder to be repeated that number of times in the final output list.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `images` | IMAGE | A list of loaded image tensors. |
+| `texts` | STRING | A list of text captions corresponding to each loaded image. |
diff --git a/built-in-nodes/LoadImageTextSetFromFolderNode.mdx b/built-in-nodes/LoadImageTextSetFromFolderNode.mdx
new file mode 100644
index 000000000..f04a94aec
--- /dev/null
+++ b/built-in-nodes/LoadImageTextSetFromFolderNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "LoadImageTextSetFromFolderNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageTextSetFromFolderNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageTextSetFromFolderNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextSetFromFolderNode/en.md)
+
+Loads a batch of images and their corresponding text captions from a specified directory for training purposes. The node automatically searches for image files and their associated caption text files, processes the images according to specified resize settings, and encodes the captions using the provided CLIP model.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `folder` | STRING | Yes | - | The folder to load images from. |
+| `clip` | CLIP | Yes | - | The CLIP model used for encoding the text. |
+| `resize_method` | COMBO | No | "None"<br />"Stretch"<br />"Crop"<br />"Pad" | The method used to resize images (default: "None"). |
+| `width` | INT | No | -1 to 10000 | The width to resize the images to. -1 means use the original width (default: -1). |
+| `height` | INT | No | -1 to 10000 | The height to resize the images to. -1 means use the original height (default: -1). |
+
+**Note:** The CLIP input must be valid and cannot be None. If the CLIP model comes from a checkpoint loader node, ensure the checkpoint contains a valid CLIP or text encoder model.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The batch of loaded and processed images. |
+| `CONDITIONING` | CONDITIONING | The encoded conditioning data from the text captions. |
diff --git a/built-in-nodes/LoadLatent.mdx b/built-in-nodes/LoadLatent.mdx
new file mode 100644
index 000000000..ab23a45fb
--- /dev/null
+++ b/built-in-nodes/LoadLatent.mdx
@@ -0,0 +1,22 @@
+---
+title: "LoadLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadLatent/en.md)
+
+The LoadLatent node loads previously saved latent representations from .latent files in the input directory. It reads the latent tensor data from the file and applies any necessary scaling adjustments before returning the latent data for use in other nodes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `latent` | STRING | Yes | All .latent files in input directory | Selects which .latent file to load from the available files in the input directory |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | Returns the loaded latent representation data from the selected file |
diff --git a/built-in-nodes/LoadTrainingDataset.mdx b/built-in-nodes/LoadTrainingDataset.mdx
new file mode 100644
index 000000000..1bf0c488c
--- /dev/null
+++ b/built-in-nodes/LoadTrainingDataset.mdx
@@ -0,0 +1,23 @@
+---
+title: "LoadTrainingDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadTrainingDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadTrainingDataset"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadTrainingDataset/en.md)
+
+This node loads an encoded training dataset that has been previously saved to disk. It searches for and reads all data shard files from a specified folder within the ComfyUI output directory, then returns the combined latent vectors and conditioning data for use in training workflows.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `folder_name` | STRING | No | N/A | Name of the folder containing the saved dataset, located inside the ComfyUI output directory (default: "training_dataset"). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `latents` | LATENT | A list of latent dictionaries, where each dictionary contains a `"samples"` key with a tensor. |
+| `conditioning` | CONDITIONING | A list of conditioning lists, where each inner list contains conditioning data for a corresponding sample. |
diff --git a/built-in-nodes/LoadVideo.mdx b/built-in-nodes/LoadVideo.mdx
new file mode 100644
index 000000000..9c9a54165
--- /dev/null
+++ b/built-in-nodes/LoadVideo.mdx
@@ -0,0 +1,24 @@
+---
+title: "LoadVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadVideo/en.md)
+
+The Load Video node loads video files from the input directory and makes them available for processing in the workflow. It reads video files from the designated input folder and outputs them as video data that can be connected to other video processing nodes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `file` | STRING | Yes | Multiple options available | The video file to load from the input directory |
+
+**Note:** The available options for the `file` parameter are dynamically populated from the video files present in the input directory. Only video files with supported content types are displayed.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The loaded video data that can be passed to other video processing nodes |
diff --git a/built-in-nodes/LoraLoader.mdx b/built-in-nodes/LoraLoader.mdx
new file mode 100644
index 000000000..508e17872
--- /dev/null
+++ b/built-in-nodes/LoraLoader.mdx
@@ -0,0 +1,34 @@
+---
+title: "LoraLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraLoader"
+icon: "circle"
+mode: wide
+---
+This node automatically detects models located in the LoRA folder (including subfolders) with the corresponding model path being `ComfyUI\models\loras`. For more information, please refer to Installing LoRA Models
+
+The LoRA Loader node is primarily used to load LoRA models. You can think of LoRA models as filters that can give your images specific styles, content, and details:
+
+- Apply specific artistic styles (like ink painting)
+- Add characteristics of certain characters (like game characters)
+- Add specific details to the image
+All of these can be achieved through LoRA.
+
+If you need to load multiple LoRA models, you can directly chain multiple nodes together, as shown below:
+
+## Inputs
+
+| Parameter | Data Type | Description |
+| --- | --- | --- |
+| `model` | MODEL | Typically used to connect to the base model |
+| `clip` | CLIP | Typically used to connect to the CLIP model |
+| `lora_name` | COMBO[STRING] | Select the name of the LoRA model to use |
+| `strength_model` | FLOAT | Value range from -100.0 to 100.0, typically used between 0~1 for daily image generation. Higher values result in more pronounced model adjustment effects |
+| `strength_clip` | FLOAT | Value range from -100.0 to 100.0, typically used between 0~1 for daily image generation. Higher values result in more pronounced model adjustment effects |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+| --- | --- | --- |
+| `model` | MODEL | The model with LoRA adjustments applied |
+| `clip` | CLIP | The CLIP instance with LoRA adjustments applied |
diff --git a/built-in-nodes/LoraLoaderBypass.mdx b/built-in-nodes/LoraLoaderBypass.mdx
new file mode 100644
index 000000000..b0a37b024
--- /dev/null
+++ b/built-in-nodes/LoraLoaderBypass.mdx
@@ -0,0 +1,29 @@
+---
+title: "LoraLoaderBypass - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraLoaderBypass node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraLoaderBypass"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraLoaderBypass/en.md)
+
+The LoraLoaderBypass node applies a LoRA (Low-Rank Adaptation) to a diffusion model and a CLIP model in a special "bypass" mode. Unlike a standard LoRA loader, this method does not permanently modify the base model's weights. Instead, it computes the output by adding the LoRA's effect to the model's normal forward pass, which is useful for training or when working with models that have their weights offloaded.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model the LoRA will be applied to. |
+| `clip` | CLIP | Yes | - | The CLIP model the LoRA will be applied to. |
+| `lora_name` | COMBO | Yes | *List of available LoRA files* | The name of the LoRA file to apply. The options are loaded from the `loras` folder. |
+| `strength_model` | FLOAT | Yes | -100.0 to 100.0 | How strongly to modify the diffusion model. This value can be negative (default: 1.0). |
+| `strength_clip` | FLOAT | Yes | -100.0 to 100.0 | How strongly to modify the CLIP model. This value can be negative (default: 1.0). |
+
+**Note:** If both `strength_model` and `strength_clip` are set to 0, the node will return the original, unmodified `model` and `clip` inputs without processing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | The diffusion model with the LoRA applied in bypass mode. |
+| `CLIP` | CLIP | The CLIP model with the LoRA applied in bypass mode. |
diff --git a/built-in-nodes/LoraLoaderBypassModelOnly.mdx b/built-in-nodes/LoraLoaderBypassModelOnly.mdx
new file mode 100644
index 000000000..293b86bb0
--- /dev/null
+++ b/built-in-nodes/LoraLoaderBypassModelOnly.mdx
@@ -0,0 +1,24 @@
+---
+title: "LoraLoaderBypassModelOnly - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraLoaderBypassModelOnly node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraLoaderBypassModelOnly"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraLoaderBypassModelOnly/en.md)
+
+This node applies a LoRA (Low-Rank Adaptation) to a model to modify its behavior, but only affects the model component itself. It loads a specified LoRA file and adjusts the model's weights by a given strength, leaving other components like the CLIP text encoder unchanged.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The base model to which the LoRA adjustments will be applied. |
+| `lora_name` | STRING | Yes | (List of available LoRA files) | The name of the LoRA file to load and apply. The options are populated from the files in the `loras` directory. |
+| `strength_model` | FLOAT | Yes | -100.0 to 100.0 | The strength of the LoRA's effect on the model's weights. A positive value applies the LoRA, a negative value applies the inverse, and a value of 0 has no effect (default: 1.0). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with the LoRA adjustments applied to its weights. |
diff --git a/built-in-nodes/LoraLoaderModelOnly.mdx b/built-in-nodes/LoraLoaderModelOnly.mdx
new file mode 100644
index 000000000..a25334757
--- /dev/null
+++ b/built-in-nodes/LoraLoaderModelOnly.mdx
@@ -0,0 +1,25 @@
+---
+title: "LoraLoaderModelOnly - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraLoaderModelOnly node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraLoaderModelOnly"
+icon: "circle"
+mode: wide
+---
+
+This node will detect models located in the `ComfyUI/models/loras` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+This node specializes in loading a LoRA model without requiring a CLIP model, focusing on enhancing or modifying a given model based on LoRA parameters. It allows for the dynamic adjustment of the model's strength through LoRA parameters, facilitating fine-tuned control over the model's behavior.
+
+## Inputs
+
+| Field             | Comfy dtype       | Description                                                                                   |
+|-------------------|-------------------|-----------------------------------------------------------------------------------------------|
+| `model`           | `MODEL`           | The base model for modifications, to which LoRA adjustments will be applied.                   |
+| `lora_name`       | `COMBO[STRING]`   | The name of the LoRA file to be loaded, specifying the adjustments to apply to the model.      |
+| `strength_model`  | `FLOAT`           | Determines the intensity of the LoRA adjustments, with higher values indicating stronger modifications. |
+
+## Outputs
+
+| Field   | Data Type | Description                                                              |
+|---------|-------------|--------------------------------------------------------------------------|
+| `model` | `MODEL`     | The modified model with LoRA adjustments applied, reflecting changes in model behavior or capabilities. |
diff --git a/built-in-nodes/LoraModelLoader.mdx b/built-in-nodes/LoraModelLoader.mdx
new file mode 100644
index 000000000..31056e66a
--- /dev/null
+++ b/built-in-nodes/LoraModelLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "LoraModelLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraModelLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraModelLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraModelLoader/en.md)
+
+The LoraModelLoader node applies trained LoRA (Low-Rank Adaptation) weights to a diffusion model. It modifies the base model by loading LoRA weights from a trained LoRA model and adjusting their influence strength. This allows you to customize the behavior of diffusion models without retraining them from scratch.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model the LoRA will be applied to. |
+| `lora` | LORA_MODEL | Yes | - | The LoRA model to apply to the diffusion model. |
+| `strength_model` | FLOAT | Yes | -100.0 to 100.0 | How strongly to modify the diffusion model. This value can be negative (default: 1.0). |
+
+**Note:** When `strength_model` is set to 0, the node returns the original model without applying any LoRA modifications.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified diffusion model with LoRA weights applied. |
diff --git a/built-in-nodes/LoraSave.mdx b/built-in-nodes/LoraSave.mdx
new file mode 100644
index 000000000..6844f50e3
--- /dev/null
+++ b/built-in-nodes/LoraSave.mdx
@@ -0,0 +1,29 @@
+---
+title: "LoraSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraSave"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraSave/en.md)
+
+The LoraSave node extracts and saves LoRA (Low-Rank Adaptation) files from model differences. It can process diffusion model differences, text encoder differences, or both, converting them into LoRA format with specified rank and type. The resulting LoRA file is saved to the output directory for later use.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `filename_prefix` | STRING | Yes | - | The prefix for the output filename (default: "loras/ComfyUI_extracted_lora") |
+| `rank` | INT | Yes | 1-4096 | The rank value for the LoRA, controlling the size and complexity (default: 8) |
+| `lora_type` | COMBO | Yes | Multiple options available | The type of LoRA to create, with various available options |
+| `bias_diff` | BOOLEAN | Yes | - | Whether to include bias differences in the LoRA calculation (default: True) |
+| `model_diff` | MODEL | No | - | The ModelSubtract output to be converted to a lora |
+| `text_encoder_diff` | CLIP | No | - | The CLIPSubtract output to be converted to a lora |
+
+**Note:** At least one of `model_diff` or `text_encoder_diff` must be provided for the node to function. If both are omitted, the node will produce no output.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| - | - | This node saves a LoRA file to the output directory but does not return any data through the workflow |
diff --git a/built-in-nodes/LossGraphNode.mdx b/built-in-nodes/LossGraphNode.mdx
new file mode 100644
index 000000000..49811809e
--- /dev/null
+++ b/built-in-nodes/LossGraphNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "LossGraphNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LossGraphNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LossGraphNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LossGraphNode/en.md)
+
+The LossGraphNode creates a visual graph of training loss values over time and saves it as an image file. It takes loss data from training processes and generates a line chart showing how the loss changes across training steps. The resulting graph includes axis labels, min/max loss values, and is automatically saved to the temporary output directory with a timestamp.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `loss` | LOSS | Yes | Multiple options available | The loss data containing loss values to plot (default: empty dictionary) |
+| `filename_prefix` | STRING | Yes | - | The prefix for the output image filename (default: "loss_graph") |
+
+**Note:** The `loss` parameter requires a valid loss dictionary containing a "loss" key with loss values. The node automatically scales the loss values to fit the graph dimensions and generates a line plot showing the loss progression over training steps.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `ui.images` | IMAGE | The generated loss graph image saved to the temporary directory |
diff --git a/built-in-nodes/LotusConditioning.mdx b/built-in-nodes/LotusConditioning.mdx
new file mode 100644
index 000000000..1dbe25fed
--- /dev/null
+++ b/built-in-nodes/LotusConditioning.mdx
@@ -0,0 +1,22 @@
+---
+title: "LotusConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LotusConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LotusConditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LotusConditioning/en.md)
+
+The LotusConditioning node provides pre-computed conditioning embeddings for the Lotus model. It uses a frozen encoder with null conditioning and returns hardcoded prompt embeddings to achieve parity with the reference implementation without requiring inference or loading large tensor files. This node outputs a fixed conditioning tensor that can be used directly in the generation pipeline.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| *No inputs* | - | - | - | This node does not accept any input parameters. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | The pre-computed conditioning embeddings for the Lotus model, containing fixed prompt embeddings and an empty dictionary. |
diff --git a/built-in-nodes/LtxvApiImageToVideo.mdx b/built-in-nodes/LtxvApiImageToVideo.mdx
new file mode 100644
index 000000000..d8a59e1f8
--- /dev/null
+++ b/built-in-nodes/LtxvApiImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "LtxvApiImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LtxvApiImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LtxvApiImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LtxvApiImageToVideo/en.md)
+
+The LTXV Image To Video node generates a professional-quality video from a single starting image. It uses an external API to create a video sequence based on your text prompt, allowing you to customize the duration, resolution, and frame rate.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | First frame to be used for the video. |
+| `model` | COMBO | Yes | `"LTX-2 (Fast)"`<br />`"LTX-2 (Quality)"` | The AI model to use for video generation. The "Fast" model is optimized for speed, while the "Quality" model prioritizes visual fidelity. |
+| `prompt` | STRING | Yes | - | A text description that guides the content and motion of the generated video. |
+| `duration` | COMBO | Yes | `6`<br />`8`<br />`10`<br />`12`<br />`14`<br />`16`<br />`18`<br />`20` | The length of the video in seconds (default: 8). |
+| `resolution` | COMBO | Yes | `"1920x1080"`<br />`"2560x1440"`<br />`"3840x2160"` | The output resolution of the generated video. |
+| `fps` | COMBO | Yes | `25`<br />`50` | The frames per second for the video (default: 25). |
+| `generate_audio` | BOOLEAN | No | - | When true, the generated video will include AI-generated audio matching the scene (default: False). |
+
+**Important Constraints:**
+
+* The `image` input must contain exactly one image.
+* The `prompt` must be between 1 and 10,000 characters long.
+* If you select a `duration` longer than 10 seconds, you must use the **"LTX-2 (Fast)"** model, a **"1920x1080"** resolution, and **25** FPS. This combination is required for longer videos.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/LtxvApiTextToVideo.mdx b/built-in-nodes/LtxvApiTextToVideo.mdx
new file mode 100644
index 000000000..d655f2951
--- /dev/null
+++ b/built-in-nodes/LtxvApiTextToVideo.mdx
@@ -0,0 +1,32 @@
+---
+title: "LtxvApiTextToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LtxvApiTextToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LtxvApiTextToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LtxvApiTextToVideo/en.md)
+
+The LTXV Text To Video node generates professional-quality videos from a text description. It connects to an external API to create videos with customizable duration, resolution, and frame rate. You can also choose to have AI-generated audio added to the video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"LTX-2 (Fast)"`<br />`"LTX-2 (Quality)"`<br />`"LTX-2 (Turbo)"` | The AI model to use for video generation. The available models are mapped from the source code's `MODELS_MAP`. |
+| `prompt` | STRING | Yes | - | The text description that the AI will use to generate the video. This field supports multiple lines of text. |
+| `duration` | COMBO | Yes | `6`<br />`8`<br />`10`<br />`12`<br />`14`<br />`16`<br />`18`<br />`20` | The length of the generated video in seconds (default: 8). |
+| `resolution` | COMBO | Yes | `"1920x1080"`<br />`"2560x1440"`<br />`"3840x2160"` | The pixel dimensions (width x height) of the output video. |
+| `fps` | COMBO | Yes | `25`<br />`50` | The frames per second for the video (default: 25). |
+| `generate_audio` | BOOLEAN | No | - | When enabled, the generated video will include AI-generated audio matching the scene (default: False). |
+
+**Important Constraints:**
+
+* The `prompt` must be between 1 and 10,000 characters long.
+* If you select a `duration` greater than 10 seconds, you must also use the `"LTX-2 (Fast)"` model, a resolution of `"1920x1080"`, and an `fps` of `25`. This combination is required for longer videos.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/LumaConceptsNode.mdx b/built-in-nodes/LumaConceptsNode.mdx
new file mode 100644
index 000000000..078288824
--- /dev/null
+++ b/built-in-nodes/LumaConceptsNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "LumaConceptsNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaConceptsNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaConceptsNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaConceptsNode/en.md)
+
+Holds one or more Camera Concepts for use with Luma Text to Video and Luma Image to Video nodes. This node allows you to select up to four camera concepts and optionally combine them with existing concept chains.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `concept1` | STRING | Yes | Multiple options available<br />Includes "None" option | First camera concept selection from available Luma concepts |
+| `concept2` | STRING | Yes | Multiple options available<br />Includes "None" option | Second camera concept selection from available Luma concepts |
+| `concept3` | STRING | Yes | Multiple options available<br />Includes "None" option | Third camera concept selection from available Luma concepts |
+| `concept4` | STRING | Yes | Multiple options available<br />Includes "None" option | Fourth camera concept selection from available Luma concepts |
+| `luma_concepts` | LUMA_CONCEPTS | No | N/A | Optional Camera Concepts to add to the ones chosen here |
+
+**Note:** All concept parameters (`concept1` through `concept4`) can be set to "None" if you don't want to use all four concept slots. The node will merge any provided `luma_concepts` with the selected concepts to create a combined concept chain.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `luma_concepts` | LUMA_CONCEPTS | Combined camera concept chain containing all selected concepts |
diff --git a/built-in-nodes/LumaImageModifyNode.mdx b/built-in-nodes/LumaImageModifyNode.mdx
new file mode 100644
index 000000000..b2f319a3f
--- /dev/null
+++ b/built-in-nodes/LumaImageModifyNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "LumaImageModifyNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaImageModifyNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaImageModifyNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageModifyNode/en.md)
+
+Modifies images synchronously based on prompt and aspect ratio. This node takes an input image and transforms it according to the provided text prompt while maintaining the original image's aspect ratio.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be modified |
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: "") |
+| `image_weight` | FLOAT | No | 0.0-0.98 | Weight of the image; the closer to 1.0, the less the image will be modified (default: 0.1) |
+| `model` | MODEL | Yes | Multiple options available | The Luma model to use for image modification |
+| `seed` | INT | No | 0-18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The modified image generated by the Luma model |
diff --git a/built-in-nodes/LumaImageNode.mdx b/built-in-nodes/LumaImageNode.mdx
new file mode 100644
index 000000000..a0c53a762
--- /dev/null
+++ b/built-in-nodes/LumaImageNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "LumaImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageNode/en.md)
+
+Generates images synchronously based on prompt and aspect ratio. This node creates images using text descriptions and allows you to control the image dimensions and style through various reference inputs.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: empty string) |
+| `model` | COMBO | Yes | Multiple options available | Model selection for image generation |
+| `aspect_ratio` | COMBO | Yes | Multiple options available | Aspect ratio for the generated image (default: 16:9 ratio) |
+| `seed` | INT | Yes | 0 to 18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0) |
+| `style_image_weight` | FLOAT | No | 0.0 to 1.0 | Weight of style image. Ignored if no style_image provided (default: 1.0) |
+| `image_luma_ref` | LUMA_REF | No | - | Luma Reference node connection to influence generation with input images; up to 4 images can be considered |
+| `style_image` | IMAGE | No | - | Style reference image; only 1 image will be used |
+| `character_image` | IMAGE | No | - | Character reference images; can be a batch of multiple, up to 4 images can be considered |
+
+**Parameter Constraints:**
+
+- The `image_luma_ref` parameter can accept up to 4 reference images
+- The `character_image` parameter can accept up to 4 character reference images
+- The `style_image` parameter accepts only 1 style reference image
+- The `style_image_weight` parameter is only used when `style_image` is provided
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image based on the input parameters |
diff --git a/built-in-nodes/LumaImageToVideoNode.mdx b/built-in-nodes/LumaImageToVideoNode.mdx
new file mode 100644
index 000000000..edf7c68ec
--- /dev/null
+++ b/built-in-nodes/LumaImageToVideoNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "LumaImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageToVideoNode/en.md)
+
+Generates videos synchronously based on prompt, input images, and output_size. This node creates videos using the Luma API by providing text prompts and optional starting/ending images to define the video content and structure.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the video generation (default: "") |
+| `model` | COMBO | Yes | Multiple options available | Selects the video generation model from available Luma models |
+| `resolution` | COMBO | Yes | Multiple options available | Output resolution for the generated video (default: 540p) |
+| `duration` | COMBO | Yes | Multiple options available | Duration of the generated video |
+| `loop` | BOOLEAN | Yes | - | Whether the generated video should loop (default: False) |
+| `seed` | INT | Yes | 0 to 18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. (default: 0) |
+| `first_image` | IMAGE | No | - | First frame of generated video. (optional) |
+| `last_image` | IMAGE | No | - | Last frame of generated video. (optional) |
+| `luma_concepts` | CUSTOM | No | - | Optional Camera Concepts to dictate camera motion via the Luma Concepts node. (optional) |
+
+**Note:** At least one of `first_image` or `last_image` must be provided. The node will raise an exception if both are missing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/LumaReferenceNode.mdx b/built-in-nodes/LumaReferenceNode.mdx
new file mode 100644
index 000000000..81393575e
--- /dev/null
+++ b/built-in-nodes/LumaReferenceNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "LumaReferenceNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaReferenceNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaReferenceNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaReferenceNode/en.md)
+
+This node holds an image and weight value for use with the Luma Generate Image node. It creates a reference chain that can be passed to other Luma nodes to influence image generation. The node can either start a new reference chain or add to an existing one.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | Image to use as reference. |
+| `weight` | FLOAT | Yes | 0.0 - 1.0 | Weight of image reference (default: 1.0). |
+| `luma_ref` | LUMA_REF | No | - | Optional existing Luma reference chain to add to. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `luma_ref` | LUMA_REF | The Luma reference chain containing the image and weight. |
diff --git a/built-in-nodes/LumaVideoNode.mdx b/built-in-nodes/LumaVideoNode.mdx
new file mode 100644
index 000000000..2751e0fdc
--- /dev/null
+++ b/built-in-nodes/LumaVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "LumaVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaVideoNode/en.md)
+
+Generates videos synchronously based on prompt and output settings. This node creates video content using text descriptions and various generation parameters, producing the final video output once the generation process is complete.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the video generation (default: empty string) |
+| `model` | COMBO | Yes | Multiple options available | The video generation model to use |
+| `aspect_ratio` | COMBO | Yes | Multiple options available | The aspect ratio for the generated video (default: 16:9) |
+| `resolution` | COMBO | Yes | Multiple options available | The output resolution for the video (default: 540p) |
+| `duration` | COMBO | Yes | Multiple options available | The duration of the generated video |
+| `loop` | BOOLEAN | Yes | - | Whether the video should loop (default: False) |
+| `seed` | INT | Yes | 0 to 18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0) |
+| `luma_concepts` | CUSTOM | No | - | Optional Camera Concepts to dictate camera motion via the Luma Concepts node |
+
+**Note:** When using the `ray_1_6` model, the `duration` and `resolution` parameters are automatically set to None and do not affect the generation.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/MagnificImageRelightNode.mdx b/built-in-nodes/MagnificImageRelightNode.mdx
new file mode 100644
index 000000000..5acf4fe3c
--- /dev/null
+++ b/built-in-nodes/MagnificImageRelightNode.mdx
@@ -0,0 +1,42 @@
+---
+title: "MagnificImageRelightNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageRelightNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageRelightNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageRelightNode/en.md)
+
+The Magnific Image Relight node adjusts the lighting of an input image. It can apply stylistic lighting based on a text prompt or transfer the lighting characteristics from an optional reference image. The node offers various controls for fine-tuning the brightness, contrast, and overall mood of the final output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | N/A | The image to relight. Exactly one image is required. Minimum dimensions are 160x160 pixels. Aspect ratio must be between 1:3 and 3:1. |
+| `prompt` | STRING | No | N/A | Descriptive guidance for lighting. Supports emphasis notation (1-1.4). Default is an empty string. |
+| `light_transfer_strength` | INT | Yes | 0 to 100 | Intensity of light transfer application. Default: 100. |
+| `style` | COMBO | Yes | `"standard"`<br />`"darker_but_realistic"`<br />`"clean"`<br />`"smooth"`<br />`"brighter"`<br />`"contrasted_n_hdr"`<br />`"just_composition"` | Stylistic output preference. |
+| `interpolate_from_original` | BOOLEAN | Yes | N/A | Restricts generation freedom to match original more closely. Default: False. |
+| `change_background` | BOOLEAN | Yes | N/A | Modifies background based on prompt/reference. Default: True. |
+| `preserve_details` | BOOLEAN | Yes | N/A | Maintains texture and fine details from original. Default: True. |
+| `advanced_settings` | DYNAMICCOMBO | Yes | `"disabled"`<br />`"enabled"` | Fine-tuning options for advanced lighting control. When set to `"enabled"`, additional parameters become available. |
+| `reference_image` | IMAGE | No | N/A | Optional reference image to transfer lighting from. If provided, exactly one image is required. Minimum dimensions are 160x160 pixels. Aspect ratio must be between 1:3 and 3:1. |
+
+**Note on Advanced Settings:** When `advanced_settings` is set to `"enabled"`, the following nested parameters become active:
+
+* `whites`: Adjusts the brightest tones in the image. Range: 0 to 100. Default: 50.
+* `blacks`: Adjusts the darkest tones in the image. Range: 0 to 100. Default: 50.
+* `brightness`: Overall brightness adjustment. Range: 0 to 100. Default: 50.
+* `contrast`: Contrast adjustment. Range: 0 to 100. Default: 50.
+* `saturation`: Color saturation adjustment. Range: 0 to 100. Default: 50.
+* `engine`: Processing engine selection. Options: `"automatic"`, `"balanced"`, `"cool"`, `"real"`, `"illusio"`, `"fairy"`, `"colorful_anime"`, `"hard_transform"`, `"softy"`.
+* `transfer_light_a`: The intensity of light transfer. Options: `"automatic"`, `"low"`, `"medium"`, `"normal"`, `"high"`, `"high_on_faces"`.
+* `transfer_light_b`: Also modifies light transfer intensity. Can be combined with the previous control for varied effects. Options: `"automatic"`, `"composition"`, `"straight"`, `"smooth_in"`, `"smooth_out"`, `"smooth_both"`, `"reverse_both"`, `"soft_in"`, `"soft_out"`, `"soft_mid"`, `"style_shift"`, `"strong_shift"`.
+* `fixed_generation`: Ensures consistent output with the same settings. Default: True.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The relit image. |
diff --git a/built-in-nodes/MagnificImageSkinEnhancerNode.mdx b/built-in-nodes/MagnificImageSkinEnhancerNode.mdx
new file mode 100644
index 000000000..91e0bdebb
--- /dev/null
+++ b/built-in-nodes/MagnificImageSkinEnhancerNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "MagnificImageSkinEnhancerNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageSkinEnhancerNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageSkinEnhancerNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageSkinEnhancerNode/en.md)
+
+The Magnific Image Skin Enhancer node applies specialized AI processing to portrait images to improve skin appearance. It offers three distinct modes for different enhancement goals: creative for artistic effects, faithful for preserving the original look, and flexible for targeted improvements like lighting or realism. The node uploads the image to an external API for processing and returns the enhanced result.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The portrait image to enhance. |
+| `sharpen` | INT | No | 0 to 100 | Sharpening intensity level (default: 0). |
+| `smart_grain` | INT | No | 0 to 100 | Smart grain intensity level (default: 2). |
+| `mode` | COMBO | Yes | `"creative"`<br />`"faithful"`<br />`"flexible"` | The processing mode to use. `"creative"` is for artistic enhancement, `"faithful"` for preserving the original appearance, and `"flexible"` for targeted optimization. |
+| `skin_detail` | INT | No | 0 to 100 | Skin detail enhancement level. This input is only available and required when the `mode` is set to `"faithful"` (default: 80). |
+| `optimized_for` | COMBO | No | `"enhance_skin"`<br />`"improve_lighting"`<br />`"enhance_everything"`<br />`"transform_to_real"`<br />`"no_make_up"` | Enhancement optimization target. This input is only available and required when the `mode` is set to `"flexible"`. |
+
+**Constraints:**
+
+* The node accepts exactly one input image.
+* The input image must have a minimum height and width of 160 pixels.
+* The `skin_detail` parameter is only active when `mode` is set to `"faithful"`.
+* The `optimized_for` parameter is only active when `mode` is set to `"flexible"`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The enhanced portrait image. |
diff --git a/built-in-nodes/MagnificImageStyleTransferNode.mdx b/built-in-nodes/MagnificImageStyleTransferNode.mdx
new file mode 100644
index 000000000..4c8f91144
--- /dev/null
+++ b/built-in-nodes/MagnificImageStyleTransferNode.mdx
@@ -0,0 +1,39 @@
+---
+title: "MagnificImageStyleTransferNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageStyleTransferNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageStyleTransferNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageStyleTransferNode/en.md)
+
+This node applies the visual style from a reference image to your input image. It uses an external AI service to process the images, allowing you to control the strength of the style transfer and the preservation of the original image's structure.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The image to apply style transfer to. |
+| `reference_image` | IMAGE | Yes | - | The reference image to extract style from. |
+| `prompt` | STRING | No | - | An optional text prompt to guide the style transfer. |
+| `style_strength` | INT | No | 0 to 100 | Percentage of style strength (default: 100). |
+| `structure_strength` | INT | No | 0 to 100 | Maintains the structure of the original image (default: 50). |
+| `flavor` | COMBO | No | "faithful"<br />"gen_z"<br />"psychedelia"<br />"detaily"<br />"clear"<br />"donotstyle"<br />"donotstyle_sharp" | Style transfer flavor. |
+| `engine` | COMBO | No | "balanced"<br />"definio"<br />"illusio"<br />"3d_cartoon"<br />"colorful_anime"<br />"caricature"<br />"real"<br />"super_real"<br />"softy" | Processing engine selection. |
+| `portrait_mode` | COMBO | No | "disabled"<br />"enabled" | Enable portrait mode for facial enhancements. |
+| `portrait_style` | COMBO | No | "standard"<br />"pop"<br />"super_pop" | Visual style applied to portrait images. This input is only available when `portrait_mode` is set to "enabled". |
+| `portrait_beautifier` | COMBO | No | "none"<br />"beautify_face"<br />"beautify_face_max" | Facial beautification intensity on portraits. This input is only available when `portrait_mode` is set to "enabled". |
+| `fixed_generation` | BOOLEAN | No | - | When disabled, expect each generation to introduce a degree of randomness, leading to more diverse outcomes (default: True). |
+
+**Constraints:**
+
+* Exactly one `image` and one `reference_image` are required.
+* Both images must have an aspect ratio between 1:3 and 3:1.
+* Both images must have a minimum height and width of 160 pixels.
+* The `portrait_style` and `portrait_beautifier` parameters are only active and required when `portrait_mode` is set to "enabled".
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resulting image after style transfer has been applied. |
diff --git a/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx b/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx
new file mode 100644
index 000000000..9c608e9a8
--- /dev/null
+++ b/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx
@@ -0,0 +1,38 @@
+---
+title: "MagnificImageUpscalerCreativeNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageUpscalerCreativeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageUpscalerCreativeNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageUpscalerCreativeNode/en.md)
+
+This node uses the Magnific AI service to upscale and creatively enhance an image. It allows you to guide the enhancement with a text prompt, choose a specific style to optimize for, and control various aspects of the creative process like detail, resemblance to the original, and stylization strength. The node outputs an upscaled image at your chosen factor (2x, 4x, 8x, or 16x), with a maximum output size of 25.3 megapixels.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be upscaled and enhanced. |
+| `prompt` | STRING | No | - | A text description to guide the creative enhancement of the image. This is optional (default: empty). |
+| `scale_factor` | COMBO | Yes | `"2x"`<br />`"4x"`<br />`"8x"`<br />`"16x"` | The factor by which to upscale the image's dimensions. |
+| `optimized_for` | COMBO | Yes | `"standard"`<br />`"soft_portraits"`<br />`"hard_portraits"`<br />`"art_n_illustration"`<br />`"videogame_assets"`<br />`"nature_n_landscapes"`<br />`"films_n_photography"`<br />`"3d_renders"`<br />`"science_fiction_n_horror"` | The style or content type to optimize the enhancement process for. |
+| `creativity` | INT | No | -10 to 10 | Controls the level of creative interpretation applied to the image (default: 0). |
+| `hdr` | INT | No | -10 to 10 | The level of definition and detail (default: 0). |
+| `resemblance` | INT | No | -10 to 10 | The level of resemblance to the original image (default: 0). |
+| `fractality` | INT | No | -10 to 10 | The strength of the prompt and intricacy per square pixel (default: 0). |
+| `engine` | COMBO | Yes | `"automatic"`<br />`"magnific_illusio"`<br />`"magnific_sharpy"`<br />`"magnific_sparkle"` | The specific AI engine to use for processing. |
+| `auto_downscale` | BOOLEAN | No | - | When enabled, the node will automatically downscale the input image if the requested upscale would exceed the maximum allowed output size of 25.3 megapixels (default: False). |
+
+**Constraints:**
+
+* The input `image` must be exactly one image.
+* The input image must have a minimum height and width of 160 pixels.
+* The input image's aspect ratio must be between 1:3 and 3:1.
+* The final output size (input dimensions multiplied by the `scale_factor`) cannot exceed 25,300,000 pixels. If `auto_downscale` is disabled and this limit would be exceeded, the node will raise an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The creatively enhanced and upscaled output image. |
diff --git a/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx b/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx
new file mode 100644
index 000000000..6f9ed2a25
--- /dev/null
+++ b/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx
@@ -0,0 +1,30 @@
+---
+title: "MagnificImageUpscalerPreciseV2Node - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageUpscalerPreciseV2Node node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageUpscalerPreciseV2Node"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageUpscalerPreciseV2Node/en.md)
+
+The Magnific Image Upscale (Precise V2) node performs high-fidelity image upscaling with precise control over sharpness, grain, and detail enhancement. It processes images through an external API, supporting up to a maximum output resolution of 10060×10060 pixels. The node offers different processing styles and can automatically downscale the input if the requested output would exceed the maximum allowed size.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be upscaled. Exactly one image is required. Minimum dimensions are 160x160 pixels. The aspect ratio must be between 1:3 and 3:1. |
+| `scale_factor` | STRING | Yes | `"2x"`<br />`"4x"`<br />`"8x"`<br />`"16x"` | The desired upscaling multiplier. |
+| `flavor` | STRING | Yes | `"sublime"`<br />`"photo"`<br />`"photo_denoiser"` | The processing style. "sublime" is for general use, "photo" is optimized for photographs, and "photo_denoiser" is for noisy photos. |
+| `sharpen` | INT | No | 0 to 100 | Controls the intensity of image sharpening to increase edge definition and clarity. Higher values produce a sharper result. Default: 7. |
+| `smart_grain` | INT | No | 0 to 100 | Adds intelligent grain or texture enhancement to prevent the upscaled image from looking too smooth or artificial. Default: 7. |
+| `ultra_detail` | INT | No | 0 to 100 | Controls the amount of fine detail, textures, and micro-details added during the upscaling process. Default: 30. |
+| `auto_downscale` | BOOLEAN | No | - | When enabled, the node will automatically downscale the input image if the calculated output dimensions would exceed the maximum allowed resolution of 10060x10060 pixels. This helps prevent errors but may affect quality. Default: False. |
+
+**Note:** If `auto_downscale` is disabled and the requested output size (input dimensions × `scale_factor`) exceeds 10060x10060 pixels, the node will raise an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resulting upscaled image. |
diff --git a/built-in-nodes/Mahiro.mdx b/built-in-nodes/Mahiro.mdx
new file mode 100644
index 000000000..473a7d699
--- /dev/null
+++ b/built-in-nodes/Mahiro.mdx
@@ -0,0 +1,22 @@
+---
+title: "Mahiro - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Mahiro node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Mahiro"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Mahiro/en.md)
+
+The Mahiro node modifies the guidance function to focus more on the direction of the positive prompt rather than the difference between positive and negative prompts. It creates a patched model that applies a custom guidance scaling approach using cosine similarity between normalized conditional and unconditional denoised outputs. This experimental node helps steer the generation more strongly toward the positive prompt's intended direction.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | | The model to be patched with the modified guidance function |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | The modified model with the Mahiro guidance function applied |
diff --git a/built-in-nodes/MakeTrainingDataset.mdx b/built-in-nodes/MakeTrainingDataset.mdx
new file mode 100644
index 000000000..f48b9596b
--- /dev/null
+++ b/built-in-nodes/MakeTrainingDataset.mdx
@@ -0,0 +1,30 @@
+---
+title: "MakeTrainingDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MakeTrainingDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MakeTrainingDataset"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MakeTrainingDataset/en.md)
+
+This node prepares data for training by encoding images and text. It takes a list of images and a corresponding list of text captions, then uses a VAE model to convert the images into latent representations and a CLIP model to convert the text into conditioning data. The resulting paired latents and conditioning are output as lists, ready for use in training workflows.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | N/A | List of images to encode. |
+| `vae` | VAE | Yes | N/A | VAE model for encoding images to latents. |
+| `clip` | CLIP | Yes | N/A | CLIP model for encoding text to conditioning. |
+| `texts` | STRING | No | N/A | List of text captions. Can be length n (matching images), 1 (repeated for all), or omitted (uses empty string). |
+
+**Parameter Constraints:**
+
+* The number of items in the `texts` list must be 0, 1, or exactly match the number of items in the `images` list. If it is 0, an empty string is used for all images. If it is 1, that single text is repeated for all images.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `latents` | LATENT | List of latent dicts. |
+| `conditioning` | CONDITIONING | List of conditioning lists. |
diff --git a/built-in-nodes/ManualSigmas.mdx b/built-in-nodes/ManualSigmas.mdx
new file mode 100644
index 000000000..81e28640e
--- /dev/null
+++ b/built-in-nodes/ManualSigmas.mdx
@@ -0,0 +1,22 @@
+---
+title: "ManualSigmas - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ManualSigmas node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ManualSigmas"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ManualSigmas/en.md)
+
+The ManualSigmas node allows you to manually define a custom sequence of noise levels (sigmas) for the sampling process. You input a list of numbers as a string, and the node converts them into a tensor that can be used by other sampling nodes. This is useful for testing or creating specific noise schedules.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `sigmas` | STRING | Yes | Any comma or space-separated numbers | A string containing the sigma values. The node will extract all numbers from this string. For example, "1, 0.5, 0.1" or "1 0.5 0.1". The default value is "1, 0.5". |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | The tensor containing the sequence of sigma values extracted from the input string. |
diff --git a/built-in-nodes/MarkdownNote.mdx b/built-in-nodes/MarkdownNote.mdx
new file mode 100644
index 000000000..e1597ada5
--- /dev/null
+++ b/built-in-nodes/MarkdownNote.mdx
@@ -0,0 +1,14 @@
+---
+title: "MarkdownNote - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MarkdownNote node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MarkdownNote"
+icon: "circle"
+mode: wide
+---
+Node to add annotations to a workflow. It supports text formatting using Markdown syntax.
+
+## Inputs
+
+## Outputs
+
+The node doesn't have outputs.
diff --git a/built-in-nodes/MaskComposite.mdx b/built-in-nodes/MaskComposite.mdx
new file mode 100644
index 000000000..3248976cc
--- /dev/null
+++ b/built-in-nodes/MaskComposite.mdx
@@ -0,0 +1,25 @@
+---
+title: "MaskComposite - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MaskComposite node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MaskComposite"
+icon: "circle"
+mode: wide
+---
+
+This node specializes in combining two mask inputs through a variety of operations such as addition, subtraction, and logical operations, to produce a new, modified mask. It abstractly handles the manipulation of mask data to achieve complex masking effects, serving as a crucial component in mask-based image editing and processing workflows.
+
+## Inputs
+
+| Parameter    | Data Type | Description                                                                                                                                      |
+| ------------ | ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `destination`| MASK        | The primary mask that will be modified based on the operation with the source mask. It plays a central role in the composite operation, acting as the base for modifications. |
+| `source`     | MASK        | The secondary mask that will be used in conjunction with the destination mask to perform the specified operation, influencing the final output mask. |
+| `x`          | INT         | The horizontal offset at which the source mask will be applied to the destination mask, affecting the positioning of the composite result.       |
+| `y`          | INT         | The vertical offset at which the source mask will be applied to the destination mask, affecting the positioning of the composite result.         |
+| `operation`  | COMBO[STRING]| Specifies the type of operation to apply between the destination and source masks, such as 'add', 'subtract', or logical operations, determining the nature of the composite effect. |
+
+## Outputs
+
+| Parameter | Data Type | Description                                                                 |
+| --------- | ------------ | ---------------------------------------------------------------------------- |
+| `mask`    | MASK        | The resulting mask after applying the specified operation between the destination and source masks, representing the composite outcome. |
diff --git a/built-in-nodes/MaskPreview.mdx b/built-in-nodes/MaskPreview.mdx
new file mode 100644
index 000000000..01329e7a3
--- /dev/null
+++ b/built-in-nodes/MaskPreview.mdx
@@ -0,0 +1,25 @@
+---
+title: "MaskPreview - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MaskPreview node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MaskPreview"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MaskPreview/en.md)
+
+The MaskPreview node generates a visual preview of a mask by converting it into a 3-channel image format and saving it as a temporary file. It takes a mask input and reshapes it into a format suitable for image display, then saves the result to the temporary directory with a random filename prefix. This allows users to visually inspect mask data during workflow execution.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `mask` | MASK | Yes | - | The mask data to be previewed and converted to image format |
+| `filename_prefix` | STRING | No | - | Prefix for the output filename (default: "ComfyUI") |
+| `prompt` | PROMPT | No | - | Prompt information for metadata (automatically provided) |
+| `extra_pnginfo` | EXTRA_PNGINFO | No | - | Additional PNG information for metadata (automatically provided) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `ui` | DICT | Contains the preview image information and metadata for display |
diff --git a/built-in-nodes/MaskToImage.mdx b/built-in-nodes/MaskToImage.mdx
new file mode 100644
index 000000000..17f35a87d
--- /dev/null
+++ b/built-in-nodes/MaskToImage.mdx
@@ -0,0 +1,21 @@
+---
+title: "MaskToImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MaskToImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MaskToImage"
+icon: "circle"
+mode: wide
+---
+
+The `MaskToImage` node is designed to convert a mask into an image format. This transformation allows for the visualization and further processing of masks as images, facilitating a bridge between mask-based operations and image-based applications.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | `MASK`      | The mask input is essential for the conversion process, serving as the source data that will be transformed into an image format. This input dictates the shape and content of the resulting image. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The output is an image representation of the input mask, enabling visual inspection and further image-based manipulations. |
diff --git a/built-in-nodes/MergeImageLists.mdx b/built-in-nodes/MergeImageLists.mdx
new file mode 100644
index 000000000..71e4d220d
--- /dev/null
+++ b/built-in-nodes/MergeImageLists.mdx
@@ -0,0 +1,24 @@
+---
+title: "MergeImageLists - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MergeImageLists node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MergeImageLists"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MergeImageLists/en.md)
+
+The Merge Image Lists node combines multiple separate lists of images into a single, continuous list. It works by taking all the images from each connected input and appending them together in the order they are received. This is useful for organizing or batching images from different sources for further processing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | A list of images to be merged. This input can accept multiple connections, and each connected list will be concatenated into the final output. |
+
+**Note:** This node is designed to receive multiple inputs. You can connect several image lists to the single `images` input socket. The node will automatically concatenate all images from all connected lists into one output list.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `images` | IMAGE | The single, merged list containing all images from every connected input list. |
diff --git a/built-in-nodes/MergeTextLists.mdx b/built-in-nodes/MergeTextLists.mdx
new file mode 100644
index 000000000..a102132e5
--- /dev/null
+++ b/built-in-nodes/MergeTextLists.mdx
@@ -0,0 +1,24 @@
+---
+title: "MergeTextLists - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MergeTextLists node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MergeTextLists"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MergeTextLists/en.md)
+
+This node merges multiple text lists into a single, combined list. It is designed to receive text inputs as lists and concatenates them together. The node logs the total number of texts in the merged list.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `texts` | STRING | Yes | N/A | The text lists to be merged. Multiple lists can be connected to the input, and they will be concatenated into one. |
+
+**Note:** This node is configured as a group process (`is_group_process = True`), meaning it automatically handles multiple list inputs by concatenating them before the main processing function runs.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `texts` | STRING | The single, merged list containing all the input texts. |
diff --git a/built-in-nodes/MeshyAnimateModelNode.mdx b/built-in-nodes/MeshyAnimateModelNode.mdx
new file mode 100644
index 000000000..1d84fa123
--- /dev/null
+++ b/built-in-nodes/MeshyAnimateModelNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "MeshyAnimateModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyAnimateModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyAnimateModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyAnimateModelNode/en.md)
+
+This node applies a specific animation to a 3D character model that has already been rigged using the Meshy service. It takes a task ID from a previous rigging operation and an action ID to select the desired animation from the library. The node then processes the request and returns the animated model in both GLB and FBX file formats.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `rig_task_id` | STRING | Yes | N/A | The unique task ID from a previously completed Meshy character rigging operation. |
+| `action_id` | INT | Yes | 0 to 696 | The ID number of the animation action to apply. Visit [https://docs.meshy.ai/en/api/animation-library](https://docs.meshy.ai/en/api/animation-library) for a list of available values. (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | A string identifier for the animated model. This output is provided for backward compatibility only. |
+| `GLB` | FILE3DGLB | The animated 3D model file in GLB format. |
+| `FBX` | FILE3DFBX | The animated 3D model file in FBX format. |
diff --git a/built-in-nodes/MeshyImageToModelNode.mdx b/built-in-nodes/MeshyImageToModelNode.mdx
new file mode 100644
index 000000000..581c0c475
--- /dev/null
+++ b/built-in-nodes/MeshyImageToModelNode.mdx
@@ -0,0 +1,42 @@
+---
+title: "MeshyImageToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyImageToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyImageToModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyImageToModelNode/en.md)
+
+The Meshy: Image to Model node uses the Meshy API to generate a 3D model from a single input image. It uploads your image, submits a processing task, and returns the generated 3D model files (GLB and FBX) along with the task ID for reference.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"latest"` | Specifies the AI model version to use for generation. |
+| `image` | IMAGE | Yes | - | The input image to convert into a 3D model. |
+| `should_remesh` | DYNAMIC COMBO | Yes | `"true"`<br />`"false"` | Determines if the generated mesh should be processed. When set to `"false"`, the node returns an unprocessed triangular mesh. |
+| `topology` | COMBO | No* | `"triangle"`<br />`"quad"` | The target polygon topology for the remeshed model. This input is only available and required when `should_remesh` is set to `"true"`. |
+| `target_polycount` | INT | No* | 100 - 300000 | The target number of polygons for the remeshed model. This input is only available and required when `should_remesh` is set to `"true"`. The default value is 300000. |
+| `symmetry_mode` | COMBO | Yes | `"auto"`<br />`"on"`<br />`"off"` | Controls the symmetry applied to the generated 3D model. |
+| `should_texture` | DYNAMIC COMBO | Yes | `"true"`<br />`"false"` | Determines whether textures are generated for the model. Setting it to `"false"` skips the texture phase and returns a mesh without textures. |
+| `enable_pbr` | BOOLEAN | No* | - | When `should_texture` is `"true"`, this option generates PBR maps (metallic, roughness, normal) in addition to the base color. The default value is `False`. |
+| `texture_prompt` | STRING | No* | - | A text prompt to guide the texturing process (maximum 600 characters). This input is only available when `should_texture` is `"true"`. It cannot be used at the same time as `texture_image`. |
+| `texture_image` | IMAGE | No* | - | An image to guide the texturing process. This input is only available when `should_texture` is `"true"`. It cannot be used at the same time as `texture_prompt`. |
+| `pose_mode` | COMBO | Yes | `""`<br />`"A-pose"`<br />`"T-pose"` | Specifies the pose mode for the generated model. |
+| `seed` | INT | Yes | 0 - 2147483647 | A seed value for the generation process. The results are non-deterministic regardless of the seed value. The default value is 0. |
+
+**Note on Parameter Constraints:**
+
+* The `topology` and `target_polycount` inputs are only required when `should_remesh` is set to `"true"`.
+* The `enable_pbr`, `texture_prompt`, and `texture_image` inputs are only available when `should_texture` is set to `"true"`.
+* You cannot use `texture_prompt` and `texture_image` at the same time. If both are provided when `should_texture` is `"true"`, the node will raise an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The filename of the generated GLB model. (Maintained for backward compatibility). |
+| `meshy_task_id` | MESHY_TASK_ID | The unique identifier for the Meshy API task, which can be used for reference or troubleshooting. |
+| `GLB` | FILE3DGLB | The generated 3D model in the GLB file format. |
+| `FBX` | FILE3DFBX | The generated 3D model in the FBX file format. |
diff --git a/built-in-nodes/MeshyMultiImageToModelNode.mdx b/built-in-nodes/MeshyMultiImageToModelNode.mdx
new file mode 100644
index 000000000..8c89f2155
--- /dev/null
+++ b/built-in-nodes/MeshyMultiImageToModelNode.mdx
@@ -0,0 +1,43 @@
+---
+title: "MeshyMultiImageToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyMultiImageToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyMultiImageToModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyMultiImageToModelNode/en.md)
+
+This node uses the Meshy API to generate a 3D model from multiple input images. It uploads the provided images, submits a processing task, and returns the resulting 3D model files (GLB and FBX) along with the task ID for reference.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+| :--- | :--- | :--- | :--- | :--- |
+| `model` | COMBO | Yes | `"latest"` | Specifies the AI model version to use. |
+| `images` | IMAGE | Yes | 2 to 4 images | A set of images used to generate the 3D model. You must provide between 2 and 4 images. |
+| `should_remesh` | COMBO | Yes | `"true"`<br />`"false"` | Determines if the generated mesh should be processed. When set to `"false"`, the node returns an unprocessed triangular mesh. |
+| `topology` | COMBO | No | `"triangle"`<br />`"quad"` | The target polygon type for the remeshed output. This parameter is only available and required when `should_remesh` is set to `"true"`. |
+| `target_polycount` | INT | No | 100 to 300000 | The target number of polygons for the remeshed model (default: 300000). This parameter is only available when `should_remesh` is set to `"true"`. |
+| `symmetry_mode` | COMBO | Yes | `"auto"`<br />`"on"`<br />`"off"` | Controls whether symmetry is applied to the generated model. |
+| `should_texture` | COMBO | Yes | `"true"`<br />`"false"` | Determines whether textures are generated. Setting it to `"false"` skips the texture phase and returns a mesh without textures. |
+| `enable_pbr` | BOOLEAN | No | `True` / `False` | When `should_texture` is `"true"`, this option generates PBR Maps (metallic, roughness, normal) in addition to the base color (default: `False`). |
+| `texture_prompt` | STRING | No | - | A text prompt to guide the texturing process (maximum 600 characters). Cannot be used at the same time as `texture_image`. This parameter is only available when `should_texture` is set to `"true"`. |
+| `texture_image` | IMAGE | No | - | An image to guide the texturing process. Only one of `texture_image` or `texture_prompt` may be used at the same time. This parameter is only available when `should_texture` is set to `"true"`. |
+| `pose_mode` | COMBO | Yes | `""`<br />`"A-pose"`<br />`"T-pose"` | Specifies the pose mode for the generated model. |
+| `seed` | INT | Yes | 0 to 2147483647 | A seed value for the generation process (default: 0). Results are non-deterministic regardless of the seed, but changing the seed can trigger the node to re-run. |
+
+**Parameter Constraints:**
+
+* You must provide between 2 and 4 images for the `images` input.
+* The `topology` and `target_polycount` parameters are only active when `should_remesh` is set to `"true"`.
+* The `enable_pbr`, `texture_prompt`, and `texture_image` parameters are only active when `should_texture` is set to `"true"`.
+* You cannot use `texture_prompt` and `texture_image` at the same time; they are mutually exclusive.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+| :--- | :--- | :--- |
+| `model_file` | STRING | The filename of the generated GLB model. This output is provided for backward compatibility. |
+| `meshy_task_id` | MESHY_TASK_ID | The unique identifier for the Meshy API task. |
+| `GLB` | FILE3DGLB | The generated 3D model in GLB format. |
+| `FBX` | FILE3DFBX | The generated 3D model in FBX format. |
diff --git a/built-in-nodes/MeshyRefineNode.mdx b/built-in-nodes/MeshyRefineNode.mdx
new file mode 100644
index 000000000..ff2ade2bb
--- /dev/null
+++ b/built-in-nodes/MeshyRefineNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "MeshyRefineNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyRefineNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyRefineNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRefineNode/en.md)
+
+The Meshy: Refine Draft Model node takes a previously generated 3D draft model and improves its quality, optionally adding textures. It submits a refinement task to the Meshy API and returns the final 3D model files once processing is complete.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"latest"` | Specifies the AI model to use for refinement. Currently, only the "latest" model is available. |
+| `meshy_task_id` | MESHY_TASK_ID | Yes | - | The unique task ID of the draft model you want to refine. |
+| `enable_pbr` | BOOLEAN | No | - | Generate PBR Maps (metallic, roughness, normal) in addition to the base color. Note: this should be set to false when using Sculpture style, as Sculpture style generates its own set of PBR maps. (default: `False`) |
+| `texture_prompt` | STRING | No | - | Provide a text prompt to guide the texturing process. Maximum 600 characters. Cannot be used at the same time as 'texture_image'. (default: empty string) |
+| `texture_image` | IMAGE | No | - | Only one of 'texture_image' or 'texture_prompt' may be used at the same time. (optional) |
+
+**Note:** The `texture_prompt` and `texture_image` inputs are mutually exclusive. You cannot provide both a text prompt and an image for texturing in the same operation.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The filename of the generated GLB model. (For backward compatibility only) |
+| `meshy_task_id` | MESHY_TASK_ID | The unique task ID for the submitted refinement job. |
+| `GLB` | FILE3DGLB | The final refined 3D model in GLB format. |
+| `FBX` | FILE3DFBX | The final refined 3D model in FBX format. |
diff --git a/built-in-nodes/MeshyRigModelNode.mdx b/built-in-nodes/MeshyRigModelNode.mdx
new file mode 100644
index 000000000..831226e87
--- /dev/null
+++ b/built-in-nodes/MeshyRigModelNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "MeshyRigModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyRigModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyRigModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRigModelNode/en.md)
+
+The Meshy: Rig Model node takes a 3D model task from Meshy and generates a rigged character model. It automatically creates a skeleton for the model, allowing it to be posed and animated. The node outputs the rigged model in both GLB and FBX file formats.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `meshy_task_id` | STRING | Yes | N/A | The unique task ID from a previous Meshy operation (e.g., text-to-3D or image-to-3D) that generated the model to be rigged. |
+| `height_meters` | FLOAT | Yes | 0.1 to 15.0 | The approximate height of the character model in meters. This aids in scaling and rigging accuracy (default: 1.7). |
+| `texture_image` | IMAGE | No | N/A | The model's UV-unwrapped base color texture image. |
+
+**Note:** The auto-rigging process is currently not suitable for untextured meshes, non-humanoid assets, or humanoid assets with unclear limb and body structure.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | A legacy output for backward compatibility, containing the filename of the GLB model. |
+| `rig_task_id` | STRING | The unique task ID for this rigging operation, which can be used to reference the result. |
+| `GLB` | FILE3DGLB | The rigged 3D character model saved in the GLB file format. |
+| `FBX` | FILE3DFBX | The rigged 3D character model saved in the FBX file format. |
diff --git a/built-in-nodes/MeshyTextToModelNode.mdx b/built-in-nodes/MeshyTextToModelNode.mdx
new file mode 100644
index 000000000..eaf6ac388
--- /dev/null
+++ b/built-in-nodes/MeshyTextToModelNode.mdx
@@ -0,0 +1,35 @@
+---
+title: "MeshyTextToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyTextToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyTextToModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextToModelNode/en.md)
+
+The Meshy: Text to Model node uses the Meshy API to generate a 3D model from a text description. It sends a request to the API with your prompt and settings, then waits for the generation to complete and downloads the resulting model files.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"latest"` | Specifies the AI model version to use. Currently, only the "latest" version is available. |
+| `prompt` | STRING | Yes | - | The text description of the 3D model you want to generate. Must be between 1 and 600 characters long. |
+| `style` | COMBO | Yes | `"realistic"`<br />`"sculpture"` | The artistic style for the generated 3D model. |
+| `should_remesh` | DYNAMIC COMBO | Yes | `"true"`<br />`"false"` | Controls whether the generated mesh is processed. When set to "false", the node returns an unprocessed triangular mesh. Selecting "true" reveals additional parameters for topology and polycount. |
+| `topology` | COMBO | No* | `"triangle"`<br />`"quad"` | The target polygon type for the remeshed model. This parameter is only available and required when `should_remesh` is set to "true". |
+| `target_polycount` | INT | No* | 100 - 300000 | The target number of polygons for the remeshed model. Default is 300000. This parameter is only available and required when `should_remesh` is set to "true". |
+| `symmetry_mode` | COMBO | Yes | `"auto"`<br />`"on"`<br />`"off"` | Controls symmetry in the generated model. |
+| `pose_mode` | COMBO | Yes | `""`<br />`"A-pose"`<br />`"T-pose"` | Specifies the pose mode for the generated model. An empty string means no specific pose is requested. |
+| `seed` | INT | Yes | 0 - 2147483647 | A seed value for generation. Setting this controls whether the node should re-run, but results are non-deterministic regardless of the seed value. Default is 0. |
+
+*Note: The `topology` and `target_polycount` parameters are conditionally required. They only appear and must be set when the `should_remesh` parameter is set to "true".
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The filename of the generated GLB model. This output is provided for backward compatibility. |
+| `meshy_task_id` | MESHY_TASK_ID | The unique identifier for the Meshy API task. |
+| `GLB` | FILE3DGLB | The generated 3D model file in GLB format. |
+| `FBX` | FILE3DFBX | The generated 3D model file in FBX format. |
diff --git a/built-in-nodes/MeshyTextureNode.mdx b/built-in-nodes/MeshyTextureNode.mdx
new file mode 100644
index 000000000..a842d008a
--- /dev/null
+++ b/built-in-nodes/MeshyTextureNode.mdx
@@ -0,0 +1,35 @@
+---
+title: "MeshyTextureNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyTextureNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyTextureNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextureNode/en.md)
+
+The Meshy: Texture Node applies AI-generated textures to a 3D model. It takes a task ID from a previous Meshy 3D generation or conversion node and uses either a text description or a reference image to create new textures for the model. The node outputs the textured model in GLB and FBX file formats.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"latest"` | The AI model version to use for texturing. Currently, only the "latest" version is available. |
+| `meshy_task_id` | MESHY_TASK_ID | Yes | - | The unique identifier (task ID) from a previous Meshy 3D generation or conversion task. This provides the base 3D model to be textured. |
+| `enable_original_uv` | BOOLEAN | No | - | When enabled (default: `True`), the node uses the original UV layout of the uploaded model, preserving any existing textures. If the model has no original UV, the output quality may be lower. |
+| `pbr` | BOOLEAN | No | - | Enables Physically Based Rendering (PBR) material output for the textured model (default: `False`). |
+| `text_style_prompt` | STRING | No | - | A text description of the desired texture style for the object. Maximum 600 characters. Cannot be used at the same time as `image_style`. |
+| `image_style` | IMAGE | No | - | A 2D reference image to guide the texturing process. Cannot be used at the same time as `text_style_prompt`. |
+
+**Parameter Constraints:**
+
+* You must provide either a `text_style_prompt` or an `image_style`, but you cannot provide both at the same time.
+* The `text_style_prompt` is limited to a maximum of 600 characters.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The filename of the generated GLB model. This output is provided for backward compatibility. |
+| `meshy_task_id` | MODEL_TASK_ID | The unique task identifier for this texturing job, which can be used to reference the result. |
+| `GLB` | FILE3DGLB | The textured 3D model saved in the GLB file format. |
+| `FBX` | FILE3DFBX | The textured 3D model saved in the FBX file format. |
diff --git a/built-in-nodes/MinimaxHailuoVideoNode.mdx b/built-in-nodes/MinimaxHailuoVideoNode.mdx
new file mode 100644
index 000000000..d0df74997
--- /dev/null
+++ b/built-in-nodes/MinimaxHailuoVideoNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "MinimaxHailuoVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MinimaxHailuoVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MinimaxHailuoVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxHailuoVideoNode/en.md)
+
+Generates videos from text prompts using the MiniMax Hailuo-02 model. You can optionally provide a starting image as the first frame to create a video that continues from that image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt_text` | STRING | Yes | - | Text prompt to guide the video generation. |
+| `seed` | INT | No | 0 to 18446744073709551615 | The random seed used for creating the noise (default: 0). |
+| `first_frame_image` | IMAGE | No | - | Optional image to use as the first frame to generate a video. |
+| `prompt_optimizer` | BOOLEAN | No | - | Optimize prompt to improve generation quality when needed (default: True). |
+| `duration` | COMBO | No | `6`<br />`10` | The length of the output video in seconds (default: 6). |
+| `resolution` | COMBO | No | `"768P"`<br />`"1080P"` | The dimensions of the video display. 1080p is 1920x1080, 768p is 1366x768 (default: "768P"). |
+
+**Note:** When using the MiniMax-Hailuo-02 model with 1080P resolution, the duration is limited to 6 seconds.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/MinimaxImageToVideoNode.mdx b/built-in-nodes/MinimaxImageToVideoNode.mdx
new file mode 100644
index 000000000..bff2ad93a
--- /dev/null
+++ b/built-in-nodes/MinimaxImageToVideoNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "MinimaxImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MinimaxImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MinimaxImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxImageToVideoNode/en.md)
+
+Generates videos synchronously based on an image and prompt, and optional parameters using MiniMax's API. This node takes an input image and text description to create a video sequence, with various model options and configuration settings available.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | Image to use as first frame of video generation |
+| `prompt_text` | STRING | Yes | - | Text prompt to guide the video generation (default: empty string) |
+| `model` | COMBO | Yes | "I2V-01-Director"<br />"I2V-01"<br />"I2V-01-live" | Model to use for video generation (default: "I2V-01") |
+| `seed` | INT | No | 0 to 18446744073709551615 | The random seed used for creating the noise (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video output |
diff --git a/built-in-nodes/MinimaxSubjectToVideoNode.mdx b/built-in-nodes/MinimaxSubjectToVideoNode.mdx
new file mode 100644
index 000000000..f258cc546
--- /dev/null
+++ b/built-in-nodes/MinimaxSubjectToVideoNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "MinimaxSubjectToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MinimaxSubjectToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MinimaxSubjectToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxSubjectToVideoNode/en.md)
+
+Generates videos synchronously based on an image and prompt, and optional parameters using MiniMax's API. This node takes a subject image and text description to create a video using MiniMax's video generation service.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `subject` | IMAGE | Yes | - | Image of subject to reference for video generation |
+| `prompt_text` | STRING | Yes | - | Text prompt to guide the video generation (default: empty string) |
+| `model` | COMBO | No | "S2V-01"<br /> | Model to use for video generation (default: "S2V-01") |
+| `seed` | INT | No | 0 to 18446744073709551615 | The random seed used for creating the noise (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video based on the input subject image and prompt |
diff --git a/built-in-nodes/MinimaxTextToVideoNode.mdx b/built-in-nodes/MinimaxTextToVideoNode.mdx
new file mode 100644
index 000000000..3608b41e7
--- /dev/null
+++ b/built-in-nodes/MinimaxTextToVideoNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "MinimaxTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MinimaxTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MinimaxTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxTextToVideoNode/en.md)
+
+Generates videos synchronously based on a prompt, and optional parameters using MiniMax's API. This node creates video content from text descriptions by connecting to MiniMax's text-to-video service.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt_text` | STRING | Yes | - | Text prompt to guide the video generation |
+| `model` | COMBO | No | "T2V-01"<br />"T2V-01-Director" | Model to use for video generation (default: "T2V-01") |
+| `seed` | INT | No | 0 to 18446744073709551615 | The random seed used for creating the noise (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video based on the input prompt |
diff --git a/built-in-nodes/ModelComputeDtype.mdx b/built-in-nodes/ModelComputeDtype.mdx
new file mode 100644
index 000000000..d99f85191
--- /dev/null
+++ b/built-in-nodes/ModelComputeDtype.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelComputeDtype - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelComputeDtype node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelComputeDtype"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelComputeDtype/en.md)
+
+The ModelComputeDtype node allows you to change the computational data type used by a model during inference. It creates a copy of the input model and applies the specified data type setting, which can help optimize memory usage and performance depending on your hardware capabilities. This is particularly useful for debugging and testing different precision settings.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The input model to modify with a new compute data type |
+| `dtype` | STRING | Yes | "default"<br />"fp32"<br />"fp16"<br />"bf16" | The computational data type to apply to the model |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with the new compute data type applied |
diff --git a/built-in-nodes/ModelMergeAdd.mdx b/built-in-nodes/ModelMergeAdd.mdx
new file mode 100644
index 000000000..42bcab504
--- /dev/null
+++ b/built-in-nodes/ModelMergeAdd.mdx
@@ -0,0 +1,22 @@
+---
+title: "ModelMergeAdd - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeAdd node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeAdd"
+icon: "circle"
+mode: wide
+---
+
+The ModelMergeAdd node is designed for merging two models by adding key patches from one model to another. This process involves cloning the first model and then applying patches from the second model, allowing for the combination of features or behaviors from both models.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model1`  | `MODEL`     | The first model to be cloned and to which patches from the second model will be added. It serves as the base model for the merging process. |
+| `model2`  | `MODEL`     | The second model from which key patches are extracted and added to the first model. It contributes additional features or behaviors to the merged model. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The result of merging two models by adding key patches from the second model to the first. This merged model combines features or behaviors from both models. |
diff --git a/built-in-nodes/ModelMergeAuraflow.mdx b/built-in-nodes/ModelMergeAuraflow.mdx
new file mode 100644
index 000000000..b97bc7bf5
--- /dev/null
+++ b/built-in-nodes/ModelMergeAuraflow.mdx
@@ -0,0 +1,66 @@
+---
+title: "ModelMergeAuraflow - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeAuraflow node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeAuraflow"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeAuraflow/en.md)
+
+The ModelMergeAuraflow node allows you to blend two different models together by adjusting specific blending weights for various model components. It provides fine-grained control over how different parts of the models are merged, from initial layers to final outputs. This node is particularly useful for creating custom model combinations with precise control over the merging process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The first model to be merged |
+| `model2` | MODEL | Yes | - | The second model to be merged |
+| `init_x_linear.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for the initial linear transformation (default: 1.0) |
+| `positional_encoding` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for positional encoding components (default: 1.0) |
+| `cond_seq_linear.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for conditional sequence linear layers (default: 1.0) |
+| `register_tokens` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for token registration components (default: 1.0) |
+| `t_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for time embedding components (default: 1.0) |
+| `double_layers.0.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for double layer group 0 (default: 1.0) |
+| `double_layers.1.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for double layer group 1 (default: 1.0) |
+| `double_layers.2.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for double layer group 2 (default: 1.0) |
+| `double_layers.3.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for double layer group 3 (default: 1.0) |
+| `single_layers.0.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 0 (default: 1.0) |
+| `single_layers.1.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 1 (default: 1.0) |
+| `single_layers.2.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 2 (default: 1.0) |
+| `single_layers.3.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 3 (default: 1.0) |
+| `single_layers.4.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 4 (default: 1.0) |
+| `single_layers.5.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 5 (default: 1.0) |
+| `single_layers.6.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 6 (default: 1.0) |
+| `single_layers.7.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 7 (default: 1.0) |
+| `single_layers.8.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 8 (default: 1.0) |
+| `single_layers.9.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 9 (default: 1.0) |
+| `single_layers.10.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 10 (default: 1.0) |
+| `single_layers.11.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 11 (default: 1.0) |
+| `single_layers.12.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 12 (default: 1.0) |
+| `single_layers.13.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 13 (default: 1.0) |
+| `single_layers.14.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 14 (default: 1.0) |
+| `single_layers.15.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 15 (default: 1.0) |
+| `single_layers.16.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 16 (default: 1.0) |
+| `single_layers.17.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 17 (default: 1.0) |
+| `single_layers.18.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 18 (default: 1.0) |
+| `single_layers.19.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 19 (default: 1.0) |
+| `single_layers.20.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 20 (default: 1.0) |
+| `single_layers.21.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 21 (default: 1.0) |
+| `single_layers.22.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 22 (default: 1.0) |
+| `single_layers.23.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 23 (default: 1.0) |
+| `single_layers.24.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 24 (default: 1.0) |
+| `single_layers.25.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 25 (default: 1.0) |
+| `single_layers.26.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 26 (default: 1.0) |
+| `single_layers.27.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 27 (default: 1.0) |
+| `single_layers.28.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 28 (default: 1.0) |
+| `single_layers.29.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 29 (default: 1.0) |
+| `single_layers.30.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 30 (default: 1.0) |
+| `single_layers.31.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for single layer 31 (default: 1.0) |
+| `modF.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for modF components (default: 1.0) |
+| `final_linear.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for final linear transformation (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining features from both input models according to the specified blending weights |
diff --git a/built-in-nodes/ModelMergeBlocks.mdx b/built-in-nodes/ModelMergeBlocks.mdx
new file mode 100644
index 000000000..aaa469bcf
--- /dev/null
+++ b/built-in-nodes/ModelMergeBlocks.mdx
@@ -0,0 +1,25 @@
+---
+title: "ModelMergeBlocks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeBlocks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeBlocks"
+icon: "circle"
+mode: wide
+---
+
+ModelMergeBlocks is designed for advanced model merging operations, allowing for the integration of two models with customizable blending ratios for different parts of the models. This node facilitates the creation of hybrid models by selectively merging components from two source models based on specified parameters.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model1`  | `MODEL`     | The first model to be merged. It serves as the base model onto which patches from the second model are applied. |
+| `model2`  | `MODEL`     | The second model from which patches are extracted and applied to the first model, based on the specified blending ratios. |
+| `input`   | `FLOAT`     | Specifies the blending ratio for the input layer of the models. It determines how much of the second model's input layer is merged into the first model. |
+| `middle`  | `FLOAT`     | Defines the blending ratio for the middle layers of the models. This parameter controls the integration level of the models' middle layers. |
+| `out`     | `FLOAT`     | Determines the blending ratio for the output layer of the models. It affects the final output by adjusting the contribution of the second model's output layer. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The resulting merged model, which is a hybrid of the two input models with patches applied according to the specified blending ratios. |
diff --git a/built-in-nodes/ModelMergeCosmos14B.mdx b/built-in-nodes/ModelMergeCosmos14B.mdx
new file mode 100644
index 000000000..571b94291
--- /dev/null
+++ b/built-in-nodes/ModelMergeCosmos14B.mdx
@@ -0,0 +1,65 @@
+---
+title: "ModelMergeCosmos14B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeCosmos14B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeCosmos14B"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeCosmos14B/en.md)
+
+The ModelMergeCosmos14B node merges two AI models using a block-based approach specifically designed for Cosmos 14B model architecture. It allows you to blend different components of the models by adjusting weight values between 0.0 and 1.0 for each model block and embedding layer.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | First model to merge |
+| `model2` | MODEL | Yes | - | Second model to merge |
+| `pos_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Position embedder weight (default: 1.0) |
+| `extra_pos_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Extra position embedder weight (default: 1.0) |
+| `x_embedder.` | FLOAT | Yes | 0.0 - 1.0 | X embedder weight (default: 1.0) |
+| `t_embedder.` | FLOAT | Yes | 0.0 - 1.0 | T embedder weight (default: 1.0) |
+| `affline_norm.` | FLOAT | Yes | 0.0 - 1.0 | Affine normalization weight (default: 1.0) |
+| `blocks.block0.` | FLOAT | Yes | 0.0 - 1.0 | Block 0 weight (default: 1.0) |
+| `blocks.block1.` | FLOAT | Yes | 0.0 - 1.0 | Block 1 weight (default: 1.0) |
+| `blocks.block2.` | FLOAT | Yes | 0.0 - 1.0 | Block 2 weight (default: 1.0) |
+| `blocks.block3.` | FLOAT | Yes | 0.0 - 1.0 | Block 3 weight (default: 1.0) |
+| `blocks.block4.` | FLOAT | Yes | 0.0 - 1.0 | Block 4 weight (default: 1.0) |
+| `blocks.block5.` | FLOAT | Yes | 0.0 - 1.0 | Block 5 weight (default: 1.0) |
+| `blocks.block6.` | FLOAT | Yes | 0.0 - 1.0 | Block 6 weight (default: 1.0) |
+| `blocks.block7.` | FLOAT | Yes | 0.0 - 1.0 | Block 7 weight (default: 1.0) |
+| `blocks.block8.` | FLOAT | Yes | 0.0 - 1.0 | Block 8 weight (default: 1.0) |
+| `blocks.block9.` | FLOAT | Yes | 0.0 - 1.0 | Block 9 weight (default: 1.0) |
+| `blocks.block10.` | FLOAT | Yes | 0.0 - 1.0 | Block 10 weight (default: 1.0) |
+| `blocks.block11.` | FLOAT | Yes | 0.0 - 1.0 | Block 11 weight (default: 1.0) |
+| `blocks.block12.` | FLOAT | Yes | 0.0 - 1.0 | Block 12 weight (default: 1.0) |
+| `blocks.block13.` | FLOAT | Yes | 0.0 - 1.0 | Block 13 weight (default: 1.0) |
+| `blocks.block14.` | FLOAT | Yes | 0.0 - 1.0 | Block 14 weight (default: 1.0) |
+| `blocks.block15.` | FLOAT | Yes | 0.0 - 1.0 | Block 15 weight (default: 1.0) |
+| `blocks.block16.` | FLOAT | Yes | 0.0 - 1.0 | Block 16 weight (default: 1.0) |
+| `blocks.block17.` | FLOAT | Yes | 0.0 - 1.0 | Block 17 weight (default: 1.0) |
+| `blocks.block18.` | FLOAT | Yes | 0.0 - 1.0 | Block 18 weight (default: 1.0) |
+| `blocks.block19.` | FLOAT | Yes | 0.0 - 1.0 | Block 19 weight (default: 1.0) |
+| `blocks.block20.` | FLOAT | Yes | 0.0 - 1.0 | Block 20 weight (default: 1.0) |
+| `blocks.block21.` | FLOAT | Yes | 0.0 - 1.0 | Block 21 weight (default: 1.0) |
+| `blocks.block22.` | FLOAT | Yes | 0.0 - 1.0 | Block 22 weight (default: 1.0) |
+| `blocks.block23.` | FLOAT | Yes | 0.0 - 1.0 | Block 23 weight (default: 1.0) |
+| `blocks.block24.` | FLOAT | Yes | 0.0 - 1.0 | Block 24 weight (default: 1.0) |
+| `blocks.block25.` | FLOAT | Yes | 0.0 - 1.0 | Block 25 weight (default: 1.0) |
+| `blocks.block26.` | FLOAT | Yes | 0.0 - 1.0 | Block 26 weight (default: 1.0) |
+| `blocks.block27.` | FLOAT | Yes | 0.0 - 1.0 | Block 27 weight (default: 1.0) |
+| `blocks.block28.` | FLOAT | Yes | 0.0 - 1.0 | Block 28 weight (default: 1.0) |
+| `blocks.block29.` | FLOAT | Yes | 0.0 - 1.0 | Block 29 weight (default: 1.0) |
+| `blocks.block30.` | FLOAT | Yes | 0.0 - 1.0 | Block 30 weight (default: 1.0) |
+| `blocks.block31.` | FLOAT | Yes | 0.0 - 1.0 | Block 31 weight (default: 1.0) |
+| `blocks.block32.` | FLOAT | Yes | 0.0 - 1.0 | Block 32 weight (default: 1.0) |
+| `blocks.block33.` | FLOAT | Yes | 0.0 - 1.0 | Block 33 weight (default: 1.0) |
+| `blocks.block34.` | FLOAT | Yes | 0.0 - 1.0 | Block 34 weight (default: 1.0) |
+| `blocks.block35.` | FLOAT | Yes | 0.0 - 1.0 | Block 35 weight (default: 1.0) |
+| `final_layer.` | FLOAT | Yes | 0.0 - 1.0 | Final layer weight (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining features from both input models |
diff --git a/built-in-nodes/ModelMergeCosmos7B.mdx b/built-in-nodes/ModelMergeCosmos7B.mdx
new file mode 100644
index 000000000..4959f6971
--- /dev/null
+++ b/built-in-nodes/ModelMergeCosmos7B.mdx
@@ -0,0 +1,57 @@
+---
+title: "ModelMergeCosmos7B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeCosmos7B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeCosmos7B"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeCosmos7B/en.md)
+
+The ModelMergeCosmos7B node merges two AI models together using weighted blending of specific components. It allows fine-grained control over how different parts of the models are combined by adjusting individual weights for position embeddings, transformer blocks, and final layers.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | First model to merge |
+| `model2` | MODEL | Yes | - | Second model to merge |
+| `pos_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Weight for position embedder component (default: 1.0) |
+| `extra_pos_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Weight for extra position embedder component (default: 1.0) |
+| `x_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Weight for x embedder component (default: 1.0) |
+| `t_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Weight for t embedder component (default: 1.0) |
+| `affline_norm.` | FLOAT | Yes | 0.0 - 1.0 | Weight for affine normalization component (default: 1.0) |
+| `blocks.block0.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 0 (default: 1.0) |
+| `blocks.block1.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 1 (default: 1.0) |
+| `blocks.block2.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 2 (default: 1.0) |
+| `blocks.block3.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 3 (default: 1.0) |
+| `blocks.block4.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 4 (default: 1.0) |
+| `blocks.block5.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 5 (default: 1.0) |
+| `blocks.block6.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 6 (default: 1.0) |
+| `blocks.block7.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 7 (default: 1.0) |
+| `blocks.block8.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 8 (default: 1.0) |
+| `blocks.block9.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 9 (default: 1.0) |
+| `blocks.block10.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 10 (default: 1.0) |
+| `blocks.block11.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 11 (default: 1.0) |
+| `blocks.block12.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 12 (default: 1.0) |
+| `blocks.block13.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 13 (default: 1.0) |
+| `blocks.block14.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 14 (default: 1.0) |
+| `blocks.block15.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 15 (default: 1.0) |
+| `blocks.block16.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 16 (default: 1.0) |
+| `blocks.block17.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 17 (default: 1.0) |
+| `blocks.block18.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 18 (default: 1.0) |
+| `blocks.block19.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 19 (default: 1.0) |
+| `blocks.block20.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 20 (default: 1.0) |
+| `blocks.block21.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 21 (default: 1.0) |
+| `blocks.block22.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 22 (default: 1.0) |
+| `blocks.block23.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 23 (default: 1.0) |
+| `blocks.block24.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 24 (default: 1.0) |
+| `blocks.block25.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 25 (default: 1.0) |
+| `blocks.block26.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 26 (default: 1.0) |
+| `blocks.block27.` | FLOAT | Yes | 0.0 - 1.0 | Weight for transformer block 27 (default: 1.0) |
+| `final_layer.` | FLOAT | Yes | 0.0 - 1.0 | Weight for final layer component (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining features from both input models |
diff --git a/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx b/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx
new file mode 100644
index 000000000..ab5735095
--- /dev/null
+++ b/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx
@@ -0,0 +1,66 @@
+---
+title: "ModelMergeCosmosPredict2_14B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeCosmosPredict2_14B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeCosmosPredict2_14B"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeCosmosPredict2_14B/en.md)
+
+The ModelMergeCosmosPredict2_14B node allows you to merge two AI models by adjusting the influence of different model components. It provides fine-grained control over how much each part of the second model contributes to the final merged model, using blending weights for specific model layers and components.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The base model to merge with |
+| `model2` | MODEL | Yes | - | The secondary model to merge into the base model |
+| `pos_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Position embedder blending weight (default: 1.0) |
+| `x_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Input embedder blending weight (default: 1.0) |
+| `t_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Time embedder blending weight (default: 1.0) |
+| `t_embedding_norm.` | FLOAT | Yes | 0.0 - 1.0 | Time embedding normalization blending weight (default: 1.0) |
+| `blocks.0.` | FLOAT | Yes | 0.0 - 1.0 | Block 0 blending weight (default: 1.0) |
+| `blocks.1.` | FLOAT | Yes | 0.0 - 1.0 | Block 1 blending weight (default: 1.0) |
+| `blocks.2.` | FLOAT | Yes | 0.0 - 1.0 | Block 2 blending weight (default: 1.0) |
+| `blocks.3.` | FLOAT | Yes | 0.0 - 1.0 | Block 3 blending weight (default: 1.0) |
+| `blocks.4.` | FLOAT | Yes | 0.0 - 1.0 | Block 4 blending weight (default: 1.0) |
+| `blocks.5.` | FLOAT | Yes | 0.0 - 1.0 | Block 5 blending weight (default: 1.0) |
+| `blocks.6.` | FLOAT | Yes | 0.0 - 1.0 | Block 6 blending weight (default: 1.0) |
+| `blocks.7.` | FLOAT | Yes | 0.0 - 1.0 | Block 7 blending weight (default: 1.0) |
+| `blocks.8.` | FLOAT | Yes | 0.0 - 1.0 | Block 8 blending weight (default: 1.0) |
+| `blocks.9.` | FLOAT | Yes | 0.0 - 1.0 | Block 9 blending weight (default: 1.0) |
+| `blocks.10.` | FLOAT | Yes | 0.0 - 1.0 | Block 10 blending weight (default: 1.0) |
+| `blocks.11.` | FLOAT | Yes | 0.0 - 1.0 | Block 11 blending weight (default: 1.0) |
+| `blocks.12.` | FLOAT | Yes | 0.0 - 1.0 | Block 12 blending weight (default: 1.0) |
+| `blocks.13.` | FLOAT | Yes | 0.0 - 1.0 | Block 13 blending weight (default: 1.0) |
+| `blocks.14.` | FLOAT | Yes | 0.0 - 1.0 | Block 14 blending weight (default: 1.0) |
+| `blocks.15.` | FLOAT | Yes | 0.0 - 1.0 | Block 15 blending weight (default: 1.0) |
+| `blocks.16.` | FLOAT | Yes | 0.0 - 1.0 | Block 16 blending weight (default: 1.0) |
+| `blocks.17.` | FLOAT | Yes | 0.0 - 1.0 | Block 17 blending weight (default: 1.0) |
+| `blocks.18.` | FLOAT | Yes | 0.0 - 1.0 | Block 18 blending weight (default: 1.0) |
+| `blocks.19.` | FLOAT | Yes | 0.0 - 1.0 | Block 19 blending weight (default: 1.0) |
+| `blocks.20.` | FLOAT | Yes | 0.0 - 1.0 | Block 20 blending weight (default: 1.0) |
+| `blocks.21.` | FLOAT | Yes | 0.0 - 1.0 | Block 21 blending weight (default: 1.0) |
+| `blocks.22.` | FLOAT | Yes | 0.0 - 1.0 | Block 22 blending weight (default: 1.0) |
+| `blocks.23.` | FLOAT | Yes | 0.0 - 1.0 | Block 23 blending weight (default: 1.0) |
+| `blocks.24.` | FLOAT | Yes | 0.0 - 1.0 | Block 24 blending weight (default: 1.0) |
+| `blocks.25.` | FLOAT | Yes | 0.0 - 1.0 | Block 25 blending weight (default: 1.0) |
+| `blocks.26.` | FLOAT | Yes | 0.0 - 1.0 | Block 26 blending weight (default: 1.0) |
+| `blocks.27.` | FLOAT | Yes | 0.0 - 1.0 | Block 27 blending weight (default: 1.0) |
+| `blocks.28.` | FLOAT | Yes | 0.0 - 1.0 | Block 28 blending weight (default: 1.0) |
+| `blocks.29.` | FLOAT | Yes | 0.0 - 1.0 | Block 29 blending weight (default: 1.0) |
+| `blocks.30.` | FLOAT | Yes | 0.0 - 1.0 | Block 30 blending weight (default: 1.0) |
+| `blocks.31.` | FLOAT | Yes | 0.0 - 1.0 | Block 31 blending weight (default: 1.0) |
+| `blocks.32.` | FLOAT | Yes | 0.0 - 1.0 | Block 32 blending weight (default: 1.0) |
+| `blocks.33.` | FLOAT | Yes | 0.0 - 1.0 | Block 33 blending weight (default: 1.0) |
+| `blocks.34.` | FLOAT | Yes | 0.0 - 1.0 | Block 34 blending weight (default: 1.0) |
+| `blocks.35.` | FLOAT | Yes | 0.0 - 1.0 | Block 35 blending weight (default: 1.0) |
+| `final_layer.` | FLOAT | Yes | 0.0 - 1.0 | Final layer blending weight (default: 1.0) |
+
+**Note:** All blending weight parameters accept values between 0.0 and 1.0, where 0.0 means no contribution from model2 and 1.0 means full contribution from model2 for that specific component.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining features from both input models |
diff --git a/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx b/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx
new file mode 100644
index 000000000..f70156f8d
--- /dev/null
+++ b/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx
@@ -0,0 +1,56 @@
+---
+title: "ModelMergeCosmosPredict2_2B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeCosmosPredict2_2B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeCosmosPredict2_2B"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeCosmosPredict2_2B/en.md)
+
+The ModelMergeCosmosPredict2_2B node merges two diffusion models using a block-based approach with fine-grained control over different model components. It allows you to blend specific parts of two models by adjusting interpolation weights for position embedders, time embedders, transformer blocks, and final layers. This provides precise control over how different architectural components from each model contribute to the final merged result.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The first model to merge |
+| `model2` | MODEL | Yes | - | The second model to merge |
+| `pos_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Position embedder interpolation weight (default: 1.0) |
+| `x_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Input embedder interpolation weight (default: 1.0) |
+| `t_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Time embedder interpolation weight (default: 1.0) |
+| `t_embedding_norm.` | FLOAT | Yes | 0.0 - 1.0 | Time embedding normalization interpolation weight (default: 1.0) |
+| `blocks.0.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 0 interpolation weight (default: 1.0) |
+| `blocks.1.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 1 interpolation weight (default: 1.0) |
+| `blocks.2.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 2 interpolation weight (default: 1.0) |
+| `blocks.3.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 3 interpolation weight (default: 1.0) |
+| `blocks.4.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 4 interpolation weight (default: 1.0) |
+| `blocks.5.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 5 interpolation weight (default: 1.0) |
+| `blocks.6.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 6 interpolation weight (default: 1.0) |
+| `blocks.7.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 7 interpolation weight (default: 1.0) |
+| `blocks.8.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 8 interpolation weight (default: 1.0) |
+| `blocks.9.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 9 interpolation weight (default: 1.0) |
+| `blocks.10.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 10 interpolation weight (default: 1.0) |
+| `blocks.11.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 11 interpolation weight (default: 1.0) |
+| `blocks.12.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 12 interpolation weight (default: 1.0) |
+| `blocks.13.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 13 interpolation weight (default: 1.0) |
+| `blocks.14.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 14 interpolation weight (default: 1.0) |
+| `blocks.15.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 15 interpolation weight (default: 1.0) |
+| `blocks.16.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 16 interpolation weight (default: 1.0) |
+| `blocks.17.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 17 interpolation weight (default: 1.0) |
+| `blocks.18.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 18 interpolation weight (default: 1.0) |
+| `blocks.19.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 19 interpolation weight (default: 1.0) |
+| `blocks.20.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 20 interpolation weight (default: 1.0) |
+| `blocks.21.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 21 interpolation weight (default: 1.0) |
+| `blocks.22.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 22 interpolation weight (default: 1.0) |
+| `blocks.23.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 23 interpolation weight (default: 1.0) |
+| `blocks.24.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 24 interpolation weight (default: 1.0) |
+| `blocks.25.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 25 interpolation weight (default: 1.0) |
+| `blocks.26.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 26 interpolation weight (default: 1.0) |
+| `blocks.27.` | FLOAT | Yes | 0.0 - 1.0 | Transformer block 27 interpolation weight (default: 1.0) |
+| `final_layer.` | FLOAT | Yes | 0.0 - 1.0 | Final layer interpolation weight (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining features from both input models |
diff --git a/built-in-nodes/ModelMergeFlux1.mdx b/built-in-nodes/ModelMergeFlux1.mdx
new file mode 100644
index 000000000..5c4676c2e
--- /dev/null
+++ b/built-in-nodes/ModelMergeFlux1.mdx
@@ -0,0 +1,86 @@
+---
+title: "ModelMergeFlux1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeFlux1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeFlux1"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeFlux1/en.md)
+
+The ModelMergeFlux1 node merges two diffusion models by blending their components using weighted interpolation. It allows fine-grained control over how different parts of the models are combined, including image processing blocks, time embedding layers, guidance mechanisms, vector inputs, text encoders, and various transformer blocks. This enables creating hybrid models with customized characteristics from two source models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | First source model to merge |
+| `model2` | MODEL | Yes | - | Second source model to merge |
+| `img_in.` | FLOAT | Yes | 0.0 to 1.0 | Image input interpolation weight (default: 1.0) |
+| `time_in.` | FLOAT | Yes | 0.0 to 1.0 | Time embedding interpolation weight (default: 1.0) |
+| `guidance_in` | FLOAT | Yes | 0.0 to 1.0 | Guidance mechanism interpolation weight (default: 1.0) |
+| `vector_in.` | FLOAT | Yes | 0.0 to 1.0 | Vector input interpolation weight (default: 1.0) |
+| `txt_in.` | FLOAT | Yes | 0.0 to 1.0 | Text encoder interpolation weight (default: 1.0) |
+| `double_blocks.0.` | FLOAT | Yes | 0.0 to 1.0 | Double block 0 interpolation weight (default: 1.0) |
+| `double_blocks.1.` | FLOAT | Yes | 0.0 to 1.0 | Double block 1 interpolation weight (default: 1.0) |
+| `double_blocks.2.` | FLOAT | Yes | 0.0 to 1.0 | Double block 2 interpolation weight (default: 1.0) |
+| `double_blocks.3.` | FLOAT | Yes | 0.0 to 1.0 | Double block 3 interpolation weight (default: 1.0) |
+| `double_blocks.4.` | FLOAT | Yes | 0.0 to 1.0 | Double block 4 interpolation weight (default: 1.0) |
+| `double_blocks.5.` | FLOAT | Yes | 0.0 to 1.0 | Double block 5 interpolation weight (default: 1.0) |
+| `double_blocks.6.` | FLOAT | Yes | 0.0 to 1.0 | Double block 6 interpolation weight (default: 1.0) |
+| `double_blocks.7.` | FLOAT | Yes | 0.0 to 1.0 | Double block 7 interpolation weight (default: 1.0) |
+| `double_blocks.8.` | FLOAT | Yes | 0.0 to 1.0 | Double block 8 interpolation weight (default: 1.0) |
+| `double_blocks.9.` | FLOAT | Yes | 0.0 to 1.0 | Double block 9 interpolation weight (default: 1.0) |
+| `double_blocks.10.` | FLOAT | Yes | 0.0 to 1.0 | Double block 10 interpolation weight (default: 1.0) |
+| `double_blocks.11.` | FLOAT | Yes | 0.0 to 1.0 | Double block 11 interpolation weight (default: 1.0) |
+| `double_blocks.12.` | FLOAT | Yes | 0.0 to 1.0 | Double block 12 interpolation weight (default: 1.0) |
+| `double_blocks.13.` | FLOAT | Yes | 0.0 to 1.0 | Double block 13 interpolation weight (default: 1.0) |
+| `double_blocks.14.` | FLOAT | Yes | 0.0 to 1.0 | Double block 14 interpolation weight (default: 1.0) |
+| `double_blocks.15.` | FLOAT | Yes | 0.0 to 1.0 | Double block 15 interpolation weight (default: 1.0) |
+| `double_blocks.16.` | FLOAT | Yes | 0.0 to 1.0 | Double block 16 interpolation weight (default: 1.0) |
+| `double_blocks.17.` | FLOAT | Yes | 0.0 to 1.0 | Double block 17 interpolation weight (default: 1.0) |
+| `double_blocks.18.` | FLOAT | Yes | 0.0 to 1.0 | Double block 18 interpolation weight (default: 1.0) |
+| `single_blocks.0.` | FLOAT | Yes | 0.0 to 1.0 | Single block 0 interpolation weight (default: 1.0) |
+| `single_blocks.1.` | FLOAT | Yes | 0.0 to 1.0 | Single block 1 interpolation weight (default: 1.0) |
+| `single_blocks.2.` | FLOAT | Yes | 0.0 to 1.0 | Single block 2 interpolation weight (default: 1.0) |
+| `single_blocks.3.` | FLOAT | Yes | 0.0 to 1.0 | Single block 3 interpolation weight (default: 1.0) |
+| `single_blocks.4.` | FLOAT | Yes | 0.0 to 1.0 | Single block 4 interpolation weight (default: 1.0) |
+| `single_blocks.5.` | FLOAT | Yes | 0.0 to 1.0 | Single block 5 interpolation weight (default: 1.0) |
+| `single_blocks.6.` | FLOAT | Yes | 0.0 to 1.0 | Single block 6 interpolation weight (default: 1.0) |
+| `single_blocks.7.` | FLOAT | Yes | 0.0 to 1.0 | Single block 7 interpolation weight (default: 1.0) |
+| `single_blocks.8.` | FLOAT | Yes | 0.0 to 1.0 | Single block 8 interpolation weight (default: 1.0) |
+| `single_blocks.9.` | FLOAT | Yes | 0.0 to 1.0 | Single block 9 interpolation weight (default: 1.0) |
+| `single_blocks.10.` | FLOAT | Yes | 0.0 to 1.0 | Single block 10 interpolation weight (default: 1.0) |
+| `single_blocks.11.` | FLOAT | Yes | 0.0 to 1.0 | Single block 11 interpolation weight (default: 1.0) |
+| `single_blocks.12.` | FLOAT | Yes | 0.0 to 1.0 | Single block 12 interpolation weight (default: 1.0) |
+| `single_blocks.13.` | FLOAT | Yes | 0.0 to 1.0 | Single block 13 interpolation weight (default: 1.0) |
+| `single_blocks.14.` | FLOAT | Yes | 0.0 to 1.0 | Single block 14 interpolation weight (default: 1.0) |
+| `single_blocks.15.` | FLOAT | Yes | 0.0 to 1.0 | Single block 15 interpolation weight (default: 1.0) |
+| `single_blocks.16.` | FLOAT | Yes | 0.0 to 1.0 | Single block 16 interpolation weight (default: 1.0) |
+| `single_blocks.17.` | FLOAT | Yes | 0.0 to 1.0 | Single block 17 interpolation weight (default: 1.0) |
+| `single_blocks.18.` | FLOAT | Yes | 0.0 to 1.0 | Single block 18 interpolation weight (default: 1.0) |
+| `single_blocks.19.` | FLOAT | Yes | 0.0 to 1.0 | Single block 19 interpolation weight (default: 1.0) |
+| `single_blocks.20.` | FLOAT | Yes | 0.0 to 1.0 | Single block 20 interpolation weight (default: 1.0) |
+| `single_blocks.21.` | FLOAT | Yes | 0.0 to 1.0 | Single block 21 interpolation weight (default: 1.0) |
+| `single_blocks.22.` | FLOAT | Yes | 0.0 to 1.0 | Single block 22 interpolation weight (default: 1.0) |
+| `single_blocks.23.` | FLOAT | Yes | 0.0 to 1.0 | Single block 23 interpolation weight (default: 1.0) |
+| `single_blocks.24.` | FLOAT | Yes | 0.0 to 1.0 | Single block 24 interpolation weight (default: 1.0) |
+| `single_blocks.25.` | FLOAT | Yes | 0.0 to 1.0 | Single block 25 interpolation weight (default: 1.0) |
+| `single_blocks.26.` | FLOAT | Yes | 0.0 to 1.0 | Single block 26 interpolation weight (default: 1.0) |
+| `single_blocks.27.` | FLOAT | Yes | 0.0 to 1.0 | Single block 27 interpolation weight (default: 1.0) |
+| `single_blocks.28.` | FLOAT | Yes | 0.0 to 1.0 | Single block 28 interpolation weight (default: 1.0) |
+| `single_blocks.29.` | FLOAT | Yes | 0.0 to 1.0 | Single block 29 interpolation weight (default: 1.0) |
+| `single_blocks.30.` | FLOAT | Yes | 0.0 to 1.0 | Single block 30 interpolation weight (default: 1.0) |
+| `single_blocks.31.` | FLOAT | Yes | 0.0 to 1.0 | Single block 31 interpolation weight (default: 1.0) |
+| `single_blocks.32.` | FLOAT | Yes | 0.0 to 1.0 | Single block 32 interpolation weight (default: 1.0) |
+| `single_blocks.33.` | FLOAT | Yes | 0.0 to 1.0 | Single block 33 interpolation weight (default: 1.0) |
+| `single_blocks.34.` | FLOAT | Yes | 0.0 to 1.0 | Single block 34 interpolation weight (default: 1.0) |
+| `single_blocks.35.` | FLOAT | Yes | 0.0 to 1.0 | Single block 35 interpolation weight (default: 1.0) |
+| `single_blocks.36.` | FLOAT | Yes | 0.0 to 1.0 | Single block 36 interpolation weight (default: 1.0) |
+| `single_blocks.37.` | FLOAT | Yes | 0.0 to 1.0 | Single block 37 interpolation weight (default: 1.0) |
+| `final_layer.` | FLOAT | Yes | 0.0 to 1.0 | Final layer interpolation weight (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining characteristics from both input models |
diff --git a/built-in-nodes/ModelMergeLTXV.mdx b/built-in-nodes/ModelMergeLTXV.mdx
new file mode 100644
index 000000000..dd43b4dd4
--- /dev/null
+++ b/built-in-nodes/ModelMergeLTXV.mdx
@@ -0,0 +1,56 @@
+---
+title: "ModelMergeLTXV - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeLTXV node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeLTXV"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeLTXV/en.md)
+
+The ModelMergeLTXV node performs advanced model merging operations specifically designed for LTXV model architectures. It allows you to blend two different models together by adjusting interpolation weights for various model components including transformer blocks, projection layers, and other specialized modules.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The first model to merge |
+| `model2` | MODEL | Yes | - | The second model to merge |
+| `patchify_proj.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for patchify projection layers (default: 1.0) |
+| `adaln_single.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for adaptive layer normalization single layers (default: 1.0) |
+| `caption_projection.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for caption projection layers (default: 1.0) |
+| `transformer_blocks.0.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 0 (default: 1.0) |
+| `transformer_blocks.1.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 1 (default: 1.0) |
+| `transformer_blocks.2.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 2 (default: 1.0) |
+| `transformer_blocks.3.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 3 (default: 1.0) |
+| `transformer_blocks.4.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 4 (default: 1.0) |
+| `transformer_blocks.5.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 5 (default: 1.0) |
+| `transformer_blocks.6.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 6 (default: 1.0) |
+| `transformer_blocks.7.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 7 (default: 1.0) |
+| `transformer_blocks.8.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 8 (default: 1.0) |
+| `transformer_blocks.9.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 9 (default: 1.0) |
+| `transformer_blocks.10.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 10 (default: 1.0) |
+| `transformer_blocks.11.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 11 (default: 1.0) |
+| `transformer_blocks.12.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 12 (default: 1.0) |
+| `transformer_blocks.13.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 13 (default: 1.0) |
+| `transformer_blocks.14.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 14 (default: 1.0) |
+| `transformer_blocks.15.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 15 (default: 1.0) |
+| `transformer_blocks.16.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 16 (default: 1.0) |
+| `transformer_blocks.17.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 17 (default: 1.0) |
+| `transformer_blocks.18.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 18 (default: 1.0) |
+| `transformer_blocks.19.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 19 (default: 1.0) |
+| `transformer_blocks.20.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 20 (default: 1.0) |
+| `transformer_blocks.21.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 21 (default: 1.0) |
+| `transformer_blocks.22.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 22 (default: 1.0) |
+| `transformer_blocks.23.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 23 (default: 1.0) |
+| `transformer_blocks.24.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 24 (default: 1.0) |
+| `transformer_blocks.25.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 25 (default: 1.0) |
+| `transformer_blocks.26.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 26 (default: 1.0) |
+| `transformer_blocks.27.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for transformer block 27 (default: 1.0) |
+| `scale_shift_table` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for scale shift table (default: 1.0) |
+| `proj_out.` | FLOAT | Yes | 0.0 - 1.0 | Interpolation weight for projection output layers (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining features from both input models according to the specified interpolation weights |
diff --git a/built-in-nodes/ModelMergeMochiPreview.mdx b/built-in-nodes/ModelMergeMochiPreview.mdx
new file mode 100644
index 000000000..853c0da14
--- /dev/null
+++ b/built-in-nodes/ModelMergeMochiPreview.mdx
@@ -0,0 +1,76 @@
+---
+title: "ModelMergeMochiPreview - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeMochiPreview node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeMochiPreview"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeMochiPreview/en.md)
+
+This node merges two AI models using a block-based approach with fine-grained control over different model components. It allows you to blend models by adjusting interpolation weights for specific sections including positional frequencies, embedding layers, and individual transformer blocks. The merging process combines the architectures and parameters from both input models according to the specified weight values.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The first model to merge |
+| `model2` | MODEL | Yes | - | The second model to merge |
+| `pos_frequencies.` | FLOAT | Yes | 0.0 - 1.0 | Weight for positional frequencies interpolation (default: 1.0) |
+| `t_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Weight for time embedder interpolation (default: 1.0) |
+| `t5_y_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Weight for T5-Y embedder interpolation (default: 1.0) |
+| `t5_yproj.` | FLOAT | Yes | 0.0 - 1.0 | Weight for T5-Y projection interpolation (default: 1.0) |
+| `blocks.0.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 0 interpolation (default: 1.0) |
+| `blocks.1.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 1 interpolation (default: 1.0) |
+| `blocks.2.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 2 interpolation (default: 1.0) |
+| `blocks.3.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 3 interpolation (default: 1.0) |
+| `blocks.4.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 4 interpolation (default: 1.0) |
+| `blocks.5.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 5 interpolation (default: 1.0) |
+| `blocks.6.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 6 interpolation (default: 1.0) |
+| `blocks.7.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 7 interpolation (default: 1.0) |
+| `blocks.8.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 8 interpolation (default: 1.0) |
+| `blocks.9.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 9 interpolation (default: 1.0) |
+| `blocks.10.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 10 interpolation (default: 1.0) |
+| `blocks.11.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 11 interpolation (default: 1.0) |
+| `blocks.12.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 12 interpolation (default: 1.0) |
+| `blocks.13.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 13 interpolation (default: 1.0) |
+| `blocks.14.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 14 interpolation (default: 1.0) |
+| `blocks.15.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 15 interpolation (default: 1.0) |
+| `blocks.16.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 16 interpolation (default: 1.0) |
+| `blocks.17.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 17 interpolation (default: 1.0) |
+| `blocks.18.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 18 interpolation (default: 1.0) |
+| `blocks.19.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 19 interpolation (default: 1.0) |
+| `blocks.20.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 20 interpolation (default: 1.0) |
+| `blocks.21.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 21 interpolation (default: 1.0) |
+| `blocks.22.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 22 interpolation (default: 1.0) |
+| `blocks.23.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 23 interpolation (default: 1.0) |
+| `blocks.24.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 24 interpolation (default: 1.0) |
+| `blocks.25.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 25 interpolation (default: 1.0) |
+| `blocks.26.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 26 interpolation (default: 1.0) |
+| `blocks.27.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 27 interpolation (default: 1.0) |
+| `blocks.28.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 28 interpolation (default: 1.0) |
+| `blocks.29.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 29 interpolation (default: 1.0) |
+| `blocks.30.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 30 interpolation (default: 1.0) |
+| `blocks.31.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 31 interpolation (default: 1.0) |
+| `blocks.32.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 32 interpolation (default: 1.0) |
+| `blocks.33.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 33 interpolation (default: 1.0) |
+| `blocks.34.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 34 interpolation (default: 1.0) |
+| `blocks.35.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 35 interpolation (default: 1.0) |
+| `blocks.36.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 36 interpolation (default: 1.0) |
+| `blocks.37.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 37 interpolation (default: 1.0) |
+| `blocks.38.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 38 interpolation (default: 1.0) |
+| `blocks.39.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 39 interpolation (default: 1.0) |
+| `blocks.40.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 40 interpolation (default: 1.0) |
+| `blocks.41.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 41 interpolation (default: 1.0) |
+| `blocks.42.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 42 interpolation (default: 1.0) |
+| `blocks.43.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 43 interpolation (default: 1.0) |
+| `blocks.44.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 44 interpolation (default: 1.0) |
+| `blocks.45.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 45 interpolation (default: 1.0) |
+| `blocks.46.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 46 interpolation (default: 1.0) |
+| `blocks.47.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 47 interpolation (default: 1.0) |
+| `final_layer.` | FLOAT | Yes | 0.0 - 1.0 | Weight for final layer interpolation (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining features from both input models according to the specified weights |
diff --git a/built-in-nodes/ModelMergeQwenImage.mdx b/built-in-nodes/ModelMergeQwenImage.mdx
new file mode 100644
index 000000000..c94e9d944
--- /dev/null
+++ b/built-in-nodes/ModelMergeQwenImage.mdx
@@ -0,0 +1,30 @@
+---
+title: "ModelMergeQwenImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeQwenImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeQwenImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeQwenImage/en.md)
+
+The ModelMergeQwenImage node merges two AI models by combining their components with adjustable weights. It allows you to blend specific parts of Qwen image models, including transformer blocks, positional embeddings, and text processing components. You can control how much influence each model has on different sections of the merged result.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The first model to merge (default: none) |
+| `model2` | MODEL | Yes | - | The second model to merge (default: none) |
+| `pos_embeds.` | FLOAT | Yes | 0.0 to 1.0 | Weight for positional embeddings blending (default: 1.0) |
+| `img_in.` | FLOAT | Yes | 0.0 to 1.0 | Weight for image input processing blending (default: 1.0) |
+| `txt_norm.` | FLOAT | Yes | 0.0 to 1.0 | Weight for text normalization blending (default: 1.0) |
+| `txt_in.` | FLOAT | Yes | 0.0 to 1.0 | Weight for text input processing blending (default: 1.0) |
+| `time_text_embed.` | FLOAT | Yes | 0.0 to 1.0 | Weight for time and text embedding blending (default: 1.0) |
+| `transformer_blocks.0.` to `transformer_blocks.59.` | FLOAT | Yes | 0.0 to 1.0 | Weight for each transformer block blending (default: 1.0) |
+| `proj_out.` | FLOAT | Yes | 0.0 to 1.0 | Weight for output projection blending (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining components from both input models with the specified weights |
diff --git a/built-in-nodes/ModelMergeSD1.mdx b/built-in-nodes/ModelMergeSD1.mdx
new file mode 100644
index 000000000..bdbc5c454
--- /dev/null
+++ b/built-in-nodes/ModelMergeSD1.mdx
@@ -0,0 +1,53 @@
+---
+title: "ModelMergeSD1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSD1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSD1"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeSD1/en.md)
+
+The ModelMergeSD1 node allows you to blend two Stable Diffusion 1.x models together by adjusting the influence of different model components. It provides individual control over time embedding, label embedding, and all input, middle, and output blocks, enabling fine-tuned model merging for specific use cases.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The first model to merge |
+| `model2` | MODEL | Yes | - | The second model to merge |
+| `time_embed.` | FLOAT | Yes | 0.0 - 1.0 | Time embedding layer blending weight (default: 1.0) |
+| `label_emb.` | FLOAT | Yes | 0.0 - 1.0 | Label embedding layer blending weight (default: 1.0) |
+| `input_blocks.0.` | FLOAT | Yes | 0.0 - 1.0 | Input block 0 blending weight (default: 1.0) |
+| `input_blocks.1.` | FLOAT | Yes | 0.0 - 1.0 | Input block 1 blending weight (default: 1.0) |
+| `input_blocks.2.` | FLOAT | Yes | 0.0 - 1.0 | Input block 2 blending weight (default: 1.0) |
+| `input_blocks.3.` | FLOAT | Yes | 0.0 - 1.0 | Input block 3 blending weight (default: 1.0) |
+| `input_blocks.4.` | FLOAT | Yes | 0.0 - 1.0 | Input block 4 blending weight (default: 1.0) |
+| `input_blocks.5.` | FLOAT | Yes | 0.0 - 1.0 | Input block 5 blending weight (default: 1.0) |
+| `input_blocks.6.` | FLOAT | Yes | 0.0 - 1.0 | Input block 6 blending weight (default: 1.0) |
+| `input_blocks.7.` | FLOAT | Yes | 0.0 - 1.0 | Input block 7 blending weight (default: 1.0) |
+| `input_blocks.8.` | FLOAT | Yes | 0.0 - 1.0 | Input block 8 blending weight (default: 1.0) |
+| `input_blocks.9.` | FLOAT | Yes | 0.0 - 1.0 | Input block 9 blending weight (default: 1.0) |
+| `input_blocks.10.` | FLOAT | Yes | 0.0 - 1.0 | Input block 10 blending weight (default: 1.0) |
+| `input_blocks.11.` | FLOAT | Yes | 0.0 - 1.0 | Input block 11 blending weight (default: 1.0) |
+| `middle_block.0.` | FLOAT | Yes | 0.0 - 1.0 | Middle block 0 blending weight (default: 1.0) |
+| `middle_block.1.` | FLOAT | Yes | 0.0 - 1.0 | Middle block 1 blending weight (default: 1.0) |
+| `middle_block.2.` | FLOAT | Yes | 0.0 - 1.0 | Middle block 2 blending weight (default: 1.0) |
+| `output_blocks.0.` | FLOAT | Yes | 0.0 - 1.0 | Output block 0 blending weight (default: 1.0) |
+| `output_blocks.1.` | FLOAT | Yes | 0.0 - 1.0 | Output block 1 blending weight (default: 1.0) |
+| `output_blocks.2.` | FLOAT | Yes | 0.0 - 1.0 | Output block 2 blending weight (default: 1.0) |
+| `output_blocks.3.` | FLOAT | Yes | 0.0 - 1.0 | Output block 3 blending weight (default: 1.0) |
+| `output_blocks.4.` | FLOAT | Yes | 0.0 - 1.0 | Output block 4 blending weight (default: 1.0) |
+| `output_blocks.5.` | FLOAT | Yes | 0.0 - 1.0 | Output block 5 blending weight (default: 1.0) |
+| `output_blocks.6.` | FLOAT | Yes | 0.0 - 1.0 | Output block 6 blending weight (default: 1.0) |
+| `output_blocks.7.` | FLOAT | Yes | 0.0 - 1.0 | Output block 7 blending weight (default: 1.0) |
+| `output_blocks.8.` | FLOAT | Yes | 0.0 - 1.0 | Output block 8 blending weight (default: 1.0) |
+| `output_blocks.9.` | FLOAT | Yes | 0.0 - 1.0 | Output block 9 blending weight (default: 1.0) |
+| `output_blocks.10.` | FLOAT | Yes | 0.0 - 1.0 | Output block 10 blending weight (default: 1.0) |
+| `output_blocks.11.` | FLOAT | Yes | 0.0 - 1.0 | Output block 11 blending weight (default: 1.0) |
+| `out.` | FLOAT | Yes | 0.0 - 1.0 | Output layer blending weight (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | The merged model combining features from both input models |
diff --git a/built-in-nodes/ModelMergeSD35_Large.mdx b/built-in-nodes/ModelMergeSD35_Large.mdx
new file mode 100644
index 000000000..7d146cbba
--- /dev/null
+++ b/built-in-nodes/ModelMergeSD35_Large.mdx
@@ -0,0 +1,69 @@
+---
+title: "ModelMergeSD35_Large - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSD35_Large node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSD35_Large"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeSD35_Large/en.md)
+
+The ModelMergeSD35_Large node allows you to blend two Stable Diffusion 3.5 Large models together by adjusting the influence of different model components. It provides precise control over how much each part of the second model contributes to the final merged model, from embedding layers to joint blocks and final layers.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The base model that serves as the foundation for merging |
+| `model2` | MODEL | Yes | - | The secondary model whose components will be blended into the base model |
+| `pos_embed.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of the position embedding from model2 is blended into the merged model (default: 1.0) |
+| `x_embedder.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of the x embedder from model2 is blended into the merged model (default: 1.0) |
+| `context_embedder.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of the context embedder from model2 is blended into the merged model (default: 1.0) |
+| `y_embedder.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of the y embedder from model2 is blended into the merged model (default: 1.0) |
+| `t_embedder.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of the t embedder from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.0.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 0 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.1.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 1 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.2.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 2 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.3.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 3 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.4.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 4 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.5.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 5 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.6.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 6 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.7.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 7 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.8.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 8 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.9.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 9 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.10.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 10 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.11.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 11 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.12.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 12 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.13.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 13 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.14.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 14 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.15.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 15 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.16.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 16 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.17.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 17 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.18.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 18 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.19.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 19 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.20.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 20 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.21.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 21 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.22.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 22 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.23.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 23 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.24.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 24 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.25.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 25 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.26.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 26 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.27.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 27 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.28.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 28 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.29.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 29 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.30.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 30 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.31.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 31 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.32.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 32 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.33.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 33 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.34.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 34 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.35.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 35 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.36.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 36 from model2 is blended into the merged model (default: 1.0) |
+| `joint_blocks.37.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of joint block 37 from model2 is blended into the merged model (default: 1.0) |
+| `final_layer.` | FLOAT | Yes | 0.0 to 1.0 | Controls how much of the final layer from model2 is blended into the merged model (default: 1.0) |
+
+**Note:** All blend parameters accept values from 0.0 to 1.0, where 0.0 means no contribution from model2 and 1.0 means full contribution from model2 for that specific component.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The resulting merged model combining features from both input models according to the specified blend parameters |
diff --git a/built-in-nodes/ModelMergeSD3_2B.mdx b/built-in-nodes/ModelMergeSD3_2B.mdx
new file mode 100644
index 000000000..e43a8753f
--- /dev/null
+++ b/built-in-nodes/ModelMergeSD3_2B.mdx
@@ -0,0 +1,53 @@
+---
+title: "ModelMergeSD3_2B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSD3_2B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSD3_2B"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeSD3_2B/en.md)
+
+The ModelMergeSD3_2B node allows you to merge two Stable Diffusion 3 2B models by blending their components with adjustable weights. It provides individual control over embedding layers and transformer blocks, enabling fine-tuned model combinations for specialized generation tasks.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The first model to merge |
+| `model2` | MODEL | Yes | - | The second model to merge |
+| `pos_embed.` | FLOAT | Yes | 0.0 - 1.0 | Position embedding interpolation weight (default: 1.0) |
+| `x_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Input embedding interpolation weight (default: 1.0) |
+| `context_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Context embedding interpolation weight (default: 1.0) |
+| `y_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Y embedding interpolation weight (default: 1.0) |
+| `t_embedder.` | FLOAT | Yes | 0.0 - 1.0 | Time embedding interpolation weight (default: 1.0) |
+| `joint_blocks.0.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 0 interpolation weight (default: 1.0) |
+| `joint_blocks.1.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 1 interpolation weight (default: 1.0) |
+| `joint_blocks.2.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 2 interpolation weight (default: 1.0) |
+| `joint_blocks.3.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 3 interpolation weight (default: 1.0) |
+| `joint_blocks.4.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 4 interpolation weight (default: 1.0) |
+| `joint_blocks.5.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 5 interpolation weight (default: 1.0) |
+| `joint_blocks.6.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 6 interpolation weight (default: 1.0) |
+| `joint_blocks.7.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 7 interpolation weight (default: 1.0) |
+| `joint_blocks.8.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 8 interpolation weight (default: 1.0) |
+| `joint_blocks.9.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 9 interpolation weight (default: 1.0) |
+| `joint_blocks.10.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 10 interpolation weight (default: 1.0) |
+| `joint_blocks.11.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 11 interpolation weight (default: 1.0) |
+| `joint_blocks.12.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 12 interpolation weight (default: 1.0) |
+| `joint_blocks.13.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 13 interpolation weight (default: 1.0) |
+| `joint_blocks.14.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 14 interpolation weight (default: 1.0) |
+| `joint_blocks.15.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 15 interpolation weight (default: 1.0) |
+| `joint_blocks.16.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 16 interpolation weight (default: 1.0) |
+| `joint_blocks.17.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 17 interpolation weight (default: 1.0) |
+| `joint_blocks.18.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 18 interpolation weight (default: 1.0) |
+| `joint_blocks.19.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 19 interpolation weight (default: 1.0) |
+| `joint_blocks.20.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 20 interpolation weight (default: 1.0) |
+| `joint_blocks.21.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 21 interpolation weight (default: 1.0) |
+| `joint_blocks.22.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 22 interpolation weight (default: 1.0) |
+| `joint_blocks.23.` | FLOAT | Yes | 0.0 - 1.0 | Joint block 23 interpolation weight (default: 1.0) |
+| `final_layer.` | FLOAT | Yes | 0.0 - 1.0 | Final layer interpolation weight (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining features from both input models |
diff --git a/built-in-nodes/ModelMergeSDXL.mdx b/built-in-nodes/ModelMergeSDXL.mdx
new file mode 100644
index 000000000..4205309c2
--- /dev/null
+++ b/built-in-nodes/ModelMergeSDXL.mdx
@@ -0,0 +1,47 @@
+---
+title: "ModelMergeSDXL - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSDXL node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSDXL"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeSDXL/en.md)
+
+The ModelMergeSDXL node allows you to blend two SDXL models together by adjusting the influence of each model on different parts of the architecture. You can control how much each model contributes to time embeddings, label embeddings, and various blocks within the model structure. This creates a hybrid model that combines characteristics from both input models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | The first SDXL model to merge |
+| `model2` | MODEL | Yes | - | The second SDXL model to merge |
+| `time_embed.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for time embedding layers (default: 1.0) |
+| `label_emb.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for label embedding layers (default: 1.0) |
+| `input_blocks.0` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 0 (default: 1.0) |
+| `input_blocks.1` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 1 (default: 1.0) |
+| `input_blocks.2` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 2 (default: 1.0) |
+| `input_blocks.3` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 3 (default: 1.0) |
+| `input_blocks.4` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 4 (default: 1.0) |
+| `input_blocks.5` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 5 (default: 1.0) |
+| `input_blocks.6` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 6 (default: 1.0) |
+| `input_blocks.7` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 7 (default: 1.0) |
+| `input_blocks.8` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for input block 8 (default: 1.0) |
+| `middle_block.0` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for middle block 0 (default: 1.0) |
+| `middle_block.1` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for middle block 1 (default: 1.0) |
+| `middle_block.2` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for middle block 2 (default: 1.0) |
+| `output_blocks.0` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 0 (default: 1.0) |
+| `output_blocks.1` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 1 (default: 1.0) |
+| `output_blocks.2` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 2 (default: 1.0) |
+| `output_blocks.3` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 3 (default: 1.0) |
+| `output_blocks.4` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 4 (default: 1.0) |
+| `output_blocks.5` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 5 (default: 1.0) |
+| `output_blocks.6` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 6 (default: 1.0) |
+| `output_blocks.7` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 7 (default: 1.0) |
+| `output_blocks.8` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output block 8 (default: 1.0) |
+| `out.` | FLOAT | Yes | 0.0 - 1.0 | Blending weight for output layers (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged SDXL model combining characteristics from both input models |
diff --git a/built-in-nodes/ModelMergeSimple.mdx b/built-in-nodes/ModelMergeSimple.mdx
new file mode 100644
index 000000000..e125ca452
--- /dev/null
+++ b/built-in-nodes/ModelMergeSimple.mdx
@@ -0,0 +1,24 @@
+---
+title: "ModelMergeSimple - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSimple node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSimple"
+icon: "circle"
+mode: wide
+---
+The ModelMergeSimple node is designed for merging two models by blending their parameters based on a specified ratio. This node facilitates the creation of hybrid models that combine the strengths or characteristics of both input models.
+
+The `ratio` parameter determines the blending ratio between the two models. When this value is 1, the output model is 100% `model1`, and when this value is 0, the output model is 100% `model2`.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model1`  | `MODEL`     | The first model to be merged. It serves as the base model onto which patches from the second model are applied. |
+| `model2`  | `MODEL`     | The second model whose patches are applied onto the first model, influenced by the specified ratio. |
+| `ratio`   | `FLOAT`     | When this value is 1, the output model is 100% `model1`, and when this value is 0, the output model is 100% `model2`. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The resulting merged model, incorporating elements from both input models according to the specified ratio. |
diff --git a/built-in-nodes/ModelMergeSubtract.mdx b/built-in-nodes/ModelMergeSubtract.mdx
new file mode 100644
index 000000000..230290c71
--- /dev/null
+++ b/built-in-nodes/ModelMergeSubtract.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelMergeSubtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSubtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSubtract"
+icon: "circle"
+mode: wide
+---
+
+This node is designed for advanced model merging operations, specifically to subtract the parameters of one model from another based on a specified multiplier. It enables the customization of model behaviors by adjusting the influence of one model's parameters over another, facilitating the creation of new, hybrid models.
+
+## Inputs
+
+| Parameter     | Data Type | Description |
+|---------------|--------------|-------------|
+| `model1`      | `MODEL`     | The base model from which parameters will be subtracted. |
+| `model2`      | `MODEL`     | The model whose parameters will be subtracted from the base model. |
+| `multiplier`  | `FLOAT`     | A floating-point value that scales the subtraction effect on the base model's parameters. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The resulting model after subtracting the parameters of one model from another, scaled by the multiplier. |
diff --git a/built-in-nodes/ModelMergeWAN2_1.mdx b/built-in-nodes/ModelMergeWAN2_1.mdx
new file mode 100644
index 000000000..cbe6de822
--- /dev/null
+++ b/built-in-nodes/ModelMergeWAN2_1.mdx
@@ -0,0 +1,71 @@
+---
+title: "ModelMergeWAN2_1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeWAN2_1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeWAN2_1"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeWAN2_1/en.md)
+
+The ModelMergeWAN2_1 node merges two models by blending their components using weighted averages. It supports different model sizes including 1.3B models with 30 blocks and 14B models with 40 blocks, with special handling for image to video models that include an extra image embedding component. Each component of the models can be individually weighted to control the blending ratio between the two input models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | Yes | - | First model to merge |
+| `model2` | MODEL | Yes | - | Second model to merge |
+| `patch_embedding.` | FLOAT | Yes | 0.0 - 1.0 | Weight for patch embedding component (default: 1.0) |
+| `time_embedding.` | FLOAT | Yes | 0.0 - 1.0 | Weight for time embedding component (default: 1.0) |
+| `time_projection.` | FLOAT | Yes | 0.0 - 1.0 | Weight for time projection component (default: 1.0) |
+| `text_embedding.` | FLOAT | Yes | 0.0 - 1.0 | Weight for text embedding component (default: 1.0) |
+| `img_emb.` | FLOAT | Yes | 0.0 - 1.0 | Weight for image embedding component, used in image to video models (default: 1.0) |
+| `blocks.0.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 0 (default: 1.0) |
+| `blocks.1.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 1 (default: 1.0) |
+| `blocks.2.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 2 (default: 1.0) |
+| `blocks.3.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 3 (default: 1.0) |
+| `blocks.4.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 4 (default: 1.0) |
+| `blocks.5.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 5 (default: 1.0) |
+| `blocks.6.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 6 (default: 1.0) |
+| `blocks.7.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 7 (default: 1.0) |
+| `blocks.8.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 8 (default: 1.0) |
+| `blocks.9.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 9 (default: 1.0) |
+| `blocks.10.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 10 (default: 1.0) |
+| `blocks.11.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 11 (default: 1.0) |
+| `blocks.12.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 12 (default: 1.0) |
+| `blocks.13.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 13 (default: 1.0) |
+| `blocks.14.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 14 (default: 1.0) |
+| `blocks.15.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 15 (default: 1.0) |
+| `blocks.16.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 16 (default: 1.0) |
+| `blocks.17.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 17 (default: 1.0) |
+| `blocks.18.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 18 (default: 1.0) |
+| `blocks.19.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 19 (default: 1.0) |
+| `blocks.20.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 20 (default: 1.0) |
+| `blocks.21.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 21 (default: 1.0) |
+| `blocks.22.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 22 (default: 1.0) |
+| `blocks.23.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 23 (default: 1.0) |
+| `blocks.24.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 24 (default: 1.0) |
+| `blocks.25.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 25 (default: 1.0) |
+| `blocks.26.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 26 (default: 1.0) |
+| `blocks.27.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 27 (default: 1.0) |
+| `blocks.28.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 28 (default: 1.0) |
+| `blocks.29.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 29 (default: 1.0) |
+| `blocks.30.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 30 (default: 1.0) |
+| `blocks.31.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 31 (default: 1.0) |
+| `blocks.32.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 32 (default: 1.0) |
+| `blocks.33.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 33 (default: 1.0) |
+| `blocks.34.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 34 (default: 1.0) |
+| `blocks.35.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 35 (default: 1.0) |
+| `blocks.36.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 36 (default: 1.0) |
+| `blocks.37.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 37 (default: 1.0) |
+| `blocks.38.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 38 (default: 1.0) |
+| `blocks.39.` | FLOAT | Yes | 0.0 - 1.0 | Weight for block 39 (default: 1.0) |
+| `head.` | FLOAT | Yes | 0.0 - 1.0 | Weight for head component (default: 1.0) |
+
+**Note:** All weight parameters use a range from 0.0 to 1.0 with 0.01 step increments. The node supports up to 40 blocks to accommodate different model sizes, where 1.3B models use 30 blocks and 14B models use 40 blocks. The `img_emb.` parameter is specifically for image to video models.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The merged model combining components from both input models according to the specified weights |
diff --git a/built-in-nodes/ModelPatchLoader.mdx b/built-in-nodes/ModelPatchLoader.mdx
new file mode 100644
index 000000000..288dacff4
--- /dev/null
+++ b/built-in-nodes/ModelPatchLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "ModelPatchLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelPatchLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelPatchLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelPatchLoader/en.md)
+
+The ModelPatchLoader node loads specialized model patches from the model_patches folder. It automatically detects the type of patch file and loads the appropriate model architecture, then wraps it in a ModelPatcher for use in the workflow. This node supports different patch types including controlnet blocks and feature embedder models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `name` | STRING | Yes | All available model patch files from model_patches folder | The filename of the model patch to load from the model_patches directory |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `MODEL_PATCH` | MODEL_PATCH | The loaded model patch wrapped in a ModelPatcher for use in the workflow |
diff --git a/built-in-nodes/ModelSamplingAuraFlow.mdx b/built-in-nodes/ModelSamplingAuraFlow.mdx
new file mode 100644
index 000000000..c78039759
--- /dev/null
+++ b/built-in-nodes/ModelSamplingAuraFlow.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelSamplingAuraFlow - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingAuraFlow node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingAuraFlow"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingAuraFlow/en.md)
+
+The ModelSamplingAuraFlow node applies a specialized sampling configuration to diffusion models, specifically designed for AuraFlow model architectures. It modifies the model's sampling behavior by applying a shift parameter that adjusts the sampling distribution. This node inherits from the SD3 model sampling framework and provides fine control over the sampling process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to apply the AuraFlow sampling configuration to |
+| `shift` | FLOAT | Yes | 0.0 - 100.0 | The shift value to apply to the sampling distribution (default: 1.73) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with AuraFlow sampling configuration applied |
diff --git a/built-in-nodes/ModelSamplingContinuousEDM.mdx b/built-in-nodes/ModelSamplingContinuousEDM.mdx
new file mode 100644
index 000000000..74a16eb87
--- /dev/null
+++ b/built-in-nodes/ModelSamplingContinuousEDM.mdx
@@ -0,0 +1,24 @@
+---
+title: "ModelSamplingContinuousEDM - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingContinuousEDM node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingContinuousEDM"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to enhance a model's sampling capabilities by integrating continuous EDM (Energy-based Diffusion Models) sampling techniques. It allows for the dynamic adjustment of the noise levels within the model's sampling process, offering a more refined control over the generation quality and diversity.
+
+## Inputs
+
+| Parameter   | Data Type | Python dtype        | Description |
+|-------------|--------------|----------------------|-------------|
+| `model`     | `MODEL`     | `torch.nn.Module`   | The model to be enhanced with continuous EDM sampling capabilities. It serves as the foundation for applying the advanced sampling techniques. |
+| `sampling`  | COMBO[STRING] | `str`             | Specifies the type of sampling to be applied, either 'eps' for epsilon sampling or 'v_prediction' for velocity prediction, influencing the model's behavior during the sampling process. |
+| `sigma_max` | `FLOAT`     | `float`             | The maximum sigma value for noise level, allowing for upper bound control in the noise injection process during sampling. |
+| `sigma_min` | `FLOAT`     | `float`             | The minimum sigma value for noise level, setting the lower limit for noise injection, thus affecting the model's sampling precision. |
+
+## Outputs
+
+| Parameter | Data Type | Python dtype        | Description |
+|-----------|-------------|----------------------|-------------|
+| `model`   | MODEL     | `torch.nn.Module`   | The enhanced model with integrated continuous EDM sampling capabilities, ready for further use in generation tasks. |
diff --git a/built-in-nodes/ModelSamplingContinuousV.mdx b/built-in-nodes/ModelSamplingContinuousV.mdx
new file mode 100644
index 000000000..d34c07fe8
--- /dev/null
+++ b/built-in-nodes/ModelSamplingContinuousV.mdx
@@ -0,0 +1,25 @@
+---
+title: "ModelSamplingContinuousV - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingContinuousV node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingContinuousV"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingContinuousV/en.md)
+
+The ModelSamplingContinuousV node modifies a model's sampling behavior by applying continuous V-prediction sampling parameters. It creates a clone of the input model and configures it with custom sigma range settings for advanced sampling control. This allows users to fine-tune the sampling process with specific minimum and maximum sigma values.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The input model to be modified with continuous V-prediction sampling |
+| `sampling` | STRING | Yes | "v_prediction" | The sampling method to apply (currently only V-prediction is supported) |
+| `sigma_max` | FLOAT | Yes | 0.0 - 1000.0 | The maximum sigma value for sampling (default: 500.0) |
+| `sigma_min` | FLOAT | Yes | 0.0 - 1000.0 | The minimum sigma value for sampling (default: 0.03) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with continuous V-prediction sampling applied |
diff --git a/built-in-nodes/ModelSamplingDiscrete.mdx b/built-in-nodes/ModelSamplingDiscrete.mdx
new file mode 100644
index 000000000..d65eeda6f
--- /dev/null
+++ b/built-in-nodes/ModelSamplingDiscrete.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelSamplingDiscrete - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingDiscrete node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingDiscrete"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to modify the sampling behavior of a model by applying a discrete sampling strategy. It allows for the selection of different sampling methods, such as epsilon, v_prediction, lcm, or x0, and optionally adjusts the model's noise reduction strategy based on the zero-shot noise ratio (zsnr) setting.
+
+## Inputs
+
+| Parameter | Data Type | Python dtype     | Description |
+|-----------|--------------|-------------------|-------------|
+| `model`   | MODEL     | `torch.nn.Module` | The model to which the discrete sampling strategy will be applied. This parameter is crucial as it defines the base model that will undergo modification. |
+| `sampling`| COMBO[STRING] | `str`           | Specifies the discrete sampling method to be applied to the model. The choice of method affects how the model generates samples, offering different strategies for sampling. |
+| `zsnr`    | `BOOLEAN`   | `bool`           | A boolean flag that, when enabled, adjusts the model's noise reduction strategy based on the zero-shot noise ratio. This can influence the quality and characteristics of the generated samples. |
+
+## Outputs
+
+| Parameter | Data Type | Python dtype     | Description |
+|-----------|-------------|-------------------|-------------|
+| `model`   | MODEL     | `torch.nn.Module` | The modified model with the applied discrete sampling strategy. This model is now equipped to generate samples using the specified method and adjustments. |
diff --git a/built-in-nodes/ModelSamplingFlux.mdx b/built-in-nodes/ModelSamplingFlux.mdx
new file mode 100644
index 000000000..c761aaaf9
--- /dev/null
+++ b/built-in-nodes/ModelSamplingFlux.mdx
@@ -0,0 +1,26 @@
+---
+title: "ModelSamplingFlux - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingFlux node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingFlux"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingFlux/en.md)
+
+The ModelSamplingFlux node applies Flux model sampling to a given model by calculating a shift parameter based on image dimensions. It creates a specialized sampling configuration that adjusts the model's behavior according to the specified width, height, and shift parameters, then returns the modified model with the new sampling settings applied.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply Flux sampling to |
+| `max_shift` | FLOAT | Yes | 0.0 - 100.0 | Maximum shift value for sampling calculation (default: 1.15) |
+| `base_shift` | FLOAT | Yes | 0.0 - 100.0 | Base shift value for sampling calculation (default: 0.5) |
+| `width` | INT | Yes | 16 - MAX_RESOLUTION | Width of the target image in pixels (default: 1024) |
+| `height` | INT | Yes | 16 - MAX_RESOLUTION | Height of the target image in pixels (default: 1024) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with Flux sampling configuration applied |
diff --git a/built-in-nodes/ModelSamplingLTXV.mdx b/built-in-nodes/ModelSamplingLTXV.mdx
new file mode 100644
index 000000000..96f00dfc8
--- /dev/null
+++ b/built-in-nodes/ModelSamplingLTXV.mdx
@@ -0,0 +1,25 @@
+---
+title: "ModelSamplingLTXV - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingLTXV node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingLTXV"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingLTXV/en.md)
+
+The ModelSamplingLTXV node applies advanced sampling parameters to a model based on token count. It calculates a shift value using a linear interpolation between base and maximum shift values, with the calculation depending on the number of tokens in the input latent. The node then creates a specialized model sampling configuration and applies it to the input model.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The input model to apply sampling parameters to |
+| `max_shift` | FLOAT | No | 0.0 to 100.0 | The maximum shift value used in calculation (default: 2.05) |
+| `base_shift` | FLOAT | No | 0.0 to 100.0 | The base shift value used in calculation (default: 0.95) |
+| `latent` | LATENT | No | - | Optional latent input used to determine token count for shift calculation |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with applied sampling parameters |
diff --git a/built-in-nodes/ModelSamplingSD3.mdx b/built-in-nodes/ModelSamplingSD3.mdx
new file mode 100644
index 000000000..4cc44e034
--- /dev/null
+++ b/built-in-nodes/ModelSamplingSD3.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelSamplingSD3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingSD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingSD3"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingSD3/en.md)
+
+The ModelSamplingSD3 node applies Stable Diffusion 3 sampling parameters to a model. It modifies the model's sampling behavior by adjusting the shift parameter, which controls the sampling distribution characteristics. The node creates a modified copy of the input model with the specified sampling configuration applied.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The input model to apply SD3 sampling parameters to |
+| `shift` | FLOAT | Yes | 0.0 - 100.0 | Controls the sampling shift parameter (default: 3.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with SD3 sampling parameters applied |
diff --git a/built-in-nodes/ModelSamplingStableCascade.mdx b/built-in-nodes/ModelSamplingStableCascade.mdx
new file mode 100644
index 000000000..48dd781ae
--- /dev/null
+++ b/built-in-nodes/ModelSamplingStableCascade.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelSamplingStableCascade - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingStableCascade node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingStableCascade"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingStableCascade/en.md)
+
+The ModelSamplingStableCascade node applies stable cascade sampling to a model by adjusting the sampling parameters with a shift value. It creates a modified version of the input model with custom sampling configuration for stable cascade generation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The input model to apply stable cascade sampling to |
+| `shift` | FLOAT | Yes | 0.0 - 100.0 | The shift value to apply to the sampling parameters (default: 2.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with stable cascade sampling applied |
diff --git a/built-in-nodes/ModelSave.mdx b/built-in-nodes/ModelSave.mdx
new file mode 100644
index 000000000..ee70b99db
--- /dev/null
+++ b/built-in-nodes/ModelSave.mdx
@@ -0,0 +1,25 @@
+---
+title: "ModelSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSave"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSave/en.md)
+
+The ModelSave node saves trained or modified models to your computer's storage. It takes a model as input and writes it to a file with your specified filename. This allows you to preserve your work and reuse models in future projects.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to be saved to disk |
+| `filename_prefix` | STRING | Yes | - | The filename and path prefix for the saved model file (default: "diffusion_models/ComfyUI") |
+| `prompt` | PROMPT | No | - | Workflow prompt information (automatically provided) |
+| `extra_pnginfo` | EXTRA_PNGINFO | No | - | Additional workflow metadata (automatically provided) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| *None* | - | This node does not return any output values |
diff --git a/built-in-nodes/MoonvalleyImg2VideoNode.mdx b/built-in-nodes/MoonvalleyImg2VideoNode.mdx
new file mode 100644
index 000000000..3f7821f48
--- /dev/null
+++ b/built-in-nodes/MoonvalleyImg2VideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "MoonvalleyImg2VideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MoonvalleyImg2VideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MoonvalleyImg2VideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MoonvalleyImg2VideoNode/en.md)
+
+The Moonvalley Marey Image to Video node transforms a reference image into a video using the Moonvalley API. It takes an input image and a text prompt to generate a video with specified resolution, quality settings, and creative controls. The node handles the entire process from image upload to video generation and download.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The reference image used to generate the video |
+| `prompt` | STRING | Yes | - | Text description for video generation (multiline input) |
+| `negative_prompt` | STRING | No | - | Negative prompt text to exclude unwanted elements (default: extensive negative prompt list) |
+| `resolution` | COMBO | No | "16:9 (1920 x 1080)"<br />"9:16 (1080 x 1920)"<br />"1:1 (1152 x 1152)"<br />"4:3 (1536 x 1152)"<br />"3:4 (1152 x 1536)" | Resolution of the output video (default: "16:9 (1920 x 1080)") |
+| `prompt_adherence` | FLOAT | No | 1.0 - 20.0 | Guidance scale for generation control (default: 4.5, step: 1.0) |
+| `seed` | INT | No | 0 - 4294967295 | Random seed value (default: 9, control after generate enabled) |
+| `steps` | INT | No | 1 - 100 | Number of denoising steps (default: 33, step: 1) |
+
+**Constraints:**
+
+- The input image must have dimensions between 300x300 pixels and the maximum allowed height/width
+- Prompt and negative prompt text length is limited to the Moonvalley Marey maximum prompt length
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video output |
diff --git a/built-in-nodes/MoonvalleyTxt2VideoNode.mdx b/built-in-nodes/MoonvalleyTxt2VideoNode.mdx
new file mode 100644
index 000000000..a4f58bf3c
--- /dev/null
+++ b/built-in-nodes/MoonvalleyTxt2VideoNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "MoonvalleyTxt2VideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MoonvalleyTxt2VideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MoonvalleyTxt2VideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MoonvalleyTxt2VideoNode/en.md)
+
+The Moonvalley Marey Text to Video node generates video content from text descriptions using the Moonvalley API. It takes a text prompt and converts it into a video with customizable settings for resolution, quality, and style. The node handles the entire process from sending the generation request to downloading the final video output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text description of the video content to generate |
+| `negative_prompt` | STRING | No | - | Negative prompt text (default: extensive list of excluded elements like synthetic, scene cut, artifacts, noise, etc.) |
+| `resolution` | STRING | No | "16:9 (1920 x 1080)"<br />"9:16 (1080 x 1920)"<br />"1:1 (1152 x 1152)"<br />"4:3 (1536 x 1152)"<br />"3:4 (1152 x 1536)"<br />"21:9 (2560 x 1080)" | Resolution of the output video (default: "16:9 (1920 x 1080)") |
+| `prompt_adherence` | FLOAT | No | 1.0-20.0 | Guidance scale for generation control (default: 4.0) |
+| `seed` | INT | No | 0-4294967295 | Random seed value (default: 9) |
+| `steps` | INT | No | 1-100 | Inference steps (default: 33) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The generated video output based on the text prompt |
diff --git a/built-in-nodes/MoonvalleyVideo2VideoNode.mdx b/built-in-nodes/MoonvalleyVideo2VideoNode.mdx
new file mode 100644
index 000000000..d596e6c9c
--- /dev/null
+++ b/built-in-nodes/MoonvalleyVideo2VideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "MoonvalleyVideo2VideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MoonvalleyVideo2VideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MoonvalleyVideo2VideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MoonvalleyVideo2VideoNode/en.md)
+
+The Moonvalley Marey Video to Video node transforms an input video into a new video based on a text description. It uses the Moonvalley API to generate videos that match your prompt while preserving motion or pose characteristics from the original video. You can control the style and content of the output video through text prompts and various generation parameters.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Describes the video to generate (multiline input) |
+| `negative_prompt` | STRING | No | - | Negative prompt text (default: extensive list of negative descriptors) |
+| `seed` | INT | Yes | 0-4294967295 | Random seed value (default: 9) |
+| `video` | VIDEO | Yes | - | The reference video used to generate the output video. Must be at least 5 seconds long. Videos longer than 5s will be automatically trimmed. Only MP4 format supported. |
+| `control_type` | COMBO | No | "Motion Transfer"<br />"Pose Transfer" | Control type selection (default: "Motion Transfer") |
+| `motion_intensity` | INT | No | 0-100 | Only used if control_type is 'Motion Transfer' (default: 100) |
+| `steps` | INT | Yes | 1-100 | Number of inference steps (default: 33) |
+
+**Note:** The `motion_intensity` parameter is only applied when `control_type` is set to "Motion Transfer". When using "Pose Transfer", this parameter is ignored.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video output |
diff --git a/built-in-nodes/Morphology.mdx b/built-in-nodes/Morphology.mdx
new file mode 100644
index 000000000..eb9e47f88
--- /dev/null
+++ b/built-in-nodes/Morphology.mdx
@@ -0,0 +1,24 @@
+---
+title: "Morphology - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Morphology node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Morphology"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Morphology/en.md)
+
+The Morphology node applies various morphological operations to images, which are mathematical operations used to process and analyze shapes in images. It can perform operations like erosion, dilation, opening, closing, and more using a customizable kernel size to control the effect strength.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to process |
+| `operation` | STRING | Yes | `"erode"`<br />`"dilate"`<br />`"open"`<br />`"close"`<br />`"gradient"`<br />`"bottom_hat"`<br />`"top_hat"` | The morphological operation to apply |
+| `kernel_size` | INT | No | 3-999 | The size of the structuring element kernel (default: 3) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The processed image after applying the morphological operation |
diff --git a/built-in-nodes/NAGuidance.mdx b/built-in-nodes/NAGuidance.mdx
new file mode 100644
index 000000000..3a818ef6d
--- /dev/null
+++ b/built-in-nodes/NAGuidance.mdx
@@ -0,0 +1,25 @@
+---
+title: "NAGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the NAGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "NAGuidance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NAGuidance/en.md)
+
+The NAGuidance node applies Normalized Attention Guidance to a model. This technique enables the use of negative prompts with distilled or schnell models by modifying the model's attention mechanism during the sampling process to steer the generation away from undesired concepts.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply Normalized Attention Guidance to. |
+| `nag_scale` | FLOAT | Yes | 0.0 - 50.0 | The guidance scale factor. Higher values push the generation further from the negative prompt. (default: 5.0) |
+| `nag_alpha` | FLOAT | Yes | 0.0 - 1.0 | The blending factor for the normalized attention. A value of 1.0 fully replaces the original attention, while 0.0 has no effect. (default: 0.5) |
+| `nag_tau` | FLOAT | Yes | 1.0 - 10.0 | A scaling factor used to limit the normalization ratio. (default: 1.5) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The patched model with Normalized Attention Guidance enabled. |
diff --git a/built-in-nodes/NormalizeImages.mdx b/built-in-nodes/NormalizeImages.mdx
new file mode 100644
index 000000000..6346738e9
--- /dev/null
+++ b/built-in-nodes/NormalizeImages.mdx
@@ -0,0 +1,24 @@
+---
+title: "NormalizeImages - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the NormalizeImages node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "NormalizeImages"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeImages/en.md)
+
+This node adjusts the pixel values of an input image using a mathematical normalization process. It subtracts a specified mean value from each pixel and then divides the result by a specified standard deviation. This is a common preprocessing step to prepare image data for other machine learning models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be normalized. |
+| `mean` | FLOAT | No | 0.0 - 1.0 | The mean value to subtract from the image pixels (default: 0.5). |
+| `std` | FLOAT | No | 0.001 - 1.0 | The standard deviation value to divide the image pixels by (default: 0.5). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resulting image after the normalization process has been applied. |
diff --git a/built-in-nodes/NormalizeVideoLatentStart.mdx b/built-in-nodes/NormalizeVideoLatentStart.mdx
new file mode 100644
index 000000000..4bb2cede3
--- /dev/null
+++ b/built-in-nodes/NormalizeVideoLatentStart.mdx
@@ -0,0 +1,26 @@
+---
+title: "NormalizeVideoLatentStart - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the NormalizeVideoLatentStart node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "NormalizeVideoLatentStart"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeVideoLatentStart/en.md)
+
+This node adjusts the first few frames of a video latent to make them look more like the frames that come after. It calculates the average and variation from a set of reference frames later in the video and applies those same characteristics to the starting frames. This helps create a smoother and more consistent visual transition at the beginning of a video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `latent` | LATENT | Yes | - | The video latent representation to process. |
+| `start_frame_count` | INT | No | 1 to 16384 | Number of latent frames to normalize, counted from the start (default: 4). |
+| `reference_frame_count` | INT | No | 1 to 16384 | Number of latent frames after the start frames to use as reference (default: 5). |
+
+**Note:** The `reference_frame_count` is automatically limited to the number of frames available after the starting frames. If the video latent is only 1 frame long, no normalization is performed and the original latent is returned unchanged.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `latent` | LATENT | The processed video latent with the starting frames normalized. |
diff --git a/built-in-nodes/Note.mdx b/built-in-nodes/Note.mdx
new file mode 100644
index 000000000..ecf7b1806
--- /dev/null
+++ b/built-in-nodes/Note.mdx
@@ -0,0 +1,14 @@
+---
+title: "Note - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Note node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Note"
+icon: "circle"
+mode: wide
+---
+Node to add annotations to a workflow.
+
+## Inputs
+
+## Outputs
+
+The node doesn't have outputs.
diff --git a/built-in-nodes/OpenAIChatConfig.mdx b/built-in-nodes/OpenAIChatConfig.mdx
new file mode 100644
index 000000000..c5239fcfd
--- /dev/null
+++ b/built-in-nodes/OpenAIChatConfig.mdx
@@ -0,0 +1,24 @@
+---
+title: "OpenAIChatConfig - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIChatConfig node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIChatConfig"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIChatConfig/en.md)
+
+The OpenAIChatConfig node allows setting additional configuration options for the OpenAI Chat Node. It provides advanced settings that control how the model generates responses, including truncation behavior, output length limits, and custom instructions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `truncation` | COMBO | Yes | `"auto"`<br />`"disabled"` | The truncation strategy to use for the model response. auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.disabled: If a model response will exceed the context window size for a model, the request will fail with a 400 error (default: "auto") |
+| `max_output_tokens` | INT | No | 16-16384 | An upper bound for the number of tokens that can be generated for a response, including visible output tokens (default: 4096) |
+| `instructions` | STRING | No | - | Additional instructions for the model response (multiline input supported) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `OPENAI_CHAT_CONFIG` | OPENAI_CHAT_CONFIG | Configuration object containing the specified settings for use with OpenAI Chat Nodes |
diff --git a/built-in-nodes/OpenAIChatNode.mdx b/built-in-nodes/OpenAIChatNode.mdx
new file mode 100644
index 000000000..a25d5ed4d
--- /dev/null
+++ b/built-in-nodes/OpenAIChatNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "OpenAIChatNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIChatNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIChatNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIChatNode/en.md)
+
+This node generates text responses from an OpenAI model. It allows you to have conversations with the AI model by sending text prompts and receiving generated responses. The node supports multi-turn conversations where it can remember previous context, and it can also process images and files as additional context for the model.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text inputs to the model, used to generate a response (default: empty) |
+| `persist_context` | BOOLEAN | Yes | - | Persist chat context between calls for multi-turn conversation (default: True) |
+| `model` | COMBO | Yes | Multiple OpenAI models available | The OpenAI model to use for generating responses |
+| `images` | IMAGE | No | - | Optional image(s) to use as context for the model. To include multiple images, you can use the Batch Images node (default: None) |
+| `files` | OPENAI_INPUT_FILES | No | - | Optional file(s) to use as context for the model. Accepts inputs from the OpenAI Chat Input Files node (default: None) |
+| `advanced_options` | OPENAI_CHAT_CONFIG | No | - | Optional configuration for the model. Accepts inputs from the OpenAI Chat Advanced Options node (default: None) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output_text` | STRING | The text response generated by the OpenAI model |
diff --git a/built-in-nodes/OpenAIDalle2.mdx b/built-in-nodes/OpenAIDalle2.mdx
new file mode 100644
index 000000000..6135449f2
--- /dev/null
+++ b/built-in-nodes/OpenAIDalle2.mdx
@@ -0,0 +1,33 @@
+---
+title: "OpenAIDalle2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIDalle2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIDalle2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIDalle2/en.md)
+
+```markdown
+Generates images synchronously via OpenAI's DALL·E 2 endpoint.
+
+## How It Works
+
+This node connects to OpenAI's DALL·E 2 API to create images based on text descriptions. When you provide a text prompt, the node sends it to OpenAI's servers which generate corresponding images and return them to ComfyUI. The node can operate in two modes: standard image generation using just a text prompt, or image editing mode when both an image and mask are provided. In editing mode, it uses the mask to determine which parts of the original image should be modified while keeping other areas unchanged.
+
+## Inputs
+
+| Parameter | Data Type | Input Type | Default | Range | Description |
+|-----------|-----------|------------|---------|-------|-------------|
+| `prompt` | STRING | required | "" | - | Text prompt for DALL·E |
+| `seed` | INT | optional | 0 | 0 to 2147483647 | not implemented yet in backend |
+| `size` | COMBO | optional | "1024x1024" | "256x256", "512x512", "1024x1024" | Image size |
+| `n` | INT | optional | 1 | 1 to 8 | How many images to generate |
+| `image` | IMAGE | optional | None | - | Optional reference image for image editing. |
+| `mask` | MASK | optional | None | - | Optional mask for inpainting (white areas will be replaced) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The generated or edited image(s) from DALL·E 2 |
+```
diff --git a/built-in-nodes/OpenAIDalle3.mdx b/built-in-nodes/OpenAIDalle3.mdx
new file mode 100644
index 000000000..738ec6e75
--- /dev/null
+++ b/built-in-nodes/OpenAIDalle3.mdx
@@ -0,0 +1,26 @@
+---
+title: "OpenAIDalle3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIDalle3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIDalle3"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIDalle3/en.md)
+
+Generates images synchronously via OpenAI's DALL·E 3 endpoint. This node takes a text prompt and creates corresponding images using OpenAI's DALL·E 3 model, allowing you to specify image quality, style, and dimensions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text prompt for DALL·E (default: "") |
+| `seed` | INT | No | 0 to 2147483647 | not implemented yet in backend (default: 0) |
+| `quality` | COMBO | No | "standard"<br />"hd" | Image quality (default: "standard") |
+| `style` | COMBO | No | "natural"<br />"vivid" | Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. (default: "natural") |
+| `size` | COMBO | No | "1024x1024"<br />"1024x1792"<br />"1792x1024" | Image size (default: "1024x1024") |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The generated image from DALL·E 3 |
diff --git a/built-in-nodes/OpenAIGPTImage1.mdx b/built-in-nodes/OpenAIGPTImage1.mdx
new file mode 100644
index 000000000..2d25be883
--- /dev/null
+++ b/built-in-nodes/OpenAIGPTImage1.mdx
@@ -0,0 +1,36 @@
+---
+title: "OpenAIGPTImage1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIGPTImage1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIGPTImage1"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIGPTImage1/en.md)
+
+Generates images synchronously via OpenAI's GPT Image 1 endpoint. This node can create new images from text prompts or edit existing images when provided with an input image and optional mask.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text prompt for GPT Image 1 (default: "") |
+| `seed` | INT | No | 0 to 2147483647 | Random seed for generation (default: 0) - not implemented yet in backend |
+| `quality` | COMBO | No | "low"<br />"medium"<br />"high" | Image quality, affects cost and generation time (default: "low") |
+| `background` | COMBO | No | "opaque"<br />"transparent" | Return image with or without background (default: "opaque") |
+| `size` | COMBO | No | "auto"<br />"1024x1024"<br />"1024x1536"<br />"1536x1024" | Image size (default: "auto") |
+| `n` | INT | No | 1 to 8 | How many images to generate (default: 1) |
+| `image` | IMAGE | No | - | Optional reference image for image editing (default: None) |
+| `mask` | MASK | No | - | Optional mask for inpainting (white areas will be replaced) (default: None) |
+
+**Parameter Constraints:**
+
+- When `image` is provided, the node switches to image editing mode
+- `mask` can only be used when `image` is provided
+- When using `mask`, only single images are supported (batch size must be 1)
+- `mask` and `image` must be the same size
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | Generated or edited image(s) |
diff --git a/built-in-nodes/OpenAIInputFiles.mdx b/built-in-nodes/OpenAIInputFiles.mdx
new file mode 100644
index 000000000..6181a499a
--- /dev/null
+++ b/built-in-nodes/OpenAIInputFiles.mdx
@@ -0,0 +1,29 @@
+---
+title: "OpenAIInputFiles - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIInputFiles node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIInputFiles"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIInputFiles/en.md)
+
+Loads and formats input files for OpenAI API. This node prepares text and PDF files to include as context inputs for the OpenAI Chat Node. The files will be read by the OpenAI model when generating responses. Multiple input file nodes can be chained together to include multiple files in a single message.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `file` | COMBO | Yes | Multiple options available | Input files to include as context for the model. Only accepts text (.txt) and PDF (.pdf) files for now. Files must be smaller than 32MB. |
+| `OPENAI_INPUT_FILES` | OPENAI_INPUT_FILES | No | N/A | An optional additional file(s) to batch together with the file loaded from this node. Allows chaining of input files so that a single message can include multiple input files. |
+
+**File Constraints:**
+
+- Only .txt and .pdf files are supported
+- Maximum file size: 32MB
+- Files are loaded from the input directory
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `OPENAI_INPUT_FILES` | OPENAI_INPUT_FILES | Formatted input files ready to be used as context for OpenAI API calls. |
diff --git a/built-in-nodes/OpenAIVideoSora2.mdx b/built-in-nodes/OpenAIVideoSora2.mdx
new file mode 100644
index 000000000..18c22b3cb
--- /dev/null
+++ b/built-in-nodes/OpenAIVideoSora2.mdx
@@ -0,0 +1,33 @@
+---
+title: "OpenAIVideoSora2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIVideoSora2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIVideoSora2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIVideoSora2/en.md)
+
+The OpenAIVideoSora2 node generates videos using OpenAI's Sora models. It creates video content based on text prompts and optional input images, then returns the generated video output. The node supports different video durations and resolutions depending on the selected model.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | "sora-2"<br />"sora-2-pro" | The OpenAI Sora model to use for video generation (default: "sora-2") |
+| `prompt` | STRING | Yes | - | Guiding text; may be empty if an input image is present (default: empty) |
+| `size` | COMBO | Yes | "720x1280"<br />"1280x720"<br />"1024x1792"<br />"1792x1024" | The resolution for the generated video (default: "1280x720") |
+| `duration` | COMBO | Yes | 4<br />8<br />12 | The duration of the generated video in seconds (default: 8) |
+| `image` | IMAGE | No | - | Optional input image for video generation |
+| `seed` | INT | No | 0 to 2147483647 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0) |
+
+**Constraints and Limitations:**
+
+- The "sora-2" model only supports "720x1280" and "1280x720" resolutions
+- Only one input image is supported when using the image parameter
+- Results are nondeterministic regardless of the seed value
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video output |
diff --git a/built-in-nodes/OptimalStepsScheduler.mdx b/built-in-nodes/OptimalStepsScheduler.mdx
new file mode 100644
index 000000000..0fcefc3d3
--- /dev/null
+++ b/built-in-nodes/OptimalStepsScheduler.mdx
@@ -0,0 +1,26 @@
+---
+title: "OptimalStepsScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OptimalStepsScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OptimalStepsScheduler"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OptimalStepsScheduler/en.md)
+
+The OptimalStepsScheduler node calculates noise schedule sigmas for diffusion models based on the selected model type and step configuration. It adjusts the total number of steps according to the denoise parameter and interpolates the noise levels to match the requested step count. The node returns a sequence of sigma values that determine the noise levels used during the diffusion sampling process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_type` | COMBO | Yes | "FLUX"<br />"Wan"<br />"Chroma" | The type of diffusion model to use for noise level calculation |
+| `steps` | INT | Yes | 3-1000 | The total number of sampling steps to calculate (default: 20) |
+| `denoise` | FLOAT | No | 0.0-1.0 | Controls the denoising strength, which adjusts the effective number of steps (default: 1.0) |
+
+**Note:** When `denoise` is set to less than 1.0, the node calculates the effective steps as `steps * denoise`. If `denoise` is set to 0.0, the node returns an empty tensor.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | A sequence of sigma values representing the noise schedule for diffusion sampling |
diff --git a/built-in-nodes/PairConditioningCombine.mdx b/built-in-nodes/PairConditioningCombine.mdx
new file mode 100644
index 000000000..bed971685
--- /dev/null
+++ b/built-in-nodes/PairConditioningCombine.mdx
@@ -0,0 +1,26 @@
+---
+title: "PairConditioningCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PairConditioningCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PairConditioningCombine"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningCombine/en.md)
+
+The PairConditioningCombine node combines two pairs of conditioning data (positive and negative) into a single pair. It takes two separate conditioning pairs as input and merges them using ComfyUI's internal conditioning combination logic. This node is experimental and primarily used for advanced conditioning manipulation workflows.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive_A` | CONDITIONING | Yes | - | First positive conditioning input |
+| `negative_A` | CONDITIONING | Yes | - | First negative conditioning input |
+| `positive_B` | CONDITIONING | Yes | - | Second positive conditioning input |
+| `negative_B` | CONDITIONING | Yes | - | Second negative conditioning input |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Combined positive conditioning output |
+| `negative` | CONDITIONING | Combined negative conditioning output |
diff --git a/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx b/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx
new file mode 100644
index 000000000..2562c78db
--- /dev/null
+++ b/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx
@@ -0,0 +1,27 @@
+---
+title: "PairConditioningSetDefaultAndCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PairConditioningSetDefaultAndCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PairConditioningSetDefaultAndCombine"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetDefaultAndCombine/en.md)
+
+The PairConditioningSetDefaultAndCombine node sets default conditioning values and combines them with input conditioning data. It takes positive and negative conditioning inputs along with their default counterparts, then processes them through ComfyUI's hook system to produce final conditioning outputs that incorporate the default values.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The primary positive conditioning input to be processed |
+| `negative` | CONDITIONING | Yes | - | The primary negative conditioning input to be processed |
+| `positive_DEFAULT` | CONDITIONING | Yes | - | The default positive conditioning values to be used as fallback |
+| `negative_DEFAULT` | CONDITIONING | Yes | - | The default negative conditioning values to be used as fallback |
+| `hooks` | HOOKS | No | - | Optional hook group for custom processing logic |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The processed positive conditioning with default values incorporated |
+| `negative` | CONDITIONING | The processed negative conditioning with default values incorporated |
diff --git a/built-in-nodes/PairConditioningSetProperties.mdx b/built-in-nodes/PairConditioningSetProperties.mdx
new file mode 100644
index 000000000..74fb609c6
--- /dev/null
+++ b/built-in-nodes/PairConditioningSetProperties.mdx
@@ -0,0 +1,29 @@
+---
+title: "PairConditioningSetProperties - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PairConditioningSetProperties node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PairConditioningSetProperties"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetProperties/en.md)
+
+The PairConditioningSetProperties node allows you to modify the properties of both positive and negative conditioning pairs simultaneously. It applies strength adjustments, conditioning area settings, and optional masking or timing controls to both conditioning inputs, returning the modified positive and negative conditioning data.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive_NEW` | CONDITIONING | Yes | - | The positive conditioning input to modify |
+| `negative_NEW` | CONDITIONING | Yes | - | The negative conditioning input to modify |
+| `strength` | FLOAT | Yes | 0.0 to 10.0 | The strength multiplier applied to the conditioning (default: 1.0) |
+| `set_cond_area` | STRING | Yes | "default"<br />"mask bounds" | Determines how the conditioning area is calculated |
+| `mask` | MASK | No | - | Optional mask to constrain the conditioning area |
+| `hooks` | HOOKS | No | - | Optional hook group for advanced conditioning modifications |
+| `timesteps` | TIMESTEPS_RANGE | No | - | Optional timestep range to limit when conditioning is applied |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The modified positive conditioning with applied properties |
+| `negative` | CONDITIONING | The modified negative conditioning with applied properties |
diff --git a/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx b/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx
new file mode 100644
index 000000000..8954293b5
--- /dev/null
+++ b/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx
@@ -0,0 +1,31 @@
+---
+title: "PairConditioningSetPropertiesAndCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PairConditioningSetPropertiesAndCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PairConditioningSetPropertiesAndCombine"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetPropertiesAndCombine/en.md)
+
+The PairConditioningSetPropertiesAndCombine node modifies and combines conditioning pairs by applying new conditioning data to existing positive and negative conditioning inputs. It allows you to adjust the strength of the applied conditioning and control how the conditioning area is set. This node is particularly useful for advanced conditioning manipulation workflows where you need to blend multiple conditioning sources together.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The original positive conditioning input |
+| `negative` | CONDITIONING | Yes | - | The original negative conditioning input |
+| `positive_NEW` | CONDITIONING | Yes | - | The new positive conditioning to apply |
+| `negative_NEW` | CONDITIONING | Yes | - | The new negative conditioning to apply |
+| `strength` | FLOAT | Yes | 0.0 to 10.0 | The strength factor for applying the new conditioning (default: 1.0) |
+| `set_cond_area` | STRING | Yes | "default"<br />"mask bounds" | Controls how the conditioning area is applied |
+| `mask` | MASK | No | - | Optional mask to constrain the conditioning application area |
+| `hooks` | HOOKS | No | - | Optional hook group for advanced control |
+| `timesteps` | TIMESTEPS_RANGE | No | - | Optional timestep range specification |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The combined positive conditioning output |
+| `negative` | CONDITIONING | The combined negative conditioning output |
diff --git a/built-in-nodes/PatchModelAddDownscale.mdx b/built-in-nodes/PatchModelAddDownscale.mdx
new file mode 100644
index 000000000..d0f8ef6ff
--- /dev/null
+++ b/built-in-nodes/PatchModelAddDownscale.mdx
@@ -0,0 +1,29 @@
+---
+title: "PatchModelAddDownscale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PatchModelAddDownscale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PatchModelAddDownscale"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PatchModelAddDownscale/en.md)
+
+The PatchModelAddDownscale node implements Kohya Deep Shrink functionality by applying downscaling and upscaling operations to specific blocks in a model. It reduces the resolution of intermediate features during processing and then restores them to their original size, which can improve performance while maintaining quality. The node allows precise control over when and how these scaling operations occur during the model's execution.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply the downscale patch to |
+| `block_number` | INT | No | 1-32 | The specific block number where downscaling will be applied (default: 3) |
+| `downscale_factor` | FLOAT | No | 0.1-9.0 | The factor by which to downscale the features (default: 2.0) |
+| `start_percent` | FLOAT | No | 0.0-1.0 | The starting point in the denoising process where downscaling begins (default: 0.0) |
+| `end_percent` | FLOAT | No | 0.0-1.0 | The ending point in the denoising process where downscaling stops (default: 0.35) |
+| `downscale_after_skip` | BOOLEAN | No | - | Whether to apply downscaling after skip connections (default: True) |
+| `downscale_method` | COMBO | No | "bicubic"<br />"nearest-exact"<br />"bilinear"<br />"area"<br />"bislerp" | The interpolation method used for downscaling operations |
+| `upscale_method` | COMBO | No | "bicubic"<br />"nearest-exact"<br />"bilinear"<br />"area"<br />"bislerp" | The interpolation method used for upscaling operations |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with downscale patch applied |
diff --git a/built-in-nodes/PerpNeg.mdx b/built-in-nodes/PerpNeg.mdx
new file mode 100644
index 000000000..0d619c9b0
--- /dev/null
+++ b/built-in-nodes/PerpNeg.mdx
@@ -0,0 +1,26 @@
+---
+title: "PerpNeg - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PerpNeg node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PerpNeg"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PerpNeg/en.md)
+
+The PerpNeg node applies perpendicular negative guidance to a model's sampling process. This node modifies the model's configuration function to adjust noise predictions using negative conditioning and scaling factors. It has been deprecated and replaced by the PerpNegGuider node for improved functionality.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply perpendicular negative guidance to |
+| `empty_conditioning` | CONDITIONING | Yes | - | Empty conditioning used for negative guidance calculations |
+| `neg_scale` | FLOAT | No | 0.0 - 100.0 | Scaling factor for negative guidance (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with perpendicular negative guidance applied |
+
+**Note**: This node is deprecated and has been replaced by PerpNegGuider. It is marked as experimental and should not be used in production workflows.
diff --git a/built-in-nodes/PerpNegGuider.mdx b/built-in-nodes/PerpNegGuider.mdx
new file mode 100644
index 000000000..a8f3e1c61
--- /dev/null
+++ b/built-in-nodes/PerpNegGuider.mdx
@@ -0,0 +1,27 @@
+---
+title: "PerpNegGuider - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PerpNegGuider node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PerpNegGuider"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PerpNegGuider/en.md)
+
+The PerpNegGuider node creates a guidance system for controlling image generation using perpendicular negative conditioning. It takes positive, negative, and empty conditioning inputs and applies a specialized guidance algorithm to steer the generation process. This node is designed for testing purposes and provides fine control over the guidance strength and negative scaling.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to use for guidance generation |
+| `positive` | CONDITIONING | Yes | - | The positive conditioning that guides the generation toward desired content |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning that guides the generation away from unwanted content |
+| `empty_conditioning` | CONDITIONING | Yes | - | The empty or neutral conditioning used as a baseline reference |
+| `cfg` | FLOAT | No | 0.0 - 100.0 | The classifier-free guidance scale that controls how strongly the conditioning influences the generation (default: 8.0) |
+| `neg_scale` | FLOAT | No | 0.0 - 100.0 | The negative scaling factor that adjusts the strength of negative conditioning (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `guider` | GUIDER | A configured guidance system ready for use in the generation pipeline |
diff --git a/built-in-nodes/PerturbedAttentionGuidance.mdx b/built-in-nodes/PerturbedAttentionGuidance.mdx
new file mode 100644
index 000000000..0daf74f9b
--- /dev/null
+++ b/built-in-nodes/PerturbedAttentionGuidance.mdx
@@ -0,0 +1,23 @@
+---
+title: "PerturbedAttentionGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PerturbedAttentionGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PerturbedAttentionGuidance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PerturbedAttentionGuidance/en.md)
+
+The PerturbedAttentionGuidance node applies perturbed attention guidance to a diffusion model to enhance generation quality. It modifies the model's self-attention mechanism during sampling by replacing it with a simplified version that focuses on value projections. This technique helps improve the coherence and quality of generated images by adjusting the conditional denoising process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to apply perturbed attention guidance to |
+| `scale` | FLOAT | No | 0.0 - 100.0 | The strength of the perturbed attention guidance effect (default: 3.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with perturbed attention guidance applied |
diff --git a/built-in-nodes/PhotoMakerEncode.mdx b/built-in-nodes/PhotoMakerEncode.mdx
new file mode 100644
index 000000000..8f93c8c51
--- /dev/null
+++ b/built-in-nodes/PhotoMakerEncode.mdx
@@ -0,0 +1,27 @@
+---
+title: "PhotoMakerEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PhotoMakerEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PhotoMakerEncode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PhotoMakerEncode/en.md)
+
+The PhotoMakerEncode node processes images and text to generate conditioning data for AI image generation. It takes a reference image and text prompt, then creates embeddings that can be used to guide image generation based on the visual characteristics of the reference image. The node specifically looks for the "photomaker" token in the text to determine where to apply the image-based conditioning.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `photomaker` | PHOTOMAKER | Yes | - | The PhotoMaker model used for processing the image and generating embeddings |
+| `image` | IMAGE | Yes | - | The reference image that provides visual characteristics for conditioning |
+| `clip` | CLIP | Yes | - | The CLIP model used for text tokenization and encoding |
+| `text` | STRING | Yes | - | The text prompt for conditioning generation (default: "photograph of photomaker") |
+
+**Note:** When the text contains the word "photomaker", the node applies image-based conditioning at that position in the prompt. If "photomaker" is not found in the text, the node generates standard text conditioning without image influence.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The conditioning data containing image and text embeddings for guiding image generation |
diff --git a/built-in-nodes/PhotoMakerLoader.mdx b/built-in-nodes/PhotoMakerLoader.mdx
new file mode 100644
index 000000000..bc59fbe07
--- /dev/null
+++ b/built-in-nodes/PhotoMakerLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "PhotoMakerLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PhotoMakerLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PhotoMakerLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PhotoMakerLoader/en.md)
+
+The PhotoMakerLoader node loads a PhotoMaker model from the available model files. It reads the specified model file and prepares the PhotoMaker ID encoder for use in identity-based image generation tasks. This node is marked as experimental and is intended for testing purposes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `photomaker_model_name` | STRING | Yes | Multiple options available | The name of the PhotoMaker model file to load. The available options are determined by the model files present in the photomaker folder. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `photomaker_model` | PHOTOMAKER | The loaded PhotoMaker model containing the ID encoder, ready for use in identity encoding operations. |
diff --git a/built-in-nodes/PikaImageToVideoNode2_2.mdx b/built-in-nodes/PikaImageToVideoNode2_2.mdx
new file mode 100644
index 000000000..2a9c332e9
--- /dev/null
+++ b/built-in-nodes/PikaImageToVideoNode2_2.mdx
@@ -0,0 +1,27 @@
+---
+title: "PikaImageToVideoNode2_2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PikaImageToVideoNode2_2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PikaImageToVideoNode2_2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PikaImageToVideoNode2_2/en.md)
+
+The Pika Image to Video node sends an image and text prompt to the Pika API version 2.2 to generate a video. It converts your input image into video format based on the provided description and settings. The node handles the API communication and returns the generated video as output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The image to convert to video |
+| `prompt_text` | STRING | Yes | - | The text description guiding video generation |
+| `negative_prompt` | STRING | Yes | - | Text describing what to avoid in the video |
+| `seed` | INT | Yes | - | Random seed value for reproducible results |
+| `resolution` | STRING | Yes | - | Output video resolution setting |
+| `duration` | INT | Yes | - | Length of the generated video in seconds |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/PikaScenesV2_2.mdx b/built-in-nodes/PikaScenesV2_2.mdx
new file mode 100644
index 000000000..98ec5f264
--- /dev/null
+++ b/built-in-nodes/PikaScenesV2_2.mdx
@@ -0,0 +1,35 @@
+---
+title: "PikaScenesV2_2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PikaScenesV2_2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PikaScenesV2_2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PikaScenesV2_2/en.md)
+
+The PikaScenes v2.2 node combines multiple images to create a video that incorporates objects from all the input images. You can upload up to five different images as ingredients and generate a high-quality video that blends them together seamlessly.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt_text` | STRING | Yes | - | Text description of what to generate |
+| `negative_prompt` | STRING | Yes | - | Text description of what to avoid in the generation |
+| `seed` | INT | Yes | - | Random seed value for generation |
+| `resolution` | STRING | Yes | - | Output resolution for the video |
+| `duration` | INT | Yes | - | Duration of the generated video |
+| `ingredients_mode` | COMBO | No | "creative"<br />"precise" | Mode for combining ingredients (default: "creative") |
+| `aspect_ratio` | FLOAT | No | 0.4 - 2.5 | Aspect ratio (width / height) (default: 1.778) |
+| `image_ingredient_1` | IMAGE | No | - | Image that will be used as ingredient to create a video |
+| `image_ingredient_2` | IMAGE | No | - | Image that will be used as ingredient to create a video |
+| `image_ingredient_3` | IMAGE | No | - | Image that will be used as ingredient to create a video |
+| `image_ingredient_4` | IMAGE | No | - | Image that will be used as ingredient to create a video |
+| `image_ingredient_5` | IMAGE | No | - | Image that will be used as ingredient to create a video |
+
+**Note:** You can provide up to 5 image ingredients, but at least one image is required to generate a video. The node will use all provided images to create the final video composition.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video combining all input images |
diff --git a/built-in-nodes/PikaStartEndFrameNode2_2.mdx b/built-in-nodes/PikaStartEndFrameNode2_2.mdx
new file mode 100644
index 000000000..eb9d842d2
--- /dev/null
+++ b/built-in-nodes/PikaStartEndFrameNode2_2.mdx
@@ -0,0 +1,28 @@
+---
+title: "PikaStartEndFrameNode2_2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PikaStartEndFrameNode2_2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PikaStartEndFrameNode2_2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PikaStartEndFrameNode2_2/en.md)
+
+The PikaFrames v2.2 Node generates videos by combining your first and last frame. You upload two images to define the start and end points, and the AI creates a smooth transition between them to produce a complete video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image_start` | IMAGE | Yes | - | The first image to combine. |
+| `image_end` | IMAGE | Yes | - | The last image to combine. |
+| `prompt_text` | STRING | Yes | - | Text prompt describing the desired video content. |
+| `negative_prompt` | STRING | Yes | - | Text describing what to avoid in the video. |
+| `seed` | INT | Yes | - | Random seed value for generation consistency. |
+| `resolution` | STRING | Yes | - | Output video resolution. |
+| `duration` | INT | Yes | - | Duration of the generated video. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video combining the start and end frames with AI transitions. |
diff --git a/built-in-nodes/PikaTextToVideoNode2_2.mdx b/built-in-nodes/PikaTextToVideoNode2_2.mdx
new file mode 100644
index 000000000..65183568e
--- /dev/null
+++ b/built-in-nodes/PikaTextToVideoNode2_2.mdx
@@ -0,0 +1,27 @@
+---
+title: "PikaTextToVideoNode2_2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PikaTextToVideoNode2_2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PikaTextToVideoNode2_2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PikaTextToVideoNode2_2/en.md)
+
+The Pika Text2Video v2.2 Node sends a text prompt to the Pika API version 2.2 to generate a video. It converts your text description into a video using Pika's AI video generation service. The node allows you to customize various aspects of the video generation process including aspect ratio, duration, and resolution.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt_text` | STRING | Yes | - | The main text description that describes what you want to generate in the video |
+| `negative_prompt` | STRING | Yes | - | Text describing what you don't want to appear in the generated video |
+| `seed` | INT | Yes | - | A number that controls the randomness of the generation for reproducible results |
+| `resolution` | STRING | Yes | - | The resolution setting for the output video |
+| `duration` | INT | Yes | - | The length of the video in seconds |
+| `aspect_ratio` | FLOAT | No | 0.4 - 2.5 | Aspect ratio (width / height) (default: 1.7777777777777777) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file returned from the Pika API |
diff --git a/built-in-nodes/Pikadditions.mdx b/built-in-nodes/Pikadditions.mdx
new file mode 100644
index 000000000..1d729088b
--- /dev/null
+++ b/built-in-nodes/Pikadditions.mdx
@@ -0,0 +1,26 @@
+---
+title: "Pikadditions - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Pikadditions node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Pikadditions"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Pikadditions/en.md)
+
+The Pikadditions node allows you to add any object or image into your video. You upload a video and specify what you'd like to add to create a seamlessly integrated result. This node uses the Pika API to insert images into videos with natural-looking integration.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | - | The video to add an image to. |
+| `image` | IMAGE | Yes | - | The image to add to the video. |
+| `prompt_text` | STRING | Yes | - | Text description of what to add to the video. |
+| `negative_prompt` | STRING | Yes | - | Text description of what to avoid in the video. |
+| `seed` | INT | Yes | 0 to 4294967295 | Random seed value for reproducible results. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The processed video with the image inserted. |
diff --git a/built-in-nodes/Pikaffects.mdx b/built-in-nodes/Pikaffects.mdx
new file mode 100644
index 000000000..8bd234b46
--- /dev/null
+++ b/built-in-nodes/Pikaffects.mdx
@@ -0,0 +1,26 @@
+---
+title: "Pikaffects - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Pikaffects node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Pikaffects"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Pikaffects/en.md)
+
+The Pikaffects node generates videos with various visual effects applied to an input image. It uses Pika's video generation API to transform static images into animated videos with specific effects like melting, exploding, or levitating. The node requires an API key and authentication token to access the Pika service.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The reference image to apply the Pikaffect to. |
+| `pikaffect` | COMBO | Yes | "Cake-ify"<br />"Crumble"<br />"Crush"<br />"Decapitate"<br />"Deflate"<br />"Dissolve"<br />"Explode"<br />"Eye-pop"<br />"Inflate"<br />"Levitate"<br />"Melt"<br />"Peel"<br />"Poke"<br />"Squish"<br />"Ta-da"<br />"Tear" | The specific visual effect to apply to the image (default: "Cake-ify"). |
+| `prompt_text` | STRING | Yes | - | Text description guiding the video generation. |
+| `negative_prompt` | STRING | Yes | - | Text description of what to avoid in the generated video. |
+| `seed` | INT | Yes | 0 to 4294967295 | Random seed value for reproducible results. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video with the applied Pikaffect. |
diff --git a/built-in-nodes/Pikaswaps.mdx b/built-in-nodes/Pikaswaps.mdx
new file mode 100644
index 000000000..eaf1efd0d
--- /dev/null
+++ b/built-in-nodes/Pikaswaps.mdx
@@ -0,0 +1,29 @@
+---
+title: "Pikaswaps - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Pikaswaps node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Pikaswaps"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Pikaswaps/en.md)
+
+The Pika Swaps node allows you to replace objects or regions in your video with new images. You can define the areas to replace using either a mask or coordinates, and the node will seamlessly swap the specified content throughout the video sequence.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | - | The video to swap an object in. |
+| `image` | IMAGE | Yes | - | The image used to replace the masked object in the video. |
+| `mask` | MASK | Yes | - | Use the mask to define areas in the video to replace. |
+| `prompt_text` | STRING | Yes | - | Text prompt describing the desired replacement. |
+| `negative_prompt` | STRING | Yes | - | Text prompt describing what to avoid in the replacement. |
+| `seed` | INT | Yes | 0 to 4294967295 | Random seed value for consistent results. |
+
+**Note:** This node requires all input parameters to be provided. The `video`, `image`, and `mask` work together to define the replacement operation, where the mask specifies which areas of the video will be replaced with the provided image.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The processed video with the specified object or region replaced. |
diff --git a/built-in-nodes/PixverseImageToVideoNode.mdx b/built-in-nodes/PixverseImageToVideoNode.mdx
new file mode 100644
index 000000000..d0afa5539
--- /dev/null
+++ b/built-in-nodes/PixverseImageToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "PixverseImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PixverseImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PixverseImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseImageToVideoNode/en.md)
+
+Generates videos based on an input image and text prompt. This node takes an image and creates an animated video by applying the specified motion and quality settings to transform the static image into a moving sequence.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | Input image to transform into video |
+| `prompt` | STRING | Yes | - | Prompt for the video generation |
+| `quality` | COMBO | Yes | `res_540p`<br />`res_1080p` | Video quality setting (default: res_540p) |
+| `duration_seconds` | COMBO | Yes | `dur_2`<br />`dur_5`<br />`dur_10` | Duration of the generated video in seconds |
+| `motion_mode` | COMBO | Yes | `normal`<br />`fast`<br />`slow`<br />`zoom_in`<br />`zoom_out`<br />`pan_left`<br />`pan_right`<br />`pan_up`<br />`pan_down`<br />`tilt_up`<br />`tilt_down`<br />`roll_clockwise`<br />`roll_counterclockwise` | Motion style applied to the video generation |
+| `seed` | INT | Yes | 0-2147483647 | Seed for video generation (default: 0) |
+| `negative_prompt` | STRING | No | - | An optional text description of undesired elements on an image |
+| `pixverse_template` | CUSTOM | No | - | An optional template to influence style of generation, created by the PixVerse Template node |
+
+**Note:** When using 1080p quality, the motion mode is automatically set to normal and duration is limited to 5 seconds. For durations other than 5 seconds, the motion mode is also automatically set to normal.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | Generated video based on the input image and parameters |
diff --git a/built-in-nodes/PixverseTemplateNode.mdx b/built-in-nodes/PixverseTemplateNode.mdx
new file mode 100644
index 000000000..54671c6d0
--- /dev/null
+++ b/built-in-nodes/PixverseTemplateNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "PixverseTemplateNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PixverseTemplateNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PixverseTemplateNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTemplateNode/en.md)
+
+The PixVerse Template node allows you to select from available templates for PixVerse video generation. It converts your selected template name into the corresponding template ID that the PixVerse API requires for video creation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `template` | STRING | Yes | Multiple options available | The template to use for PixVerse video generation. The available options correspond to predefined templates in the PixVerse system. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `pixverse_template` | INT | The template ID corresponding to the selected template name, which can be used by other PixVerse nodes for video generation. |
diff --git a/built-in-nodes/PixverseTextToVideoNode.mdx b/built-in-nodes/PixverseTextToVideoNode.mdx
new file mode 100644
index 000000000..3d3ef8d08
--- /dev/null
+++ b/built-in-nodes/PixverseTextToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "PixverseTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PixverseTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PixverseTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTextToVideoNode/en.md)
+
+Generates videos based on prompt and output_size. This node creates video content using text descriptions and various generation parameters, producing video output through the PixVerse API.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the video generation (default: "") |
+| `aspect_ratio` | COMBO | Yes | Options from PixverseAspectRatio | Aspect ratio for the generated video |
+| `quality` | COMBO | Yes | Options from PixverseQuality | Video quality setting (default: PixverseQuality.res_540p) |
+| `duration_seconds` | COMBO | Yes | Options from PixverseDuration | Duration of the generated video in seconds |
+| `motion_mode` | COMBO | Yes | Options from PixverseMotionMode | Motion style for the video generation |
+| `seed` | INT | Yes | 0 to 2147483647 | Seed for video generation (default: 0) |
+| `negative_prompt` | STRING | No | - | An optional text description of undesired elements on an image (default: "") |
+| `pixverse_template` | CUSTOM | No | - | An optional template to influence style of generation, created by the PixVerse Template node |
+
+**Note:** When using 1080p quality, the motion mode is automatically set to normal and duration is limited to 5 seconds. For non-5 second durations, the motion mode is also automatically set to normal.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/PixverseTransitionVideoNode.mdx b/built-in-nodes/PixverseTransitionVideoNode.mdx
new file mode 100644
index 000000000..d46c79df5
--- /dev/null
+++ b/built-in-nodes/PixverseTransitionVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "PixverseTransitionVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PixverseTransitionVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PixverseTransitionVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTransitionVideoNode/en.md)
+
+Generates videos based on prompt and output_size. This node creates transition videos between two input images using the PixVerse API, allowing you to specify the video quality, duration, motion style, and generation parameters.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `first_frame` | IMAGE | Yes | - | The starting image for the video transition |
+| `last_frame` | IMAGE | Yes | - | The ending image for the video transition |
+| `prompt` | STRING | Yes | - | Prompt for the video generation (default: empty string) |
+| `quality` | COMBO | Yes | Available quality options from PixverseQuality enum<br />Default: res_540p | Video quality setting |
+| `duration_seconds` | COMBO | Yes | Available duration options from PixverseDuration enum | Video duration in seconds |
+| `motion_mode` | COMBO | Yes | Available motion mode options from PixverseMotionMode enum | Motion style for the transition |
+| `seed` | INT | Yes | 0 to 2147483647 | Seed for video generation (default: 0) |
+| `negative_prompt` | STRING | No | - | An optional text description of undesired elements on an image (default: empty string) |
+
+**Note:** When using 1080p quality, the motion mode is automatically set to normal and duration is limited to 5 seconds. For non-5 second durations, the motion mode is also automatically set to normal.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated transition video |
diff --git a/built-in-nodes/PolyexponentialScheduler.mdx b/built-in-nodes/PolyexponentialScheduler.mdx
new file mode 100644
index 000000000..70cd62013
--- /dev/null
+++ b/built-in-nodes/PolyexponentialScheduler.mdx
@@ -0,0 +1,24 @@
+---
+title: "PolyexponentialScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PolyexponentialScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PolyexponentialScheduler"
+icon: "circle"
+mode: wide
+---
+
+The PolyexponentialScheduler node is designed to generate a sequence of noise levels (sigmas) based on a polyexponential noise schedule. This schedule is a polynomial function in the logarithm of sigma, allowing for a flexible and customizable progression of noise levels throughout the diffusion process.
+
+## Inputs
+
+| Parameter   | Data Type | Description                                                                                                                                                                                                                                                                                                                                                      |
+|-------------|-------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `steps`     | INT         | Specifies the number of steps in the diffusion process, affecting the granularity of the generated noise levels.                                                                                                                                                                                                                                                                        |
+| `sigma_max` | FLOAT       | The maximum noise level, setting the upper bound of the noise schedule.                                                                                                                                                                                                                                                                                                                                 |
+| `sigma_min` | FLOAT       | The minimum noise level, setting the lower bound of the noise schedule.                                                                                                                                                                                                                                                                                                                                 |
+| `rho`       | FLOAT       | A parameter that controls the shape of the polyexponential noise schedule, influencing how noise levels progress between the minimum and maximum values.                                                                                                                                                                                                               |
+
+## Outputs
+
+| Parameter | Data Type | Description                                                                 |
+|-----------|-------------|-----------------------------------------------------------------------------|
+| `sigmas`  | SIGMAS      | The output is a sequence of noise levels (sigmas) tailored to the specified polyexponential noise schedule. |
diff --git a/built-in-nodes/PorterDuffImageComposite.mdx b/built-in-nodes/PorterDuffImageComposite.mdx
new file mode 100644
index 000000000..a981e76f0
--- /dev/null
+++ b/built-in-nodes/PorterDuffImageComposite.mdx
@@ -0,0 +1,26 @@
+---
+title: "PorterDuffImageComposite - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PorterDuffImageComposite node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PorterDuffImageComposite"
+icon: "circle"
+mode: wide
+---
+
+The PorterDuffImageComposite node is designed to perform image compositing using the Porter-Duff compositing operators. It allows for the combination of source and destination images according to various blending modes, enabling the creation of complex visual effects by manipulating image transparency and overlaying images in creative ways.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+| --------- | ------------ | ----------- |
+| `source`  | `IMAGE`     | The source image tensor to be composited over the destination image. It plays a crucial role in determining the final visual outcome based on the selected compositing mode. |
+| `source_alpha` | `MASK` | The alpha channel of the source image, which specifies the transparency of each pixel in the source image. It affects how the source image blends with the destination image. |
+| `destination` | `IMAGE` | The destination image tensor that serves as the backdrop over which the source image is composited. It contributes to the final composited image based on the blending mode. |
+| `destination_alpha` | `MASK` | The alpha channel of the destination image, defining the transparency of the destination image's pixels. It influences the blending of the source and destination images. |
+| `mode` | COMBO[STRING] | The Porter-Duff compositing mode to apply, which determines how the source and destination images are blended together. Each mode creates different visual effects. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+| --------- | ------------ | ----------- |
+| `image`   | `IMAGE`     | The composited image resulting from the application of the specified Porter-Duff mode. |
+| `mask`    | `MASK`      | The alpha channel of the composited image, indicating the transparency of each pixel. |
diff --git a/built-in-nodes/Preview3D.mdx b/built-in-nodes/Preview3D.mdx
new file mode 100644
index 000000000..ebd9f15e4
--- /dev/null
+++ b/built-in-nodes/Preview3D.mdx
@@ -0,0 +1,108 @@
+---
+title: "Preview3D - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Preview3D node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Preview3D"
+icon: "circle"
+mode: wide
+---
+Preview3D node is mainly used to preview 3D model outputs. This node takes two inputs: one is the `camera_info` from the Load3D node, and the other is the path to the 3D model file. The model file path must be located in the `ComfyUI/output` folder.
+
+**Supported Formats**
+Currently, this node supports multiple 3D file formats, including `.gltf`, `.glb`, `.obj`, `.fbx`, and `.stl`.
+
+**3D Node Preferences**
+Some related preferences for 3D nodes can be configured in ComfyUI's settings menu. Please refer to the following documentation for corresponding settings:
+[Settings Menu](https://docs.comfy.org/interface/settings/3d)
+
+## Inputs
+
+| Parameter Name | Type           | Description                                  |
+| -------------- | -------------- | -------------------------------------------- |
+| camera_info    | LOAD3D_CAMERA  | Camera information                           |
+| model_file     | LOAD3D_CAMERA  | Model file path under `ComfyUI/output/`      |
+
+## Canvas Area Description
+
+Currently, the 3D-related nodes in the ComfyUI frontend share the same canvas component, so their basic operations are mostly consistent except for some functional differences.
+
+> The following content and interface are mainly based on the Load3D node. Please refer to the actual node interface for specific features.
+
+The Canvas area includes various view operations, such as:
+
+- Preview view settings (grid, background color, preview view)
+- Camera control: FOV, camera type
+- Global illumination intensity: adjust lighting
+- Model export: supports `GLB`, `OBJ`, `STL` formats
+- etc.
+
+![Load 3D Node UI](/images/built-in-nodes/Preview3D/preview3d_canvas.jpg)
+
+1. Contains multiple menus and hidden menus of the Load 3D node
+2. 3D view operation axis
+
+### 1. View Operations
+
+<video controls width="640" height="360">
+  <source src="https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/view_operations.mp4" type="video/mp4" />
+  Your browser does not support video playback.
+</video>
+
+View control operations:
+
+- Left-click + drag: Rotate the view
+- Right-click + drag: Pan the view
+- Middle wheel scroll or middle-click + drag: Zoom in/out
+- Coordinate axis: Switch views
+
+### 2. Left Menu Functions
+
+![Menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu.webp)
+
+In the preview area, some view operation menus are hidden in the menu. Click the menu button to expand different menus.
+
+- 1. Scene: Contains preview window grid, background color, thumbnail settings
+- 2. Model: Model rendering mode, texture material, up direction settings
+- 3. Camera: Switch between orthographic and perspective views, set perspective angle
+- 4. Light: Scene global illumination intensity
+- 5. Export: Export model to other formats (GLB, OBJ, STL)
+
+#### Scene
+
+![scene menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_scene.webp)
+
+The Scene menu provides some basic scene setting functions:
+
+1. Show/Hide grid
+2. Set background color
+3. Click to upload a background image
+4. Hide preview thumbnail
+
+#### Model
+
+![Menu_Scene](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_model.webp)
+
+The Model menu provides some model-related functions:
+
+1. **Up direction**: Determine which axis is the up direction for the model
+2. **Material mode**: Switch model rendering modes - Original, Normal, Wireframe, Lineart
+
+#### Camera
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_camera.webp)
+
+This menu provides switching between orthographic and perspective views, and perspective angle size settings:
+
+1. **Camera**: Quickly switch between orthographic and perspective views
+2. **FOV**: Adjust FOV angle
+
+#### Light
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_light.webp)
+
+Through this menu, you can quickly adjust the scene's global illumination intensity
+
+#### Export
+
+![menu_export](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_export.webp)
+
+This menu provides the ability to quickly convert and export model formats
diff --git a/built-in-nodes/Preview3DAnimation.mdx b/built-in-nodes/Preview3DAnimation.mdx
new file mode 100644
index 000000000..828520639
--- /dev/null
+++ b/built-in-nodes/Preview3DAnimation.mdx
@@ -0,0 +1,108 @@
+---
+title: "Preview3DAnimation - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Preview3DAnimation node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Preview3DAnimation"
+icon: "circle"
+mode: wide
+---
+Preview3DAnimation node is mainly used to preview 3D model outputs. This node takes two inputs: one is the `camera_info` from the Load3D node, and the other is the path to the 3D model file. The model file path must be located in the `ComfyUI/output` folder.
+
+**Supported Formats**
+Currently, this node supports multiple 3D file formats, including `.gltf`, `.glb`, `.obj`, `.fbx`, and `.stl`.
+
+**3D Node Preferences**
+Some related preferences for 3D nodes can be configured in ComfyUI's settings menu. Please refer to the following documentation for corresponding settings:
+[Settings Menu](https://docs.comfy.org/interface/settings/3d)
+
+## Inputs
+
+| Parameter Name | Type           | Description                                  |
+| -------------- | -------------- | -------------------------------------------- |
+| camera_info    | LOAD3D_CAMERA  | Camera information                           |
+| model_file     | STRING  | Model file path under `ComfyUI/output/`      |
+
+## Canvas Area Description
+
+Currently, the 3D-related nodes in the ComfyUI frontend share the same canvas component, so their basic operations are mostly consistent except for some functional differences.
+
+> The following content and interface are mainly based on the Load3D node. Please refer to the actual node interface for specific features.
+
+The Canvas area includes various view operations, such as:
+
+- Preview view settings (grid, background color, preview view)
+- Camera control: FOV, camera type
+- Global illumination intensity: adjust lighting
+- Model export: supports `GLB`, `OBJ`, `STL` formats
+- etc.
+
+![Load 3D Node UI](/images/built-in-nodes/Preview3DAnimation/preview3d_canvas.jpg)
+
+1. Contains multiple menus and hidden menus of the Load 3D node
+2. 3D view operation axis
+
+### 1. View Operations
+
+<video controls width="640" height="360">
+  <source src="https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/view_operations.mp4" type="video/mp4" />
+  Your browser does not support video playback.
+</video>
+
+View control operations:
+
+- Left-click + drag: Rotate the view
+- Right-click + drag: Pan the view
+- Middle wheel scroll or middle-click + drag: Zoom in/out
+- Coordinate axis: Switch views
+
+### 2. Left Menu Functions
+
+![Menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu.webp)
+
+In the preview area, some view operation menus are hidden in the menu. Click the menu button to expand different menus.
+
+- 1. Scene: Contains preview window grid, background color, thumbnail settings
+- 2. Model: Model rendering mode, texture material, up direction settings
+- 3. Camera: Switch between orthographic and perspective views, set perspective angle
+- 4. Light: Scene global illumination intensity
+- 5. Export: Export model to other formats (GLB, OBJ, STL)
+
+#### Scene
+
+![scene menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_scene.webp)
+
+The Scene menu provides some basic scene setting functions:
+
+1. Show/Hide grid
+2. Set background color
+3. Click to upload a background image
+4. Hide preview thumbnail
+
+#### Model
+
+![Menu_Scene](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_model.webp)
+
+The Model menu provides some model-related functions:
+
+1. **Up direction**: Determine which axis is the up direction for the model
+2. **Material mode**: Switch model rendering modes - Original, Normal, Wireframe, Lineart
+
+#### Camera
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_camera.webp)
+
+This menu provides switching between orthographic and perspective views, and perspective angle size settings:
+
+1. **Camera**: Quickly switch between orthographic and perspective views
+2. **FOV**: Adjust FOV angle
+
+#### Light
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_light.webp)
+
+Through this menu, you can quickly adjust the scene's global illumination intensity
+
+#### Export
+
+![menu_export](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_export.webp)
+
+This menu provides the ability to quickly convert and export model formats
diff --git a/built-in-nodes/PreviewAny.mdx b/built-in-nodes/PreviewAny.mdx
new file mode 100644
index 000000000..059487ad6
--- /dev/null
+++ b/built-in-nodes/PreviewAny.mdx
@@ -0,0 +1,22 @@
+---
+title: "PreviewAny - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PreviewAny node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PreviewAny"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAny/en.md)
+
+The PreviewAny node displays a preview of any input data type in text format. It accepts any data type as input and converts it to a readable string representation for viewing. The node automatically handles different data types including strings, numbers, booleans, and complex objects by attempting to serialize them to JSON format.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `source` | ANY | Yes | Any data type | Accepts any input data type for preview display |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| UI Text Display | TEXT | Displays the input data converted to text format in the user interface |
diff --git a/built-in-nodes/PreviewAudio.mdx b/built-in-nodes/PreviewAudio.mdx
new file mode 100644
index 000000000..d2d539569
--- /dev/null
+++ b/built-in-nodes/PreviewAudio.mdx
@@ -0,0 +1,24 @@
+---
+title: "PreviewAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PreviewAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PreviewAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAudio/en.md)
+
+The PreviewAudio node generates a temporary audio preview file that can be displayed in the interface. It inherits from SaveAudio but saves files to a temporary directory with a random filename prefix. This allows users to quickly preview audio outputs without creating permanent files.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The audio data to preview |
+| `prompt` | PROMPT | No | - | Hidden parameter for internal use |
+| `extra_pnginfo` | EXTRA_PNGINFO | No | - | Hidden parameter for internal use |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `ui` | UI | Displays the audio preview in the interface |
diff --git a/built-in-nodes/PreviewImage.mdx b/built-in-nodes/PreviewImage.mdx
new file mode 100644
index 000000000..5ef07a7b6
--- /dev/null
+++ b/built-in-nodes/PreviewImage.mdx
@@ -0,0 +1,19 @@
+---
+title: "PreviewImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PreviewImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PreviewImage"
+icon: "circle"
+mode: wide
+---
+
+The PreviewImage node is designed for creating temporary preview images. It automatically generates a unique temporary file name for each image, compresses the image to a specified level, and saves it to a temporary directory. This functionality is particularly useful for generating previews of images during processing without affecting the original files.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `images`  | `IMAGE`     | The 'images' input specifies the images to be processed and saved as temporary preview images. This is the primary input for the node, determining which images will undergo the preview generation process. |
+
+## Outputs
+
+The node doesn't have output types.
diff --git a/built-in-nodes/PrimitiveBoolean.mdx b/built-in-nodes/PrimitiveBoolean.mdx
new file mode 100644
index 000000000..99d36872f
--- /dev/null
+++ b/built-in-nodes/PrimitiveBoolean.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveBoolean - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveBoolean node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveBoolean"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveBoolean/en.md)
+
+The Boolean node provides a simple way to pass boolean (true/false) values through your workflow. It takes a boolean input value and outputs the same value unchanged, allowing you to control boolean parameters in other nodes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `value` | BOOLEAN | Yes | true<br />false | The boolean value to pass through the node |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | BOOLEAN | The same boolean value that was provided as input |
diff --git a/built-in-nodes/PrimitiveBoundingBox.mdx b/built-in-nodes/PrimitiveBoundingBox.mdx
new file mode 100644
index 000000000..72d53452f
--- /dev/null
+++ b/built-in-nodes/PrimitiveBoundingBox.mdx
@@ -0,0 +1,25 @@
+---
+title: "PrimitiveBoundingBox - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveBoundingBox node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveBoundingBox"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveBoundingBox/en.md)
+
+The PrimitiveBoundingBox node creates a simple rectangular area defined by its position and size. It takes X and Y coordinates for the top-left corner, along with width and height values, and outputs a bounding box data structure that can be used by other nodes in a workflow.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `x` | INT | No | 0 to 8192 | The X-coordinate for the top-left corner of the bounding box (default: 0). |
+| `y` | INT | No | 0 to 8192 | The Y-coordinate for the top-left corner of the bounding box (default: 0). |
+| `width` | INT | No | 1 to 8192 | The width of the bounding box (default: 512). |
+| `height` | INT | No | 1 to 8192 | The height of the bounding box (default: 512). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `bounding_box` | BOUNDING_BOX | A data structure containing the `x`, `y`, `width`, and `height` properties of the defined rectangle. |
diff --git a/built-in-nodes/PrimitiveFloat.mdx b/built-in-nodes/PrimitiveFloat.mdx
new file mode 100644
index 000000000..55db475a7
--- /dev/null
+++ b/built-in-nodes/PrimitiveFloat.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveFloat - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveFloat node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveFloat"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveFloat/en.md)
+
+The PrimitiveFloat node creates a floating-point number value that can be used in your workflow. It takes a single numeric input and outputs that same value, allowing you to define and pass float values between different nodes in your ComfyUI pipeline.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `value` | FLOAT | Yes | -sys.maxsize to sys.maxsize | The floating-point number value to output |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | FLOAT | The input floating-point number value |
diff --git a/built-in-nodes/PrimitiveInt.mdx b/built-in-nodes/PrimitiveInt.mdx
new file mode 100644
index 000000000..b240f5df2
--- /dev/null
+++ b/built-in-nodes/PrimitiveInt.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveInt - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveInt node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveInt"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveInt/en.md)
+
+The PrimitiveInt node provides a simple way to work with integer values in your workflow. It takes an integer input and outputs the same value, making it useful for passing integer parameters between nodes or setting specific numeric values for other operations.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `value` | INT | Yes | -9223372036854775807 to 9223372036854775807 | The integer value to output |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | INT | The input integer value passed through unchanged |
diff --git a/built-in-nodes/PrimitiveString.mdx b/built-in-nodes/PrimitiveString.mdx
new file mode 100644
index 000000000..1e6a97168
--- /dev/null
+++ b/built-in-nodes/PrimitiveString.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveString - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveString node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveString"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveString/en.md)
+
+The String node provides a simple way to input and pass through text data in your workflow. It takes a text string as input and outputs the same string unchanged, making it useful for providing text inputs to other nodes that require string parameters.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `value` | STRING | Yes | Any text | The text string to be passed through the node |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The same text string that was provided as input |
diff --git a/built-in-nodes/PrimitiveStringMultiline.mdx b/built-in-nodes/PrimitiveStringMultiline.mdx
new file mode 100644
index 000000000..61403b9fc
--- /dev/null
+++ b/built-in-nodes/PrimitiveStringMultiline.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveStringMultiline - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveStringMultiline node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveStringMultiline"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveStringMultiline/en.md)
+
+The PrimitiveStringMultiline node provides a multiline text input field for entering and passing string values through your workflow. It accepts text input with multiple lines and outputs the same string value unchanged. This node is useful when you need to input longer text content or formatted text that spans multiple lines.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `value` | STRING | Yes | N/A | The text input value that can span multiple lines |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The same string value that was provided as input |
diff --git a/built-in-nodes/QuadrupleCLIPLoader.mdx b/built-in-nodes/QuadrupleCLIPLoader.mdx
new file mode 100644
index 000000000..6cb144f11
--- /dev/null
+++ b/built-in-nodes/QuadrupleCLIPLoader.mdx
@@ -0,0 +1,14 @@
+---
+title: "QuadrupleCLIPLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the QuadrupleCLIPLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "QuadrupleCLIPLoader"
+icon: "circle"
+mode: wide
+---
+The Quadruple CLIP Loader, QuadrupleCLIPLoader, is one of the core nodes of ComfyUI, first added to support the HiDream I1 version model. If you find this node missing, try updating ComfyUI to the latest version to ensure node support.
+
+It requires 4 CLIP models, corresponding to the parameters `clip_name1`, `clip_name2`, `clip_name3`, and `clip_name4`, and will provide a CLIP model output for subsequent nodes.
+
+This node will detect models located in the `ComfyUI/models/text_encoders` folder,
+ and it will also read models from additional paths configured in the extra_model_paths.yaml file.
+ Sometimes, after adding models, you may need to **reload the ComfyUI interface** to allow it to read the model files in the corresponding folder.
diff --git a/built-in-nodes/QwenImageDiffsynthControlnet.mdx b/built-in-nodes/QwenImageDiffsynthControlnet.mdx
new file mode 100644
index 000000000..d7b82796c
--- /dev/null
+++ b/built-in-nodes/QwenImageDiffsynthControlnet.mdx
@@ -0,0 +1,29 @@
+---
+title: "QwenImageDiffsynthControlnet - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the QwenImageDiffsynthControlnet node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "QwenImageDiffsynthControlnet"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/QwenImageDiffsynthControlnet/en.md)
+
+The QwenImageDiffsynthControlnet node applies a diffusion synthesis control network patch to modify a base model's behavior. It uses an image input and optional mask to guide the model's generation process with adjustable strength, creating a patched model that incorporates the control network's influence for more controlled image synthesis.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The base model to be patched with the control network |
+| `model_patch` | MODEL_PATCH | Yes | - | The control network patch model to apply to the base model |
+| `vae` | VAE | Yes | - | The VAE (Variational Autoencoder) used in the diffusion process |
+| `image` | IMAGE | Yes | - | The input image used to guide the control network (only RGB channels are used) |
+| `strength` | FLOAT | Yes | -10.0 to 10.0 | The strength of the control network influence (default: 1.0) |
+| `mask` | MASK | No | - | Optional mask that defines areas where the control network should be applied (inverted internally) |
+
+**Note:** When a mask is provided, it is automatically inverted (1.0 - mask) and reshaped to match the expected dimensions for the control network processing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with the diffusion synthesis control network patch applied |
diff --git a/built-in-nodes/RandomCropImages.mdx b/built-in-nodes/RandomCropImages.mdx
new file mode 100644
index 000000000..c273d383a
--- /dev/null
+++ b/built-in-nodes/RandomCropImages.mdx
@@ -0,0 +1,27 @@
+---
+title: "RandomCropImages - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RandomCropImages node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RandomCropImages"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RandomCropImages/en.md)
+
+The Random Crop Images node randomly selects a rectangular section from each input image and crops it to a specified width and height. This is commonly used for data augmentation to create variations of training images. The random position for the crop is determined by a seed value, ensuring the same crop can be reproduced.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The image to be cropped. |
+| `width` | INT | No | 1 - 8192 | The width of the crop area (default: 512). |
+| `height` | INT | No | 1 - 8192 | The height of the crop area (default: 512). |
+| `seed` | INT | No | 0 - 18446744073709551615 | A number used to control the random position of the crop (default: 0). |
+
+**Note:** The `width` and `height` parameters must be less than or equal to the dimensions of the input image. If a specified dimension is larger than the image, the crop will be limited to the image's boundary.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resulting image after the random crop has been applied. |
diff --git a/built-in-nodes/RandomNoise.mdx b/built-in-nodes/RandomNoise.mdx
new file mode 100644
index 000000000..3406f9fa7
--- /dev/null
+++ b/built-in-nodes/RandomNoise.mdx
@@ -0,0 +1,22 @@
+---
+title: "RandomNoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RandomNoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RandomNoise"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RandomNoise/en.md)
+
+The RandomNoise node generates random noise patterns based on a seed value. It creates reproducible noise that can be used for various image processing and generation tasks. The same seed will always produce the same noise pattern, allowing for consistent results across multiple runs.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `noise_seed` | INT | Yes | 0 to 18446744073709551615 | The seed value used to generate the random noise pattern (default: 0). The same seed will always produce the same noise output. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `noise` | NOISE | The generated random noise pattern based on the provided seed value. |
diff --git a/built-in-nodes/RebatchImages.mdx b/built-in-nodes/RebatchImages.mdx
new file mode 100644
index 000000000..087b7083d
--- /dev/null
+++ b/built-in-nodes/RebatchImages.mdx
@@ -0,0 +1,22 @@
+---
+title: "RebatchImages - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RebatchImages node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RebatchImages"
+icon: "circle"
+mode: wide
+---
+
+The RebatchImages node is designed to reorganize a batch of images into a new batch configuration, adjusting the batch size as specified. This process is essential for managing and optimizing the processing of image data in batch operations, ensuring that images are grouped according to the desired batch size for efficient handling.
+
+## Inputs
+
+| Field       | Data Type | Description                                                                         |
+|-------------|-------------|-------------------------------------------------------------------------------------|
+| `images`    | `IMAGE`     | A list of images to be rebatched. This parameter is crucial for determining the input data that will undergo the rebatching process. |
+| `batch_size`| `INT`       | Specifies the desired size of the output batches. This parameter directly influences how the input images are grouped and processed, impacting the structure of the output. |
+
+## Outputs
+
+| Field | Data Type | Description                                                                   |
+|-------|-------------|-------------------------------------------------------------------------------|
+| `image`| `IMAGE`     | The output consists of a list of image batches, reorganized according to the specified batch size. This allows for flexible and efficient processing of image data in batch operations. |
diff --git a/built-in-nodes/RebatchLatents.mdx b/built-in-nodes/RebatchLatents.mdx
new file mode 100644
index 000000000..ebd0eecc4
--- /dev/null
+++ b/built-in-nodes/RebatchLatents.mdx
@@ -0,0 +1,22 @@
+---
+title: "RebatchLatents - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RebatchLatents node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RebatchLatents"
+icon: "circle"
+mode: wide
+---
+
+The RebatchLatents node is designed to reorganize a batch of latent representations into a new batch configuration, based on a specified batch size. It ensures that the latent samples are grouped appropriately, handling variations in dimensions and sizes, to facilitate further processing or model inference.
+
+## Inputs
+
+| Parameter    | Data Type | Description |
+|--------------|-------------|-------------|
+| `latents`    | `LATENT`    | The 'latents' parameter represents the input latent representations to be rebatched. It is crucial for determining the structure and content of the output batch. |
+| `batch_size` | `INT`      | The 'batch_size' parameter specifies the desired number of samples per batch in the output. It directly influences the grouping and division of the input latents into new batches. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a reorganized batch of latent representations, adjusted according to the specified batch size. It facilitates further processing or analysis. |
diff --git a/built-in-nodes/RecordAudio.mdx b/built-in-nodes/RecordAudio.mdx
new file mode 100644
index 000000000..dbf326fb9
--- /dev/null
+++ b/built-in-nodes/RecordAudio.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecordAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecordAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecordAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecordAudio/en.md)
+
+The RecordAudio node loads audio files that have been recorded or selected through the audio recording interface. It processes the audio file and converts it into a waveform format that can be used by other audio processing nodes in the workflow. The node automatically detects the sample rate and prepares the audio data for further manipulation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO_RECORD | Yes | N/A | The audio recording input from the audio recording interface |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | The processed audio data containing waveform and sample rate information |
diff --git a/built-in-nodes/RecraftColorRGB.mdx b/built-in-nodes/RecraftColorRGB.mdx
new file mode 100644
index 000000000..a921f8512
--- /dev/null
+++ b/built-in-nodes/RecraftColorRGB.mdx
@@ -0,0 +1,25 @@
+---
+title: "RecraftColorRGB - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftColorRGB node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftColorRGB"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftColorRGB/en.md)
+
+Create Recraft Color by choosing specific RGB values. This node allows you to define a color by specifying individual red, green, and blue values, which are then converted into a Recraft color format that can be used in other Recraft operations.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `r` | INT | Yes | 0-255 | Red value of color (default: 0) |
+| `g` | INT | Yes | 0-255 | Green value of color (default: 0) |
+| `b` | INT | Yes | 0-255 | Blue value of color (default: 0) |
+| `recraft_color` | COLOR | No | - | Optional existing Recraft color to extend |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `recraft_color` | COLOR | The created Recraft color object containing the specified RGB values |
diff --git a/built-in-nodes/RecraftControls.mdx b/built-in-nodes/RecraftControls.mdx
new file mode 100644
index 000000000..ffa1878cb
--- /dev/null
+++ b/built-in-nodes/RecraftControls.mdx
@@ -0,0 +1,23 @@
+---
+title: "RecraftControls - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftControls node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftControls"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftControls/en.md)
+
+Creates Recraft Controls for customizing Recraft generation. This node allows you to configure color settings that will be used during the Recraft image generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `colors` | COLOR | No | - | Color settings for the main elements |
+| `background_color` | COLOR | No | - | Background color setting |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `recraft_controls` | CONTROLS | The configured Recraft controls containing color settings |
diff --git a/built-in-nodes/RecraftCreateStyleNode.mdx b/built-in-nodes/RecraftCreateStyleNode.mdx
new file mode 100644
index 000000000..98a73589c
--- /dev/null
+++ b/built-in-nodes/RecraftCreateStyleNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "RecraftCreateStyleNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftCreateStyleNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftCreateStyleNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreateStyleNode/en.md)
+
+This node creates a custom style for image generation by uploading reference images. You can upload between 1 and 5 images to define the new style, and the node will return a unique style ID that can be used with other Recraft nodes. The total combined file size of all uploaded images must not exceed 5 MB.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `style` | STRING | Yes | `"realistic_image"`<br />`"digital_illustration"` | The base style of the generated images. |
+| `images` | IMAGE | Yes | 1 to 5 images | A set of 1 to 5 reference images used to create the custom style. |
+
+**Note:** The total file size of all images in the `images` input must be less than 5 MB. The node will fail if this limit is exceeded.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `style_id` | STRING | The unique identifier for the newly created custom style. |
diff --git a/built-in-nodes/RecraftCreativeUpscaleNode.mdx b/built-in-nodes/RecraftCreativeUpscaleNode.mdx
new file mode 100644
index 000000000..4e074b52b
--- /dev/null
+++ b/built-in-nodes/RecraftCreativeUpscaleNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecraftCreativeUpscaleNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftCreativeUpscaleNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftCreativeUpscaleNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreativeUpscaleNode/en.md)
+
+The Recraft Creative Upscale Image node enhances a raster image by increasing its resolution. It uses a "creative upscale" process that focuses on improving small details and faces within the image. This operation is performed synchronously through an external API.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | | The input image to be upscaled. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resulting upscaled image with enhanced details. |
diff --git a/built-in-nodes/RecraftCrispUpscaleNode.mdx b/built-in-nodes/RecraftCrispUpscaleNode.mdx
new file mode 100644
index 000000000..9205bae21
--- /dev/null
+++ b/built-in-nodes/RecraftCrispUpscaleNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "RecraftCrispUpscaleNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftCrispUpscaleNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftCrispUpscaleNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCrispUpscaleNode/en.md)
+
+Upscale image synchronously. Enhances a given raster image using 'crisp upscale' tool, increasing image resolution, making the image sharper and cleaner.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be upscaled |
+| `auth_token` | STRING | No | - | Authentication token for Recraft API |
+| `comfy_api_key` | STRING | No | - | API key for Comfy.org services |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The upscaled image with enhanced resolution and clarity |
diff --git a/built-in-nodes/RecraftImageInpaintingNode.mdx b/built-in-nodes/RecraftImageInpaintingNode.mdx
new file mode 100644
index 000000000..d8b4dcb73
--- /dev/null
+++ b/built-in-nodes/RecraftImageInpaintingNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftImageInpaintingNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftImageInpaintingNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftImageInpaintingNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageInpaintingNode/en.md)
+
+This node modifies images based on a text prompt and mask. It uses the Recraft API to intelligently edit specific areas of an image that you define with a mask, while keeping the rest of the image unchanged.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be modified |
+| `mask` | MASK | Yes | - | The mask defining which areas of the image should be modified |
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: empty string) |
+| `n` | INT | Yes | 1-6 | The number of images to generate (default: 1, minimum: 1, maximum: 6) |
+| `seed` | INT | Yes | 0-18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0, minimum: 0, maximum: 18446744073709551615) |
+| `recraft_style` | STYLEV3 | No | - | Optional style parameter for Recraft API |
+| `negative_prompt` | STRING | No | - | An optional text description of undesired elements on an image (default: empty string) |
+
+*Note: The `image` and `mask` must be provided together for the inpainting operation to work. The mask will be automatically resized to match the image dimensions.*
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The modified image(s) generated based on the prompt and mask |
diff --git a/built-in-nodes/RecraftImageToImageNode.mdx b/built-in-nodes/RecraftImageToImageNode.mdx
new file mode 100644
index 000000000..fa6923545
--- /dev/null
+++ b/built-in-nodes/RecraftImageToImageNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "RecraftImageToImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftImageToImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftImageToImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageToImageNode/en.md)
+
+This node modifies an existing image based on a text prompt and strength parameter. It uses the Recraft API to transform the input image according to the provided description while maintaining some similarity to the original image based on the strength setting.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be modified |
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: "") |
+| `n` | INT | Yes | 1-6 | The number of images to generate (default: 1) |
+| `strength` | FLOAT | Yes | 0.0-1.0 | Defines the difference with the original image, should lie in [0, 1], where 0 means almost identical, and 1 means miserable similarity (default: 0.5) |
+| `seed` | INT | Yes | 0-18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0) |
+| `recraft_style` | STYLEV3 | No | - | Optional style selection for the image generation |
+| `negative_prompt` | STRING | No | - | An optional text description of undesired elements on an image (default: "") |
+| `recraft_controls` | CONTROLS | No | - | Optional additional controls over the generation via the Recraft Controls node |
+
+**Note:** The `seed` parameter only triggers re-execution of the node but does not guarantee deterministic results. The strength parameter is rounded to 2 decimal places internally.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The generated image(s) based on the input image and prompt |
diff --git a/built-in-nodes/RecraftRemoveBackgroundNode.mdx b/built-in-nodes/RecraftRemoveBackgroundNode.mdx
new file mode 100644
index 000000000..d1f137b4e
--- /dev/null
+++ b/built-in-nodes/RecraftRemoveBackgroundNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "RecraftRemoveBackgroundNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftRemoveBackgroundNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftRemoveBackgroundNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftRemoveBackgroundNode/en.md)
+
+This node removes the background from images using the Recraft API service. It processes each image in the input batch and returns both the processed images with transparent backgrounds and corresponding alpha masks that indicate the removed background areas.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image(s) to process for background removal |
+| `auth_token` | STRING | No | - | Authentication token for Recraft API access |
+| `comfy_api_key` | STRING | No | - | API key for Comfy.org service integration |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | Processed images with transparent backgrounds |
+| `mask` | MASK | Alpha channel masks indicating the removed background areas |
diff --git a/built-in-nodes/RecraftReplaceBackgroundNode.mdx b/built-in-nodes/RecraftReplaceBackgroundNode.mdx
new file mode 100644
index 000000000..9c028a7fb
--- /dev/null
+++ b/built-in-nodes/RecraftReplaceBackgroundNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "RecraftReplaceBackgroundNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftReplaceBackgroundNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftReplaceBackgroundNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftReplaceBackgroundNode/en.md)
+
+Replace background on image, based on provided prompt. This node uses the Recraft API to generate new backgrounds for your images according to your text description, allowing you to completely transform the background while keeping the main subject intact.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to process |
+| `prompt` | STRING | Yes | - | Prompt for the image generation (default: empty) |
+| `n` | INT | Yes | 1-6 | The number of images to generate (default: 1) |
+| `seed` | INT | Yes | 0-18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0) |
+| `recraft_style` | STYLEV3 | No | - | Optional style selection for the generated background |
+| `negative_prompt` | STRING | No | - | An optional text description of undesired elements on an image (default: empty) |
+
+**Note:** The `seed` parameter controls when the node re-executes but does not guarantee deterministic results due to the nature of the external API.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The generated image(s) with replaced background |
diff --git a/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx b/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx
new file mode 100644
index 000000000..f40d63157
--- /dev/null
+++ b/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecraftStyleV3DigitalIllustration - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3DigitalIllustration node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3DigitalIllustration"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3DigitalIllustration/en.md)
+
+This node configures a style for use with the Recraft API, specifically selecting the "digital_illustration" style. It allows you to choose an optional substyle to further refine the artistic direction of the generated image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `substyle` | STRING | No | `"digital_illustration"`<br />`"digital_illustration_anime"`<br />`"digital_illustration_cartoon"`<br />`"digital_illustration_comic"`<br />`"digital_illustration_concept_art"`<br />`"digital_illustration_fantasy"`<br />`"digital_illustration_futuristic"`<br />`"digital_illustration_graffiti"`<br />`"digital_illustration_graphic_novel"`<br />`"digital_illustration_hyperrealistic"`<br />`"digital_illustration_ink"`<br />`"digital_illustration_manga"`<br />`"digital_illustration_minimalist"`<br />`"digital_illustration_pixel_art"`<br />`"digital_illustration_pop_art"`<br />`"digital_illustration_retro"`<br />`"digital_illustration_sci_fi"`<br />`"digital_illustration_sticker"`<br />`"digital_illustration_street_art"`<br />`"digital_illustration_surreal"`<br />`"digital_illustration_vector"` | An optional substyle to specify a particular type of digital illustration. If not selected, the base "digital_illustration" style is used. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `recraft_style` | STYLEV3 | A configured style object containing the selected "digital_illustration" style and optional substyle, ready to be passed to other Recraft API nodes. |
diff --git a/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx b/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx
new file mode 100644
index 000000000..3c9145f2f
--- /dev/null
+++ b/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx
@@ -0,0 +1,24 @@
+---
+title: "RecraftStyleV3InfiniteStyleLibrary - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3InfiniteStyleLibrary node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3InfiniteStyleLibrary"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3InfiniteStyleLibrary/en.md)
+
+This node allows you to select a style from Recraft's Infinite Style Library using a preexisting UUID. It retrieves the style information based on the provided style identifier and returns it for use in other Recraft nodes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `style_id` | STRING | Yes | Any valid UUID | UUID of style from Infinite Style Library. |
+
+**Note:** The `style_id` input cannot be empty. If an empty string is provided, the node will raise an exception.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `recraft_style` | STYLEV3 | The selected style object from Recraft's Infinite Style Library |
diff --git a/built-in-nodes/RecraftStyleV3LogoRaster.mdx b/built-in-nodes/RecraftStyleV3LogoRaster.mdx
new file mode 100644
index 000000000..7dd8842e7
--- /dev/null
+++ b/built-in-nodes/RecraftStyleV3LogoRaster.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecraftStyleV3LogoRaster - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3LogoRaster node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3LogoRaster"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3LogoRaster/en.md)
+
+This node allows you to select the logo raster style and choose from available substyles. It specializes in generating logo designs with raster-based styling options, providing various visual treatments for logo creation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `substyle` | STRING | Yes | Multiple options available | The specific logo raster substyle to apply for logo generation |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated logo image with the selected raster style applied |
diff --git a/built-in-nodes/RecraftStyleV3RealisticImage.mdx b/built-in-nodes/RecraftStyleV3RealisticImage.mdx
new file mode 100644
index 000000000..e395504ca
--- /dev/null
+++ b/built-in-nodes/RecraftStyleV3RealisticImage.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecraftStyleV3RealisticImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3RealisticImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3RealisticImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3RealisticImage/en.md)
+
+This node creates a realistic image style configuration for use with Recraft's API. It allows you to select the realistic_image style and choose from various substyle options to customize the output appearance.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `substyle` | STRING | Yes | Multiple options available | The specific substyle to apply to the realistic_image style. If set to "None", no substyle will be applied. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `recraft_style` | STYLEV3 | Returns a Recraft style configuration object containing the realistic_image style and selected substyle settings. |
diff --git a/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx b/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx
new file mode 100644
index 000000000..81e9e2736
--- /dev/null
+++ b/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecraftStyleV3VectorIllustrationNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3VectorIllustrationNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3VectorIllustrationNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3VectorIllustrationNode/en.md)
+
+This node configures a style for use with the Recraft API, specifically selecting the `vector_illustration` style. It allows you to optionally choose a more specific substyle within that category. The node outputs a style configuration object that can be passed to other Recraft API nodes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `substyle` | STRING | No | `"vector_illustration"`<br />`"vector_illustration_flat"`<br />`"vector_illustration_3d"`<br />`"vector_illustration_hand_drawn"`<br />`"vector_illustration_retro"`<br />`"vector_illustration_modern"`<br />`"vector_illustration_abstract"`<br />`"vector_illustration_geometric"`<br />`"vector_illustration_organic"`<br />`"vector_illustration_minimalist"`<br />`"vector_illustration_detailed"`<br />`"vector_illustration_colorful"`<br />`"vector_illustration_monochrome"`<br />`"vector_illustration_grayscale"`<br />`"vector_illustration_pastel"`<br />`"vector_illustration_vibrant"`<br />`"vector_illustration_muted"`<br />`"vector_illustration_warm"`<br />`"vector_illustration_cool"`<br />`"vector_illustration_neutral"`<br />`"vector_illustration_bold"`<br />`"vector_illustration_subtle"`<br />`"vector_illustration_playful"`<br />`"vector_illustration_serious"`<br />`"vector_illustration_elegant"`<br />`"vector_illustration_rustic"`<br />`"vector_illustration_urban"`<br />`"vector_illustration_nature"`<br />`"vector_illustration_fantasy"`<br />`"vector_illustration_sci_fi"`<br />`"vector_illustration_historical"`<br />`"vector_illustration_futuristic"`<br />`"vector_illustration_whimsical"`<br />`"vector_illustration_surreal"`<br />`"vector_illustration_realistic"`<br />`"vector_illustration_stylized"`<br />`"vector_illustration_cartoony"`<br />`"vector_illustration_anime"`<br />`"vector_illustration_comic"`<br />`"vector_illustration_pixel"`<br />`"vector_illustration_low_poly"`<br />`"vector_illustration_high_poly"`<br />`"vector_illustration_isometric"`<br />`"vector_illustration_orthographic"`<br />`"vector_illustration_perspective"`<br />`"vector_illustration_2d"`<br />`"vector_illustration_2.5d"`<br />`"vector_illustration_3d"`<br />`"vector_illustration_4d"` | An optional, more specific style within the `vector_illustration` category. If not selected, the base `vector_illustration` style is used. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `recraft_style` | STYLEV3 | A Recraft API style configuration object containing the selected `vector_illustration` style and optional substyle. This can be connected to other Recraft nodes. |
diff --git a/built-in-nodes/RecraftTextToImageNode.mdx b/built-in-nodes/RecraftTextToImageNode.mdx
new file mode 100644
index 000000000..decff0095
--- /dev/null
+++ b/built-in-nodes/RecraftTextToImageNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftTextToImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftTextToImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftTextToImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftTextToImageNode/en.md)
+
+Generates images synchronously based on prompt and resolution. This node connects to the Recraft API to create images from text descriptions with specified dimensions and style options.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the image generation. (default: "") |
+| `size` | COMBO | Yes | "1024x1024"<br />"1152x896"<br />"896x1152"<br />"1216x832"<br />"832x1216"<br />"1344x768"<br />"768x1344"<br />"1536x640"<br />"640x1536" | The size of the generated image. (default: "1024x1024") |
+| `n` | INT | Yes | 1-6 | The number of images to generate. (default: 1) |
+| `seed` | INT | Yes | 0-18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. (default: 0) |
+| `recraft_style` | COMBO | No | Multiple options available | Optional style selection for image generation. |
+| `negative_prompt` | STRING | No | - | An optional text description of undesired elements on an image. (default: "") |
+| `recraft_controls` | COMBO | No | Multiple options available | Optional additional controls over the generation via the Recraft Controls node. |
+
+**Note:** The `seed` parameter only controls when the node re-runs but does not make the image generation deterministic. The actual output images will vary even with the same seed value.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The generated image(s) as tensor output. |
diff --git a/built-in-nodes/RecraftTextToVectorNode.mdx b/built-in-nodes/RecraftTextToVectorNode.mdx
new file mode 100644
index 000000000..c77334f38
--- /dev/null
+++ b/built-in-nodes/RecraftTextToVectorNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftTextToVectorNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftTextToVectorNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftTextToVectorNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftTextToVectorNode/en.md)
+
+Generates SVG synchronously based on prompt and resolution. This node creates vector illustrations by sending text prompts to the Recraft API and returns the generated SVG content.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Prompt for the image generation. (default: "") |
+| `substyle` | COMBO | Yes | Multiple options available | The specific illustration style to use for generation. Options are determined by the vector illustration substyles available in RecraftStyleV3. |
+| `size` | COMBO | Yes | Multiple options available | The size of the generated image. (default: 1024x1024) |
+| `n` | INT | Yes | 1-6 | The number of images to generate. (default: 1, min: 1, max: 6) |
+| `seed` | INT | Yes | 0-18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. (default: 0, min: 0, max: 18446744073709551615) |
+| `negative_prompt` | STRING | No | - | An optional text description of undesired elements on an image. (default: "") |
+| `recraft_controls` | CONTROLS | No | - | Optional additional controls over the generation via the Recraft Controls node. |
+
+**Note:** The `seed` parameter only controls when the node re-runs but does not make the generation results deterministic.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `SVG` | SVG | The generated vector illustration in SVG format |
diff --git a/built-in-nodes/RecraftV4TextToImageNode.mdx b/built-in-nodes/RecraftV4TextToImageNode.mdx
new file mode 100644
index 000000000..494a31114
--- /dev/null
+++ b/built-in-nodes/RecraftV4TextToImageNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftV4TextToImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftV4TextToImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftV4TextToImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftV4TextToImageNode/en.md)
+
+This node generates images from text descriptions using the Recraft V4 or V4 Pro AI models. It sends your prompt to an external API and returns the generated images. You can control the output by specifying the model, image size, and number of images to create.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | N/A | Prompt for the image generation. Maximum 10,000 characters. |
+| `negative_prompt` | STRING | No | N/A | An optional text description of undesired elements on an image. |
+| `model` | COMBO | Yes | `"recraftv4"`<br />`"recraftv4_pro"` | The model to use for generation. Selecting a model determines the available image sizes. |
+| `size` | COMBO | Yes | Varies by model | The size of the generated image. The available options depend on the selected model. For `recraftv4`, the default is "1024x1024". For `recraftv4_pro`, the default is "2048x2048". |
+| `n` | INT | Yes | 1 to 6 | The number of images to generate (default: 1). |
+| `seed` | INT | Yes | 0 to 18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0). |
+| `recraft_controls` | CUSTOM | No | N/A | Optional additional controls over the generation via the Recraft Controls node. |
+
+**Note:** The `size` parameter is a dynamic input whose available options change based on the selected `model`. The `seed` value does not guarantee reproducible image outputs.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image or batch of images. |
diff --git a/built-in-nodes/RecraftV4TextToVectorNode.mdx b/built-in-nodes/RecraftV4TextToVectorNode.mdx
new file mode 100644
index 000000000..4d7a460be
--- /dev/null
+++ b/built-in-nodes/RecraftV4TextToVectorNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftV4TextToVectorNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftV4TextToVectorNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftV4TextToVectorNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftV4TextToVectorNode/en.md)
+
+The Recraft V4 Text to Vector node generates Scalable Vector Graphics (SVG) illustrations from a text description. It connects to an external API to use either the Recraft V4 or Recraft V4 Pro model for image generation. The node outputs one or more SVG images based on your prompt.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | N/A | Prompt for the image generation. Maximum 10,000 characters. |
+| `negative_prompt` | STRING | No | N/A | An optional text description of undesired elements on an image. |
+| `model` | COMBO | Yes | `"recraftv4"`<br />`"recraftv4_pro"` | The model to use for generation. Selecting a model changes the available `size` options. |
+| `size` | COMBO | Yes | For `recraftv4`: `"1024x1024"`, `"1152x896"`, `"896x1152"`, `"1216x832"`, `"832x1216"`, `"1344x768"`, `"768x1344"`, `"1536x640"`, `"640x1536"`<br />For `recraftv4_pro`: `"2048x2048"`, `"2304x1792"`, `"1792x2304"`, `"2432x1664"`, `"1664x2432"`, `"2688x1536"`, `"1536x2688"`, `"3072x1280"`, `"1280x3072"` | The size of the generated image. The available options depend on the selected `model`. Default is `"1024x1024"` for `recraftv4` and `"2048x2048"` for `recraftv4_pro`. |
+| `n` | INT | Yes | 1 to 6 | The number of images to generate (default: 1). |
+| `seed` | INT | Yes | 0 to 18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. |
+| `recraft_controls` | CUSTOM | No | N/A | Optional additional controls over the generation via the Recraft Controls node. |
+
+**Note:** The `size` parameter is a dynamic input whose available options change based on the selected `model`. The `seed` value does not guarantee reproducible results from the external API.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | SVG | The generated Scalable Vector Graphics (SVG) image(s). |
diff --git a/built-in-nodes/RecraftVectorizeImageNode.mdx b/built-in-nodes/RecraftVectorizeImageNode.mdx
new file mode 100644
index 000000000..dbdae080c
--- /dev/null
+++ b/built-in-nodes/RecraftVectorizeImageNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "RecraftVectorizeImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftVectorizeImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftVectorizeImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftVectorizeImageNode/en.md)
+
+Generates SVG synchronously from an input image. This node converts raster images into vector graphics format by processing each image in the input batch and combining the results into a single SVG output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to convert to SVG format |
+| `auth_token` | AUTH_TOKEN_COMFY_ORG | No | - | Authentication token for API access |
+| `comfy_api_key` | API_KEY_COMFY_ORG | No | - | API key for Comfy.org services |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `SVG` | SVG | The generated vector graphics output combining all processed images |
diff --git a/built-in-nodes/ReferenceLatent.mdx b/built-in-nodes/ReferenceLatent.mdx
new file mode 100644
index 000000000..dabf6ae5a
--- /dev/null
+++ b/built-in-nodes/ReferenceLatent.mdx
@@ -0,0 +1,23 @@
+---
+title: "ReferenceLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ReferenceLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ReferenceLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReferenceLatent/en.md)
+
+This node sets the guiding latent for an edit model. It takes conditioning data and an optional latent input, then modifies the conditioning to include reference latent information. If the model supports it, you can chain multiple ReferenceLatent nodes to set multiple reference images.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | Yes | - | The conditioning data to be modified with reference latent information |
+| `latent` | LATENT | No | - | Optional latent data to use as reference for the edit model |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | CONDITIONING | The modified conditioning data containing reference latent information |
diff --git a/built-in-nodes/ReferenceTimbreAudio.mdx b/built-in-nodes/ReferenceTimbreAudio.mdx
new file mode 100644
index 000000000..92d6bda11
--- /dev/null
+++ b/built-in-nodes/ReferenceTimbreAudio.mdx
@@ -0,0 +1,23 @@
+---
+title: "ReferenceTimbreAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ReferenceTimbreAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ReferenceTimbreAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReferenceTimbreAudio/en.md)
+
+This node sets a reference audio timbre for use in the "ace step 1.5" process. It works by taking a conditioning input and optionally a latent representation of audio, then attaches that latent data to the conditioning for use by subsequent nodes in the workflow.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | Yes | | The conditioning data to which the reference audio information will be attached. |
+| `latent` | LATENT | No | | An optional latent representation of the reference audio. When provided, its samples are added to the conditioning. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | The modified conditioning data, now containing the reference audio timbre latents if the optional `latent` input was provided. |
diff --git a/built-in-nodes/RegexExtract.mdx b/built-in-nodes/RegexExtract.mdx
new file mode 100644
index 000000000..ec74dd98f
--- /dev/null
+++ b/built-in-nodes/RegexExtract.mdx
@@ -0,0 +1,30 @@
+---
+title: "RegexExtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RegexExtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RegexExtract"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexExtract/en.md)
+
+The RegexExtract node searches for patterns in text using regular expressions. It can find the first match, all matches, specific groups from matches, or all groups across multiple matches. The node supports various regex flags for case sensitivity, multiline matching, and dotall behavior.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | - | The input text to search for patterns |
+| `regex_pattern` | STRING | Yes | - | The regular expression pattern to search for |
+| `mode` | COMBO | Yes | "First Match"<br />"All Matches"<br />"First Group"<br />"All Groups" | The extraction mode determines what parts of matches are returned |
+| `case_insensitive` | BOOLEAN | No | - | Whether to ignore case when matching (default: True) |
+| `multiline` | BOOLEAN | No | - | Whether to treat the string as multiple lines (default: False) |
+| `dotall` | BOOLEAN | No | - | Whether the dot (.) matches newlines (default: False) |
+| `group_index` | INT | No | 0-100 | The capture group index to extract when using group modes (default: 1) |
+
+**Note:** When using "First Group" or "All Groups" modes, the `group_index` parameter specifies which capture group to extract. Group 0 represents the entire match, while groups 1+ represent the numbered capture groups in your regex pattern.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The extracted text based on the selected mode and parameters |
diff --git a/built-in-nodes/RegexMatch.mdx b/built-in-nodes/RegexMatch.mdx
new file mode 100644
index 000000000..6c8b8cc13
--- /dev/null
+++ b/built-in-nodes/RegexMatch.mdx
@@ -0,0 +1,26 @@
+---
+title: "RegexMatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RegexMatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RegexMatch"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexMatch/en.md)
+
+The RegexMatch node checks if a text string matches a specified regular expression pattern. It searches the input string for any occurrence of the regex pattern and returns whether a match was found. You can configure various regex flags like case sensitivity, multiline mode, and dotall mode to control how the pattern matching behaves.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | - | The text string to search for matches |
+| `regex_pattern` | STRING | Yes | - | The regular expression pattern to match against the string |
+| `case_insensitive` | BOOLEAN | No | - | Whether to ignore case when matching (default: True) |
+| `multiline` | BOOLEAN | No | - | Whether to enable multiline mode for regex matching (default: False) |
+| `dotall` | BOOLEAN | No | - | Whether to enable dotall mode for regex matching (default: False) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `matches` | BOOLEAN | Returns True if the regex pattern matches any part of the input string, False otherwise |
diff --git a/built-in-nodes/RegexReplace.mdx b/built-in-nodes/RegexReplace.mdx
new file mode 100644
index 000000000..7bfe4b8d7
--- /dev/null
+++ b/built-in-nodes/RegexReplace.mdx
@@ -0,0 +1,28 @@
+---
+title: "RegexReplace - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RegexReplace node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RegexReplace"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexReplace/en.md)
+
+The RegexReplace node finds and replaces text in strings using regular expression patterns. It allows you to search for text patterns and replace them with new text, with options to control how the pattern matching works including case sensitivity, multiline matching, and limiting the number of replacements.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | - | The input text string to search and replace within |
+| `regex_pattern` | STRING | Yes | - | The regular expression pattern to search for in the input string |
+| `replace` | STRING | Yes | - | The replacement text to substitute for matched patterns |
+| `case_insensitive` | BOOLEAN | No | - | When enabled, makes the pattern matching ignore case differences (default: True) |
+| `multiline` | BOOLEAN | No | - | When enabled, changes the behavior of ^ and $ to match at the start/end of each line rather than just the start/end of the entire string (default: False) |
+| `dotall` | BOOLEAN | No | - | When enabled, the dot (.) character will match any character including newline characters. When disabled, dots won't match newlines (default: False) |
+| `count` | INT | No | 0-100 | Maximum number of replacements to make. Set to 0 to replace all occurrences (default). Set to 1 to replace only the first match, 2 for the first two matches, etc. (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The modified string with the specified replacements applied |
diff --git a/built-in-nodes/RenormCFG.mdx b/built-in-nodes/RenormCFG.mdx
new file mode 100644
index 000000000..f34ce2783
--- /dev/null
+++ b/built-in-nodes/RenormCFG.mdx
@@ -0,0 +1,24 @@
+---
+title: "RenormCFG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RenormCFG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RenormCFG"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RenormCFG/en.md)
+
+The RenormCFG node modifies the classifier-free guidance (CFG) process in diffusion models by applying conditional scaling and normalization. It adjusts the denoising process based on specified timestep thresholds and renormalization factors to control the influence of conditional versus unconditional predictions during image generation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to apply renormalized CFG to |
+| `cfg_trunc` | FLOAT | No | 0.0 - 100.0 | Timestep threshold for applying CFG scaling (default: 100.0) |
+| `renorm_cfg` | FLOAT | No | 0.0 - 100.0 | Renormalization factor for controlling conditional guidance strength (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with renormalized CFG function applied |
diff --git a/built-in-nodes/RepeatImageBatch.mdx b/built-in-nodes/RepeatImageBatch.mdx
new file mode 100644
index 000000000..c6be4abb6
--- /dev/null
+++ b/built-in-nodes/RepeatImageBatch.mdx
@@ -0,0 +1,22 @@
+---
+title: "RepeatImageBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RepeatImageBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RepeatImageBatch"
+icon: "circle"
+mode: wide
+---
+
+The RepeatImageBatch node is designed to replicate a given image a specified number of times, creating a batch of identical images. This functionality is useful for operations that require multiple instances of the same image, such as batch processing or data augmentation.
+
+## Inputs
+
+| Field   | Data Type | Description                                                                 |
+|---------|-------------|-----------------------------------------------------------------------------|
+| `image` | `IMAGE`     | The 'image' parameter represents the image to be replicated. It is crucial for defining the content that will be duplicated across the batch. |
+| `amount`| `INT`       | The 'amount' parameter specifies the number of times the input image should be replicated. It directly influences the size of the output batch, allowing for flexible batch creation. |
+
+## Outputs
+
+| Field | Data Type | Description                                                              |
+|-------|-------------|--------------------------------------------------------------------------|
+| `image`| `IMAGE`     | The output is a batch of images, each identical to the input image, replicated according to the specified 'amount'. |
diff --git a/built-in-nodes/RepeatLatentBatch.mdx b/built-in-nodes/RepeatLatentBatch.mdx
new file mode 100644
index 000000000..ea740cdde
--- /dev/null
+++ b/built-in-nodes/RepeatLatentBatch.mdx
@@ -0,0 +1,22 @@
+---
+title: "RepeatLatentBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RepeatLatentBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RepeatLatentBatch"
+icon: "circle"
+mode: wide
+---
+
+The RepeatLatentBatch node is designed to replicate a given batch of latent representations a specified number of times, potentially including additional data like noise masks and batch indices. This functionality is crucial for operations that require multiple instances of the same latent data, such as data augmentation or specific generative tasks.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `samples` | `LATENT`    | The 'samples' parameter represents the latent representations to be replicated. It is essential for defining the data that will undergo repetition. |
+| `amount`  | `INT`       | The 'amount' parameter specifies the number of times the input samples should be repeated. It directly influences the size of the output batch, thereby affecting the computational load and the diversity of the generated data. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a modified version of the input latent representations, replicated according to the specified 'amount'. It may include replicated noise masks and adjusted batch indices, if applicable. |
diff --git a/built-in-nodes/ReplaceText.mdx b/built-in-nodes/ReplaceText.mdx
new file mode 100644
index 000000000..58a9295bd
--- /dev/null
+++ b/built-in-nodes/ReplaceText.mdx
@@ -0,0 +1,24 @@
+---
+title: "ReplaceText - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ReplaceText node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ReplaceText"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReplaceText/en.md)
+
+The Replace Text node performs a simple text substitution. It searches for a specified piece of text within the input and replaces every occurrence with a new piece of text. The operation is applied to all text inputs provided to the node.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | Yes | - | The text to process. |
+| `find` | STRING | No | - | The text to find and replace (default: empty string). |
+| `replace` | STRING | No | - | The text to replace the found text with (default: empty string). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `text` | STRING | The processed text with all occurrences of the `find` text replaced by the `replace` text. |
diff --git a/built-in-nodes/ReplaceVideoLatentFrames.mdx b/built-in-nodes/ReplaceVideoLatentFrames.mdx
new file mode 100644
index 000000000..b3a0e940b
--- /dev/null
+++ b/built-in-nodes/ReplaceVideoLatentFrames.mdx
@@ -0,0 +1,29 @@
+---
+title: "ReplaceVideoLatentFrames - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ReplaceVideoLatentFrames node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ReplaceVideoLatentFrames"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReplaceVideoLatentFrames/en.md)
+
+The ReplaceVideoLatentFrames node inserts frames from a source latent video into a destination latent video, starting at a specified frame index. If the source latent is not provided, the destination latent is returned unchanged. The node handles negative indexing and will issue a warning if the source frames do not fit within the destination.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `destination` | LATENT | Yes | - | The destination latent where frames will be replaced. |
+| `source` | LATENT | No | - | The source latent providing frames to insert into the destination latent. If not provided, the destination latent is returned unchanged. |
+| `index` | INT | No | -MAX_RESOLUTION to MAX_RESOLUTION | The starting latent frame index in the destination latent where the source latent frames will be placed. Negative values count from the end (default: 0). |
+
+**Constraints:**
+
+* The `index` must be within the bounds of the destination latent's frame count. If it is not, a warning is logged and the destination is returned unchanged.
+* The source latent frames must fit within the destination latent frames starting from the specified `index`. If they do not, a warning is logged and the destination is returned unchanged.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | LATENT | The resulting latent video after the frame replacement operation. |
diff --git a/built-in-nodes/Reroute.mdx b/built-in-nodes/Reroute.mdx
new file mode 100644
index 000000000..3431c6737
--- /dev/null
+++ b/built-in-nodes/Reroute.mdx
@@ -0,0 +1,20 @@
+---
+title: "Reroute - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Reroute node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Reroute"
+icon: "circle"
+mode: wide
+---
+Node Name: Reroute Node
+Node Purpose: Mainly used to organize the logic of overly long connection lines in the ComfyUI workflow.
+
+## How to Use Reroute Nodes
+
+| Menu Options | Description |
+| --- | --- |
+| Show Type | Display the node's type property |
+| Hide Type By Default | Hide the node's type property by default |
+| Set Vertical | Set the node's wiring direction to vertical |
+| Set Horizontal | Set the node's wiring direction to horizontal |
+
+When your wiring logic is too long and complex, and you want to tidy up the interface, you can insert a ```Reroute``` node between two connection points. The input and output of this node are not type-restricted, and the default style is horizontal. You can change the wiring direction to vertical through the right-click menu.
diff --git a/built-in-nodes/RescaleCFG.mdx b/built-in-nodes/RescaleCFG.mdx
new file mode 100644
index 000000000..c4f7edf43
--- /dev/null
+++ b/built-in-nodes/RescaleCFG.mdx
@@ -0,0 +1,22 @@
+---
+title: "RescaleCFG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RescaleCFG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RescaleCFG"
+icon: "circle"
+mode: wide
+---
+
+The RescaleCFG node is designed to adjust the conditioning and unconditioning scales of a model's output based on a specified multiplier, aiming to achieve a more balanced and controlled generation process. It operates by rescaling the model's output to modify the influence of conditioned and unconditioned components, thereby potentially enhancing the model's performance or output quality.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The model parameter represents the generative model to be adjusted. It is crucial as the node applies a rescaling function to the model's output, directly influencing the generation process. |
+| `multiplier` | `FLOAT` | The multiplier parameter controls the extent of rescaling applied to the model's output. It determines the balance between the original and rescaled components, affecting the final output's characteristics. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The modified model with adjusted conditioning and unconditioning scales. This model is expected to produce outputs with potentially enhanced characteristics due to the applied rescaling. |
diff --git a/built-in-nodes/ResizeAndPadImage.mdx b/built-in-nodes/ResizeAndPadImage.mdx
new file mode 100644
index 000000000..9a370ce9f
--- /dev/null
+++ b/built-in-nodes/ResizeAndPadImage.mdx
@@ -0,0 +1,26 @@
+---
+title: "ResizeAndPadImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResizeAndPadImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResizeAndPadImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeAndPadImage/en.md)
+
+The ResizeAndPadImage node resizes an image to fit within specified dimensions while maintaining its original aspect ratio. It scales the image down proportionally to fit within the target width and height, then adds padding around the edges to fill any remaining space. The padding color and interpolation method can be customized to control the appearance of the padded areas and the quality of the resizing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be resized and padded |
+| `target_width` | INT | Yes | 1 to MAX_RESOLUTION | The desired width of the output image (default: 512) |
+| `target_height` | INT | Yes | 1 to MAX_RESOLUTION | The desired height of the output image (default: 512) |
+| `padding_color` | COMBO | Yes | "white"<br />"black" | The color to use for padding areas around the resized image |
+| `interpolation` | COMBO | Yes | "area"<br />"bicubic"<br />"nearest-exact"<br />"bilinear"<br />"lanczos" | The interpolation method used for resizing the image |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resized and padded output image |
diff --git a/built-in-nodes/ResizeImageMaskNode.mdx b/built-in-nodes/ResizeImageMaskNode.mdx
new file mode 100644
index 000000000..bf42af09b
--- /dev/null
+++ b/built-in-nodes/ResizeImageMaskNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "ResizeImageMaskNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResizeImageMaskNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResizeImageMaskNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImageMaskNode/en.md)
+
+The Resize Image/Mask node provides multiple methods to change the dimensions of an input image or mask. It can scale by a multiplier, set specific dimensions, match the size of another input, or adjust based on pixel count, using various interpolation methods for quality.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `input` | IMAGE or MASK | Yes | N/A | The image or mask to be resized. |
+| `resize_type` | COMBO | Yes | `SCALE_BY`<br />`SCALE_DIMENSIONS`<br />`SCALE_LONGER_DIMENSION`<br />`SCALE_SHORTER_DIMENSION`<br />`SCALE_WIDTH`<br />`SCALE_HEIGHT`<br />`SCALE_TOTAL_PIXELS`<br />`MATCH_SIZE` | The method used to determine the new size. The required parameters change based on the selected type. |
+| `multiplier` | FLOAT | No | 0.01 to 8.0 | The scaling factor. Required when `resize_type` is `SCALE_BY` (default: 1.00). |
+| `width` | INT | No | 0 to 8192 | The target width in pixels. Required when `resize_type` is `SCALE_DIMENSIONS` or `SCALE_WIDTH` (default: 512). |
+| `height` | INT | No | 0 to 8192 | The target height in pixels. Required when `resize_type` is `SCALE_DIMENSIONS` or `SCALE_HEIGHT` (default: 512). |
+| `crop` | COMBO | No | `"disabled"`<br />`"center"` | The cropping method to apply when dimensions don't match the aspect ratio. Only available when `resize_type` is `SCALE_DIMENSIONS` or `MATCH_SIZE` (default: "center"). |
+| `longer_size` | INT | No | 0 to 8192 | The target size for the longer side of the image. Required when `resize_type` is `SCALE_LONGER_DIMENSION` (default: 512). |
+| `shorter_size` | INT | No | 0 to 8192 | The target size for the shorter side of the image. Required when `resize_type` is `SCALE_SHORTER_DIMENSION` (default: 512). |
+| `megapixels` | FLOAT | No | 0.01 to 16.0 | The target total number of megapixels. Required when `resize_type` is `SCALE_TOTAL_PIXELS` (default: 1.0). |
+| `match` | IMAGE or MASK | No | N/A | An image or mask whose dimensions the input will be resized to match. Required when `resize_type` is `MATCH_SIZE`. |
+| `scale_method` | COMBO | Yes | `"nearest-exact"`<br />`"bilinear"`<br />`"area"`<br />`"bicubic"`<br />`"lanczos"` | The interpolation algorithm used for scaling (default: "area"). |
+
+**Note:** The `crop` parameter is only available and relevant when the `resize_type` is set to `SCALE_DIMENSIONS` or `MATCH_SIZE`. When using `SCALE_WIDTH` or `SCALE_HEIGHT`, the other dimension is automatically scaled to maintain the original aspect ratio.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `resized` | IMAGE or MASK | The resized image or mask, matching the data type of the input. |
diff --git a/built-in-nodes/ResizeImagesByLongerEdge.mdx b/built-in-nodes/ResizeImagesByLongerEdge.mdx
new file mode 100644
index 000000000..ecf36d606
--- /dev/null
+++ b/built-in-nodes/ResizeImagesByLongerEdge.mdx
@@ -0,0 +1,23 @@
+---
+title: "ResizeImagesByLongerEdge - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResizeImagesByLongerEdge node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResizeImagesByLongerEdge"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByLongerEdge/en.md)
+
+The Resize Images by Longer Edge node resizes one or more images so that their longest side matches a specified target length. It automatically determines whether the width or height is longer and scales the other dimension proportionally to preserve the original aspect ratio. This is useful for standardizing image sizes based on their largest dimension.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image or batch of images to be resized. |
+| `longer_edge` | INT | No | 1 - 8192 | Target length for the longer edge. The shorter edge will be scaled proportionally. (default: 1024) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resized image or batch of images. The output will have the same number of images as the input, with each one's longer edge matching the specified `longer_edge` length. |
diff --git a/built-in-nodes/ResizeImagesByShorterEdge.mdx b/built-in-nodes/ResizeImagesByShorterEdge.mdx
new file mode 100644
index 000000000..3a0b705be
--- /dev/null
+++ b/built-in-nodes/ResizeImagesByShorterEdge.mdx
@@ -0,0 +1,23 @@
+---
+title: "ResizeImagesByShorterEdge - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResizeImagesByShorterEdge node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResizeImagesByShorterEdge"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByShorterEdge/en.md)
+
+This node resizes images by adjusting their dimensions so that the length of the shorter side matches a specified target value. It calculates new dimensions to maintain the original image's aspect ratio. The resized image is returned.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be resized. |
+| `shorter_edge` | INT | No | 1 to 8192 | Target length for the shorter edge. (default: 512) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The resized image. |
diff --git a/built-in-nodes/ResolutionBucket.mdx b/built-in-nodes/ResolutionBucket.mdx
new file mode 100644
index 000000000..9d92cb883
--- /dev/null
+++ b/built-in-nodes/ResolutionBucket.mdx
@@ -0,0 +1,26 @@
+---
+title: "ResolutionBucket - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResolutionBucket node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResolutionBucket"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResolutionBucket/en.md)
+
+This node organizes a list of latent images and their corresponding conditioning data by their resolution. It groups together items that share the same height and width, creating separate batches for each unique resolution. This process is useful for preparing data for efficient training, as it allows models to process multiple items of the same size together.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `latents` | LATENT | Yes | N/A | List of latent dicts to bucket by resolution. |
+| `conditioning` | CONDITIONING | Yes | N/A | List of conditioning lists (must match latents length). |
+
+**Note:** The number of items in the `latents` list must exactly match the number of items in the `conditioning` list. Each latent dictionary can contain a batch of samples, and the corresponding conditioning list must contain a matching number of conditioning items for that batch.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `latents` | LATENT | List of batched latent dicts, one per resolution bucket. |
+| `conditioning` | CONDITIONING | List of condition lists, one per resolution bucket. |
diff --git a/built-in-nodes/Rodin3D_Detail.mdx b/built-in-nodes/Rodin3D_Detail.mdx
new file mode 100644
index 000000000..44b3c535e
--- /dev/null
+++ b/built-in-nodes/Rodin3D_Detail.mdx
@@ -0,0 +1,25 @@
+---
+title: "Rodin3D_Detail - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Detail node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Detail"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Detail/en.md)
+
+The Rodin 3D Detail node generates detailed 3D assets using the Rodin API. It takes input images and processes them through the Rodin service to create high-quality 3D models with detailed geometry and materials. The node handles the entire workflow from task creation to downloading the final 3D model file.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | Yes | - | Input images used for 3D model generation |
+| `Seed` | INT | Yes | - | Random seed value for reproducible results |
+| `Material_Type` | STRING | Yes | - | Type of material to apply to the 3D model |
+| `Polygon_count` | STRING | Yes | - | Target polygon count for the generated 3D model |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | File path to the generated 3D model |
diff --git a/built-in-nodes/Rodin3D_Gen2.mdx b/built-in-nodes/Rodin3D_Gen2.mdx
new file mode 100644
index 000000000..1a5c24e5c
--- /dev/null
+++ b/built-in-nodes/Rodin3D_Gen2.mdx
@@ -0,0 +1,26 @@
+---
+title: "Rodin3D_Gen2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Gen2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Gen2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen2/en.md)
+
+The Rodin3D_Gen2 node generates 3D assets using the Rodin API. It takes input images and converts them into 3D models with various material types and polygon counts. The node handles the entire generation process including task creation, status polling, and file downloading automatically.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | Yes | - | Input images to use for 3D model generation |
+| `Seed` | INT | No | 0-65535 | Random seed value for generation (default: 0) |
+| `Material_Type` | COMBO | No | "PBR"<br />"Shaded" | Type of material to apply to the 3D model (default: "PBR") |
+| `Polygon_count` | COMBO | No | "4K-Quad"<br />"8K-Quad"<br />"18K-Quad"<br />"50K-Quad"<br />"2K-Triangle"<br />"20K-Triangle"<br />"150K-Triangle"<br />"500K-Triangle" | Target polygon count for the generated 3D model (default: "500K-Triangle") |
+| `TAPose` | BOOLEAN | No | - | Whether to apply TAPose processing (default: False) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | File path to the generated 3D model |
diff --git a/built-in-nodes/Rodin3D_Regular.mdx b/built-in-nodes/Rodin3D_Regular.mdx
new file mode 100644
index 000000000..651cc76de
--- /dev/null
+++ b/built-in-nodes/Rodin3D_Regular.mdx
@@ -0,0 +1,25 @@
+---
+title: "Rodin3D_Regular - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Regular node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Regular"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Regular/en.md)
+
+The Rodin 3D Regular node generates 3D assets using the Rodin API. It takes input images and processes them through the Rodin service to create 3D models. The node handles the entire workflow from task creation to downloading the final 3D model files.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | Yes | - | Input images used for 3D model generation |
+| `Seed` | INT | Yes | - | Random seed value for reproducible results |
+| `Material_Type` | STRING | Yes | - | Type of material to apply to the 3D model |
+| `Polygon_count` | STRING | Yes | - | Target polygon count for the generated 3D model |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | File path to the generated 3D model |
diff --git a/built-in-nodes/Rodin3D_Sketch.mdx b/built-in-nodes/Rodin3D_Sketch.mdx
new file mode 100644
index 000000000..339cf33f7
--- /dev/null
+++ b/built-in-nodes/Rodin3D_Sketch.mdx
@@ -0,0 +1,23 @@
+---
+title: "Rodin3D_Sketch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Sketch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Sketch"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Sketch/en.md)
+
+This node generates 3D assets using the Rodin API. It takes input images and converts them into 3D models through an external service. The node handles the entire process from task creation to downloading the final 3D model files.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | Yes | - | Input images to be converted into 3D models |
+| `Seed` | INT | No | 0-65535 | Random seed value for generation (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | File path to the generated 3D model |
diff --git a/built-in-nodes/Rodin3D_Smooth.mdx b/built-in-nodes/Rodin3D_Smooth.mdx
new file mode 100644
index 000000000..3832edbc9
--- /dev/null
+++ b/built-in-nodes/Rodin3D_Smooth.mdx
@@ -0,0 +1,25 @@
+---
+title: "Rodin3D_Smooth - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Smooth node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Smooth"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Smooth/en.md)
+
+The Rodin 3D Smooth node generates 3D assets using the Rodin API by processing input images and converting them into smooth 3D models. It takes multiple images as input and produces a downloadable 3D model file. The node handles the entire generation process including task creation, status polling, and file downloading automatically.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | Yes | - | Input images to use for 3D model generation |
+| `Seed` | INT | Yes | - | Random seed value for generation consistency |
+| `Material_Type` | STRING | Yes | - | Type of material to apply to the 3D model |
+| `Polygon_count` | STRING | Yes | - | Target polygon count for the generated 3D model |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | File path to the downloaded 3D model |
diff --git a/built-in-nodes/RunwayFirstLastFrameNode.mdx b/built-in-nodes/RunwayFirstLastFrameNode.mdx
new file mode 100644
index 000000000..2408cb538
--- /dev/null
+++ b/built-in-nodes/RunwayFirstLastFrameNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "RunwayFirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RunwayFirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RunwayFirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayFirstLastFrameNode/en.md)
+
+The Runway First-Last-Frame to Video node generates videos by uploading first and last keyframes along with a text prompt. It creates smooth transitions between the provided start and end frames using Runway's Gen-3 model. This is particularly useful for complex transitions where the end frame differs significantly from the start frame.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | N/A | Text prompt for the generation (default: empty string) |
+| `start_frame` | IMAGE | Yes | N/A | Start frame to be used for the video |
+| `end_frame` | IMAGE | Yes | N/A | End frame to be used for the video. Supported for gen3a_turbo only. |
+| `duration` | COMBO | Yes | Multiple options available | Video duration selection from available Duration options |
+| `ratio` | COMBO | Yes | Multiple options available | Aspect ratio selection from available RunwayGen3aAspectRatio options |
+| `seed` | INT | No | 0-4294967295 | Random seed for generation (default: 0) |
+
+**Parameter Constraints:**
+
+- The `prompt` must contain at least 1 character
+- Both `start_frame` and `end_frame` must have maximum dimensions of 7999x7999 pixels
+- Both `start_frame` and `end_frame` must have aspect ratios between 0.5 and 2.0
+- The `end_frame` parameter is only supported when using the gen3a_turbo model
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video transitioning between the start and end frames |
diff --git a/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx b/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx
new file mode 100644
index 000000000..ee3da353e
--- /dev/null
+++ b/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx
@@ -0,0 +1,32 @@
+---
+title: "RunwayImageToVideoNodeGen3a - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RunwayImageToVideoNodeGen3a node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RunwayImageToVideoNodeGen3a"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayImageToVideoNodeGen3a/en.md)
+
+The Runway Image to Video (Gen3a Turbo) node generates a video from a single starting frame using Runway's Gen3a Turbo model. It takes a text prompt and an initial image frame, then creates a video sequence based on the specified duration and aspect ratio. This node connects to Runway's API to process the generation remotely.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | N/A | Text prompt for the generation (default: "") |
+| `start_frame` | IMAGE | Yes | N/A | Start frame to be used for the video |
+| `duration` | COMBO | Yes | Multiple options available | Video duration selection from available options |
+| `ratio` | COMBO | Yes | Multiple options available | Aspect ratio selection from available options |
+| `seed` | INT | No | 0-4294967295 | Random seed for generation (default: 0) |
+
+**Parameter Constraints:**
+
+- The `start_frame` must have dimensions not exceeding 7999x7999 pixels
+- The `start_frame` must have an aspect ratio between 0.5 and 2.0
+- The `prompt` must contain at least one character (cannot be empty)
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video sequence |
diff --git a/built-in-nodes/RunwayImageToVideoNodeGen4.mdx b/built-in-nodes/RunwayImageToVideoNodeGen4.mdx
new file mode 100644
index 000000000..6da121412
--- /dev/null
+++ b/built-in-nodes/RunwayImageToVideoNodeGen4.mdx
@@ -0,0 +1,32 @@
+---
+title: "RunwayImageToVideoNodeGen4 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RunwayImageToVideoNodeGen4 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RunwayImageToVideoNodeGen4"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayImageToVideoNodeGen4/en.md)
+
+The Runway Image to Video (Gen4 Turbo) node generates a video from a single starting frame using Runway's Gen4 Turbo model. It takes a text prompt and an initial image frame, then creates a video sequence based on the provided duration and aspect ratio settings. The node handles uploading the starting frame to Runway's API and returns the generated video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text prompt for the generation (default: empty string) |
+| `start_frame` | IMAGE | Yes | - | Start frame to be used for the video |
+| `duration` | COMBO | Yes | Multiple options available | Video duration selection from available duration options |
+| `ratio` | COMBO | Yes | Multiple options available | Aspect ratio selection from available Gen4 Turbo aspect ratio options |
+| `seed` | INT | No | 0 to 4294967295 | Random seed for generation (default: 0) |
+
+**Parameter Constraints:**
+
+- The `start_frame` image must have dimensions not exceeding 7999x7999 pixels
+- The `start_frame` image must have an aspect ratio between 0.5 and 2.0
+- The `prompt` must contain at least one character
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video based on the input frame and prompt |
diff --git a/built-in-nodes/RunwayTextToImageNode.mdx b/built-in-nodes/RunwayTextToImageNode.mdx
new file mode 100644
index 000000000..8cdad4104
--- /dev/null
+++ b/built-in-nodes/RunwayTextToImageNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "RunwayTextToImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RunwayTextToImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RunwayTextToImageNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayTextToImageNode/en.md)
+
+The Runway Text to Image node generates images from text prompts using Runway's Gen 4 model. You can provide a text description and optionally include a reference image to guide the image generation process. The node handles the API communication and returns the generated image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text prompt for the generation (default: "") |
+| `ratio` | COMBO | Yes | "16:9"<br />"1:1"<br />"21:9"<br />"2:3"<br />"3:2"<br />"4:5"<br />"5:4"<br />"9:16"<br />"9:21" | Aspect ratio for the generated image |
+| `reference_image` | IMAGE | No | - | Optional reference image to guide the generation |
+
+**Note:** The reference image must have dimensions not exceeding 7999x7999 pixels and an aspect ratio between 0.5 and 2.0. When a reference image is provided, it guides the image generation process.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image based on the text prompt and optional reference image |
diff --git a/built-in-nodes/SDTurboScheduler.mdx b/built-in-nodes/SDTurboScheduler.mdx
new file mode 100644
index 000000000..3a808b9e3
--- /dev/null
+++ b/built-in-nodes/SDTurboScheduler.mdx
@@ -0,0 +1,23 @@
+---
+title: "SDTurboScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SDTurboScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SDTurboScheduler"
+icon: "circle"
+mode: wide
+---
+
+SDTurboScheduler is designed to generate a sequence of sigma values for image sampling, adjusting the sequence based on the denoise level and the number of steps specified. It leverages a specific model's sampling capabilities to produce these sigma values, which are crucial for controlling the denoising process during image generation.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+| --- | --- | --- |
+| `model` | `MODEL` | The model parameter specifies the generative model to be used for sigma value generation. It is crucial for determining the specific sampling behavior and capabilities of the scheduler. |
+| `steps` | `INT` | The steps parameter determines the length of the sigma sequence to be generated, directly influencing the granularity of the denoising process. |
+| `denoise` | `FLOAT` | The denoise parameter adjusts the starting point of the sigma sequence, allowing for finer control over the denoising level applied during image generation. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+| --- | --- | --- |
+| `sigmas` | `SIGMAS` | A sequence of sigma values generated based on the specified model, steps, and denoise level. These values are essential for controlling the denoising process in image generation. |
diff --git a/built-in-nodes/SD_4XUpscale_Conditioning.mdx b/built-in-nodes/SD_4XUpscale_Conditioning.mdx
new file mode 100644
index 000000000..5989aeda8
--- /dev/null
+++ b/built-in-nodes/SD_4XUpscale_Conditioning.mdx
@@ -0,0 +1,28 @@
+---
+title: "SD_4XUpscale_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SD_4XUpscale_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SD_4XUpscale_Conditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SD_4XUpscale_Conditioning/en.md)
+
+The SD_4XUpscale_Conditioning node prepares conditioning data for upscaling images using diffusion models. It takes input images and conditioning data, then applies scaling and noise augmentation to create modified conditioning that guides the upscaling process. The node outputs both positive and negative conditioning along with latent representations for the upscaled dimensions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | Input images to be upscaled |
+| `positive` | CONDITIONING | Yes | - | Positive conditioning data that guides the generation toward desired content |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning data that steers the generation away from unwanted content |
+| `scale_ratio` | FLOAT | No | 0.0 - 10.0 | Scaling factor applied to the input images (default: 4.0) |
+| `noise_augmentation` | FLOAT | No | 0.0 - 1.0 | Amount of noise to add during the upscaling process (default: 0.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Modified positive conditioning with upscaling information applied |
+| `negative` | CONDITIONING | Modified negative conditioning with upscaling information applied |
+| `latent` | LATENT | Empty latent representation matching the upscaled dimensions |
diff --git a/built-in-nodes/SV3D_Conditioning.mdx b/built-in-nodes/SV3D_Conditioning.mdx
new file mode 100644
index 000000000..c6f5095d4
--- /dev/null
+++ b/built-in-nodes/SV3D_Conditioning.mdx
@@ -0,0 +1,30 @@
+---
+title: "SV3D_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SV3D_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SV3D_Conditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SV3D_Conditioning/en.md)
+
+The SV3D_Conditioning node prepares conditioning data for 3D video generation using the SV3D model. It takes an initial image and processes it through CLIP vision and VAE encoders to create positive and negative conditioning, along with a latent representation. The node generates camera elevation and azimuth sequences for multi-frame video generation based on the specified number of video frames.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip_vision` | CLIP_VISION | Yes | - | The CLIP vision model used for encoding the input image |
+| `init_image` | IMAGE | Yes | - | The initial image that serves as the starting point for 3D video generation |
+| `vae` | VAE | Yes | - | The VAE model used for encoding the image into latent space |
+| `width` | INT | No | 16 to MAX_RESOLUTION | The output width for the generated video frames (default: 576, must be divisible by 8) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | The output height for the generated video frames (default: 576, must be divisible by 8) |
+| `video_frames` | INT | No | 1 to 4096 | The number of frames to generate for the video sequence (default: 21) |
+| `elevation` | FLOAT | No | -90.0 to 90.0 | The camera elevation angle in degrees for the 3D view (default: 0.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The positive conditioning data containing image embeddings and camera parameters for generation |
+| `negative` | CONDITIONING | The negative conditioning data with zeroed embeddings for contrastive generation |
+| `latent` | LATENT | An empty latent tensor with dimensions matching the specified video frames and resolution |
diff --git a/built-in-nodes/SVD_img2vid_Conditioning.mdx b/built-in-nodes/SVD_img2vid_Conditioning.mdx
new file mode 100644
index 000000000..0f2276495
--- /dev/null
+++ b/built-in-nodes/SVD_img2vid_Conditioning.mdx
@@ -0,0 +1,32 @@
+---
+title: "SVD_img2vid_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SVD_img2vid_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SVD_img2vid_Conditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SVD_img2vid_Conditioning/en.md)
+
+The SVD_img2vid_Conditioning node prepares conditioning data for video generation using Stable Video Diffusion. It takes an initial image and processes it through CLIP vision and VAE encoders to create positive and negative conditioning pairs, along with an empty latent space for video generation. This node sets up the necessary parameters for controlling motion, frame rate, and augmentation levels in the generated video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip_vision` | CLIP_VISION | Yes | - | CLIP vision model for encoding the input image |
+| `init_image` | IMAGE | Yes | - | Initial image to use as the starting point for video generation |
+| `vae` | VAE | Yes | - | VAE model for encoding the image into latent space |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Output video width (default: 1024, step: 8) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Output video height (default: 576, step: 8) |
+| `video_frames` | INT | Yes | 1 to 4096 | Number of frames to generate in the video (default: 14) |
+| `motion_bucket_id` | INT | Yes | 1 to 1023 | Controls the amount of motion in the generated video (default: 127) |
+| `fps` | INT | Yes | 1 to 1024 | Frames per second for the generated video (default: 6) |
+| `augmentation_level` | FLOAT | Yes | 0.0 to 10.0 | Level of noise augmentation to apply to the input image (default: 0.0, step: 0.01) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning data containing image embeddings and video parameters |
+| `negative` | CONDITIONING | Negative conditioning data with zeroed embeddings and video parameters |
+| `latent` | LATENT | Empty latent space tensor ready for video generation |
diff --git a/built-in-nodes/SamplerCustom.mdx b/built-in-nodes/SamplerCustom.mdx
new file mode 100644
index 000000000..e04da7848
--- /dev/null
+++ b/built-in-nodes/SamplerCustom.mdx
@@ -0,0 +1,30 @@
+---
+title: "SamplerCustom - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerCustom node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerCustom"
+icon: "circle"
+mode: wide
+---
+
+The SamplerCustom node is designed to provide a flexible and customizable sampling mechanism for various applications. It enables users to select and configure different sampling strategies tailored to their specific needs, enhancing the adaptability and efficiency of the sampling process.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|--------------|-------------|
+| `model`   | `MODEL`      | The 'model' input type specifies the model to be used for sampling, playing a crucial role in determining the sampling behavior and output. |
+| `add_noise` | `BOOLEAN`    | The 'add_noise' input type allows users to specify whether noise should be added to the sampling process, influencing the diversity and characteristics of the generated samples. |
+| `noise_seed` | `INT`        | The 'noise_seed' input type provides a seed for the noise generation, ensuring reproducibility and consistency in the sampling process when adding noise. |
+| `cfg`     | `FLOAT`      | The 'cfg' input type sets the configuration for the sampling process, allowing for fine-tuning of the sampling parameters and behavior. |
+| `positive` | `CONDITIONING` | The 'positive' input type represents positive conditioning information, guiding the sampling process towards generating samples that align with specified positive attributes. |
+| `negative` | `CONDITIONING` | The 'negative' input type represents negative conditioning information, steering the sampling process away from generating samples that exhibit specified negative attributes. |
+| `sampler` | `SAMPLER`    | The 'sampler' input type selects the specific sampling strategy to be employed, directly impacting the nature and quality of the generated samples. |
+| `sigmas`  | `SIGMAS`     | The 'sigmas' input type defines the noise levels to be used in the sampling process, affecting the exploration of the sample space and the diversity of the output. |
+| `latent_image` | `LATENT` | The 'latent_image' input type provides an initial latent image for the sampling process, serving as a starting point for sample generation. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|--------------|-------------|
+| `output`  | `LATENT`     | The 'output' represents the primary result of the sampling process, containing the generated samples. |
+| `denoised_output` | `LATENT` | The 'denoised_output' represents the samples after a denoising process has been applied, potentially enhancing the clarity and quality of the generated samples. |
diff --git a/built-in-nodes/SamplerCustomAdvanced.mdx b/built-in-nodes/SamplerCustomAdvanced.mdx
new file mode 100644
index 000000000..693eeb6a0
--- /dev/null
+++ b/built-in-nodes/SamplerCustomAdvanced.mdx
@@ -0,0 +1,27 @@
+---
+title: "SamplerCustomAdvanced - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerCustomAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerCustomAdvanced"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerCustomAdvanced/en.md)
+
+The SamplerCustomAdvanced node performs advanced latent space sampling using custom noise, guidance, and sampling configurations. It processes a latent image through a guided sampling process with customizable noise generation and sigma schedules, producing both the final sampled output and a denoised version when available.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `noise` | NOISE | Yes | - | The noise generator that provides the initial noise pattern and seed for the sampling process |
+| `guider` | GUIDER | Yes | - | The guidance model that directs the sampling process toward desired outputs |
+| `sampler` | SAMPLER | Yes | - | The sampling algorithm that defines how the latent space is traversed during generation |
+| `sigmas` | SIGMAS | Yes | - | The sigma schedule that controls the noise levels throughout the sampling steps |
+| `latent_image` | LATENT | Yes | - | The initial latent representation that serves as the starting point for sampling |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | LATENT | The final sampled latent representation after completing the sampling process |
+| `denoised_output` | LATENT | A denoised version of the output when available, otherwise returns the same as the output |
diff --git a/built-in-nodes/SamplerDPMAdaptative.mdx b/built-in-nodes/SamplerDPMAdaptative.mdx
new file mode 100644
index 000000000..4eec203ba
--- /dev/null
+++ b/built-in-nodes/SamplerDPMAdaptative.mdx
@@ -0,0 +1,31 @@
+---
+title: "SamplerDPMAdaptative - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMAdaptative node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMAdaptative"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMAdaptative/en.md)
+
+The SamplerDPMAdaptative node implements an adaptive DPM (Diffusion Probabilistic Model) sampler that automatically adjusts step sizes during the sampling process. It uses tolerance-based error control to determine optimal step sizes, balancing computational efficiency with sampling accuracy. This adaptive approach helps maintain quality while potentially reducing the number of steps needed.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `order` | INT | Yes | 2-3 | The order of the sampler method (default: 3) |
+| `rtol` | FLOAT | Yes | 0.0-100.0 | Relative tolerance for error control (default: 0.05) |
+| `atol` | FLOAT | Yes | 0.0-100.0 | Absolute tolerance for error control (default: 0.0078) |
+| `h_init` | FLOAT | Yes | 0.0-100.0 | Initial step size (default: 0.05) |
+| `pcoeff` | FLOAT | Yes | 0.0-100.0 | Proportional coefficient for step size control (default: 0.0) |
+| `icoeff` | FLOAT | Yes | 0.0-100.0 | Integral coefficient for step size control (default: 1.0) |
+| `dcoeff` | FLOAT | Yes | 0.0-100.0 | Derivative coefficient for step size control (default: 0.0) |
+| `accept_safety` | FLOAT | Yes | 0.0-100.0 | Safety factor for step acceptance (default: 0.81) |
+| `eta` | FLOAT | Yes | 0.0-100.0 | Stochasticity parameter (default: 0.0) |
+| `s_noise` | FLOAT | Yes | 0.0-100.0 | Noise scaling factor (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | Returns a configured DPM adaptive sampler instance |
diff --git a/built-in-nodes/SamplerDPMPP_2M_SDE.mdx b/built-in-nodes/SamplerDPMPP_2M_SDE.mdx
new file mode 100644
index 000000000..631d9de48
--- /dev/null
+++ b/built-in-nodes/SamplerDPMPP_2M_SDE.mdx
@@ -0,0 +1,25 @@
+---
+title: "SamplerDPMPP_2M_SDE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMPP_2M_SDE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMPP_2M_SDE"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMPP_2M_SDE/en.md)
+
+The SamplerDPMPP_2M_SDE node creates a DPM++ 2M SDE sampler for diffusion models. This sampler uses second-order differential equation solvers with stochastic differential equations to generate samples. It provides different solver types and noise handling options to control the sampling process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `solver_type` | STRING | Yes | `"midpoint"`<br />`"heun"` | The type of differential equation solver to use for the sampling process |
+| `eta` | FLOAT | Yes | 0.0 - 100.0 | Controls the stochasticity of the sampling process (default: 1.0) |
+| `s_noise` | FLOAT | Yes | 0.0 - 100.0 | Controls the amount of noise added during sampling (default: 1.0) |
+| `noise_device` | STRING | Yes | `"gpu"`<br />`"cpu"` | The device where noise calculations are performed |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | A configured sampler object ready for use in the sampling pipeline |
diff --git a/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx b/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx
new file mode 100644
index 000000000..bc331e54f
--- /dev/null
+++ b/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx
@@ -0,0 +1,23 @@
+---
+title: "SamplerDPMPP_2S_Ancestral - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMPP_2S_Ancestral node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMPP_2S_Ancestral"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMPP_2S_Ancestral/en.md)
+
+The SamplerDPMPP_2S_Ancestral node creates a sampler that uses the DPM++ 2S Ancestral sampling method for generating images. This sampler combines deterministic and stochastic elements to produce varied results while maintaining some consistency. It allows you to control the randomness and noise levels during the sampling process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `eta` | FLOAT | Yes | 0.0 - 100.0 | Controls the amount of stochastic noise added during sampling (default: 1.0) |
+| `s_noise` | FLOAT | Yes | 0.0 - 100.0 | Controls the scale of noise applied during the sampling process (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | Returns a configured sampler object that can be used in the sampling pipeline |
diff --git a/built-in-nodes/SamplerDPMPP_3M_SDE.mdx b/built-in-nodes/SamplerDPMPP_3M_SDE.mdx
new file mode 100644
index 000000000..0aa63bb0d
--- /dev/null
+++ b/built-in-nodes/SamplerDPMPP_3M_SDE.mdx
@@ -0,0 +1,24 @@
+---
+title: "SamplerDPMPP_3M_SDE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMPP_3M_SDE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMPP_3M_SDE"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMPP_3M_SDE/en.md)
+
+The SamplerDPMPP_3M_SDE node creates a DPM++ 3M SDE sampler for use in the sampling process. This sampler uses a third-order multistep stochastic differential equation method with configurable noise parameters. The node allows you to choose whether noise calculations are performed on the GPU or CPU.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `eta` | FLOAT | Yes | 0.0 - 100.0 | Controls the stochasticity of the sampling process (default: 1.0) |
+| `s_noise` | FLOAT | Yes | 0.0 - 100.0 | Controls the amount of noise added during sampling (default: 1.0) |
+| `noise_device` | COMBO | Yes | "gpu"<br />"cpu" | Selects the device for noise calculations, either GPU or CPU |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | Returns a configured sampler object for use in sampling workflows |
diff --git a/built-in-nodes/SamplerDPMPP_SDE.mdx b/built-in-nodes/SamplerDPMPP_SDE.mdx
new file mode 100644
index 000000000..f30e7f8a1
--- /dev/null
+++ b/built-in-nodes/SamplerDPMPP_SDE.mdx
@@ -0,0 +1,25 @@
+---
+title: "SamplerDPMPP_SDE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMPP_SDE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMPP_SDE"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMPP_SDE/en.md)
+
+The SamplerDPMPP_SDE node creates a DPM++ SDE (Stochastic Differential Equation) sampler for use in the sampling process. This sampler provides a stochastic sampling method with configurable noise parameters and device selection. It returns a sampler object that can be used in the sampling pipeline.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `eta` | FLOAT | Yes | 0.0 - 100.0 | Controls the stochasticity of the sampling process (default: 1.0) |
+| `s_noise` | FLOAT | Yes | 0.0 - 100.0 | Controls the amount of noise added during sampling (default: 1.0) |
+| `r` | FLOAT | Yes | 0.0 - 100.0 | A parameter that influences the sampling behavior (default: 0.5) |
+| `noise_device` | COMBO | Yes | "gpu"<br />"cpu" | Selects the device where noise calculations are performed |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | Returns a configured DPM++ SDE sampler object for use in sampling pipelines |
diff --git a/built-in-nodes/SamplerDpmpp2mSde.mdx b/built-in-nodes/SamplerDpmpp2mSde.mdx
new file mode 100644
index 000000000..041fb8479
--- /dev/null
+++ b/built-in-nodes/SamplerDpmpp2mSde.mdx
@@ -0,0 +1,24 @@
+---
+title: "SamplerDpmpp2mSde - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDpmpp2mSde node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDpmpp2mSde"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to generate a sampler for the DPMPP_2M_SDE model, allowing for the creation of samples based on specified solver types, noise levels, and computational device preferences. It abstracts the complexities of sampler configuration, providing a streamlined interface for generating samples with customized settings.
+
+## Inputs
+
+| Parameter       | Data Type | Description                                                                 |
+|-----------------|-------------|-----------------------------------------------------------------------------|
+| `solver_type`   | COMBO[STRING] | Specifies the solver type to be used in the sampling process, offering options between 'midpoint' and 'heun'. This choice influences the numerical integration method applied during sampling. |
+| `eta`           | `FLOAT`     | Determines the step size in the numerical integration, affecting the granularity of the sampling process. A higher value indicates a larger step size. |
+| `s_noise`       | `FLOAT`     | Controls the level of noise introduced during the sampling process, influencing the variability of the generated samples. |
+| `noise_device`  | COMBO[STRING] | Indicates the computational device ('gpu' or 'cpu') on which the noise generation process is executed, affecting performance and efficiency. |
+
+## Outputs
+
+| Parameter       | Data Type | Description                                                                 |
+|-----------------|-------------|-----------------------------------------------------------------------------|
+| `sampler`       | `SAMPLER`   | The output is a sampler configured according to the specified parameters, ready for generating samples. |
diff --git a/built-in-nodes/SamplerDpmppSde.mdx b/built-in-nodes/SamplerDpmppSde.mdx
new file mode 100644
index 000000000..e427b56a2
--- /dev/null
+++ b/built-in-nodes/SamplerDpmppSde.mdx
@@ -0,0 +1,24 @@
+---
+title: "SamplerDpmppSde - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDpmppSde node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDpmppSde"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to generate a sampler for the DPM++ SDE (Stochastic Differential Equation) model. It adapts to both CPU and GPU execution environments, optimizing the sampler's implementation based on the available hardware.
+
+## Inputs
+
+| Parameter      | Data Type | Description |
+|----------------|-------------|-------------|
+| `eta`          | FLOAT       | Specifies the step size for the SDE solver, influencing the granularity of the sampling process.|
+| `s_noise`      | FLOAT       | Determines the level of noise to be applied during the sampling process, affecting the diversity of the generated samples.|
+| `r`            | FLOAT       | Controls the ratio of noise reduction in the sampling process, impacting the clarity and quality of the generated samples.|
+| `noise_device` | COMBO[STRING]| Selects the execution environment (CPU or GPU) for the sampler, optimizing performance based on available hardware.|
+
+## Outputs
+
+| Parameter    | Data Type | Description |
+|----------------|-------------|-------------|
+| `sampler`    | SAMPLER     | The generated sampler configured with the specified parameters, ready for use in sampling operations. |
diff --git a/built-in-nodes/SamplerER_SDE.mdx b/built-in-nodes/SamplerER_SDE.mdx
new file mode 100644
index 000000000..29e31e531
--- /dev/null
+++ b/built-in-nodes/SamplerER_SDE.mdx
@@ -0,0 +1,30 @@
+---
+title: "SamplerER_SDE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerER_SDE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerER_SDE"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerER_SDE/en.md)
+
+The SamplerER_SDE node provides specialized sampling methods for diffusion models, offering different solver types including ER-SDE, Reverse-time SDE, and ODE approaches. It allows control over the stochastic behavior and computational stages of the sampling process. The node automatically adjusts parameters based on the selected solver type to ensure proper functionality.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `solver_type` | COMBO | Yes | "ER-SDE"<br />"Reverse-time SDE"<br />"ODE" | The type of solver to use for sampling. Determines the mathematical approach for the diffusion process. |
+| `max_stage` | INT | Yes | 1-3 | The maximum number of stages for the sampling process (default: 3). Controls the computational complexity and quality. |
+| `eta` | FLOAT | Yes | 0.0-100.0 | Stochastic strength of reverse-time SDE (default: 1.0). When eta=0, it reduces to deterministic ODE. This setting doesn't apply to ER-SDE solver type. |
+| `s_noise` | FLOAT | Yes | 0.0-100.0 | Noise scaling factor for the sampling process (default: 1.0). Controls the amount of noise applied during sampling. |
+
+**Parameter Constraints:**
+
+- When `solver_type` is set to "ODE" or when using "Reverse-time SDE" with `eta`=0, both `eta` and `s_noise` are automatically set to 0 regardless of user input values.
+- The `eta` parameter only affects "Reverse-time SDE" solver type and has no effect on "ER-SDE" solver type.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | A configured sampler object that can be used in the sampling pipeline with the specified solver settings. |
diff --git a/built-in-nodes/SamplerEulerAncestral.mdx b/built-in-nodes/SamplerEulerAncestral.mdx
new file mode 100644
index 000000000..892c5eb15
--- /dev/null
+++ b/built-in-nodes/SamplerEulerAncestral.mdx
@@ -0,0 +1,23 @@
+---
+title: "SamplerEulerAncestral - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerEulerAncestral node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerEulerAncestral"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerEulerAncestral/en.md)
+
+The SamplerEulerAncestral node creates an Euler Ancestral sampler for generating images. This sampler uses a specific mathematical approach that combines Euler integration with ancestral sampling techniques to produce image variations. The node allows you to configure the sampling behavior by adjusting parameters that control the randomness and step size during the generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `eta` | FLOAT | Yes | 0.0 - 100.0 | Controls the step size and stochasticity of the sampling process (default: 1.0) |
+| `s_noise` | FLOAT | Yes | 0.0 - 100.0 | Controls the amount of noise added during sampling (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | Returns a configured Euler Ancestral sampler that can be used in the sampling pipeline |
diff --git a/built-in-nodes/SamplerEulerAncestralCFGPP.mdx b/built-in-nodes/SamplerEulerAncestralCFGPP.mdx
new file mode 100644
index 000000000..9f868d1d1
--- /dev/null
+++ b/built-in-nodes/SamplerEulerAncestralCFGPP.mdx
@@ -0,0 +1,23 @@
+---
+title: "SamplerEulerAncestralCFGPP - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerEulerAncestralCFGPP node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerEulerAncestralCFGPP"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerEulerAncestralCFGPP/en.md)
+
+The SamplerEulerAncestralCFGPP node creates a specialized sampler for generating images using the Euler Ancestral method with classifier-free guidance. This sampler combines ancestral sampling techniques with guidance conditioning to produce diverse image variations while maintaining coherence. It allows fine-tuning of the sampling process through parameters that control noise and step size adjustments.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `eta` | FLOAT | Yes | 0.0 - 1.0 | Controls the step size during sampling, with higher values resulting in more aggressive updates (default: 1.0) |
+| `s_noise` | FLOAT | Yes | 0.0 - 10.0 | Adjusts the amount of noise added during the sampling process (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | Returns a configured sampler object that can be used in the image generation pipeline |
diff --git a/built-in-nodes/SamplerEulerCFGpp.mdx b/built-in-nodes/SamplerEulerCFGpp.mdx
new file mode 100644
index 000000000..9231eaf0d
--- /dev/null
+++ b/built-in-nodes/SamplerEulerCFGpp.mdx
@@ -0,0 +1,22 @@
+---
+title: "SamplerEulerCFGpp - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerEulerCFGpp node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerEulerCFGpp"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerEulerCFGpp/en.md)
+
+The SamplerEulerCFGpp node provides an Euler CFG++ sampling method for generating outputs. This node offers two different implementation versions of the Euler CFG++ sampler that can be selected based on user preference.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `version` | STRING | Yes | `"regular"`<br />`"alternative"` | The implementation version of the Euler CFG++ sampler to use |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | Returns a configured Euler CFG++ sampler instance |
diff --git a/built-in-nodes/SamplerLCMUpscale.mdx b/built-in-nodes/SamplerLCMUpscale.mdx
new file mode 100644
index 000000000..84ab30a36
--- /dev/null
+++ b/built-in-nodes/SamplerLCMUpscale.mdx
@@ -0,0 +1,24 @@
+---
+title: "SamplerLCMUpscale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerLCMUpscale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerLCMUpscale"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerLCMUpscale/en.md)
+
+The SamplerLCMUpscale node provides a specialized sampling method that combines Latent Consistency Model (LCM) sampling with image upscaling capabilities. It allows you to upscale images during the sampling process using various interpolation methods, making it useful for generating higher resolution outputs while maintaining image quality.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `scale_ratio` | FLOAT | No | 0.1 - 20.0 | The scaling factor to apply during upscaling (default: 1.0) |
+| `scale_steps` | INT | No | -1 - 1000 | The number of steps to use for upscaling process. Use -1 for automatic calculation (default: -1) |
+| `upscale_method` | COMBO | Yes | "bislerp"<br />"nearest-exact"<br />"bilinear"<br />"area"<br />"bicubic" | The interpolation method used for upscaling the image |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | Returns a configured sampler object that can be used in the sampling pipeline |
diff --git a/built-in-nodes/SamplerLMS.mdx b/built-in-nodes/SamplerLMS.mdx
new file mode 100644
index 000000000..afc6b725b
--- /dev/null
+++ b/built-in-nodes/SamplerLMS.mdx
@@ -0,0 +1,22 @@
+---
+title: "SamplerLMS - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerLMS node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerLMS"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerLMS/en.md)
+
+The SamplerLMS node creates a Least Mean Squares (LMS) sampler for use in diffusion models. It generates a sampler object that can be used in the sampling process, allowing you to control the order of the LMS algorithm for numerical stability and accuracy.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `order` | INT | Yes | 1 to 100 | The order parameter for the LMS sampler algorithm, which controls the numerical method's accuracy and stability (default: 4) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | A configured LMS sampler object that can be used in the sampling pipeline |
diff --git a/built-in-nodes/SamplerSASolver.mdx b/built-in-nodes/SamplerSASolver.mdx
new file mode 100644
index 000000000..4020a31c8
--- /dev/null
+++ b/built-in-nodes/SamplerSASolver.mdx
@@ -0,0 +1,30 @@
+---
+title: "SamplerSASolver - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerSASolver node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerSASolver"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerSASolver/en.md)
+
+The SamplerSASolver node implements a custom sampling algorithm for diffusion models. It uses a predictor-corrector approach with configurable order settings and stochastic differential equation (SDE) parameters to generate samples from the input model.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to use for sampling |
+| `eta` | FLOAT | Yes | 0.0 - 10.0 | Controls the step size scaling factor (default: 1.0) |
+| `sde_start_percent` | FLOAT | Yes | 0.0 - 1.0 | The starting percentage for SDE sampling (default: 0.2) |
+| `sde_end_percent` | FLOAT | Yes | 0.0 - 1.0 | The ending percentage for SDE sampling (default: 0.8) |
+| `s_noise` | FLOAT | Yes | 0.0 - 100.0 | Controls the amount of noise added during sampling (default: 1.0) |
+| `predictor_order` | INT | Yes | 1 - 6 | The order of the predictor component in the solver (default: 3) |
+| `corrector_order` | INT | Yes | 0 - 6 | The order of the corrector component in the solver (default: 4) |
+| `use_pece` | BOOLEAN | Yes | - | Enables or disables the PECE (Predict-Evaluate-Correct-Evaluate) method |
+| `simple_order_2` | BOOLEAN | Yes | - | Enables or disables simplified second-order calculations |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | A configured sampler object that can be used with diffusion models |
diff --git a/built-in-nodes/SamplerSEEDS2.mdx b/built-in-nodes/SamplerSEEDS2.mdx
new file mode 100644
index 000000000..b1c424058
--- /dev/null
+++ b/built-in-nodes/SamplerSEEDS2.mdx
@@ -0,0 +1,25 @@
+---
+title: "SamplerSEEDS2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerSEEDS2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerSEEDS2"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerSEEDS2/en.md)
+
+This node provides a configurable sampler for generating images. It implements the SEEDS-2 algorithm, which is a stochastic differential equation (SDE) solver. By adjusting its parameters, you can configure it to behave like several specific samplers, including `seeds_2`, `exp_heun_2_x0`, and `exp_heun_2_x0_sde`.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `solver_type` | COMBO | Yes | `"phi_1"`<br />`"phi_2"` | Selects the underlying solver algorithm for the sampler. |
+| `eta` | FLOAT | No | 0.0 - 100.0 | Stochastic strength (default: 1.0). |
+| `s_noise` | FLOAT | No | 0.0 - 100.0 | SDE noise multiplier (default: 1.0). |
+| `r` | FLOAT | No | 0.01 - 1.0 | Relative step size for the intermediate stage (c2 node) (default: 0.5). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | A configured sampler object that can be passed to other sampling nodes. |
diff --git a/built-in-nodes/SamplingPercentToSigma.mdx b/built-in-nodes/SamplingPercentToSigma.mdx
new file mode 100644
index 000000000..e463dc539
--- /dev/null
+++ b/built-in-nodes/SamplingPercentToSigma.mdx
@@ -0,0 +1,24 @@
+---
+title: "SamplingPercentToSigma - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplingPercentToSigma node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplingPercentToSigma"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplingPercentToSigma/en.md)
+
+The SamplingPercentToSigma node converts a sampling percentage value to a corresponding sigma value using the model's sampling parameters. It takes a percentage value between 0.0 and 1.0 and maps it to the appropriate sigma value in the model's noise schedule, with options to return either the calculated sigma or the actual maximum/minimum sigma values at the boundaries.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model containing the sampling parameters used for conversion |
+| `sampling_percent` | FLOAT | Yes | 0.0 to 1.0 | The sampling percentage to convert to sigma (default: 0.0) |
+| `return_actual_sigma` | BOOLEAN | Yes | - | Return the actual sigma value instead of the value used for interval checks. This only affects results at 0.0 and 1.0. (default: False) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigma_value` | FLOAT | The converted sigma value corresponding to the input sampling percentage |
diff --git a/built-in-nodes/SaveAnimatedPNG.mdx b/built-in-nodes/SaveAnimatedPNG.mdx
new file mode 100644
index 000000000..6f1bf58cc
--- /dev/null
+++ b/built-in-nodes/SaveAnimatedPNG.mdx
@@ -0,0 +1,24 @@
+---
+title: "SaveAnimatedPNG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAnimatedPNG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAnimatedPNG"
+icon: "circle"
+mode: wide
+---
+
+The SaveAnimatedPNG node is designed for creating and saving animated PNG images from a sequence of frames. It handles the assembly of individual image frames into a cohesive animation, allowing for customization of frame duration, looping, and metadata inclusion.
+
+## Inputs
+
+| Field             | Data Type | Description                                                                         |
+|-------------------|-------------|-------------------------------------------------------------------------------------|
+| `images`          | `IMAGE`     | A list of images to be processed and saved as an animated PNG. Each image in the list represents a frame in the animation. |
+| `filename_prefix` | `STRING`    | Specifies the base name for the output file, which will be used as a prefix for the generated animated PNG files. |
+| `fps`             | `FLOAT`     | The frames per second rate for the animation, controlling how quickly the frames are displayed. |
+| `compress_level`  | `INT`       | The level of compression applied to the animated PNG files, affecting file size and image clarity. |
+
+## Outputs
+
+| Field | Data Type | Description                                                                       |
+|-------|-------------|-----------------------------------------------------------------------------------|
+| `ui`  | N/A         | Provides a UI component displaying the generated animated PNG images and indicating whether the animation is single-frame or multi-frame. |
diff --git a/built-in-nodes/SaveAnimatedWEBP.mdx b/built-in-nodes/SaveAnimatedWEBP.mdx
new file mode 100644
index 000000000..b10719165
--- /dev/null
+++ b/built-in-nodes/SaveAnimatedWEBP.mdx
@@ -0,0 +1,26 @@
+---
+title: "SaveAnimatedWEBP - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAnimatedWEBP node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAnimatedWEBP"
+icon: "circle"
+mode: wide
+---
+
+This node is designed for saving a sequence of images as an animated WEBP file. It handles the aggregation of individual frames into a cohesive animation, applying specified metadata, and optimizing the output based on quality and compression settings.
+
+## Inputs
+
+| Field             | Data Type | Description                                                                         |
+|-------------------|-------------|-------------------------------------------------------------------------------------|
+| `images`          | `IMAGE`     | A list of images to be saved as frames in the animated WEBP. This parameter is essential for defining the visual content of the animation. |
+| `filename_prefix` | `STRING`    | Specifies the base name for the output file, which will be appended with a counter and the '.webp' extension. This parameter is crucial for identifying and organizing the saved files. |
+| `fps`             | `FLOAT`     | The frames per second rate for the animation, influencing the playback speed. |
+| `lossless`        | `BOOLEAN`   | A boolean indicating whether to use lossless compression, affecting the file size and quality of the animation. |
+| `quality`         | `INT`       | A value between 0 and 100 that sets the compression quality level, with higher values resulting in better image quality but larger file sizes. |
+| `method`          | COMBO[STRING] | Specifies the compression method to use, which can impact the encoding speed and file size. |
+
+## Outputs
+
+| Field | Data Type | Description                                                                       |
+|-------|-------------|-----------------------------------------------------------------------------------|
+| `ui`  | N/A         | Provides a UI component displaying the saved animated WEBP images along with their metadata, and indicates whether the animation is enabled. |
diff --git a/built-in-nodes/SaveAudio.mdx b/built-in-nodes/SaveAudio.mdx
new file mode 100644
index 000000000..989f82add
--- /dev/null
+++ b/built-in-nodes/SaveAudio.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudio/en.md)
+
+The SaveAudio node saves audio data to a file in FLAC format. It takes audio input and writes it to the specified output directory with the given filename prefix. The node automatically handles file naming and ensures the audio is properly saved for later use.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The audio data to be saved |
+| `filename_prefix` | STRING | No | - | The prefix for the output filename (default: "audio/ComfyUI") |
+
+*Note: The `prompt` and `extra_pnginfo` parameters are hidden and automatically handled by the system.*
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| *None* | - | This node does not return any output data but saves the audio file to the output directory |
diff --git a/built-in-nodes/SaveAudioMP3.mdx b/built-in-nodes/SaveAudioMP3.mdx
new file mode 100644
index 000000000..271880ba8
--- /dev/null
+++ b/built-in-nodes/SaveAudioMP3.mdx
@@ -0,0 +1,26 @@
+---
+title: "SaveAudioMP3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAudioMP3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAudioMP3"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioMP3/en.md)
+
+The SaveAudioMP3 node saves audio data as an MP3 file. It takes audio input and exports it to the specified output directory with customizable filename and quality settings. The node automatically handles file naming and format conversion to create a playable MP3 file.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The audio data to be saved as an MP3 file |
+| `filename_prefix` | STRING | No | - | The prefix for the output filename (default: "audio/ComfyUI") |
+| `quality` | STRING | No | "V0"<br />"128k"<br />"320k" | The audio quality setting for the MP3 file (default: "V0") |
+| `prompt` | PROMPT | No | - | Internal prompt data (automatically provided by the system) |
+| `extra_pnginfo` | EXTRA_PNGINFO | No | - | Additional PNG information (automatically provided by the system) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| *None* | - | This node does not return any output data, but saves the audio file to the output directory |
diff --git a/built-in-nodes/SaveAudioOpus.mdx b/built-in-nodes/SaveAudioOpus.mdx
new file mode 100644
index 000000000..68fcdecb9
--- /dev/null
+++ b/built-in-nodes/SaveAudioOpus.mdx
@@ -0,0 +1,24 @@
+---
+title: "SaveAudioOpus - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAudioOpus node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAudioOpus"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioOpus/en.md)
+
+The SaveAudioOpus node saves audio data to an Opus format file. It takes audio input and exports it as a compressed Opus file with configurable quality settings. The node automatically handles file naming and saves the output to the designated output directory.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The audio data to be saved as an Opus file |
+| `filename_prefix` | STRING | No | - | The prefix for the output filename (default: "audio/ComfyUI") |
+| `quality` | COMBO | No | "64k"<br />"96k"<br />"128k"<br />"192k"<br />"320k" | The audio quality setting for the Opus file (default: "128k") |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| - | - | This node does not return any output values. It saves the audio file to disk as its primary function. |
diff --git a/built-in-nodes/SaveGLB.mdx b/built-in-nodes/SaveGLB.mdx
new file mode 100644
index 000000000..155ff3a4a
--- /dev/null
+++ b/built-in-nodes/SaveGLB.mdx
@@ -0,0 +1,23 @@
+---
+title: "SaveGLB - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveGLB node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveGLB"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveGLB/en.md)
+
+The SaveGLB node saves 3D mesh data as GLB files, which is a common format for 3D models. It takes mesh data as input and exports it to the output directory with the specified filename prefix. The node can save multiple meshes if the input contains multiple mesh objects, and it automatically adds metadata to the files when metadata is enabled.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `mesh` | MESH | Yes | - | The 3D mesh data to be saved as a GLB file |
+| `filename_prefix` | STRING | No | - | The prefix for the output filename (default: "mesh/ComfyUI") |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `ui` | UI | Displays the saved GLB files in the user interface with filename and subfolder information |
diff --git a/built-in-nodes/SaveImage.mdx b/built-in-nodes/SaveImage.mdx
new file mode 100644
index 000000000..37dd5c26e
--- /dev/null
+++ b/built-in-nodes/SaveImage.mdx
@@ -0,0 +1,23 @@
+---
+title: "SaveImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImage/en.md)
+
+The SaveImage node saves the images it receives to your `ComfyUI/output` directory. It saves each image as a PNG file and can embed workflow metadata, such as the prompt, into the saved file for future reference.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | The images to save. |
+| `filename_prefix` | STRING | Yes | - | The prefix for the file to save. This may include formatting information such as `%date:yyyy-MM-dd%` or `%Empty Latent Image.width%` to include values from nodes (default: "ComfyUI"). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `ui` | UI_RESULT | This node outputs a UI result containing a list of the saved images with their filenames and subfolders. It does not output data for connecting to other nodes. |
diff --git a/built-in-nodes/SaveImageDataSetToFolder.mdx b/built-in-nodes/SaveImageDataSetToFolder.mdx
new file mode 100644
index 000000000..b4908f475
--- /dev/null
+++ b/built-in-nodes/SaveImageDataSetToFolder.mdx
@@ -0,0 +1,24 @@
+---
+title: "SaveImageDataSetToFolder - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveImageDataSetToFolder node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveImageDataSetToFolder"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageDataSetToFolder/en.md)
+
+This node saves a list of images to a specified folder within ComfyUI's output directory. It takes multiple images as input and writes them to disk with a customizable filename prefix.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | N/A | List of images to save. |
+| `folder_name` | STRING | No | N/A | Name of the folder to save images to (inside output directory). The default value is "dataset". |
+| `filename_prefix` | STRING | No | N/A | Prefix for saved image filenames. The default value is "image". |
+
+**Note:** The `images` input is a list, meaning it can receive and process multiple images at once. The `folder_name` and `filename_prefix` parameters are scalar values; if a list is connected, only the first value from that list will be used.
+
+## Outputs
+
+This node does not have any outputs. It is an output node that performs a save operation to the filesystem.
diff --git a/built-in-nodes/SaveImageTextDataSetToFolder.mdx b/built-in-nodes/SaveImageTextDataSetToFolder.mdx
new file mode 100644
index 000000000..bf0c2da03
--- /dev/null
+++ b/built-in-nodes/SaveImageTextDataSetToFolder.mdx
@@ -0,0 +1,27 @@
+---
+title: "SaveImageTextDataSetToFolder - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveImageTextDataSetToFolder node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveImageTextDataSetToFolder"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageTextDataSetToFolder/en.md)
+
+The Save Image and Text Dataset to Folder node saves a list of images and their corresponding text captions to a specified folder within ComfyUI's output directory. For each image saved as a PNG file, a matching text file with the same base name is created to store its caption. This is useful for creating organized datasets of generated images and their descriptions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | List of images to save. |
+| `texts` | STRING | Yes | - | List of text captions to save. |
+| `folder_name` | STRING | No | - | Name of the folder to save images to (inside output directory). (default: "dataset") |
+| `filename_prefix` | STRING | No | - | Prefix for saved image filenames. (default: "image") |
+
+**Note:** The `images` and `texts` inputs are lists. The node expects the number of text captions to match the number of images provided. Each caption will be saved in a `.txt` file corresponding to its paired image.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| - | - | This node does not have any outputs. It saves files directly to the filesystem. |
diff --git a/built-in-nodes/SaveLatent.mdx b/built-in-nodes/SaveLatent.mdx
new file mode 100644
index 000000000..8cbd0da9f
--- /dev/null
+++ b/built-in-nodes/SaveLatent.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLatent/en.md)
+
+The SaveLatent node saves latent tensors to disk as files for later use or sharing. It takes latent samples and saves them to the output directory with optional metadata including prompt information. The node automatically handles file naming and organization while preserving the latent data structure.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | - | The latent samples to be saved to disk |
+| `filename_prefix` | STRING | No | - | The prefix for the output filename (default: "latents/ComfyUI") |
+| `prompt` | PROMPT | No | - | Prompt information to include in metadata (hidden parameter) |
+| `extra_pnginfo` | EXTRA_PNGINFO | No | - | Additional PNG information to include in metadata (hidden parameter) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `ui` | UI | Provides file location information for the saved latent in the ComfyUI interface |
diff --git a/built-in-nodes/SaveLoRA.mdx b/built-in-nodes/SaveLoRA.mdx
new file mode 100644
index 000000000..f35e83ce4
--- /dev/null
+++ b/built-in-nodes/SaveLoRA.mdx
@@ -0,0 +1,26 @@
+---
+title: "SaveLoRA - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveLoRA node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveLoRA"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLoRA/en.md)
+
+The SaveLoRA node saves a LoRA (Low-Rank Adaptation) model to a file. It takes a LoRA model as input and writes it to a `.safetensors` file in the output directory. You can specify a filename prefix and an optional step count to be included in the final filename.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `lora` | MODEL | Yes | N/A | The LoRA model to save. Do not use the model with LoRA layers. |
+| `prefix` | STRING | Yes | N/A | The prefix to use for the saved LoRA file (default: "loras/ComfyUI_trained_lora"). |
+| `steps` | INT | No | N/A | Optional: The number of steps the LoRA has been trained for, used to name the saved file. |
+
+**Note:** The `lora` input must be a pure LoRA model. Do not provide a base model that has LoRA layers applied to it.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| *None* | N/A | This node does not output any data to the workflow. It is an output node that saves a file to disk. |
diff --git a/built-in-nodes/SaveLoRANode.mdx b/built-in-nodes/SaveLoRANode.mdx
new file mode 100644
index 000000000..30635ad46
--- /dev/null
+++ b/built-in-nodes/SaveLoRANode.mdx
@@ -0,0 +1,24 @@
+---
+title: "SaveLoRANode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveLoRANode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveLoRANode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLoRANode/en.md)
+
+The SaveLoRA node saves LoRA (Low-Rank Adaptation) models to your output directory. It takes a LoRA model as input and creates a safetensors file with an automatically generated filename. You can customize the filename prefix and optionally include the training step count in the filename for better organization.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `lora` | LORA_MODEL | Yes | - | The LoRA model to save. Do not use the model with LoRA layers. |
+| `prefix` | STRING | Yes | - | The prefix to use for the saved LoRA file (default: "loras/ComfyUI_trained_lora"). |
+| `steps` | INT | No | - | Optional: The number of steps the LoRA has been trained for, used to name the saved file. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| *None* | - | This node does not return any outputs but saves the LoRA model to the output directory. |
diff --git a/built-in-nodes/SaveSVGNode.mdx b/built-in-nodes/SaveSVGNode.mdx
new file mode 100644
index 000000000..077f6479f
--- /dev/null
+++ b/built-in-nodes/SaveSVGNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveSVGNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveSVGNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveSVGNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveSVGNode/en.md)
+
+Save SVG files on disk. This node takes SVG data as input and saves it to your output directory with optional metadata embedding. The node automatically handles file naming with counter suffixes and can embed workflow prompt information directly into the SVG file.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `svg` | SVG | Yes | - | The SVG data to be saved to disk |
+| `filename_prefix` | STRING | Yes | - | The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes. (default: "svg/ComfyUI") |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `ui` | DICT | Returns file information including filename, subfolder, and type for display in the ComfyUI interface |
+
+**Note:** This node automatically embeds workflow metadata (prompt and extra PNG information) into the SVG file when available. The metadata is inserted as a CDATA section within the SVG's metadata element.
diff --git a/built-in-nodes/SaveTrainingDataset.mdx b/built-in-nodes/SaveTrainingDataset.mdx
new file mode 100644
index 000000000..0c7984444
--- /dev/null
+++ b/built-in-nodes/SaveTrainingDataset.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveTrainingDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveTrainingDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveTrainingDataset"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveTrainingDataset/en.md)
+
+This node saves a prepared training dataset to your computer's hard drive. It takes encoded data, which includes image latents and their corresponding text conditioning, and organizes them into multiple smaller files called shards for easier management. The node automatically creates a folder in your output directory and saves both the data files and a metadata file describing the dataset.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `latents` | LATENT | Yes | N/A | List of latent dicts from MakeTrainingDataset. |
+| `conditioning` | CONDITIONING | Yes | N/A | List of conditioning lists from MakeTrainingDataset. |
+| `folder_name` | STRING | No | N/A | Name of folder to save dataset (inside output directory). (default: "training_dataset") |
+| `shard_size` | INT | No | 1 to 100000 | Number of samples per shard file. (default: 1000) |
+
+**Note:** The number of items in the `latents` list must exactly match the number of items in the `conditioning` list. The node will raise an error if these counts do not match.
+
+## Outputs
+
+This node does not produce any output data. Its function is to save files to your disk.
diff --git a/built-in-nodes/SaveVideo.mdx b/built-in-nodes/SaveVideo.mdx
new file mode 100644
index 000000000..5613b5251
--- /dev/null
+++ b/built-in-nodes/SaveVideo.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveVideo/en.md)
+
+The SaveVideo node saves input video content to your ComfyUI output directory. It allows you to specify the filename prefix, video format, and codec for the saved file. The node automatically handles file naming with counter increments and can include workflow metadata in the saved video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | - | The video to save. |
+| `filename_prefix` | STRING | No | - | The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes (default: "video/ComfyUI"). |
+| `format` | COMBO | No | Multiple options available | The format to save the video as (default: "auto"). |
+| `codec` | COMBO | No | Multiple options available | The codec to use for the video (default: "auto"). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| *No outputs* | - | This node does not return any output data. |
diff --git a/built-in-nodes/SaveWEBM.mdx b/built-in-nodes/SaveWEBM.mdx
new file mode 100644
index 000000000..eaf130dbe
--- /dev/null
+++ b/built-in-nodes/SaveWEBM.mdx
@@ -0,0 +1,26 @@
+---
+title: "SaveWEBM - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveWEBM node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveWEBM"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveWEBM/en.md)
+
+The SaveWEBM node saves a sequence of images as a WEBM video file. It takes multiple input images and encodes them into a video using either VP9 or AV1 codec with configurable quality settings and frame rate. The resulting video file is saved to the output directory with metadata including prompt information.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | Sequence of input images to encode as video frames |
+| `filename_prefix` | STRING | No | - | Prefix for the output filename (default: "ComfyUI") |
+| `codec` | COMBO | Yes | "vp9"<br />"av1" | Video codec to use for encoding |
+| `fps` | FLOAT | No | 0.01-1000.0 | Frame rate for the output video (default: 24.0) |
+| `crf` | FLOAT | No | 0-63.0 | Quality setting where higher crf means lower quality with smaller file size, lower crf means higher quality with larger file size (default: 32.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `ui` | PREVIEW | Video preview showing the saved WEBM file |
diff --git a/built-in-nodes/ScaleROPE.mdx b/built-in-nodes/ScaleROPE.mdx
new file mode 100644
index 000000000..a961988c7
--- /dev/null
+++ b/built-in-nodes/ScaleROPE.mdx
@@ -0,0 +1,28 @@
+---
+title: "ScaleROPE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ScaleROPE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ScaleROPE"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ScaleROPE/en.md)
+
+The ScaleROPE node allows you to modify the Rotary Position Embedding (ROPE) of a model by applying separate scaling and shifting factors to its X, Y, and T (time) components. This is an advanced, experimental node used to adjust the model's positional encoding behavior.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model whose ROPE parameters will be modified. |
+| `scale_x` | FLOAT | No | 0.0 - 100.0 | The scaling factor to apply to the X component of the ROPE (default: 1.0). |
+| `shift_x` | FLOAT | No | -256.0 - 256.0 | The shift value to apply to the X component of the ROPE (default: 0.0). |
+| `scale_y` | FLOAT | No | 0.0 - 100.0 | The scaling factor to apply to the Y component of the ROPE (default: 1.0). |
+| `shift_y` | FLOAT | No | -256.0 - 256.0 | The shift value to apply to the Y component of the ROPE (default: 0.0). |
+| `scale_t` | FLOAT | No | 0.0 - 100.0 | The scaling factor to apply to the T (time) component of the ROPE (default: 1.0). |
+| `shift_t` | FLOAT | No | -256.0 - 256.0 | The shift value to apply to the T (time) component of the ROPE (default: 0.0). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The model with the new ROPE scaling and shifting parameters applied. |
diff --git a/built-in-nodes/Sd4xupscaleConditioning.mdx b/built-in-nodes/Sd4xupscaleConditioning.mdx
new file mode 100644
index 000000000..b7a7a61f0
--- /dev/null
+++ b/built-in-nodes/Sd4xupscaleConditioning.mdx
@@ -0,0 +1,27 @@
+---
+title: "Sd4xupscaleConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Sd4xupscaleConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Sd4xupscaleConditioning"
+icon: "circle"
+mode: wide
+---
+
+This node specializes in enhancing the resolution of images through a 4x upscale process, incorporating conditioning elements to refine the output. It leverages diffusion techniques to upscale images while allowing for the adjustment of scale ratio and noise augmentation to fine-tune the enhancement process.
+
+## Inputs
+
+| Parameter            | Comfy dtype        | Description |
+|----------------------|--------------------|-------------|
+| `images`             | `IMAGE`            | The input images to be upscaled. This parameter is crucial as it directly influences the quality and resolution of the output images. |
+| `positive`           | `CONDITIONING`     | Positive conditioning elements that guide the upscale process towards desired attributes or features in the output images. |
+| `negative`           | `CONDITIONING`     | Negative conditioning elements that the upscale process should avoid, helping to steer the output away from undesired attributes or features. |
+| `scale_ratio`        | `FLOAT`            | Determines the factor by which the image resolution is increased. A higher scale ratio results in a larger output image, allowing for greater detail and clarity. |
+| `noise_augmentation` | `FLOAT`            | Controls the level of noise augmentation applied during the upscale process. This can be used to introduce variability and improve the robustness of the output images. |
+
+## Outputs
+
+| Parameter     | Data Type | Description |
+|---------------|--------------|-------------|
+| `positive`    | `CONDITIONING` | The refined positive conditioning elements resulting from the upscale process. |
+| `negative`    | `CONDITIONING` | The refined negative conditioning elements resulting from the upscale process. |
+| `latent`      | `LATENT`     | A latent representation generated during the upscale process, which can be utilized in further processing or model training. |
diff --git a/built-in-nodes/SelfAttentionGuidance.mdx b/built-in-nodes/SelfAttentionGuidance.mdx
new file mode 100644
index 000000000..f71a96bbb
--- /dev/null
+++ b/built-in-nodes/SelfAttentionGuidance.mdx
@@ -0,0 +1,26 @@
+---
+title: "SelfAttentionGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SelfAttentionGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SelfAttentionGuidance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SelfAttentionGuidance/en.md)
+
+The Self-Attention Guidance node applies guidance to diffusion models by modifying the attention mechanism during the sampling process. It captures attention scores from unconditional denoising steps and uses them to create blurred guidance maps that influence the final output. This technique helps guide the generation process by leveraging the model's own attention patterns.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to apply self-attention guidance to |
+| `scale` | FLOAT | No | -2.0 to 5.0 | The strength of the self-attention guidance effect (default: 0.5) |
+| `blur_sigma` | FLOAT | No | 0.0 to 10.0 | The amount of blur applied to create the guidance map (default: 2.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with self-attention guidance applied |
+
+**Note:** This node is currently experimental and has limitations with chunked batches. It can only save attention scores from one UNet call and may not work properly with larger batch sizes.
diff --git a/built-in-nodes/SetClipHooks.mdx b/built-in-nodes/SetClipHooks.mdx
new file mode 100644
index 000000000..23bb5dd08
--- /dev/null
+++ b/built-in-nodes/SetClipHooks.mdx
@@ -0,0 +1,25 @@
+---
+title: "SetClipHooks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetClipHooks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetClipHooks"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetClipHooks/en.md)
+
+The SetClipHooks node allows you to apply custom hooks to a CLIP model, enabling advanced modifications to its behavior. It can apply hooks to conditioning outputs and optionally enable clip scheduling functionality. This node creates a cloned copy of the input CLIP model with the specified hook configurations applied.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | - | The CLIP model to apply hooks to |
+| `apply_to_conds` | BOOLEAN | Yes | - | Whether to apply hooks to conditioning outputs (default: True) |
+| `schedule_clip` | BOOLEAN | Yes | - | Whether to enable clip scheduling (default: False) |
+| `hooks` | HOOKS | No | - | Optional hook group to apply to the CLIP model |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `clip` | CLIP | A cloned CLIP model with the specified hooks applied |
diff --git a/built-in-nodes/SetFirstSigma.mdx b/built-in-nodes/SetFirstSigma.mdx
new file mode 100644
index 000000000..1a042660b
--- /dev/null
+++ b/built-in-nodes/SetFirstSigma.mdx
@@ -0,0 +1,23 @@
+---
+title: "SetFirstSigma - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetFirstSigma node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetFirstSigma"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetFirstSigma/en.md)
+
+The SetFirstSigma node modifies a sequence of sigma values by replacing the first sigma value in the sequence with a custom value. It takes an existing sigma sequence and a new sigma value as inputs, then returns a new sigma sequence where only the first element has been changed while keeping all other sigma values unchanged.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `sigmas` | SIGMAS | Yes | - | The input sequence of sigma values to be modified |
+| `sigma` | FLOAT | Yes | 0.0 to 20000.0 | The new sigma value to set as the first element in the sequence (default: 136.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | The modified sigma sequence with the first element replaced by the custom sigma value |
diff --git a/built-in-nodes/SetHookKeyframes.mdx b/built-in-nodes/SetHookKeyframes.mdx
new file mode 100644
index 000000000..b14826682
--- /dev/null
+++ b/built-in-nodes/SetHookKeyframes.mdx
@@ -0,0 +1,23 @@
+---
+title: "SetHookKeyframes - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetHookKeyframes node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetHookKeyframes"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetHookKeyframes/en.md)
+
+The Set Hook Keyframes node allows you to apply keyframe scheduling to existing hook groups. It takes a hook group and optionally applies keyframe timing information to control when different hooks are executed during the generation process. When keyframes are provided, the node clones the hook group and sets the keyframe timing on all hooks within the group.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `hooks` | HOOKS | Yes | - | The hook group to which keyframe scheduling will be applied |
+| `hook_kf` | HOOK_KEYFRAMES | No | - | Optional keyframe group containing timing information for hook execution |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `hooks` | HOOKS | The modified hook group with keyframe scheduling applied (cloned if keyframes were provided) |
diff --git a/built-in-nodes/SetLatentNoiseMask.mdx b/built-in-nodes/SetLatentNoiseMask.mdx
new file mode 100644
index 000000000..989d883e6
--- /dev/null
+++ b/built-in-nodes/SetLatentNoiseMask.mdx
@@ -0,0 +1,22 @@
+---
+title: "SetLatentNoiseMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetLatentNoiseMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetLatentNoiseMask"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to apply a noise mask to a set of latent samples. It modifies the input samples by integrating a specified mask, thereby altering their noise characteristics.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `samples` | `LATENT`    | The latent samples to which the noise mask will be applied. This parameter is crucial for determining the base content that will be modified. |
+| `mask`    | `MASK`      | The mask to be applied to the latent samples. It defines the areas and intensity of noise alteration within the samples. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The modified latent samples with the applied noise mask. |
diff --git a/built-in-nodes/SetModelHooksOnCond.mdx b/built-in-nodes/SetModelHooksOnCond.mdx
new file mode 100644
index 000000000..417a0fdb4
--- /dev/null
+++ b/built-in-nodes/SetModelHooksOnCond.mdx
@@ -0,0 +1,23 @@
+---
+title: "SetModelHooksOnCond - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetModelHooksOnCond node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetModelHooksOnCond"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetModelHooksOnCond/en.md)
+
+This node attaches custom hooks to conditioning data, allowing you to intercept and modify the conditioning process during model execution. It takes a set of hooks and applies them to the provided conditioning data, enabling advanced customization of the text-to-image generation workflow. The modified conditioning with attached hooks is then returned for use in subsequent processing steps.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | Yes | - | The conditioning data to which hooks will be attached |
+| `hooks` | HOOKS | Yes | - | The hook definitions that will be applied to the conditioning data |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | The modified conditioning data with hooks attached |
diff --git a/built-in-nodes/SetUnionControlNetType.mdx b/built-in-nodes/SetUnionControlNetType.mdx
new file mode 100644
index 000000000..8d5820694
--- /dev/null
+++ b/built-in-nodes/SetUnionControlNetType.mdx
@@ -0,0 +1,23 @@
+---
+title: "SetUnionControlNetType - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetUnionControlNetType node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetUnionControlNetType"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetUnionControlNetType/en.md)
+
+The SetUnionControlNetType node allows you to specify the type of control network to use for conditioning. It takes an existing control network and sets its control type based on your selection, creating a modified copy of the control network with the specified type configuration.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `control_net` | CONTROL_NET | Yes | - | The control network to modify with a new type setting |
+| `type` | STRING | Yes | `"auto"`<br />All available UNION_CONTROLNET_TYPES keys | The control network type to apply. Use "auto" for automatic type detection or select a specific control network type from the available options |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `control_net` | CONTROL_NET | The modified control network with the specified type setting applied |
diff --git a/built-in-nodes/ShuffleDataset.mdx b/built-in-nodes/ShuffleDataset.mdx
new file mode 100644
index 000000000..416aceec3
--- /dev/null
+++ b/built-in-nodes/ShuffleDataset.mdx
@@ -0,0 +1,23 @@
+---
+title: "ShuffleDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ShuffleDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ShuffleDataset"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ShuffleDataset/en.md)
+
+The Shuffle Dataset node takes a list of images and randomly changes their order. It uses a seed value to control the randomness, ensuring the same shuffle order can be reproduced. This is useful for randomizing the sequence of images in a dataset before processing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | The list of images to be shuffled. |
+| `seed` | INT | No | 0 to 18446744073709551615 | Random seed. A value of 0 will produce a different shuffle each time. (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `images` | IMAGE | The same list of images, but in a new, randomly shuffled order. |
diff --git a/built-in-nodes/ShuffleImageTextDataset.mdx b/built-in-nodes/ShuffleImageTextDataset.mdx
new file mode 100644
index 000000000..c8bd31a6f
--- /dev/null
+++ b/built-in-nodes/ShuffleImageTextDataset.mdx
@@ -0,0 +1,27 @@
+---
+title: "ShuffleImageTextDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ShuffleImageTextDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ShuffleImageTextDataset"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ShuffleImageTextDataset/en.md)
+
+This node shuffles a list of images and a list of texts together, keeping their pairings intact. It uses a random seed to determine the shuffle order, ensuring the same input lists will be shuffled in the same way each time the seed is reused.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | List of images to shuffle. |
+| `texts` | STRING | Yes | - | List of texts to shuffle. |
+| `seed` | INT | No | 0 to 18446744073709551615 | Random seed. The shuffle order is determined by this value (default: 0). |
+
+**Note:** The `images` and `texts` inputs must be lists of the same length. The node will pair the first image with the first text, the second image with the second text, and so on, before shuffling these pairs together.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `images` | IMAGE | The shuffled list of images. |
+| `texts` | STRING | The shuffled list of texts, maintaining their original pairings with the images. |
diff --git a/built-in-nodes/SkipLayerGuidanceDiT.mdx b/built-in-nodes/SkipLayerGuidanceDiT.mdx
new file mode 100644
index 000000000..85e6df74d
--- /dev/null
+++ b/built-in-nodes/SkipLayerGuidanceDiT.mdx
@@ -0,0 +1,30 @@
+---
+title: "SkipLayerGuidanceDiT - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SkipLayerGuidanceDiT node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SkipLayerGuidanceDiT"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SkipLayerGuidanceDiT/en.md)
+
+Enhances guidance towards detailed structure by using another set of CFG negative with skipped layers. This generic version of SkipLayerGuidance can be used on every DiT model and is inspired by Perturbed Attention Guidance. The original experimental implementation was created for SD3.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply skip layer guidance to |
+| `double_layers` | STRING | Yes | - | Comma-separated layer numbers for double blocks to skip (default: "7, 8, 9") |
+| `single_layers` | STRING | Yes | - | Comma-separated layer numbers for single blocks to skip (default: "7, 8, 9") |
+| `scale` | FLOAT | Yes | 0.0 - 10.0 | Guidance scale factor (default: 3.0) |
+| `start_percent` | FLOAT | Yes | 0.0 - 1.0 | Starting percentage for guidance application (default: 0.01) |
+| `end_percent` | FLOAT | Yes | 0.0 - 1.0 | Ending percentage for guidance application (default: 0.15) |
+| `rescaling_scale` | FLOAT | Yes | 0.0 - 10.0 | Rescaling scale factor (default: 0.0) |
+
+**Note:** If both `double_layers` and `single_layers` are empty (contain no layer numbers), the node returns the original model without applying any guidance.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with skip layer guidance applied |
diff --git a/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx b/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx
new file mode 100644
index 000000000..fde36104e
--- /dev/null
+++ b/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx
@@ -0,0 +1,28 @@
+---
+title: "SkipLayerGuidanceDiTSimple - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SkipLayerGuidanceDiTSimple node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SkipLayerGuidanceDiTSimple"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SkipLayerGuidanceDiTSimple/en.md)
+
+Simple version of the SkipLayerGuidanceDiT node that only modifies the unconditional pass during the denoising process. This node applies skip layer guidance to specific transformer layers in DiT (Diffusion Transformer) models by selectively skipping certain layers during the unconditional pass based on specified timing and layer parameters.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply skip layer guidance to |
+| `double_layers` | STRING | Yes | - | Comma-separated list of double block layer indices to skip (default: "7, 8, 9") |
+| `single_layers` | STRING | Yes | - | Comma-separated list of single block layer indices to skip (default: "7, 8, 9") |
+| `start_percent` | FLOAT | Yes | 0.0 - 1.0 | The starting percentage of the denoising process when skip layer guidance begins (default: 0.0) |
+| `end_percent` | FLOAT | Yes | 0.0 - 1.0 | The ending percentage of the denoising process when skip layer guidance stops (default: 1.0) |
+
+**Note:** Skip layer guidance is only applied when both `double_layers` and `single_layers` contain valid layer indices. If both are empty, the node returns the original model unchanged.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with skip layer guidance applied to the specified layers |
diff --git a/built-in-nodes/SkipLayerGuidanceSD3.mdx b/built-in-nodes/SkipLayerGuidanceSD3.mdx
new file mode 100644
index 000000000..ba891a095
--- /dev/null
+++ b/built-in-nodes/SkipLayerGuidanceSD3.mdx
@@ -0,0 +1,26 @@
+---
+title: "SkipLayerGuidanceSD3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SkipLayerGuidanceSD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SkipLayerGuidanceSD3"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SkipLayerGuidanceSD3/en.md)
+
+The SkipLayerGuidanceSD3 node enhances guidance towards detailed structure by applying an additional set of classifier-free guidance with skipped layers. This experimental implementation is inspired by Perturbed Attention Guidance and works by selectively bypassing certain layers during the negative conditioning process to improve structural details in the generated output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply skip layer guidance to |
+| `layers` | STRING | Yes | - | Comma-separated list of layer indices to skip (default: "7, 8, 9") |
+| `scale` | FLOAT | Yes | 0.0 - 10.0 | The strength of the skip layer guidance effect (default: 3.0) |
+| `start_percent` | FLOAT | Yes | 0.0 - 1.0 | The starting point of guidance application as a percentage of total steps (default: 0.01) |
+| `end_percent` | FLOAT | Yes | 0.0 - 1.0 | The ending point of guidance application as a percentage of total steps (default: 0.15) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with skip layer guidance applied |
diff --git a/built-in-nodes/SolidMask.mdx b/built-in-nodes/SolidMask.mdx
new file mode 100644
index 000000000..c183c5f86
--- /dev/null
+++ b/built-in-nodes/SolidMask.mdx
@@ -0,0 +1,23 @@
+---
+title: "SolidMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SolidMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SolidMask"
+icon: "circle"
+mode: wide
+---
+
+The SolidMask node generates a uniform mask with a specified value across its entire area. It's designed to create masks of specific dimensions and intensity, useful in various image processing and masking tasks.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `value`   | FLOAT       | Specifies the intensity value of the mask, affecting its overall appearance and utility in subsequent operations. |
+| `width`   | INT         | Determines the width of the generated mask, directly influencing its size and aspect ratio. |
+| `height`  | INT         | Sets the height of the generated mask, affecting its size and aspect ratio. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `mask`    | MASK        | Outputs a uniform mask with the specified dimensions and value. |
diff --git a/built-in-nodes/SplitAudioChannels.mdx b/built-in-nodes/SplitAudioChannels.mdx
new file mode 100644
index 000000000..5612528ab
--- /dev/null
+++ b/built-in-nodes/SplitAudioChannels.mdx
@@ -0,0 +1,25 @@
+---
+title: "SplitAudioChannels - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SplitAudioChannels node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SplitAudioChannels"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitAudioChannels/en.md)
+
+The SplitAudioChannels node separates stereo audio into individual left and right channels. It takes a stereo audio input with two channels and outputs two separate audio streams, one for the left channel and one for the right channel.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The stereo audio input to be separated into channels |
+
+**Note:** The input audio must have exactly two channels (stereo). The node will raise an error if the input audio has only one channel.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `left` | AUDIO | The separated left channel audio |
+| `right` | AUDIO | The separated right channel audio |
diff --git a/built-in-nodes/SplitImageWithAlpha.mdx b/built-in-nodes/SplitImageWithAlpha.mdx
new file mode 100644
index 000000000..fb9fd02fe
--- /dev/null
+++ b/built-in-nodes/SplitImageWithAlpha.mdx
@@ -0,0 +1,22 @@
+---
+title: "SplitImageWithAlpha - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SplitImageWithAlpha node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SplitImageWithAlpha"
+icon: "circle"
+mode: wide
+---
+
+The SplitImageWithAlpha node is designed to separate the color and alpha components of an image. It processes an input image tensor, extracting the RGB channels as the color component and the alpha channel as the transparency component, facilitating operations that require manipulation of these distinct image aspects.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The 'image' parameter represents the input image tensor from which the RGB and alpha channels are to be separated. It is crucial for the operation as it provides the source data for the split. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The 'image' output represents the separated RGB channels of the input image, providing the color component without the transparency information. |
+| `mask`    | `MASK`      | The 'mask' output represents the separated alpha channel of the input image, providing the transparency information. |
diff --git a/built-in-nodes/SplitSigmas.mdx b/built-in-nodes/SplitSigmas.mdx
new file mode 100644
index 000000000..72daeb0bc
--- /dev/null
+++ b/built-in-nodes/SplitSigmas.mdx
@@ -0,0 +1,22 @@
+---
+title: "SplitSigmas - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SplitSigmas node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SplitSigmas"
+icon: "circle"
+mode: wide
+---
+
+The SplitSigmas node is designed for dividing a sequence of sigma values into two parts based on a specified step. This functionality is crucial for operations that require different handling or processing of the initial and subsequent parts of the sigma sequence, enabling more flexible and targeted manipulation of these values.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `sigmas`  | `SIGMAS`    | The 'sigmas' parameter represents the sequence of sigma values to be split. It is essential for determining the division point and the resulting two sequences of sigma values, impacting the node's execution and results. |
+| `step`    | `INT`       | The 'step' parameter specifies the index at which the sigma sequence should be split. It plays a critical role in defining the boundary between the two resulting sigma sequences, influencing the node's functionality and the characteristics of the output. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `sigmas`  | `SIGMAS`    | The node outputs two sequences of sigma values, each representing a part of the original sequence divided at the specified step. These outputs are crucial for subsequent operations that require differentiated handling of sigma values. |
diff --git a/built-in-nodes/SplitSigmasDenoise.mdx b/built-in-nodes/SplitSigmasDenoise.mdx
new file mode 100644
index 000000000..8b03c397d
--- /dev/null
+++ b/built-in-nodes/SplitSigmasDenoise.mdx
@@ -0,0 +1,24 @@
+---
+title: "SplitSigmasDenoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SplitSigmasDenoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SplitSigmasDenoise"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitSigmasDenoise/en.md)
+
+The SplitSigmasDenoise node divides a sequence of sigma values into two parts based on a denoising strength parameter. It splits the input sigmas into high and low sigma sequences, where the split point is determined by multiplying the total steps by the denoise factor. This allows for separating the noise schedule into different intensity ranges for specialized processing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `sigmas` | SIGMAS | Yes | - | The input sequence of sigma values representing the noise schedule |
+| `denoise` | FLOAT | Yes | 0.0 - 1.0 | The denoising strength factor that determines where to split the sigma sequence (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `high_sigmas` | SIGMAS | The first portion of the sigma sequence containing higher sigma values |
+| `low_sigmas` | SIGMAS | The second portion of the sigma sequence containing lower sigma values |
diff --git a/built-in-nodes/StabilityAudioInpaint.mdx b/built-in-nodes/StabilityAudioInpaint.mdx
new file mode 100644
index 000000000..5d2be88e7
--- /dev/null
+++ b/built-in-nodes/StabilityAudioInpaint.mdx
@@ -0,0 +1,31 @@
+---
+title: "StabilityAudioInpaint - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityAudioInpaint node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityAudioInpaint"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityAudioInpaint/en.md)
+
+Transforms part of an existing audio sample using text instructions. This node allows you to modify specific sections of audio by providing descriptive prompts, effectively "inpainting" or regenerating selected portions while preserving the rest of the audio.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | "stable-audio-2.5"<br /> | The AI model to use for audio inpainting. |
+| `prompt` | STRING | Yes |  | Text description guiding how the audio should be transformed (default: empty). |
+| `audio` | AUDIO | Yes |  | Input audio file to transform. Audio must be between 6 and 190 seconds long. |
+| `duration` | INT | No | 1-190 | Controls the duration in seconds of the generated audio (default: 190). |
+| `seed` | INT | No | 0-4294967294 | The random seed used for generation (default: 0). |
+| `steps` | INT | No | 4-8 | Controls the number of sampling steps (default: 8). |
+| `mask_start` | INT | No | 0-190 | Starting position in seconds for the audio section to transform (default: 30). |
+| `mask_end` | INT | No | 0-190 | Ending position in seconds for the audio section to transform (default: 190). |
+
+**Note:** The `mask_end` value must be greater than the `mask_start` value. The input audio must be between 6 and 190 seconds in duration.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The transformed audio output with the specified section modified according to the prompt. |
diff --git a/built-in-nodes/StabilityAudioToAudio.mdx b/built-in-nodes/StabilityAudioToAudio.mdx
new file mode 100644
index 000000000..8eaba434b
--- /dev/null
+++ b/built-in-nodes/StabilityAudioToAudio.mdx
@@ -0,0 +1,30 @@
+---
+title: "StabilityAudioToAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityAudioToAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityAudioToAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityAudioToAudio/en.md)
+
+Transforms existing audio samples into new high-quality compositions using text instructions. This node takes an input audio file and modifies it based on your text prompt to create new audio content.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | "stable-audio-2.5"<br /> | The AI model to use for audio transformation |
+| `prompt` | STRING | Yes |  | Text instructions describing how to transform the audio (default: empty) |
+| `audio` | AUDIO | Yes |  | Audio must be between 6 and 190 seconds long |
+| `duration` | INT | No | 1-190 | Controls the duration in seconds of the generated audio (default: 190) |
+| `seed` | INT | No | 0-4294967294 | The random seed used for generation (default: 0) |
+| `steps` | INT | No | 4-8 | Controls the number of sampling steps (default: 8) |
+| `strength` | FLOAT | No | 0.01-1.0 | Parameter controls how much influence the audio parameter has on the generated audio (default: 1.0) |
+
+**Note:** The input audio must be between 6 and 190 seconds in duration.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The transformed audio generated based on the input audio and text prompt |
diff --git a/built-in-nodes/StabilityStableImageSD_3_5Node.mdx b/built-in-nodes/StabilityStableImageSD_3_5Node.mdx
new file mode 100644
index 000000000..776abc1e0
--- /dev/null
+++ b/built-in-nodes/StabilityStableImageSD_3_5Node.mdx
@@ -0,0 +1,32 @@
+---
+title: "StabilityStableImageSD_3_5Node - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityStableImageSD_3_5Node node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityStableImageSD_3_5Node"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityStableImageSD_3_5Node/en.md)
+
+This node generates images synchronously using Stability AI's Stable Diffusion 3.5 model. It creates images based on text prompts and can also modify existing images when provided as input. The node supports various aspect ratios and style presets to customize the output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. (default: empty string) |
+| `model` | COMBO | Yes | Multiple options available | The Stable Diffusion 3.5 model to use for generation. |
+| `aspect_ratio` | COMBO | Yes | Multiple options available | Aspect ratio of generated image. (default: 1:1 ratio) |
+| `style_preset` | COMBO | No | Multiple options available | Optional desired style of generated image. |
+| `cfg_scale` | FLOAT | Yes | 1.0 to 10.0 | How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt). (default: 4.0) |
+| `seed` | INT | Yes | 0 to 4294967294 | The random seed used for creating the noise. (default: 0) |
+| `image` | IMAGE | No | - | Optional input image for image-to-image generation. |
+| `negative_prompt` | STRING | No | - | Keywords of what you do not wish to see in the output image. This is an advanced feature. (default: empty string) |
+| `image_denoise` | FLOAT | No | 0.0 to 1.0 | Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all. (default: 0.5) |
+
+**Note:** When an `image` is provided, the node switches to image-to-image generation mode and the `aspect_ratio` parameter is automatically determined from the input image. When no `image` is provided, the `image_denoise` parameter is ignored.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The generated or modified image. |
diff --git a/built-in-nodes/StabilityStableImageUltraNode.mdx b/built-in-nodes/StabilityStableImageUltraNode.mdx
new file mode 100644
index 000000000..275fd6f0a
--- /dev/null
+++ b/built-in-nodes/StabilityStableImageUltraNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "StabilityStableImageUltraNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityStableImageUltraNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityStableImageUltraNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityStableImageUltraNode/en.md)
+
+Generates images synchronously based on prompt and resolution. This node creates images using Stability AI's Stable Image Ultra model, processing your text prompt and generating a corresponding image with the specified aspect ratio and style.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. To control the weight of a given word use the format `(word:weight)`, where `word` is the word you'd like to control the weight of and `weight` is a value between 0 and 1. For example: `The sky was a crisp (blue:0.3) and (green:0.8)` would convey a sky that was blue and green, but more green than blue. |
+| `aspect_ratio` | COMBO | Yes | Multiple options available | Aspect ratio of generated image. |
+| `style_preset` | COMBO | No | Multiple options available | Optional desired style of generated image. |
+| `seed` | INT | Yes | 0-4294967294 | The random seed used for creating the noise. |
+| `image` | IMAGE | No | - | Optional input image. |
+| `negative_prompt` | STRING | No | - | A blurb of text describing what you do not wish to see in the output image. This is an advanced feature. |
+| `image_denoise` | FLOAT | No | 0.0-1.0 | Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all. Default: 0.5 |
+
+**Note:** When an input image is not provided, the `image_denoise` parameter is automatically disabled.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image based on the input parameters. |
diff --git a/built-in-nodes/StabilityTextToAudio.mdx b/built-in-nodes/StabilityTextToAudio.mdx
new file mode 100644
index 000000000..9272fd307
--- /dev/null
+++ b/built-in-nodes/StabilityTextToAudio.mdx
@@ -0,0 +1,26 @@
+---
+title: "StabilityTextToAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityTextToAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityTextToAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityTextToAudio/en.md)
+
+Generates high-quality music and sound effects from text descriptions. This node uses Stability AI's audio generation technology to create audio content based on your text prompts.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"stable-audio-2.5"` | The audio generation model to use (default: "stable-audio-2.5") |
+| `prompt` | STRING | Yes | - | The text description used to generate audio content (default: empty string) |
+| `duration` | INT | No | 1-190 | Controls the duration in seconds of the generated audio (default: 190) |
+| `seed` | INT | No | 0-4294967294 | The random seed used for generation (default: 0) |
+| `steps` | INT | No | 4-8 | Controls the number of sampling steps (default: 8) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The generated audio file based on the text prompt |
diff --git a/built-in-nodes/StabilityUpscaleConservativeNode.mdx b/built-in-nodes/StabilityUpscaleConservativeNode.mdx
new file mode 100644
index 000000000..c70757511
--- /dev/null
+++ b/built-in-nodes/StabilityUpscaleConservativeNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "StabilityUpscaleConservativeNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityUpscaleConservativeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityUpscaleConservativeNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleConservativeNode/en.md)
+
+Upscale image with minimal alterations to 4K resolution. This node uses Stability AI's conservative upscaling to increase image resolution while preserving the original content and making only subtle changes.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be upscaled |
+| `prompt` | STRING | Yes | - | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. (default: empty string) |
+| `creativity` | FLOAT | Yes | 0.2-0.5 | Controls the likelihood of creating additional details not heavily conditioned by the init image. (default: 0.35) |
+| `seed` | INT | Yes | 0-4294967294 | The random seed used for creating the noise. (default: 0) |
+| `negative_prompt` | STRING | No | - | Keywords of what you do not wish to see in the output image. This is an advanced feature. (default: empty string) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The upscaled image at 4K resolution |
diff --git a/built-in-nodes/StabilityUpscaleCreativeNode.mdx b/built-in-nodes/StabilityUpscaleCreativeNode.mdx
new file mode 100644
index 000000000..7d6c77977
--- /dev/null
+++ b/built-in-nodes/StabilityUpscaleCreativeNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "StabilityUpscaleCreativeNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityUpscaleCreativeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityUpscaleCreativeNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleCreativeNode/en.md)
+
+Upscale image with minimal alterations to 4K resolution. This node uses Stability AI's creative upscaling technology to enhance image resolution while preserving the original content and adding subtle creative details.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be upscaled |
+| `prompt` | STRING | Yes | - | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. (default: empty string) |
+| `creativity` | FLOAT | Yes | 0.1-0.5 | Controls the likelihood of creating additional details not heavily conditioned by the init image. (default: 0.3) |
+| `style_preset` | COMBO | Yes | Multiple options available | Optional desired style of generated image. Options include various style presets from Stability AI. |
+| `seed` | INT | Yes | 0-4294967294 | The random seed used for creating the noise. (default: 0) |
+| `negative_prompt` | STRING | No | - | Keywords of what you do not wish to see in the output image. This is an advanced feature. (default: empty string) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The upscaled image at 4K resolution |
diff --git a/built-in-nodes/StabilityUpscaleFastNode.mdx b/built-in-nodes/StabilityUpscaleFastNode.mdx
new file mode 100644
index 000000000..19fe13842
--- /dev/null
+++ b/built-in-nodes/StabilityUpscaleFastNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "StabilityUpscaleFastNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityUpscaleFastNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityUpscaleFastNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleFastNode/en.md)
+
+Quickly upscales an image via Stability API call to 4x its original size. This node is specifically intended for upscaling low-quality or compressed images by sending them to Stability AI's fast upscaling service.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be upscaled |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The upscaled image returned from the Stability AI API |
diff --git a/built-in-nodes/StableCascade_EmptyLatentImage.mdx b/built-in-nodes/StableCascade_EmptyLatentImage.mdx
new file mode 100644
index 000000000..7140055b7
--- /dev/null
+++ b/built-in-nodes/StableCascade_EmptyLatentImage.mdx
@@ -0,0 +1,26 @@
+---
+title: "StableCascade_EmptyLatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableCascade_EmptyLatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableCascade_EmptyLatentImage"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_EmptyLatentImage/en.md)
+
+The StableCascade_EmptyLatentImage node creates empty latent tensors for Stable Cascade models. It generates two separate latent representations - one for stage C and another for stage B - with appropriate dimensions based on the input resolution and compression settings. This node provides the starting point for the Stable Cascade generation pipeline.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | Yes | 256 to MAX_RESOLUTION | The width of the output image in pixels (default: 1024, step: 8) |
+| `height` | INT | Yes | 256 to MAX_RESOLUTION | The height of the output image in pixels (default: 1024, step: 8) |
+| `compression` | INT | Yes | 4 to 128 | The compression factor that determines the latent dimensions for stage C (default: 42, step: 1) |
+| `batch_size` | INT | No | 1 to 4096 | The number of latent samples to generate in a batch (default: 1) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `stage_c` | LATENT | The stage C latent tensor with dimensions [batch_size, 16, height//compression, width//compression] |
+| `stage_b` | LATENT | The stage B latent tensor with dimensions [batch_size, 4, height//4, width//4] |
diff --git a/built-in-nodes/StableCascade_StageB_Conditioning.mdx b/built-in-nodes/StableCascade_StageB_Conditioning.mdx
new file mode 100644
index 000000000..edef62dfd
--- /dev/null
+++ b/built-in-nodes/StableCascade_StageB_Conditioning.mdx
@@ -0,0 +1,23 @@
+---
+title: "StableCascade_StageB_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableCascade_StageB_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableCascade_StageB_Conditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_StageB_Conditioning/en.md)
+
+The StableCascade_StageB_Conditioning node prepares conditioning data for Stable Cascade Stage B generation by combining existing conditioning information with prior latent representations from Stage C. It modifies the conditioning data to include the latent samples from Stage C, enabling the generation process to leverage the prior information for more coherent outputs.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | Yes | - | The conditioning data to be modified with Stage C prior information |
+| `stage_c` | LATENT | Yes | - | The latent representation from Stage C containing prior samples for conditioning |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The modified conditioning data with Stage C prior information integrated |
diff --git a/built-in-nodes/StableCascade_StageC_VAEEncode.mdx b/built-in-nodes/StableCascade_StageC_VAEEncode.mdx
new file mode 100644
index 000000000..ab7bfc74e
--- /dev/null
+++ b/built-in-nodes/StableCascade_StageC_VAEEncode.mdx
@@ -0,0 +1,25 @@
+---
+title: "StableCascade_StageC_VAEEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableCascade_StageC_VAEEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableCascade_StageC_VAEEncode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_StageC_VAEEncode/en.md)
+
+The StableCascade_StageC_VAEEncode node processes images through a VAE encoder to generate latent representations for Stable Cascade models. It takes an input image and compresses it using the specified VAE model, then outputs two latent representations: one for stage C and a placeholder for stage B. The compression parameter controls how much the image is scaled down before encoding.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be encoded into latent space |
+| `vae` | VAE | Yes | - | The VAE model used for encoding the image |
+| `compression` | INT | No | 4-128 | The compression factor applied to the image before encoding (default: 42) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `stage_c` | LATENT | The encoded latent representation for stage C of the Stable Cascade model |
+| `stage_b` | LATENT | A placeholder latent representation for stage B (currently returns zeros) |
diff --git a/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx b/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx
new file mode 100644
index 000000000..8e69b9ffe
--- /dev/null
+++ b/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx
@@ -0,0 +1,25 @@
+---
+title: "StableCascade_SuperResolutionControlnet - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableCascade_SuperResolutionControlnet node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableCascade_SuperResolutionControlnet"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_SuperResolutionControlnet/en.md)
+
+The StableCascade_SuperResolutionControlnet node prepares inputs for Stable Cascade super-resolution processing. It takes an input image and encodes it using a VAE to create controlnet input, while also generating placeholder latent representations for stage C and stage B of the Stable Cascade pipeline.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | The input image to be processed for super-resolution |
+| `vae` | VAE | Yes | - | The VAE model used to encode the input image |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `controlnet_input` | IMAGE | The encoded image representation suitable for controlnet input |
+| `stage_c` | LATENT | Placeholder latent representation for stage C of Stable Cascade processing |
+| `stage_b` | LATENT | Placeholder latent representation for stage B of Stable Cascade processing |
diff --git a/built-in-nodes/StableZero123_Conditioning.mdx b/built-in-nodes/StableZero123_Conditioning.mdx
new file mode 100644
index 000000000..e51a2c3b5
--- /dev/null
+++ b/built-in-nodes/StableZero123_Conditioning.mdx
@@ -0,0 +1,33 @@
+---
+title: "StableZero123_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableZero123_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableZero123_Conditioning"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning/en.md)
+
+The StableZero123_Conditioning node processes an input image and camera angles to generate conditioning data and latent representations for 3D model generation. It uses a CLIP vision model to encode the image features, combines them with camera embedding information based on elevation and azimuth angles, and produces positive and negative conditioning along with a latent representation for downstream 3D generation tasks.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip_vision` | CLIP_VISION | Yes | - | The CLIP vision model used to encode image features |
+| `init_image` | IMAGE | Yes | - | The input image to be processed and encoded |
+| `vae` | VAE | Yes | - | The VAE model used for encoding pixels to latent space |
+| `width` | INT | No | 16 to MAX_RESOLUTION | Output width for the latent representation (default: 256, must be divisible by 8) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | Output height for the latent representation (default: 256, must be divisible by 8) |
+| `batch_size` | INT | No | 1 to 4096 | Number of samples to generate in the batch (default: 1) |
+| `elevation` | FLOAT | No | -180.0 to 180.0 | Camera elevation angle in degrees (default: 0.0) |
+| `azimuth` | FLOAT | No | -180.0 to 180.0 | Camera azimuth angle in degrees (default: 0.0) |
+
+**Note:** The `width` and `height` parameters must be divisible by 8 as the node automatically divides them by 8 to create the latent representation dimensions.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning data combining image features and camera embeddings |
+| `negative` | CONDITIONING | Negative conditioning data with zero-initialized features |
+| `latent` | LATENT | Latent representation with dimensions [batch_size, 4, height//8, width//8] |
diff --git a/built-in-nodes/StableZero123_Conditioning_Batched.mdx b/built-in-nodes/StableZero123_Conditioning_Batched.mdx
new file mode 100644
index 000000000..3c6d4a386
--- /dev/null
+++ b/built-in-nodes/StableZero123_Conditioning_Batched.mdx
@@ -0,0 +1,35 @@
+---
+title: "StableZero123_Conditioning_Batched - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableZero123_Conditioning_Batched node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableZero123_Conditioning_Batched"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning_Batched/en.md)
+
+The StableZero123_Conditioning_Batched node processes an input image and generates conditioning data for 3D model generation. It encodes the image using CLIP vision and VAE models, then creates camera embeddings based on elevation and azimuth angles to produce positive and negative conditioning along with latent representations for batch processing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip_vision` | CLIP_VISION | Yes | - | The CLIP vision model used for encoding the input image |
+| `init_image` | IMAGE | Yes | - | The initial input image to be processed and encoded |
+| `vae` | VAE | Yes | - | The VAE model used for encoding image pixels into latent space |
+| `width` | INT | No | 16 to MAX_RESOLUTION | The output width for the processed image (default: 256, must be divisible by 8) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | The output height for the processed image (default: 256, must be divisible by 8) |
+| `batch_size` | INT | No | 1 to 4096 | The number of conditioning samples to generate in the batch (default: 1) |
+| `elevation` | FLOAT | No | -180.0 to 180.0 | The initial camera elevation angle in degrees (default: 0.0) |
+| `azimuth` | FLOAT | No | -180.0 to 180.0 | The initial camera azimuth angle in degrees (default: 0.0) |
+| `elevation_batch_increment` | FLOAT | No | -180.0 to 180.0 | The amount to increment elevation for each batch item (default: 0.0) |
+| `azimuth_batch_increment` | FLOAT | No | -180.0 to 180.0 | The amount to increment azimuth for each batch item (default: 0.0) |
+
+**Note:** The `width` and `height` parameters must be divisible by 8 as the node internally divides these dimensions by 8 for latent space generation.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The positive conditioning data containing image embeddings and camera parameters |
+| `negative` | CONDITIONING | The negative conditioning data with zero-initialized embeddings |
+| `latent` | LATENT | The latent representation of the processed image with batch indexing information |
diff --git a/built-in-nodes/Stablezero123Conditioning.mdx b/built-in-nodes/Stablezero123Conditioning.mdx
new file mode 100644
index 000000000..6d06ab1c9
--- /dev/null
+++ b/built-in-nodes/Stablezero123Conditioning.mdx
@@ -0,0 +1,30 @@
+---
+title: "Stablezero123Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Stablezero123Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Stablezero123Conditioning"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to process and condition data for use in StableZero123 models, focusing on preparing the input in a specific format that is compatible and optimized for these models.
+
+## Inputs
+
+| Parameter             | Comfy dtype        | Description |
+|-----------------------|--------------------|-------------|
+| `clip_vision`         | `CLIP_VISION`      | Processes visual data to align with the model's requirements, enhancing the model's understanding of visual context. |
+| `init_image`          | `IMAGE`            | Serves as the initial image input for the model, setting the baseline for further image-based operations. |
+| `vae`                 | `VAE`              | Integrates variational autoencoder outputs, facilitating the model's ability to generate or modify images. |
+| `width`               | `INT`              | Specifies the width of the output image, allowing for dynamic resizing according to model needs. |
+| `height`              | `INT`              | Determines the height of the output image, enabling customization of the output dimensions. |
+| `batch_size`          | `INT`              | Controls the number of images processed in a single batch, optimizing computational efficiency. |
+| `elevation`           | `FLOAT`            | Adjusts the elevation angle for 3D model rendering, enhancing the model's spatial understanding. |
+| `azimuth`             | `FLOAT`            | Modifies the azimuth angle for 3D model visualization, improving the model's perception of orientation. |
+
+## Outputs
+
+| Parameter     | Data Type | Description |
+|---------------|--------------|-------------|
+| `positive`    | `CONDITIONING` | Generates positive conditioning vectors, aiding in the model's positive feature reinforcement. |
+| `negative`    | `CONDITIONING` | Produces negative conditioning vectors, assisting in the model's avoidance of certain features. |
+| `latent`      | `LATENT`     | Creates latent representations, facilitating deeper model insights into the data. |
diff --git a/built-in-nodes/Stablezero123ConditioningBatched.mdx b/built-in-nodes/Stablezero123ConditioningBatched.mdx
new file mode 100644
index 000000000..91de7ead5
--- /dev/null
+++ b/built-in-nodes/Stablezero123ConditioningBatched.mdx
@@ -0,0 +1,32 @@
+---
+title: "Stablezero123ConditioningBatched - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Stablezero123ConditioningBatched node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Stablezero123ConditioningBatched"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to process conditioning information in a batched manner specifically tailored for the StableZero123 model. It focuses on efficiently handling multiple sets of conditioning data simultaneously, optimizing the workflow for scenarios where batch processing is crucial.
+
+## Inputs
+
+| Parameter             | Data Type | Description |
+|----------------------|--------------|-------------|
+| `clip_vision`         | `CLIP_VISION` | The CLIP vision embeddings that provide visual context for the conditioning process. |
+| `init_image`          | `IMAGE`      | The initial image to be conditioned upon, serving as a starting point for the generation process. |
+| `vae`                 | `VAE`        | The variational autoencoder used for encoding and decoding images in the conditioning process. |
+| `width`               | `INT`        | The width of the output image. |
+| `height`              | `INT`        | The height of the output image. |
+| `batch_size`          | `INT`        | The number of conditioning sets to be processed in a single batch. |
+| `elevation`           | `FLOAT`      | The elevation angle for 3D model conditioning, affecting the perspective of the generated image. |
+| `azimuth`             | `FLOAT`      | The azimuth angle for 3D model conditioning, affecting the orientation of the generated image. |
+| `elevation_batch_increment` | `FLOAT` | The incremental change in elevation angle across the batch, allowing for varied perspectives. |
+| `azimuth_batch_increment` | `FLOAT` | The incremental change in azimuth angle across the batch, allowing for varied orientations. |
+
+## Outputs
+
+| Parameter     | Data Type | Description |
+|---------------|--------------|-------------|
+| `positive`    | `CONDITIONING` | The positive conditioning output, tailored for promoting certain features or aspects in the generated content. |
+| `negative`    | `CONDITIONING` | The negative conditioning output, tailored for demoting certain features or aspects in the generated content. |
+| `latent`      | `LATENT`     | The latent representation derived from the conditioning process, ready for further processing or generation steps. |
diff --git a/built-in-nodes/StringCompare.mdx b/built-in-nodes/StringCompare.mdx
new file mode 100644
index 000000000..3712072dc
--- /dev/null
+++ b/built-in-nodes/StringCompare.mdx
@@ -0,0 +1,25 @@
+---
+title: "StringCompare - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringCompare node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringCompare"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringCompare/en.md)
+
+The StringCompare node compares two text strings using different comparison methods. It can check if one string starts with another, ends with another, or if both strings are exactly equal. The comparison can be performed with or without considering letter case differences.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string_a` | STRING | Yes | - | The first string to compare |
+| `string_b` | STRING | Yes | - | The second string to compare against |
+| `mode` | COMBO | Yes | "Starts With"<br />"Ends With"<br />"Equal" | The comparison method to use |
+| `case_sensitive` | BOOLEAN | No | - | Whether to consider letter case during comparison (default: true) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | BOOLEAN | Returns true if the comparison condition is met, false otherwise |
diff --git a/built-in-nodes/StringConcatenate.mdx b/built-in-nodes/StringConcatenate.mdx
new file mode 100644
index 000000000..706f5cef1
--- /dev/null
+++ b/built-in-nodes/StringConcatenate.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringConcatenate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringConcatenate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringConcatenate"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringConcatenate/en.md)
+
+The StringConcatenate node combines two text strings into one by joining them with a specified delimiter. It takes two input strings and a delimiter character or string, then outputs a single string where the two inputs are connected with the delimiter placed between them.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string_a` | STRING | Yes | - | The first text string to concatenate |
+| `string_b` | STRING | Yes | - | The second text string to concatenate |
+| `delimiter` | STRING | No | - | The character or string to insert between the two input strings (default: empty string) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The combined string with the delimiter inserted between string_a and string_b |
diff --git a/built-in-nodes/StringContains.mdx b/built-in-nodes/StringContains.mdx
new file mode 100644
index 000000000..12594246f
--- /dev/null
+++ b/built-in-nodes/StringContains.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringContains - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringContains node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringContains"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringContains/en.md)
+
+The StringContains node checks if a given string contains a specified substring. It can perform this check with either case-sensitive or case-insensitive matching, returning a boolean result indicating whether the substring was found within the main string.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | - | The main text string to search within |
+| `substring` | STRING | Yes | - | The text to search for within the main string |
+| `case_sensitive` | BOOLEAN | No | - | Determines whether the search should be case-sensitive (default: true) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `contains` | BOOLEAN | Returns true if the substring is found in the string, false otherwise |
diff --git a/built-in-nodes/StringLength.mdx b/built-in-nodes/StringLength.mdx
new file mode 100644
index 000000000..3cb5e84a7
--- /dev/null
+++ b/built-in-nodes/StringLength.mdx
@@ -0,0 +1,22 @@
+---
+title: "StringLength - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringLength node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringLength"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringLength/en.md)
+
+The StringLength node calculates the number of characters in a text string. It takes any text input and returns the total count of characters, including spaces and punctuation. This is useful for measuring text length or validating string size requirements.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | N/A | The text string to measure the length of. Supports multiline input. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `length` | INT | The total number of characters in the input string, including spaces and special characters. |
diff --git a/built-in-nodes/StringReplace.mdx b/built-in-nodes/StringReplace.mdx
new file mode 100644
index 000000000..70f8dad29
--- /dev/null
+++ b/built-in-nodes/StringReplace.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringReplace - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringReplace node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringReplace"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringReplace/en.md)
+
+The StringReplace node performs text replacement operations on input strings. It searches for a specified substring within the input text and replaces all occurrences with a different substring. This node returns the modified string with all replacements applied.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | - | The input text string where replacements will be performed |
+| `find` | STRING | Yes | - | The substring to search for within the input text |
+| `replace` | STRING | Yes | - | The replacement text that will substitute all found occurrences |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The modified string with all occurrences of the find text replaced by the replace text |
diff --git a/built-in-nodes/StringSubstring.mdx b/built-in-nodes/StringSubstring.mdx
new file mode 100644
index 000000000..19de1f487
--- /dev/null
+++ b/built-in-nodes/StringSubstring.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringSubstring - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringSubstring node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringSubstring"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringSubstring/en.md)
+
+The StringSubstring node extracts a portion of text from a larger string. It takes a starting position and ending position to define the section you want to extract, then returns the text between those two positions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | - | The input text string to extract from |
+| `start` | INT | Yes | - | The starting position index for the substring |
+| `end` | INT | Yes | - | The ending position index for the substring |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The extracted substring from the input text |
diff --git a/built-in-nodes/StringTrim.mdx b/built-in-nodes/StringTrim.mdx
new file mode 100644
index 000000000..e51961ec7
--- /dev/null
+++ b/built-in-nodes/StringTrim.mdx
@@ -0,0 +1,23 @@
+---
+title: "StringTrim - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringTrim node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringTrim"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringTrim/en.md)
+
+The StringTrim node removes whitespace characters from the beginning, end, or both sides of a text string. You can choose to trim from the left side, right side, or both sides of the string. This is useful for cleaning up text inputs by removing unwanted spaces, tabs, or newline characters.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | Yes | - | The text string to process. Supports multiline input. |
+| `mode` | COMBO | Yes | "Both"<br />"Left"<br />"Right" | Specifies which side(s) of the string to trim. "Both" removes whitespace from both ends, "Left" removes from the beginning only, "Right" removes from the end only. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The trimmed text string with whitespace removed according to the selected mode. |
diff --git a/built-in-nodes/StripWhitespace.mdx b/built-in-nodes/StripWhitespace.mdx
new file mode 100644
index 000000000..8fdcf8461
--- /dev/null
+++ b/built-in-nodes/StripWhitespace.mdx
@@ -0,0 +1,22 @@
+---
+title: "StripWhitespace - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StripWhitespace node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StripWhitespace"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StripWhitespace/en.md)
+
+This node removes any extra spaces, tabs, or newlines from the beginning and end of a text string. It takes a text input and returns a cleaned version with the leading and trailing whitespace trimmed off.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | Yes | N/A | The text string from which to remove leading and trailing whitespace. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `text` | STRING | The processed text with all leading and trailing whitespace characters removed. |
diff --git a/built-in-nodes/StyleModelApply.mdx b/built-in-nodes/StyleModelApply.mdx
new file mode 100644
index 000000000..27592553a
--- /dev/null
+++ b/built-in-nodes/StyleModelApply.mdx
@@ -0,0 +1,25 @@
+---
+title: "StyleModelApply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StyleModelApply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StyleModelApply"
+icon: "circle"
+mode: wide
+---
+
+This node applies a style model to a given conditioning, enhancing or altering its style based on the output of a CLIP vision model. It integrates the style model's conditioning into the existing conditioning, allowing for a seamless blend of styles in the generation process.
+
+## Inputs
+
+### Required
+
+| Parameter             | Comfy dtype          | Description |
+|-----------------------|-----------------------|-------------|
+| `conditioning`        | `CONDITIONING`       | The original conditioning data to which the style model's conditioning will be applied. It's crucial for defining the base context or style that will be enhanced or altered. |
+| `style_model`         | `STYLE_MODEL`        | The style model used to generate new conditioning based on the CLIP vision model's output. It plays a key role in defining the new style to be applied. |
+| `clip_vision_output`  | `CLIP_VISION_OUTPUT` | The output from a CLIP vision model, which is used by the style model to generate new conditioning. It provides the visual context necessary for style application. |
+
+## Outputs
+
+| Parameter            | Comfy dtype           | Description |
+|----------------------|-----------------------|-------------|
+| `conditioning`       | `CONDITIONING`        | The enhanced or altered conditioning, incorporating the style model's output. It represents the final, styled conditioning ready for further processing or generation. |
diff --git a/built-in-nodes/StyleModelLoader.mdx b/built-in-nodes/StyleModelLoader.mdx
new file mode 100644
index 000000000..5a3cf47a9
--- /dev/null
+++ b/built-in-nodes/StyleModelLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "StyleModelLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StyleModelLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StyleModelLoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/style_models` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+The StyleModelLoader node is designed to load a style model from a specified path. It focuses on retrieving and initializing style models that can be used to apply specific artistic styles to images, thereby enabling the customization of visual outputs based on the loaded style model.
+
+## Inputs
+
+| Parameter Name      | Comfy dtype     | Python dtype | Description                                                                                       |
+|---------------------|-----------------|--------------|---------------------------------------------------------------------------------------------------|
+| `style_model_name`  | COMBO[STRING] | `str`        | Specifies the name of the style model to be loaded. This name is used to locate the model file within a predefined directory structure, allowing for the dynamic loading of different style models based on user input or application needs. |
+
+## Outputs
+
+| Parameter Name  | Comfy dtype   | Python dtype | Description                                                                                       |
+|-----------------|---------------|--------------|---------------------------------------------------------------------------------------------------|
+| `style_model`   | `STYLE_MODEL` | `StyleModel` | Returns the loaded style model, ready for use in applying styles to images. This enables the dynamic customization of visual outputs by applying different artistic styles. |
diff --git a/built-in-nodes/SvdImg2vidConditioning.mdx b/built-in-nodes/SvdImg2vidConditioning.mdx
new file mode 100644
index 000000000..aafc2961f
--- /dev/null
+++ b/built-in-nodes/SvdImg2vidConditioning.mdx
@@ -0,0 +1,31 @@
+---
+title: "SvdImg2vidConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SvdImg2vidConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SvdImg2vidConditioning"
+icon: "circle"
+mode: wide
+---
+
+This node is designed for generating conditioning data for video generation tasks, specifically tailored for use with SVD_img2vid models. It takes various inputs including initial images, video parameters, and a VAE model to produce conditioning data that can be used to guide the generation of video frames.
+
+## Inputs
+
+| Parameter             | Comfy dtype        | Description |
+|----------------------|--------------------|-------------|
+| `clip_vision`         | `CLIP_VISION`      | Represents the CLIP vision model used for encoding visual features from the initial image, playing a crucial role in understanding the content and context of the image for video generation. |
+| `init_image`          | `IMAGE`            | The initial image from which the video will be generated, serving as the starting point for the video generation process. |
+| `vae`                 | `VAE`              | A Variational Autoencoder (VAE) model used for encoding the initial image into a latent space, facilitating the generation of coherent and continuous video frames. |
+| `width`               | `INT`              | The desired width of the video frames to be generated, allowing for customization of the video's resolution. |
+| `height`              | `INT`              | The desired height of the video frames, enabling control over the video's aspect ratio and resolution. |
+| `video_frames`        | `INT`              | Specifies the number of frames to be generated for the video, determining the video's length. |
+| `motion_bucket_id`    | `INT`              | An identifier for categorizing the type of motion to be applied in the video generation, aiding in the creation of dynamic and engaging videos. |
+| `fps`                 | `INT`              | The frames per second (fps) rate for the video, influencing the smoothness and realism of the generated video. |
+| `augmentation_level`  | `FLOAT`            | A parameter controlling the level of augmentation applied to the initial image, affecting the diversity and variability of the generated video frames. |
+
+## Outputs
+
+| Parameter     | Comfy dtype        | Description |
+|---------------|--------------------|-------------|
+| `positive`    | `CONDITIONING`     | The positive conditioning data, consisting of encoded features and parameters for guiding the video generation process in a desired direction. |
+| `negative`    | `CONDITIONING`     | The negative conditioning data, providing a contrast to the positive conditioning, which can be used to avoid certain patterns or features in the generated video. |
+| `latent`      | `LATENT`           | Latent representations generated for each frame of the video, serving as a foundational component for the video generation process. |
diff --git a/built-in-nodes/T5TokenizerOptions.mdx b/built-in-nodes/T5TokenizerOptions.mdx
new file mode 100644
index 000000000..7a1ca22bc
--- /dev/null
+++ b/built-in-nodes/T5TokenizerOptions.mdx
@@ -0,0 +1,24 @@
+---
+title: "T5TokenizerOptions - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the T5TokenizerOptions node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "T5TokenizerOptions"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/T5TokenizerOptions/en.md)
+
+The T5TokenizerOptions node allows you to configure tokenizer settings for various T5 model types. It sets minimum padding and minimum length parameters for multiple T5 model variants including t5xxl, pile_t5xl, t5base, mt5xl, and umt5xxl. The node takes a CLIP input and returns a modified CLIP with the specified tokenizer options applied.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | - | The CLIP model to configure tokenizer options for |
+| `min_padding` | INT | No | 0-10000 | Minimum padding value to set for all T5 model types (default: 0) |
+| `min_length` | INT | No | 0-10000 | Minimum length value to set for all T5 model types (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | CLIP | The modified CLIP model with updated tokenizer options applied to all T5 variants |
diff --git a/built-in-nodes/TCFG.mdx b/built-in-nodes/TCFG.mdx
new file mode 100644
index 000000000..c5203f0a8
--- /dev/null
+++ b/built-in-nodes/TCFG.mdx
@@ -0,0 +1,22 @@
+---
+title: "TCFG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TCFG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TCFG"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TCFG/en.md)
+
+TCFG (Tangential Damping CFG) implements a guidance technique that refines the unconditional (negative) predictions to better align with the conditional (positive) predictions. This method improves output quality by applying tangential damping to the unconditional guidance, based on the research paper referenced as 2503.18137. The node modifies the model's sampling behavior by adjusting how unconditional predictions are processed during the classifier-free guidance process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply tangential damping CFG to |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | The modified model with tangential damping CFG applied |
diff --git a/built-in-nodes/TemporalScoreRescaling.mdx b/built-in-nodes/TemporalScoreRescaling.mdx
new file mode 100644
index 000000000..e32c4b47f
--- /dev/null
+++ b/built-in-nodes/TemporalScoreRescaling.mdx
@@ -0,0 +1,24 @@
+---
+title: "TemporalScoreRescaling - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TemporalScoreRescaling node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TemporalScoreRescaling"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TemporalScoreRescaling/en.md)
+
+This node applies Temporal Score Rescaling (TSR) to a diffusion model. It modifies the model's sampling behavior by rescaling the predicted noise or score during the denoising process, which can steer the diversity of the generated output. This is implemented as a post-CFG (Classifier-Free Guidance) function.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to be patched with the TSR function. |
+| `tsr_k` | FLOAT | No | 0.01 - 100.0 | Controls the rescaling strength. Lower k produces more detailed results; higher k produces smoother results in image generation. Setting k = 1 disables rescaling. (default: 0.95) |
+| `tsr_sigma` | FLOAT | No | 0.01 - 100.0 | Controls how early rescaling takes effect. Larger values take effect earlier. (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | The input model, now patched with the Temporal Score Rescaling function applied to its sampling process. |
diff --git a/built-in-nodes/Tencent3DPartNode.mdx b/built-in-nodes/Tencent3DPartNode.mdx
new file mode 100644
index 000000000..228a6812c
--- /dev/null
+++ b/built-in-nodes/Tencent3DPartNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "Tencent3DPartNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Tencent3DPartNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Tencent3DPartNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DPartNode/en.md)
+
+This node uses the Tencent Hunyuan3D API to automatically analyze a 3D model and generate or identify its components based on its structure. It processes the model and returns a new FBX file.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_3d` | FILE3D | Yes | FBX, Any | The 3D model to process. The model should be in FBX format and have less than 30000 faces. |
+| `seed` | INT | No | 0 to 2147483647 | A seed value to control whether the node should re-run. The results are non-deterministic regardless of the seed value. (default: 0) |
+
+**Note:** The `model_3d` input only supports files in the FBX format. If a different 3D file format is provided, the node will raise an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `FBX` | FILE3DFBX | The processed 3D model, returned as an FBX file. |
diff --git a/built-in-nodes/Tencent3DTextureEditNode.mdx b/built-in-nodes/Tencent3DTextureEditNode.mdx
new file mode 100644
index 000000000..90cd3865c
--- /dev/null
+++ b/built-in-nodes/Tencent3DTextureEditNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "Tencent3DTextureEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Tencent3DTextureEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Tencent3DTextureEditNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DTextureEditNode/en.md)
+
+This node uses the Tencent Hunyuan3D API to edit the textures of a 3D model. You provide a 3D model and a text description of the desired changes, and the node returns a new version of the model with its textures redrawn according to your prompt.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_3d` | FILE3D | Yes | FBX, Any | 3D model in FBX format. Model should have less than 100000 faces. |
+| `prompt` | STRING | Yes | | Describes texture editing. Supports up to 1024 UTF-8 characters. |
+| `seed` | INT | No | 0 to 2147483647 | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) |
+
+**Note:** The `model_3d` input must be a file in the FBX format. Other 3D file formats are not supported by this node.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `GLB` | FILE3D | The processed 3D model in GLB format. |
+| `FBX` | FILE3D | The processed 3D model in FBX format. |
diff --git a/built-in-nodes/TencentImageToModelNode.mdx b/built-in-nodes/TencentImageToModelNode.mdx
new file mode 100644
index 000000000..adf995b69
--- /dev/null
+++ b/built-in-nodes/TencentImageToModelNode.mdx
@@ -0,0 +1,35 @@
+---
+title: "TencentImageToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TencentImageToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TencentImageToModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentImageToModelNode/en.md)
+
+This node uses Tencent's Hunyuan3D Pro API to generate a 3D model from one or more input images. It processes the images, sends them to the API, and returns the generated 3D model files in GLB and OBJ formats.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"3.0"`<br />`"3.1"` | The version of the Hunyuan3D model to use. The LowPoly option is unavailable for the `3.1` model. |
+| `image` | IMAGE | Yes | - | The primary input image used to generate the 3D model. |
+| `image_left` | IMAGE | No | - | An optional image of the object's left side for multi-view generation. |
+| `image_right` | IMAGE | No | - | An optional image of the object's right side for multi-view generation. |
+| `image_back` | IMAGE | No | - | An optional image of the object's back side for multi-view generation. |
+| `face_count` | INT | Yes | 40000 - 1500000 | The target number of faces for the generated 3D model (default: 500000). |
+| `generate_type` | DYNAMICCOMBO | Yes | `"Normal"`<br />`"LowPoly"`<br />`"Geometry"` | The type of 3D model to generate. Selecting an option reveals additional related parameters. |
+| `generate_type.pbr` | BOOLEAN | No | - | Enables Physically Based Rendering (PBR) material generation. This parameter is only visible when `generate_type` is set to "Normal" or "LowPoly" (default: False). |
+| `generate_type.polygon_type` | COMBO | No | `"triangle"`<br />`"quadrilateral"` | The type of polygon to use for the mesh. This parameter is only visible when `generate_type` is set to "LowPoly". |
+| `seed` | INT | Yes | 0 - 2147483647 | A seed value for the generation process. Seed controls whether the node should re-run; results are non-deterministic regardless of seed (default: 0). |
+
+**Note:** All input images must have a minimum width and height of 128 pixels.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | A legacy output for backward compatibility. |
+| `GLB` | FILE3DGLB | The generated 3D model in the GLB (Binary GL Transmission Format) file format. |
+| `OBJ` | FILE3DOBJ | The generated 3D model in the OBJ (Wavefront) file format. |
diff --git a/built-in-nodes/TencentModelTo3DUVNode.mdx b/built-in-nodes/TencentModelTo3DUVNode.mdx
new file mode 100644
index 000000000..76eda7a5d
--- /dev/null
+++ b/built-in-nodes/TencentModelTo3DUVNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "TencentModelTo3DUVNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TencentModelTo3DUVNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TencentModelTo3DUVNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentModelTo3DUVNode/en.md)
+
+This node uses the Tencent Hunyuan3D API to perform UV unfolding on a 3D model. It takes a 3D model file as input, sends it to the API for processing, and returns the processed model in OBJ and FBX formats along with a generated UV texture image.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_3d` | FILE3D | Yes | GLB<br />OBJ<br />FBX | Input 3D model (GLB, OBJ, or FBX). The model must have less than 30000 faces. |
+| `seed` | INT | No | 0 to 2147483647 | A seed value (default: 1). This controls whether the node should re-run, but results are non-deterministic regardless of the seed value. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `OBJ` | FILE3D | The processed 3D model file in OBJ format. |
+| `FBX` | FILE3D | The processed 3D model file in FBX format. |
+| `Image` | IMAGE | The generated UV texture image. |
diff --git a/built-in-nodes/TencentTextToModelNode.mdx b/built-in-nodes/TencentTextToModelNode.mdx
new file mode 100644
index 000000000..706c22912
--- /dev/null
+++ b/built-in-nodes/TencentTextToModelNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "TencentTextToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TencentTextToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TencentTextToModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentTextToModelNode/en.md)
+
+This node uses Tencent's Hunyuan3D Pro API to generate a 3D model from a text description. It sends a request to create a generation task, polls for the result, and downloads the final model files in GLB and OBJ formats.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"3.0"`<br />`"3.1"` | The version of the Hunyuan3D model to use. The LowPoly option is unavailable for the `3.1` model. |
+| `prompt` | STRING | Yes | - | The text description of the 3D model to generate. Supports up to 1024 characters. |
+| `face_count` | INT | Yes | 40000 - 1500000 | The target number of faces for the generated 3D model. Default: 500000. |
+| `generate_type` | DYNAMICCOMBO | Yes | `"Normal"`<br />`"LowPoly"`<br />`"Geometry"` | The type of 3D model to generate. The available options and their associated parameters are:<br />- **Normal**: Generates a standard model. Includes a `pbr` parameter (default: `False`).<br />- **LowPoly**: Generates a low-polygon model. Includes `polygon_type` (`"triangle"` or `"quadrilateral"`) and `pbr` (default: `False`) parameters.<br />- **Geometry**: Generates a geometry-only model. |
+| `seed` | INT | No | 0 - 2147483647 | A seed value for the generation. Results are non-deterministic regardless of seed. Setting a new seed controls whether the node should re-run. Default: 0. |
+
+**Note:** The `generate_type` parameter is dynamic. Selecting `"LowPoly"` will reveal additional inputs for `polygon_type` and `pbr`. Selecting `"Normal"` will reveal an input for `pbr`. Selecting `"Geometry"` will not reveal any additional inputs.
+
+**Constraint:** The `"LowPoly"` generate type cannot be used with the `"3.1"` model.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | A legacy output for backward compatibility. |
+| `GLB` | FILE3DGLB | The generated 3D model in the GLB file format. |
+| `OBJ` | FILE3DOBJ | The generated 3D model in the OBJ file format. |
diff --git a/built-in-nodes/TerminalLog.mdx b/built-in-nodes/TerminalLog.mdx
new file mode 100644
index 000000000..644be6c2b
--- /dev/null
+++ b/built-in-nodes/TerminalLog.mdx
@@ -0,0 +1,9 @@
+---
+title: "TerminalLog - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TerminalLog node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TerminalLog"
+icon: "circle"
+mode: wide
+---
+Terminal Log (Manager) node is primarily used to display the running information of ComfyUI in the terminal within the ComfyUI interface. To use it, you need to set the `mode` to **logging** mode. This will allow it to record corresponding log information during the image generation task. If the `mode` is set to **stop** mode, it will not record log information.
+When you access and use ComfyUI via remote connections or local area network connections, Terminal Log (Manager) node becomes particularly useful. It allows you to directly view error messages from the CMD within the ComfyUI interface, making it easier to understand the current status of ComfyUI's operation.
diff --git a/built-in-nodes/TextEncodeAceStepAudio.mdx b/built-in-nodes/TextEncodeAceStepAudio.mdx
new file mode 100644
index 000000000..37587de7c
--- /dev/null
+++ b/built-in-nodes/TextEncodeAceStepAudio.mdx
@@ -0,0 +1,25 @@
+---
+title: "TextEncodeAceStepAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeAceStepAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeAceStepAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeAceStepAudio/en.md)
+
+The TextEncodeAceStepAudio node processes text inputs for audio conditioning by combining tags and lyrics into tokens, then encoding them with adjustable lyrics strength. It takes a CLIP model along with text descriptions and lyrics, tokenizes them together, and generates conditioning data suitable for audio generation tasks. The node allows fine-tuning the influence of lyrics through a strength parameter that controls their impact on the final output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | - | The CLIP model used for tokenization and encoding |
+| `tags` | STRING | Yes | - | Text tags or descriptions for audio conditioning (supports multiline input and dynamic prompts) |
+| `lyrics` | STRING | Yes | - | Lyrics text for audio conditioning (supports multiline input and dynamic prompts) |
+| `lyrics_strength` | FLOAT | No | 0.0 - 10.0 | Controls the strength of lyrics influence on the conditioning output (default: 1.0, step: 0.01) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | The encoded conditioning data containing processed text tokens with applied lyrics strength |
diff --git a/built-in-nodes/TextEncodeAceStepAudio1.5.mdx b/built-in-nodes/TextEncodeAceStepAudio1.5.mdx
new file mode 100644
index 000000000..0748d6aed
--- /dev/null
+++ b/built-in-nodes/TextEncodeAceStepAudio1.5.mdx
@@ -0,0 +1,35 @@
+---
+title: "TextEncodeAceStepAudio1.5 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeAceStepAudio1.5 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeAceStepAudio1.5"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeAceStepAudio1.5/en.md)
+
+The TextEncodeAceStepAudio1.5 node prepares text and audio-related metadata for use with the AceStepAudio 1.5 model. It takes descriptive tags, lyrics, and musical parameters, then uses a CLIP model to convert them into a conditioning format suitable for audio generation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | N/A | The CLIP model used to tokenize and encode the input text. |
+| `tags` | STRING | Yes | N/A | Descriptive tags for the audio, such as genre, mood, or instruments. Supports multiline input and dynamic prompts. |
+| `lyrics` | STRING | Yes | N/A | The lyrics for the audio track. Supports multiline input and dynamic prompts. |
+| `seed` | INT | No | 0 to 18446744073709551615 | A random seed value for reproducible generation. Has a control_after_generate widget. Default: 0. |
+| `bpm` | INT | No | 10 to 300 | The beats per minute (BPM) for the generated audio. Default: 120. |
+| `duration` | FLOAT | No | 0.0 to 2000.0 | The desired duration of the audio in seconds. Default: 120.0. |
+| `timesignature` | COMBO | No | `"2"`<br />`"3"`<br />`"4"`<br />`"6"` | The musical time signature. |
+| `language` | COMBO | No | `"en"`<br />`"ja"`<br />`"zh"`<br />`"es"`<br />`"de"`<br />`"fr"`<br />`"pt"`<br />`"ru"`<br />`"it"`<br />`"nl"`<br />`"pl"`<br />`"tr"`<br />`"vi"`<br />`"cs"`<br />`"fa"`<br />`"id"`<br />`"ko"`<br />`"uk"`<br />`"hu"`<br />`"ar"`<br />`"sv"`<br />`"ro"`<br />`"el"` | The language of the input text. |
+| `keyscale` | COMBO | No | `"C major"`<br />`"C minor"`<br />`"C# major"`<br />`"C# minor"`<br />`"Db major"`<br />`"Db minor"`<br />`"D major"`<br />`"D minor"`<br />`"D# major"`<br />`"D# minor"`<br />`"Eb major"`<br />`"Eb minor"`<br />`"E major"`<br />`"E minor"`<br />`"F major"`<br />`"F minor"`<br />`"F# major"`<br />`"F# minor"`<br />`"Gb major"`<br />`"Gb minor"`<br />`"G major"`<br />`"G minor"`<br />`"G# major"`<br />`"G# minor"`<br />`"Ab major"`<br />`"Ab minor"`<br />`"A major"`<br />`"A minor"`<br />`"A# major"`<br />`"A# minor"`<br />`"Bb major"`<br />`"Bb minor"`<br />`"B major"`<br />`"B minor"` | The musical key and scale (major or minor). |
+| `generate_audio_codes` | BOOLEAN | No | N/A | Enable the LLM that generates audio codes. This can be slow but will increase the quality of the generated audio. Turn this off if you are giving the model an audio reference. Default: True. |
+| `cfg_scale` | FLOAT | No | 0.0 to 100.0 | The classifier-free guidance scale. Higher values make the output more closely follow the prompt. Default: 2.0. |
+| `temperature` | FLOAT | No | 0.0 to 2.0 | A sampling temperature. Lower values make the output more deterministic. Default: 0.85. |
+| `top_p` | FLOAT | No | 0.0 to 2000.0 | The nucleus sampling probability (top-p). Default: 0.9. |
+| `top_k` | INT | No | 0 to 100 | The number of highest probability tokens to consider (top-k). Default: 0. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The conditioning data, which contains the encoded text and audio parameters for the AceStepAudio 1.5 model. |
diff --git a/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx b/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx
new file mode 100644
index 000000000..c5a3c0948
--- /dev/null
+++ b/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx
@@ -0,0 +1,25 @@
+---
+title: "TextEncodeHunyuanVideo_ImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeHunyuanVideo_ImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeHunyuanVideo_ImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeHunyuanVideo_ImageToVideo/en.md)
+
+The TextEncodeHunyuanVideo_ImageToVideo node creates conditioning data for video generation by combining text prompts with image embeddings. It uses a CLIP model to process both the text input and visual information from a CLIP vision output, then generates tokens that blend these two sources according to the specified image interleave setting.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | - | The CLIP model used for tokenization and encoding |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | Yes | - | The visual embeddings from a CLIP vision model that provide image context |
+| `prompt` | STRING | Yes | - | The text description to guide the video generation, supports multiline input and dynamic prompts |
+| `image_interleave` | INT | Yes | 1-512 | How much the image influences things vs the text prompt. Higher number means more influence from the text prompt. (default: 2) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The conditioning data that combines text and image information for video generation |
diff --git a/built-in-nodes/TextEncodeQwenImageEdit.mdx b/built-in-nodes/TextEncodeQwenImageEdit.mdx
new file mode 100644
index 000000000..7c7e1fd75
--- /dev/null
+++ b/built-in-nodes/TextEncodeQwenImageEdit.mdx
@@ -0,0 +1,27 @@
+---
+title: "TextEncodeQwenImageEdit - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeQwenImageEdit node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeQwenImageEdit"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeQwenImageEdit/en.md)
+
+The TextEncodeQwenImageEdit node processes text prompts and optional images to generate conditioning data for image generation or editing. It uses a CLIP model to tokenize the input and can optionally encode reference images using a VAE to create reference latents. When an image is provided, it automatically resizes the image to maintain consistent processing dimensions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | - | The CLIP model used for text and image tokenization |
+| `prompt` | STRING | Yes | - | Text prompt for conditioning generation, supports multiline input and dynamic prompts |
+| `vae` | VAE | No | - | Optional VAE model for encoding reference images into latents |
+| `image` | IMAGE | No | - | Optional input image for reference or editing purposes |
+
+**Note:** When both `image` and `vae` are provided, the node encodes the image into reference latents and attaches them to the conditioning output. The image is automatically resized to maintain a consistent processing scale of approximately 1024x1024 pixels.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | Conditioning data containing text tokens and optional reference latents for image generation |
diff --git a/built-in-nodes/TextEncodeQwenImageEditPlus.mdx b/built-in-nodes/TextEncodeQwenImageEditPlus.mdx
new file mode 100644
index 000000000..f8d733224
--- /dev/null
+++ b/built-in-nodes/TextEncodeQwenImageEditPlus.mdx
@@ -0,0 +1,29 @@
+---
+title: "TextEncodeQwenImageEditPlus - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeQwenImageEditPlus node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeQwenImageEditPlus"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeQwenImageEditPlus/en.md)
+
+The TextEncodeQwenImageEditPlus node processes text prompts and optional images to generate conditioning data for image generation or editing tasks. It uses a specialized template to analyze input images and understand how text instructions should modify them, then encodes this information for use in subsequent generation steps. The node can handle up to three input images and optionally generate reference latents when a VAE is provided.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | - | The CLIP model used for tokenization and encoding |
+| `prompt` | STRING | Yes | - | Text instruction describing the desired image modification (supports multiline input and dynamic prompts) |
+| `vae` | VAE | No | - | Optional VAE model for generating reference latents from input images |
+| `image1` | IMAGE | No | - | First optional input image for analysis and modification |
+| `image2` | IMAGE | No | - | Second optional input image for analysis and modification |
+| `image3` | IMAGE | No | - | Third optional input image for analysis and modification |
+
+**Note:** When a VAE is provided, the node generates reference latents from all input images. The node can process up to three images simultaneously, and images are automatically resized to appropriate dimensions for processing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | Encoded conditioning data containing text tokens and optional reference latents for image generation |
diff --git a/built-in-nodes/TextEncodeZImageOmni.mdx b/built-in-nodes/TextEncodeZImageOmni.mdx
new file mode 100644
index 000000000..b388a4b44
--- /dev/null
+++ b/built-in-nodes/TextEncodeZImageOmni.mdx
@@ -0,0 +1,31 @@
+---
+title: "TextEncodeZImageOmni - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeZImageOmni node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeZImageOmni"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeZImageOmni/en.md)
+
+The TextEncodeZImageOmni node is an advanced conditioning node that encodes a text prompt along with optional reference images into a conditioning format suitable for image generation models. It can process up to three images, optionally encoding them with a vision encoder and/or a VAE to produce reference latents, and integrates these visual references with the text prompt using a specific template structure.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | | The CLIP model used for tokenizing and encoding the text prompt. |
+| `image_encoder` | CLIPVision | No | | An optional vision encoder model. If provided, it will be used to encode the input images, and the resulting embeddings will be added to the conditioning. |
+| `prompt` | STRING | Yes | | The text prompt to be encoded. This field supports multiline input and dynamic prompts. |
+| `auto_resize_images` | BOOLEAN | No | | When enabled (default: True), input images will be automatically resized based on their pixel area before being passed to the VAE for encoding. |
+| `vae` | VAE | No | | An optional VAE model. If provided, it will be used to encode the input images into latent representations, which are added to the conditioning as reference latents. |
+| `image1` | IMAGE | No | | The first optional reference image. |
+| `image2` | IMAGE | No | | The second optional reference image. |
+| `image3` | IMAGE | No | | The third optional reference image. |
+
+**Note:** The node can accept a maximum of three images (`image1`, `image2`, `image3`). The `image_encoder` and `vae` inputs are only utilized if at least one image is provided. When `auto_resize_images` is True and a `vae` is connected, images are resized to have a total pixel area close to 1024x1024 before encoding.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | The final conditioning output, which contains the encoded text prompt and may include encoded image embeddings and/or reference latents if images were provided. |
diff --git a/built-in-nodes/TextGenerate.mdx b/built-in-nodes/TextGenerate.mdx
new file mode 100644
index 000000000..a2d5ec595
--- /dev/null
+++ b/built-in-nodes/TextGenerate.mdx
@@ -0,0 +1,34 @@
+---
+title: "TextGenerate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextGenerate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextGenerate"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerate/en.md)
+
+The TextGenerate node uses a CLIP model to create text based on a user's prompt. It can optionally use an image as a visual reference to guide the text generation. You can control the length of the output and choose whether to use random sampling with various settings or to generate text without sampling.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | N/A | The CLIP model used for tokenizing the prompt and generating text. |
+| `prompt` | STRING | Yes | N/A | The text prompt that guides the generation. This field supports multiple lines and dynamic prompts. The default value is an empty string. |
+| `image` | IMAGE | No | N/A | An optional image that can be used alongside the text prompt to influence the generated text. |
+| `max_length` | INT | Yes | 1 to 2048 | The maximum number of tokens the model will generate. The default value is 256. |
+| `sampling_mode` | COMBO | Yes | `"on"`<br />`"off"` | Controls whether random sampling is used during text generation. When set to "on", additional parameters for controlling the sampling become available. The default is "on". |
+| `temperature` | FLOAT | No | 0.01 to 2.0 | Controls the randomness of the output. Lower values make the output more predictable, higher values make it more creative. This parameter is only available when `sampling_mode` is "on". The default value is 0.7. |
+| `top_k` | INT | No | 0 to 1000 | Limits the sampling pool to the top K most likely next tokens. A value of 0 disables this filter. This parameter is only available when `sampling_mode` is "on". The default value is 64. |
+| `top_p` | FLOAT | No | 0.0 to 1.0 | Uses nucleus sampling, limiting choices to tokens whose cumulative probability is less than this value. This parameter is only available when `sampling_mode` is "on". The default value is 0.95. |
+| `min_p` | FLOAT | No | 0.0 to 1.0 | Sets a minimum probability threshold for tokens to be considered. This parameter is only available when `sampling_mode` is "on". The default value is 0.05. |
+| `repetition_penalty` | FLOAT | No | 0.0 to 5.0 | Penalizes tokens that have already been generated to reduce repetition. A value of 1.0 applies no penalty. This parameter is only available when `sampling_mode` is "on". The default value is 1.05. |
+| `seed` | INT | No | 0 to 18446744073709551615 | A number used to initialize the random number generator for reproducible results when sampling is "on". The default value is 0. |
+
+**Note:** The parameters `temperature`, `top_k`, `top_p`, `min_p`, `repetition_penalty`, and `seed` are only active and visible in the node interface when the `sampling_mode` is set to "on".
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `generated_text` | STRING | The text generated by the model based on the input prompt and optional image. |
diff --git a/built-in-nodes/TextGenerateLTX2Prompt.mdx b/built-in-nodes/TextGenerateLTX2Prompt.mdx
new file mode 100644
index 000000000..b93494ea5
--- /dev/null
+++ b/built-in-nodes/TextGenerateLTX2Prompt.mdx
@@ -0,0 +1,28 @@
+---
+title: "TextGenerateLTX2Prompt - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextGenerateLTX2Prompt node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextGenerateLTX2Prompt"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerateLTX2Prompt/en.md)
+
+The TextGenerateLTX2Prompt node is a specialized version of a text generation node. It takes a user's text prompt and automatically formats it with specific system instructions before sending it to a language model for enhancement or completion. The node can operate in two modes: text-only or with an image reference, using different system prompts for each case.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | Yes | | The CLIP model used for text encoding. |
+| `prompt` | STRING | Yes | | The raw text input from the user that will be enhanced or completed. |
+| `max_length` | INT | Yes | | The maximum number of tokens the language model is allowed to generate. |
+| `sampling_mode` | COMBO | Yes | `"greedy"`<br />`"top_k"`<br />`"top_p"`<br />`"temperature"` | The sampling strategy used to select the next token during text generation. |
+| `image` | IMAGE | No | | An optional input image. When provided, the node uses a different system prompt that includes a placeholder for image context. |
+
+**Note:** The behavior of the node changes based on the presence of the `image` input. If an image is provided, the generated prompt will be formatted for an image-to-video task. If no image is provided, the formatting will be for a text-to-video task.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | STRING | The enhanced or completed text string generated by the language model. |
diff --git a/built-in-nodes/TextToLowercase.mdx b/built-in-nodes/TextToLowercase.mdx
new file mode 100644
index 000000000..17dc30871
--- /dev/null
+++ b/built-in-nodes/TextToLowercase.mdx
@@ -0,0 +1,22 @@
+---
+title: "TextToLowercase - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextToLowercase node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextToLowercase"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToLowercase/en.md)
+
+The Text to Lowercase node takes a text string as input and converts all of its characters to lowercase. It is a simple utility for standardizing text case.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | Yes | Any text string | The text string to be converted to lowercase. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `text` | STRING | The input text with all characters converted to lowercase. |
diff --git a/built-in-nodes/TextToUppercase.mdx b/built-in-nodes/TextToUppercase.mdx
new file mode 100644
index 000000000..9c6a91184
--- /dev/null
+++ b/built-in-nodes/TextToUppercase.mdx
@@ -0,0 +1,22 @@
+---
+title: "TextToUppercase - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextToUppercase node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextToUppercase"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToUppercase/en.md)
+
+The Text to Uppercase node takes a text input and converts all of its characters to uppercase. It is a simple text processing utility that modifies the case of the provided string.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | Yes | N/A | The text string to be converted to uppercase. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `text` | STRING | The resulting text with all characters converted to uppercase. |
diff --git a/built-in-nodes/ThresholdMask.mdx b/built-in-nodes/ThresholdMask.mdx
new file mode 100644
index 000000000..f7e43a20d
--- /dev/null
+++ b/built-in-nodes/ThresholdMask.mdx
@@ -0,0 +1,23 @@
+---
+title: "ThresholdMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ThresholdMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ThresholdMask"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ThresholdMask/en.md)
+
+The ThresholdMask node converts a mask to a binary mask by applying a threshold value. It compares each pixel in the input mask against the specified threshold value and creates a new mask where pixels above the threshold become 1 (white) and pixels below or equal to the threshold become 0 (black).
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `mask` | MASK | Yes | - | The input mask to be processed |
+| `value` | FLOAT | Yes | 0.0 - 1.0 | The threshold value for binarization (default: 0.5) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `mask` | MASK | The resulting binary mask after thresholding |
diff --git a/built-in-nodes/TomePatchModel.mdx b/built-in-nodes/TomePatchModel.mdx
new file mode 100644
index 000000000..3350ca68b
--- /dev/null
+++ b/built-in-nodes/TomePatchModel.mdx
@@ -0,0 +1,23 @@
+---
+title: "TomePatchModel - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TomePatchModel node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TomePatchModel"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TomePatchModel/en.md)
+
+The TomePatchModel node applies Token Merging (ToMe) to a diffusion model to reduce computational requirements during inference. It works by selectively merging similar tokens in the attention mechanism, allowing the model to process fewer tokens while maintaining image quality. This technique helps speed up generation without significant quality loss.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The diffusion model to apply token merging to |
+| `ratio` | FLOAT | No | 0.0 - 1.0 | The ratio of tokens to merge (default: 0.3) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with token merging applied |
diff --git a/built-in-nodes/TopazImageEnhance.mdx b/built-in-nodes/TopazImageEnhance.mdx
new file mode 100644
index 000000000..11c41b67b
--- /dev/null
+++ b/built-in-nodes/TopazImageEnhance.mdx
@@ -0,0 +1,36 @@
+---
+title: "TopazImageEnhance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TopazImageEnhance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TopazImageEnhance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazImageEnhance/en.md)
+
+The Topaz Image Enhance node provides industry-standard upscaling and image enhancement. It processes a single input image using a cloud-based AI model to improve quality, detail, and resolution. The node offers fine-grained control over the enhancement process, including options for creative guidance, subject focus, and facial preservation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"Reimagine"` | The AI model to use for image enhancement. |
+| `image` | IMAGE | Yes | - | The input image to be enhanced. Only one image is supported. |
+| `prompt` | STRING | No | - | An optional text prompt for creative upscaling guidance (default: empty). |
+| `subject_detection` | COMBO | No | `"All"`<br />`"Foreground"`<br />`"Background"` | Controls which part of the image the enhancement focuses on (default: "All"). |
+| `face_enhancement` | BOOLEAN | No | - | Enable to enhance faces if they are present in the image (default: True). |
+| `face_enhancement_creativity` | FLOAT | No | 0.0 - 1.0 | Sets the creativity level for face enhancement (default: 0.0). |
+| `face_enhancement_strength` | FLOAT | No | 0.0 - 1.0 | Controls how sharp enhanced faces are relative to the background (default: 1.0). |
+| `crop_to_fill` | BOOLEAN | No | - | By default, the image is letterboxed when the output aspect ratio differs. Enable to crop the image to fill the output dimensions instead (default: False). |
+| `output_width` | INT | No | 0 - 32000 | The desired width of the output image. A value of 0 means it will be calculated automatically, usually based on the original size or the `output_height` if specified (default: 0). |
+| `output_height` | INT | No | 0 - 32000 | The desired height of the output image. A value of 0 means it will be calculated automatically, usually based on the original size or the `output_width` if specified (default: 0). |
+| `creativity` | INT | No | 1 - 9 | Controls the overall creativity level of the enhancement (default: 3). |
+| `face_preservation` | BOOLEAN | No | - | Preserve the facial identity of subjects in the image (default: True). |
+| `color_preservation` | BOOLEAN | No | - | Preserve the original colors of the input image (default: True). |
+
+**Note:** This node can only process a single input image. Providing a batch of multiple images will result in an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The enhanced output image. |
diff --git a/built-in-nodes/TopazVideoEnhance.mdx b/built-in-nodes/TopazVideoEnhance.mdx
new file mode 100644
index 000000000..f48203a07
--- /dev/null
+++ b/built-in-nodes/TopazVideoEnhance.mdx
@@ -0,0 +1,35 @@
+---
+title: "TopazVideoEnhance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TopazVideoEnhance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TopazVideoEnhance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazVideoEnhance/en.md)
+
+The Topaz Video Enhance node uses an external API to improve video quality. It can upscale video resolution, increase frame rate through interpolation, and apply compression. The node processes an input MP4 video and returns an enhanced version based on the selected settings.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | - | The input video file to be enhanced. |
+| `upscaler_enabled` | BOOLEAN | Yes | - | Enables or disables the video upscaling feature (default: True). |
+| `upscaler_model` | COMBO | Yes | `"Proteus v3"`<br />`"Artemis v13"`<br />`"Artemis v14"`<br />`"Artemis v15"`<br />`"Gaia v6"`<br />`"Theia v3"`<br />`"Starlight (Astra) Creative"`<br />`"Starlight (Astra) Optimized"`<br />`"Starlight (Astra) Balanced"`<br />`"Starlight (Astra) Quality"`<br />`"Starlight (Astra) Speed"` | The AI model used for upscaling the video. |
+| `upscaler_resolution` | COMBO | Yes | `"FullHD (1080p)"`<br />`"4K (2160p)"` | The target resolution for the upscaled video. |
+| `upscaler_creativity` | COMBO | No | `"low"`<br />`"middle"`<br />`"high"` | Creativity level (applies only to Starlight (Astra) Creative). (default: "low") |
+| `interpolation_enabled` | BOOLEAN | No | - | Enables or disables the frame interpolation feature (default: False). |
+| `interpolation_model` | COMBO | No | `"apo-8"` | The model used for frame interpolation (default: "apo-8"). |
+| `interpolation_slowmo` | INT | No | 1 to 16 | Slow-motion factor applied to the input video. For example, 2 makes the output twice as slow and doubles the duration. (default: 1) |
+| `interpolation_frame_rate` | INT | No | 15 to 240 | Output frame rate. (default: 60) |
+| `interpolation_duplicate` | BOOLEAN | No | - | Analyze the input for duplicate frames and remove them. (default: False) |
+| `interpolation_duplicate_threshold` | FLOAT | No | 0.001 to 0.1 | Detection sensitivity for duplicate frames. (default: 0.01) |
+| `dynamic_compression_level` | COMBO | No | `"Low"`<br />`"Mid"`<br />`"High"` | CQP level. (default: "Low") |
+
+**Note:** At least one enhancement feature must be enabled. The node will raise an error if both `upscaler_enabled` and `interpolation_enabled` are set to `False`. The input video must be in MP4 format.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The enhanced output video file. |
diff --git a/built-in-nodes/TorchCompileModel.mdx b/built-in-nodes/TorchCompileModel.mdx
new file mode 100644
index 000000000..0fd5ee6ae
--- /dev/null
+++ b/built-in-nodes/TorchCompileModel.mdx
@@ -0,0 +1,23 @@
+---
+title: "TorchCompileModel - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TorchCompileModel node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TorchCompileModel"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TorchCompileModel/en.md)
+
+The TorchCompileModel node applies PyTorch compilation to a model to optimize its performance. It creates a copy of the input model and wraps it with PyTorch's compilation functionality using the specified backend. This can improve the model's execution speed during inference.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to be compiled and optimized |
+| `backend` | STRING | Yes | "inductor"<br />"cudagraphs" | The PyTorch compilation backend to use for optimization |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The compiled model with PyTorch compilation applied |
diff --git a/built-in-nodes/TrainLoraNode.mdx b/built-in-nodes/TrainLoraNode.mdx
new file mode 100644
index 000000000..5f3543fe0
--- /dev/null
+++ b/built-in-nodes/TrainLoraNode.mdx
@@ -0,0 +1,42 @@
+---
+title: "TrainLoraNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TrainLoraNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TrainLoraNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrainLoraNode/en.md)
+
+The TrainLoraNode creates and trains a LoRA (Low-Rank Adaptation) model on a diffusion model using provided latents and conditioning data. It allows you to fine-tune a model with custom training parameters, optimizers, and loss functions. The node outputs the trained model with LoRA applied, the LoRA weights, training loss metrics, and the total training steps completed.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to train the LoRA on. |
+| `latents` | LATENT | Yes | - | The Latents to use for training, serve as dataset/input of the model. |
+| `positive` | CONDITIONING | Yes | - | The positive conditioning to use for training. |
+| `batch_size` | INT | Yes | 1-10000 | The batch size to use for training (default: 1). |
+| `grad_accumulation_steps` | INT | Yes | 1-1024 | The number of gradient accumulation steps to use for training (default: 1). |
+| `steps` | INT | Yes | 1-100000 | The number of steps to train the LoRA for (default: 16). |
+| `learning_rate` | FLOAT | Yes | 0.0000001-1.0 | The learning rate to use for training (default: 0.0005). |
+| `rank` | INT | Yes | 1-128 | The rank of the LoRA layers (default: 8). |
+| `optimizer` | COMBO | Yes | "AdamW"<br />"Adam"<br />"SGD"<br />"RMSprop" | The optimizer to use for training (default: "AdamW"). |
+| `loss_function` | COMBO | Yes | "MSE"<br />"L1"<br />"Huber"<br />"SmoothL1" | The loss function to use for training (default: "MSE"). |
+| `seed` | INT | Yes | 0-18446744073709551615 | The seed to use for training (used in generator for LoRA weight initialization and noise sampling) (default: 0). |
+| `training_dtype` | COMBO | Yes | "bf16"<br />"fp32" | The dtype to use for training (default: "bf16"). |
+| `lora_dtype` | COMBO | Yes | "bf16"<br />"fp32" | The dtype to use for lora (default: "bf16"). |
+| `algorithm` | COMBO | Yes | Multiple options available | The algorithm to use for training. |
+| `gradient_checkpointing` | BOOLEAN | Yes | - | Use gradient checkpointing for training (default: True). |
+| `existing_lora` | COMBO | Yes | Multiple options available | The existing LoRA to append to. Set to None for new LoRA (default: "[None]"). |
+
+**Note:** The number of positive conditioning inputs must match the number of latent images. If only one positive conditioning is provided with multiple images, it will be automatically repeated for all images.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_with_lora` | MODEL | The original model with the trained LoRA applied. |
+| `lora` | LORA_MODEL | The trained LoRA weights that can be saved or applied to other models. |
+| `loss` | LOSS_MAP | A dictionary containing the training loss values over time. |
+| `steps` | INT | The total number of training steps completed (including any previous steps from existing LoRA). |
diff --git a/built-in-nodes/TrimAudioDuration.mdx b/built-in-nodes/TrimAudioDuration.mdx
new file mode 100644
index 000000000..b0f92edfe
--- /dev/null
+++ b/built-in-nodes/TrimAudioDuration.mdx
@@ -0,0 +1,26 @@
+---
+title: "TrimAudioDuration - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TrimAudioDuration node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TrimAudioDuration"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrimAudioDuration/en.md)
+
+The TrimAudioDuration node allows you to cut a specific time segment from an audio file. You can specify when to start the trim and how long the resulting audio clip should be. The node works by converting time values to audio frame positions and extracting the corresponding portion of the audio waveform.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The audio input to be trimmed |
+| `start_index` | FLOAT | Yes | -0xffffffffffffffff to 0xffffffffffffffff | Start time in seconds, can be negative to count from the end (supports sub-seconds). Default: 0.0 |
+| `duration` | FLOAT | Yes | 0.0 to 0xffffffffffffffff | Duration in seconds. Default: 60.0 |
+
+**Note:** The start time must be less than the end time and within the audio length. Negative start values count backwards from the end of the audio.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | The trimmed audio segment with the specified start time and duration |
diff --git a/built-in-nodes/TrimVideoLatent.mdx b/built-in-nodes/TrimVideoLatent.mdx
new file mode 100644
index 000000000..34d7cb0f9
--- /dev/null
+++ b/built-in-nodes/TrimVideoLatent.mdx
@@ -0,0 +1,23 @@
+---
+title: "TrimVideoLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TrimVideoLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TrimVideoLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrimVideoLatent/en.md)
+
+The TrimVideoLatent node removes frames from the beginning of a video latent representation. It takes a latent video sample and trims off a specified number of frames from the start, returning the remaining portion of the video. This allows you to shorten video sequences by removing the initial frames.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | - | The input latent video representation containing the video frames to be trimmed |
+| `trim_amount` | INT | No | 0 to 99999 | The number of frames to remove from the beginning of the video (default: 0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | LATENT | The trimmed latent video representation with the specified number of frames removed from the beginning |
diff --git a/built-in-nodes/TripleCLIPLoader.mdx b/built-in-nodes/TripleCLIPLoader.mdx
new file mode 100644
index 000000000..b34235e79
--- /dev/null
+++ b/built-in-nodes/TripleCLIPLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "TripleCLIPLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripleCLIPLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripleCLIPLoader"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripleCLIPLoader/en.md)
+
+The TripleCLIPLoader node loads three different text encoder models simultaneously and combines them into a single CLIP model. This is useful for advanced text encoding scenarios where multiple text encoders are needed, such as in SD3 workflows that require clip-l, clip-g, and t5 models working together.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `clip_name1` | STRING | Yes | Multiple options available | The first text encoder model to load from the available text encoders |
+| `clip_name2` | STRING | Yes | Multiple options available | The second text encoder model to load from the available text encoders |
+| `clip_name3` | STRING | Yes | Multiple options available | The third text encoder model to load from the available text encoders |
+
+**Note:** All three text encoder parameters must be selected from the available text encoder models in your system. The node will load all three models and combine them into a single CLIP model for processing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | A combined CLIP model containing all three loaded text encoders |
diff --git a/built-in-nodes/TripoConversionNode.mdx b/built-in-nodes/TripoConversionNode.mdx
new file mode 100644
index 000000000..7016066fd
--- /dev/null
+++ b/built-in-nodes/TripoConversionNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "TripoConversionNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoConversionNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoConversionNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoConversionNode/en.md)
+
+The TripoConversionNode converts 3D models between different file formats using the Tripo API. It takes a task ID from a previous Tripo operation and converts the resulting model to your desired format with various export options.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `original_model_task_id` | MODEL_TASK_ID,RIG_TASK_ID,RETARGET_TASK_ID | Yes | MODEL_TASK_ID<br />RIG_TASK_ID<br />RETARGET_TASK_ID | The task ID from a previous Tripo operation (model generation, rigging, or retargeting) |
+| `format` | COMBO | Yes | GLTF<br />USDZ<br />FBX<br />OBJ<br />STL<br />3MF | The target file format for the converted 3D model |
+| `quad` | BOOLEAN | No | True/False | Whether to convert triangles to quads (default: False) |
+| `face_limit` | INT | No | -1 to 500000 | Maximum number of faces in the output model, use -1 for no limit (default: -1) |
+| `texture_size` | INT | No | 128 to 4096 | Size of output textures in pixels (default: 4096) |
+| `texture_format` | COMBO | No | BMP<br />DPX<br />HDR<br />JPEG<br />OPEN_EXR<br />PNG<br />TARGA<br />TIFF<br />WEBP | Format for exported textures (default: JPEG) |
+
+**Note:** The `original_model_task_id` must be a valid task ID from a previous Tripo operation (model generation, rigging, or retargeting).
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| *No named outputs* | - | This node processes the conversion asynchronously and returns the result through the Tripo API system |
diff --git a/built-in-nodes/TripoImageToModelNode.mdx b/built-in-nodes/TripoImageToModelNode.mdx
new file mode 100644
index 000000000..692bffc1e
--- /dev/null
+++ b/built-in-nodes/TripoImageToModelNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "TripoImageToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoImageToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoImageToModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImageToModelNode/en.md)
+
+Generates 3D models synchronously based on a single image using Tripo's API. This node takes an input image and converts it into a 3D model with various customization options for texture, quality, and model properties.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | Input image used to generate the 3D model |
+| `model_version` | COMBO | No | Multiple options available | The version of the Tripo model to use for generation |
+| `style` | COMBO | No | Multiple options available | Style setting for the generated model (default: "None") |
+| `texture` | BOOLEAN | No | - | Whether to generate textures for the model (default: True) |
+| `pbr` | BOOLEAN | No | - | Whether to use Physically Based Rendering (default: True) |
+| `model_seed` | INT | No | - | Random seed for model generation (default: 42) |
+| `orientation` | COMBO | No | Multiple options available | Orientation setting for the generated model |
+| `texture_seed` | INT | No | - | Random seed for texture generation (default: 42) |
+| `texture_quality` | COMBO | No | "standard"<br />"detailed" | Quality level for texture generation (default: "standard") |
+| `texture_alignment` | COMBO | No | "original_image"<br />"geometry" | Alignment method for texture mapping (default: "original_image") |
+| `face_limit` | INT | No | -1 to 500000 | Maximum number of faces in the generated model, -1 for no limit (default: -1) |
+| `quad` | BOOLEAN | No | - | Whether to use quadrilateral faces instead of triangles (default: False) |
+
+**Note:** The `image` parameter is required and must be provided for the node to function. If no image is provided, the node will raise a RuntimeError.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The generated 3D model file |
+| `model task_id` | MODEL_TASK_ID | The task ID for tracking the model generation process |
diff --git a/built-in-nodes/TripoMultiviewToModelNode.mdx b/built-in-nodes/TripoMultiviewToModelNode.mdx
new file mode 100644
index 000000000..f6d33ca92
--- /dev/null
+++ b/built-in-nodes/TripoMultiviewToModelNode.mdx
@@ -0,0 +1,38 @@
+---
+title: "TripoMultiviewToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoMultiviewToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoMultiviewToModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoMultiviewToModelNode/en.md)
+
+This node generates 3D models synchronously using Tripo's API by processing up to four images showing different views of an object. It requires a front image and at least one additional view (left, back, or right) to create a complete 3D model with texture and material options.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | Yes | - | Front view image of the object (required) |
+| `image_left` | IMAGE | No | - | Left view image of the object |
+| `image_back` | IMAGE | No | - | Back view image of the object |
+| `image_right` | IMAGE | No | - | Right view image of the object |
+| `model_version` | COMBO | No | Multiple options available | Tripo model version to use for generation |
+| `orientation` | COMBO | No | Multiple options available | Orientation setting for the 3D model |
+| `texture` | BOOLEAN | No | - | Whether to generate textures for the model (default: True) |
+| `pbr` | BOOLEAN | No | - | Whether to generate PBR (Physically Based Rendering) materials (default: True) |
+| `model_seed` | INT | No | - | Random seed for model generation (default: 42) |
+| `texture_seed` | INT | No | - | Random seed for texture generation (default: 42) |
+| `texture_quality` | COMBO | No | "standard"<br />"detailed" | Quality level for texture generation (default: "standard") |
+| `texture_alignment` | COMBO | No | "original_image"<br />"geometry" | Method for aligning textures to the model (default: "original_image") |
+| `face_limit` | INT | No | -1 to 500000 | Maximum number of faces in the generated model, -1 for no limit (default: -1) |
+| `quad` | BOOLEAN | No | - | Whether to generate quad-based geometry instead of triangles (default: False) |
+
+**Note:** The front image (`image`) is always required. At least one additional view image (`image_left`, `image_back`, or `image_right`) must be provided for multiview processing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | File path or identifier for the generated 3D model |
+| `model task_id` | MODEL_TASK_ID | Task identifier for tracking the model generation process |
diff --git a/built-in-nodes/TripoRefineNode.mdx b/built-in-nodes/TripoRefineNode.mdx
new file mode 100644
index 000000000..0d2bf4166
--- /dev/null
+++ b/built-in-nodes/TripoRefineNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "TripoRefineNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoRefineNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoRefineNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/en.md)
+
+The TripoRefineNode refines draft 3D models created specifically by v1.4 Tripo models. It takes a model task ID and processes it through the Tripo API to generate an improved version of the model. This node is designed to work exclusively with draft models produced by Tripo v1.4 models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_task_id` | MODEL_TASK_ID | Yes | - | Must be a v1.4 Tripo model |
+| `auth_token` | AUTH_TOKEN_COMFY_ORG | No | - | Authentication token for Comfy.org API |
+| `comfy_api_key` | API_KEY_COMFY_ORG | No | - | API key for Comfy.org services |
+| `unique_id` | UNIQUE_ID | No | - | Unique identifier for the operation |
+
+**Note:** This node only accepts draft models created by Tripo v1.4 models. Using models from other versions may result in errors.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The file path or reference to the refined model |
+| `model task_id` | MODEL_TASK_ID | The task identifier for the refined model operation |
diff --git a/built-in-nodes/TripoRetargetNode.mdx b/built-in-nodes/TripoRetargetNode.mdx
new file mode 100644
index 000000000..fb3f44659
--- /dev/null
+++ b/built-in-nodes/TripoRetargetNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "TripoRetargetNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoRetargetNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoRetargetNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRetargetNode/en.md)
+
+The TripoRetargetNode applies predefined animations to 3D character models by retargeting motion data. It takes a previously processed 3D model and applies one of several preset animations, generating an animated 3D model file as output. The node communicates with the Tripo API to process the animation retargeting operation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `original_model_task_id` | RIG_TASK_ID | Yes | - | The task ID of the previously processed 3D model to apply animation to |
+| `animation` | STRING | Yes | "preset:idle"<br />"preset:walk"<br />"preset:climb"<br />"preset:jump"<br />"preset:slash"<br />"preset:shoot"<br />"preset:hurt"<br />"preset:fall"<br />"preset:turn" | The animation preset to apply to the 3D model |
+| `auth_token` | AUTH_TOKEN_COMFY_ORG | No | - | Authentication token for Comfy.org API access |
+| `comfy_api_key` | API_KEY_COMFY_ORG | No | - | API key for Comfy.org service access |
+| `unique_id` | UNIQUE_ID | No | - | Unique identifier for tracking the operation |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The generated animated 3D model file |
+| `retarget task_id` | RETARGET_TASK_ID | The task ID for tracking the retargeting operation |
diff --git a/built-in-nodes/TripoRigNode.mdx b/built-in-nodes/TripoRigNode.mdx
new file mode 100644
index 000000000..b22230580
--- /dev/null
+++ b/built-in-nodes/TripoRigNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "TripoRigNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoRigNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoRigNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRigNode/en.md)
+
+The TripoRigNode generates a rigged 3D model from an original model task ID. It sends a request to the Tripo API to create an animated rig in GLB format using the Tripo specification, then polls the API until the rig generation task is complete.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `original_model_task_id` | MODEL_TASK_ID | Yes | - | The task ID of the original 3D model to be rigged |
+| `auth_token` | AUTH_TOKEN_COMFY_ORG | No | - | Authentication token for Comfy.org API access |
+| `comfy_api_key` | API_KEY_COMFY_ORG | No | - | API key for Comfy.org service authentication |
+| `unique_id` | UNIQUE_ID | No | - | Unique identifier for tracking the operation |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The generated rigged 3D model file |
+| `rig task_id` | RIG_TASK_ID | The task ID for tracking the rig generation process |
diff --git a/built-in-nodes/TripoTextToModelNode.mdx b/built-in-nodes/TripoTextToModelNode.mdx
new file mode 100644
index 000000000..81ccfe4ac
--- /dev/null
+++ b/built-in-nodes/TripoTextToModelNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "TripoTextToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoTextToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoTextToModelNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextToModelNode/en.md)
+
+Generates 3D models synchronously based on a text prompt using Tripo's API. This node takes a text description and creates a 3D model with optional texture and material properties.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text description for generating the 3D model (multiline input) |
+| `negative_prompt` | STRING | No | - | Text description of what to avoid in the generated model (multiline input) |
+| `model_version` | COMBO | No | Multiple options available | The version of the Tripo model to use for generation |
+| `style` | COMBO | No | Multiple options available | Style setting for the generated model (default: "None") |
+| `texture` | BOOLEAN | No | - | Whether to generate textures for the model (default: True) |
+| `pbr` | BOOLEAN | No | - | Whether to generate PBR (Physically Based Rendering) materials (default: True) |
+| `image_seed` | INT | No | - | Random seed for image generation (default: 42) |
+| `model_seed` | INT | No | - | Random seed for model generation (default: 42) |
+| `texture_seed` | INT | No | - | Random seed for texture generation (default: 42) |
+| `texture_quality` | COMBO | No | "standard"<br />"detailed" | Quality level for texture generation (default: "standard") |
+| `face_limit` | INT | No | -1 to 500000 | Maximum number of faces in the generated model, -1 for no limit (default: -1) |
+| `quad` | BOOLEAN | No | - | Whether to generate quad-based geometry instead of triangles (default: False) |
+
+**Note:** The `prompt` parameter is required and cannot be empty. If no prompt is provided, the node will raise an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The generated 3D model file |
+| `model task_id` | MODEL_TASK_ID | The unique task identifier for the model generation process |
diff --git a/built-in-nodes/TripoTextureNode.mdx b/built-in-nodes/TripoTextureNode.mdx
new file mode 100644
index 000000000..7360daeed
--- /dev/null
+++ b/built-in-nodes/TripoTextureNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "TripoTextureNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoTextureNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoTextureNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextureNode/en.md)
+
+The TripoTextureNode generates textured 3D models using the Tripo API. It takes a model task ID and applies texture generation with various options including PBR materials, texture quality settings, and alignment methods. The node communicates with the Tripo API to process the texture generation request and returns the resulting model file and task ID.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model_task_id` | MODEL_TASK_ID | Yes | - | The task ID of the model to apply textures to |
+| `texture` | BOOLEAN | No | - | Whether to generate textures (default: True) |
+| `pbr` | BOOLEAN | No | - | Whether to generate PBR (Physically Based Rendering) materials (default: True) |
+| `texture_seed` | INT | No | - | Random seed for texture generation (default: 42) |
+| `texture_quality` | COMBO | No | "standard"<br />"detailed" | Quality level for texture generation (default: "standard") |
+| `texture_alignment` | COMBO | No | "original_image"<br />"geometry" | Method for aligning textures (default: "original_image") |
+
+*Note: This node requires authentication tokens and API keys which are automatically handled by the system.*
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model_file` | STRING | The generated model file with applied textures |
+| `model task_id` | MODEL_TASK_ID | The task ID for tracking the texture generation process |
diff --git a/built-in-nodes/TruncateText.mdx b/built-in-nodes/TruncateText.mdx
new file mode 100644
index 000000000..d38a1e23c
--- /dev/null
+++ b/built-in-nodes/TruncateText.mdx
@@ -0,0 +1,23 @@
+---
+title: "TruncateText - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TruncateText node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TruncateText"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TruncateText/en.md)
+
+This node shortens text by cutting it off at a specified maximum length. It takes any input text and returns only the first part, up to the number of characters you set. It is a simple way to ensure text does not exceed a certain size.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | Yes | N/A | The text string to be truncated. |
+| `max_length` | INT | No | 1 to 10000 | Maximum text length. The text will be cut off after this many characters (default: 77). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `string` | STRING | The truncated text, containing only the first `max_length` characters from the input. |
diff --git a/built-in-nodes/UNETLoader.mdx b/built-in-nodes/UNETLoader.mdx
new file mode 100644
index 000000000..a59d62043
--- /dev/null
+++ b/built-in-nodes/UNETLoader.mdx
@@ -0,0 +1,24 @@
+---
+title: "UNETLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UNETLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UNETLoader"
+icon: "circle"
+mode: wide
+---
+
+The UNETLoader node is designed for loading U-Net models by name, facilitating the use of pre-trained U-Net architectures within the system.
+
+This node will detect models located in the `ComfyUI/models/diffusion_models` folder.
+
+## Inputs
+
+| Parameter   | Data Type | Description |
+|-------------|--------------|-------------|
+| `unet_name` | COMBO[STRING] | Specifies the name of the U-Net model to be loaded. This name is used to locate the model within a predefined directory structure, enabling the dynamic loading of different U-Net models. |
+| `weight_dtype` | ... | 🚧  fp8_e4m3fn fp9_e5m2  |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | Returns the loaded U-Net model, allowing it to be utilized for further processing or inference within the system. |
diff --git a/built-in-nodes/UNetCrossAttentionMultiply.mdx b/built-in-nodes/UNetCrossAttentionMultiply.mdx
new file mode 100644
index 000000000..60245b8a1
--- /dev/null
+++ b/built-in-nodes/UNetCrossAttentionMultiply.mdx
@@ -0,0 +1,26 @@
+---
+title: "UNetCrossAttentionMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UNetCrossAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UNetCrossAttentionMultiply"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/UNetCrossAttentionMultiply/en.md)
+
+The UNetCrossAttentionMultiply node applies multiplication factors to the cross-attention mechanism in a UNet model. It allows you to scale the query, key, value, and output components of the cross-attention layers to experiment with different attention behaviors and effects.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The UNet model to modify with attention scaling factors |
+| `q` | FLOAT | No | 0.0 - 10.0 | Scaling factor for query components in cross-attention (default: 1.0) |
+| `k` | FLOAT | No | 0.0 - 10.0 | Scaling factor for key components in cross-attention (default: 1.0) |
+| `v` | FLOAT | No | 0.0 - 10.0 | Scaling factor for value components in cross-attention (default: 1.0) |
+| `out` | FLOAT | No | 0.0 - 10.0 | Scaling factor for output components in cross-attention (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified UNet model with scaled cross-attention components |
diff --git a/built-in-nodes/UNetSelfAttentionMultiply.mdx b/built-in-nodes/UNetSelfAttentionMultiply.mdx
new file mode 100644
index 000000000..329cded1f
--- /dev/null
+++ b/built-in-nodes/UNetSelfAttentionMultiply.mdx
@@ -0,0 +1,26 @@
+---
+title: "UNetSelfAttentionMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UNetSelfAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UNetSelfAttentionMultiply"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/UNetSelfAttentionMultiply/en.md)
+
+The UNetSelfAttentionMultiply node applies multiplication factors to the query, key, value, and output components of the self-attention mechanism in a UNet model. It allows you to scale different parts of the attention computation to experiment with how attention weights affect the model's behavior.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The UNet model to modify with attention scaling factors |
+| `q` | FLOAT | No | 0.0 - 10.0 | Multiplication factor for query component (default: 1.0) |
+| `k` | FLOAT | No | 0.0 - 10.0 | Multiplication factor for key component (default: 1.0) |
+| `v` | FLOAT | No | 0.0 - 10.0 | Multiplication factor for value component (default: 1.0) |
+| `out` | FLOAT | No | 0.0 - 10.0 | Multiplication factor for output component (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | The modified UNet model with scaled attention components |
diff --git a/built-in-nodes/UNetTemporalAttentionMultiply.mdx b/built-in-nodes/UNetTemporalAttentionMultiply.mdx
new file mode 100644
index 000000000..58366afb4
--- /dev/null
+++ b/built-in-nodes/UNetTemporalAttentionMultiply.mdx
@@ -0,0 +1,26 @@
+---
+title: "UNetTemporalAttentionMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UNetTemporalAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UNetTemporalAttentionMultiply"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/UNetTemporalAttentionMultiply/en.md)
+
+The UNetTemporalAttentionMultiply node applies multiplication factors to different types of attention mechanisms in a temporal UNet model. It modifies the model by adjusting the weights of self-attention and cross-attention layers, distinguishing between structural and temporal components. This allows fine-tuning of how much influence each attention type has on the model's output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The input model to modify with attention multipliers |
+| `self_structural` | FLOAT | No | 0.0 - 10.0 | Multiplier for self-attention structural components (default: 1.0) |
+| `self_temporal` | FLOAT | No | 0.0 - 10.0 | Multiplier for self-attention temporal components (default: 1.0) |
+| `cross_structural` | FLOAT | No | 0.0 - 10.0 | Multiplier for cross-attention structural components (default: 1.0) |
+| `cross_temporal` | FLOAT | No | 0.0 - 10.0 | Multiplier for cross-attention temporal components (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with adjusted attention weights |
diff --git a/built-in-nodes/USOStyleReference.mdx b/built-in-nodes/USOStyleReference.mdx
new file mode 100644
index 000000000..19aa932b4
--- /dev/null
+++ b/built-in-nodes/USOStyleReference.mdx
@@ -0,0 +1,24 @@
+---
+title: "USOStyleReference - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the USOStyleReference node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "USOStyleReference"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/USOStyleReference/en.md)
+
+The USOStyleReference node applies style reference patches to models using encoded image features from CLIP vision output. It creates a modified version of the input model by incorporating style information extracted from visual inputs, enabling style transfer or reference-based generation capabilities.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The base model to apply the style reference patch to |
+| `model_patch` | MODEL_PATCH | Yes | - | The model patch containing style reference information |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | Yes | - | The encoded visual features extracted from CLIP vision processing |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with applied style reference patches |
diff --git a/built-in-nodes/UpscaleModelLoader.mdx b/built-in-nodes/UpscaleModelLoader.mdx
new file mode 100644
index 000000000..fdc1e3794
--- /dev/null
+++ b/built-in-nodes/UpscaleModelLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "UpscaleModelLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UpscaleModelLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UpscaleModelLoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/upscale_models` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+The UpscaleModelLoader node is designed for loading upscale models from a specified directory. It facilitates the retrieval and preparation of upscale models for image upscaling tasks, ensuring that the models are correctly loaded and configured for evaluation.
+
+## Inputs
+
+| Field          | Comfy dtype       | Description                                                                       |
+|----------------|-------------------|-----------------------------------------------------------------------------------|
+| `model_name`   | `COMBO[STRING]`    | Specifies the name of the upscale model to be loaded, identifying and retrieving the correct model file from the upscale models directory. |
+
+## Outputs
+
+| Field            | Comfy dtype         | Description                                                              |
+|-------------------|---------------------|--------------------------------------------------------------------------|
+| `upscale_model`  | `UPSCALE_MODEL`     | Returns the loaded and prepared upscale model, ready for use in image upscaling tasks. |
diff --git a/built-in-nodes/VAEDecode.mdx b/built-in-nodes/VAEDecode.mdx
new file mode 100644
index 000000000..0646d63f1
--- /dev/null
+++ b/built-in-nodes/VAEDecode.mdx
@@ -0,0 +1,22 @@
+---
+title: "VAEDecode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecode"
+icon: "circle"
+mode: wide
+---
+
+The VAEDecode node is designed for decoding latent representations into images using a specified Variational Autoencoder (VAE). It serves the purpose of generating images from compressed data representations, facilitating the reconstruction of images from their latent space encodings.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `samples` | `LATENT`    | The 'samples' parameter represents the latent representations to be decoded into images. It is crucial for the decoding process as it provides the compressed data from which the images are reconstructed. |
+| `vae`     | VAE       | The 'vae' parameter specifies the Variational Autoencoder model to be used for decoding the latent representations into images. It is essential for determining the decoding mechanism and the quality of the reconstructed images. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `image`   | `IMAGE`     | The output is an image reconstructed from the provided latent representation using the specified VAE model. |
diff --git a/built-in-nodes/VAEDecodeAudio.mdx b/built-in-nodes/VAEDecodeAudio.mdx
new file mode 100644
index 000000000..c26ac1baa
--- /dev/null
+++ b/built-in-nodes/VAEDecodeAudio.mdx
@@ -0,0 +1,23 @@
+---
+title: "VAEDecodeAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecodeAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecodeAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeAudio/en.md)
+
+The VAEDecodeAudio node converts latent representations back into audio waveforms using a Variational Autoencoder. It takes encoded audio samples and processes them through the VAE to reconstruct the original audio, applying normalization to ensure consistent output levels. The resulting audio is returned with a standard sample rate of 44100 Hz.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | - | The encoded audio samples in latent space that will be decoded back to audio waveform |
+| `vae` | VAE | Yes | - | The Variational Autoencoder model used to decode the latent samples into audio |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | The decoded audio waveform with normalized volume and 44100 Hz sample rate |
diff --git a/built-in-nodes/VAEDecodeAudioTiled.mdx b/built-in-nodes/VAEDecodeAudioTiled.mdx
new file mode 100644
index 000000000..a9d7e72f3
--- /dev/null
+++ b/built-in-nodes/VAEDecodeAudioTiled.mdx
@@ -0,0 +1,25 @@
+---
+title: "VAEDecodeAudioTiled - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecodeAudioTiled node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecodeAudioTiled"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeAudioTiled/en.md)
+
+This node converts a compressed audio representation (latent samples) back into an audio waveform using a Variational Autoencoder (VAE). It processes the data in smaller, overlapping sections (tiles) to manage memory usage, making it suitable for handling longer audio sequences.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | N/A | The compressed latent representation of the audio to be decoded. |
+| `vae` | VAE | Yes | N/A | The Variational Autoencoder model used to perform the decoding. |
+| `tile_size` | INT | No | 32 to 8192 | The size of each processing tile. The audio is decoded in sections of this length to conserve memory (default: 512). |
+| `overlap` | INT | No | 0 to 1024 | The number of samples that adjacent tiles overlap. This helps to reduce artifacts at the boundaries between tiles (default: 64). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | AUDIO | The decoded audio waveform. |
diff --git a/built-in-nodes/VAEDecodeHunyuan3D.mdx b/built-in-nodes/VAEDecodeHunyuan3D.mdx
new file mode 100644
index 000000000..ae4326f4b
--- /dev/null
+++ b/built-in-nodes/VAEDecodeHunyuan3D.mdx
@@ -0,0 +1,25 @@
+---
+title: "VAEDecodeHunyuan3D - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecodeHunyuan3D node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecodeHunyuan3D"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeHunyuan3D/en.md)
+
+The VAEDecodeHunyuan3D node converts latent representations into 3D voxel data using a VAE decoder. It processes the latent samples through the VAE model with configurable chunking and resolution settings to generate volumetric data suitable for 3D applications.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | - | The latent representation to be decoded into 3D voxel data |
+| `vae` | VAE | Yes | - | The VAE model used for decoding the latent samples |
+| `num_chunks` | INT | Yes | 1000-500000 | The number of chunks to split the processing into for memory management (default: 8000) |
+| `octree_resolution` | INT | Yes | 16-512 | The resolution of the octree structure used for 3D voxel generation (default: 256) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `voxels` | VOXEL | The generated 3D voxel data from the decoded latent representation |
diff --git a/built-in-nodes/VAEDecodeTiled.mdx b/built-in-nodes/VAEDecodeTiled.mdx
new file mode 100644
index 000000000..ee83c6c94
--- /dev/null
+++ b/built-in-nodes/VAEDecodeTiled.mdx
@@ -0,0 +1,29 @@
+---
+title: "VAEDecodeTiled - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecodeTiled node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecodeTiled"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeTiled/en.md)
+
+The VAEDecodeTiled node decodes latent representations into images using a tiled approach to handle large images efficiently. It processes the input in smaller tiles to manage memory usage while maintaining image quality. The node also supports video VAEs by processing temporal frames in chunks with overlap for smooth transitions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | Yes | - | The latent representation to be decoded into images |
+| `vae` | VAE | Yes | - | The VAE model used for decoding the latent samples |
+| `tile_size` | INT | Yes | 64-4096 (step: 32) | The size of each tile for processing (default: 512) |
+| `overlap` | INT | Yes | 0-4096 (step: 32) | The amount of overlap between adjacent tiles (default: 64) |
+| `temporal_size` | INT | Yes | 8-4096 (step: 4) | Only used for video VAEs: Amount of frames to decode at a time (default: 64) |
+| `temporal_overlap` | INT | Yes | 4-4096 (step: 4) | Only used for video VAEs: Amount of frames to overlap (default: 8) |
+
+**Note:** The node automatically adjusts overlap values if they exceed practical limits. If `tile_size` is less than 4 times the `overlap`, the overlap is reduced to one quarter of the tile size. Similarly, if `temporal_size` is less than twice the `temporal_overlap`, the temporal overlap is halved.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The decoded image or images generated from the latent representation |
diff --git a/built-in-nodes/VAEEncode.mdx b/built-in-nodes/VAEEncode.mdx
new file mode 100644
index 000000000..e0d6d4370
--- /dev/null
+++ b/built-in-nodes/VAEEncode.mdx
@@ -0,0 +1,22 @@
+---
+title: "VAEEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEEncode"
+icon: "circle"
+mode: wide
+---
+
+This node is designed for encoding images into a latent space representation using a specified VAE model. It abstracts the complexity of the encoding process, providing a straightforward way to transform images into their latent representations.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `pixels`  | `IMAGE`     | The 'pixels' parameter represents the image data to be encoded into the latent space. It plays a crucial role in determining the output latent representation by serving as the direct input for the encoding process. |
+| `vae`     | VAE       | The 'vae' parameter specifies the Variational Autoencoder model to be used for encoding the image data into latent space. It is essential for defining the encoding mechanism and characteristics of the generated latent representation. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output is a latent space representation of the input image, encapsulating its essential features in a compressed form. |
diff --git a/built-in-nodes/VAEEncodeAudio.mdx b/built-in-nodes/VAEEncodeAudio.mdx
new file mode 100644
index 000000000..d2124c1eb
--- /dev/null
+++ b/built-in-nodes/VAEEncodeAudio.mdx
@@ -0,0 +1,25 @@
+---
+title: "VAEEncodeAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEEncodeAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEEncodeAudio"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEEncodeAudio/en.md)
+
+The VAEEncodeAudio node converts audio data into a latent representation using a Variational Autoencoder (VAE). It takes audio input and processes it through the VAE to generate compressed latent samples that can be used for further audio generation or manipulation tasks. The node automatically resamples audio to 44100 Hz if needed before encoding.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | Yes | - | The audio data to encode, containing waveform and sample rate information |
+| `vae` | VAE | Yes | - | The Variational Autoencoder model used to encode the audio into latent space |
+
+**Note:** The audio input is automatically resampled to 44100 Hz if the original sample rate differs from this value.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | The encoded audio representation in latent space, containing compressed samples |
diff --git a/built-in-nodes/VAEEncodeForInpaint.mdx b/built-in-nodes/VAEEncodeForInpaint.mdx
new file mode 100644
index 000000000..bf0ee0dd4
--- /dev/null
+++ b/built-in-nodes/VAEEncodeForInpaint.mdx
@@ -0,0 +1,24 @@
+---
+title: "VAEEncodeForInpaint - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEEncodeForInpaint node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEEncodeForInpaint"
+icon: "circle"
+mode: wide
+---
+
+This node is designed for encoding images into a latent representation suitable for inpainting tasks, incorporating additional preprocessing steps to adjust the input image and mask for optimal encoding by the VAE model.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `pixels`  | `IMAGE`     | The input image to be encoded. This image undergoes preprocessing and resizing to match the VAE model's expected input dimensions before encoding. |
+| `vae`     | VAE       | The VAE model used for encoding the image into its latent representation. It plays a crucial role in the transformation process, determining the quality and characteristics of the output latent space. |
+| `mask`    | `MASK`      | A mask indicating the regions of the input image to be inpainted. It is used to modify the image before encoding, ensuring that the VAE focuses on the relevant areas. |
+| `grow_mask_by` | `INT` | Specifies how much to expand the inpainting mask to ensure seamless transitions in the latent space. A larger value increases the area affected by inpainting. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `latent`  | `LATENT`    | The output includes the encoded latent representation of the image and a noise mask, both crucial for subsequent inpainting tasks. |
diff --git a/built-in-nodes/VAEEncodeTiled.mdx b/built-in-nodes/VAEEncodeTiled.mdx
new file mode 100644
index 000000000..539ac53e7
--- /dev/null
+++ b/built-in-nodes/VAEEncodeTiled.mdx
@@ -0,0 +1,29 @@
+---
+title: "VAEEncodeTiled - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEEncodeTiled node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEEncodeTiled"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEEncodeTiled/en.md)
+
+The VAEEncodeTiled node processes images by breaking them into smaller tiles and encoding them using a Variational Autoencoder. This tiled approach allows handling of large images that might otherwise exceed memory limitations. The node supports both image and video VAEs, with separate tiling controls for spatial and temporal dimensions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `pixels` | IMAGE | Yes | - | The input image data to be encoded |
+| `vae` | VAE | Yes | - | The Variational Autoencoder model used for encoding |
+| `tile_size` | INT | Yes | 64-4096 (step: 64) | The size of each tile for spatial processing (default: 512) |
+| `overlap` | INT | Yes | 0-4096 (step: 32) | The amount of overlap between adjacent tiles (default: 64) |
+| `temporal_size` | INT | Yes | 8-4096 (step: 4) | Only used for video VAEs: Amount of frames to encode at a time (default: 64) |
+| `temporal_overlap` | INT | Yes | 4-4096 (step: 4) | Only used for video VAEs: Amount of frames to overlap (default: 8) |
+
+**Note:** The `temporal_size` and `temporal_overlap` parameters are only relevant when using video VAEs and have no effect on standard image VAEs.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | The encoded latent representation of the input image |
diff --git a/built-in-nodes/VAELoader.mdx b/built-in-nodes/VAELoader.mdx
new file mode 100644
index 000000000..b9450a180
--- /dev/null
+++ b/built-in-nodes/VAELoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "VAELoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAELoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAELoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/vae` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+The VAELoader node is designed for loading Variational Autoencoder (VAE) models, specifically tailored to handle both standard and approximate VAEs. It supports loading VAEs by name, including specialized handling for 'taesd' and 'taesdxl' models, and dynamically adjusts based on the VAE's specific configuration.
+
+## Inputs
+
+| Field   | Comfy dtype       | Description                                                                                   |
+|---------|-------------------|-----------------------------------------------------------------------------------------------|
+| `vae_name` | `COMBO[STRING]`    | Specifies the name of the VAE to be loaded, determining which VAE model is fetched and loaded, with support for a range of predefined VAE names including 'taesd' and 'taesdxl'. |
+
+## Outputs
+
+| Field | Data Type | Description                                                              |
+|-------|-------------|--------------------------------------------------------------------------|
+| `vae`  | `VAE`       | Returns the loaded VAE model, ready for further operations such as encoding or decoding. The output is a model object encapsulating the loaded model's state. |
diff --git a/built-in-nodes/VAESave.mdx b/built-in-nodes/VAESave.mdx
new file mode 100644
index 000000000..4e023233f
--- /dev/null
+++ b/built-in-nodes/VAESave.mdx
@@ -0,0 +1,20 @@
+---
+title: "VAESave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAESave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAESave"
+icon: "circle"
+mode: wide
+---
+
+The VAESave node is designed for saving VAE models along with their metadata, including prompts and additional PNG information, to a specified output directory. It encapsulates the functionality to serialize the model state and associated information into a file, facilitating the preservation and sharing of trained models.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `vae`     | VAE       | The VAE model to be saved. This parameter is crucial as it represents the model whose state is to be serialized and stored. |
+| `filename_prefix` | STRING   | A prefix for the filename under which the model and its metadata will be saved. This allows for organized storage and easy retrieval of models. |
+
+## Outputs
+
+The node doesn't have output types.
diff --git a/built-in-nodes/VPScheduler.mdx b/built-in-nodes/VPScheduler.mdx
new file mode 100644
index 000000000..981e0dc94
--- /dev/null
+++ b/built-in-nodes/VPScheduler.mdx
@@ -0,0 +1,24 @@
+---
+title: "VPScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VPScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VPScheduler"
+icon: "circle"
+mode: wide
+---
+
+The VPScheduler node is designed to generate a sequence of noise levels (sigmas) based on the Variance Preserving (VP) scheduling method. This sequence is crucial for guiding the denoising process in diffusion models, allowing for controlled generation of images or other data types.
+
+## Inputs
+
+| Parameter   | Data Type | Description                                                                                                                                      |
+|-------------|-------------|--------------------------------------------------------------------------------------------------------------------------------------------------|
+| `steps`     | INT         | Specifies the number of steps in the diffusion process, affecting the granularity of the generated noise levels.                              |
+| `beta_d`    | FLOAT       | Determines the overall noise level distribution, influencing the variance of the generated noise levels.                                 |
+| `beta_min`  | FLOAT       | Sets the minimum boundary for the noise level, ensuring the noise does not fall below a certain threshold.                              |
+| `eps_s`     | FLOAT       | Adjusts the starting epsilon value, fine-tuning the initial noise level in the diffusion process.                                    |
+
+## Outputs
+
+| Parameter   | Data Type | Description                                                                                   |
+|-------------|-------------|-----------------------------------------------------------------------------------------------|
+| `sigmas`    | SIGMAS      | A sequence of noise levels (sigmas) generated based on the VP scheduling method, used to guide the denoising process in diffusion models. |
diff --git a/built-in-nodes/Veo3FirstLastFrameNode.mdx b/built-in-nodes/Veo3FirstLastFrameNode.mdx
new file mode 100644
index 000000000..0b321ebd8
--- /dev/null
+++ b/built-in-nodes/Veo3FirstLastFrameNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "Veo3FirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Veo3FirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Veo3FirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3FirstLastFrameNode/en.md)
+
+The Veo3FirstLastFrameNode uses Google's Veo 3 model to generate a video. It creates a video based on a text prompt, using a provided first and last frame to guide the start and end of the sequence.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | N/A | Text description of the video (default: empty string). |
+| `negative_prompt` | STRING | No | N/A | Negative text prompt to guide what to avoid in the video (default: empty string). |
+| `resolution` | COMBO | Yes | `"720p"`<br />`"1080p"` | The resolution of the output video. |
+| `aspect_ratio` | COMBO | No | `"16:9"`<br />`"9:16"` | Aspect ratio of the output video (default: "16:9"). |
+| `duration` | INT | No | 4 to 8 | Duration of the output video in seconds (default: 8). |
+| `seed` | INT | No | 0 to 4294967295 | Seed for video generation (default: 0). |
+| `first_frame` | IMAGE | Yes | N/A | The start frame for the video. |
+| `last_frame` | IMAGE | Yes | N/A | The end frame for the video. |
+| `model` | COMBO | No | `"veo-3.1-generate"`<br />`"veo-3.1-fast-generate"` | The specific Veo 3 model to use for generation (default: "veo-3.1-fast-generate"). |
+| `generate_audio` | BOOLEAN | No | N/A | Generate audio for the video (default: True). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/Veo3VideoGenerationNode.mdx b/built-in-nodes/Veo3VideoGenerationNode.mdx
new file mode 100644
index 000000000..5bcd32551
--- /dev/null
+++ b/built-in-nodes/Veo3VideoGenerationNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "Veo3VideoGenerationNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Veo3VideoGenerationNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Veo3VideoGenerationNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3VideoGenerationNode/en.md)
+
+Generates videos from text prompts using Google's Veo 3 API. This node supports two Veo 3 models: veo-3.0-generate-001 and veo-3.0-fast-generate-001. It extends the base Veo node with Veo 3 specific features including audio generation and a fixed 8-second duration.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text description of the video (default: "") |
+| `aspect_ratio` | COMBO | Yes | "16:9"<br />"9:16" | Aspect ratio of the output video (default: "16:9") |
+| `negative_prompt` | STRING | No | - | Negative text prompt to guide what to avoid in the video (default: "") |
+| `duration_seconds` | INT | No | 8-8 | Duration of the output video in seconds (Veo 3 only supports 8 seconds) (default: 8) |
+| `enhance_prompt` | BOOLEAN | No | - | Whether to enhance the prompt with AI assistance (default: True) |
+| `person_generation` | COMBO | No | "ALLOW"<br />"BLOCK" | Whether to allow generating people in the video (default: "ALLOW") |
+| `seed` | INT | No | 0-4294967295 | Seed for video generation (0 for random) (default: 0) |
+| `image` | IMAGE | No | - | Optional reference image to guide video generation |
+| `model` | COMBO | No | "veo-3.0-generate-001"<br />"veo-3.0-fast-generate-001" | Veo 3 model to use for video generation (default: "veo-3.0-generate-001") |
+| `generate_audio` | BOOLEAN | No | - | Generate audio for the video. Supported by all Veo 3 models. (default: False) |
+
+**Note:** The `duration_seconds` parameter is fixed at 8 seconds for all Veo 3 models and cannot be changed.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/VeoVideoGenerationNode.mdx b/built-in-nodes/VeoVideoGenerationNode.mdx
new file mode 100644
index 000000000..d2e9120a6
--- /dev/null
+++ b/built-in-nodes/VeoVideoGenerationNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "VeoVideoGenerationNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VeoVideoGenerationNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VeoVideoGenerationNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VeoVideoGenerationNode/en.md)
+
+Generates videos from text prompts using Google's Veo API. This node can create videos from text descriptions and optional image inputs, with control over parameters like aspect ratio, duration, and more.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | Yes | - | Text description of the video (default: empty) |
+| `aspect_ratio` | COMBO | Yes | "16:9"<br />"9:16" | Aspect ratio of the output video (default: "16:9") |
+| `negative_prompt` | STRING | No | - | Negative text prompt to guide what to avoid in the video (default: empty) |
+| `duration_seconds` | INT | No | 5-8 | Duration of the output video in seconds (default: 5) |
+| `enhance_prompt` | BOOLEAN | No | - | Whether to enhance the prompt with AI assistance (default: True) |
+| `person_generation` | COMBO | No | "ALLOW"<br />"BLOCK" | Whether to allow generating people in the video (default: "ALLOW") |
+| `seed` | INT | No | 0-4294967295 | Seed for video generation (0 for random) (default: 0) |
+| `image` | IMAGE | No | - | Optional reference image to guide video generation |
+| `model` | COMBO | No | "veo-2.0-generate-001" | Veo 2 model to use for video generation (default: "veo-2.0-generate-001") |
+
+**Note:** The `generate_audio` parameter is only available for Veo 3.0 models and is automatically handled by the node based on the selected model.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/Video Slice.mdx b/built-in-nodes/Video Slice.mdx
new file mode 100644
index 000000000..4798f03ac
--- /dev/null
+++ b/built-in-nodes/Video Slice.mdx	
@@ -0,0 +1,25 @@
+---
+title: "Video Slice - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Video Slice node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Video Slice"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Video%20Slice/en.md)
+
+The Video Slice node allows you to extract a specific segment from a video. You can define a start time and a duration to trim the video, or simply skip the beginning frames. If the requested duration is longer than the remaining video, the node can either return what's available or raise an error.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | - | The input video to be sliced. |
+| `start_time` | FLOAT | No | -1e5 to 1e5 | The start time in seconds from which to begin the slice. A negative value will skip frames from the beginning of the video. (default: 0.0) |
+| `duration` | FLOAT | No | 0.0 and above | The length of the slice in seconds. A value of 0.0 means the node will return all video from the start time to the end. (default: 0.0) |
+| `strict_duration` | BOOLEAN | No | - | If set to True, the node will raise an error if the requested duration cannot be met (e.g., if the slice would go beyond the end of the video). If False, it will return the available video up to the end. (default: False) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The trimmed video segment. |
diff --git a/built-in-nodes/VideoLinearCFGGuidance.mdx b/built-in-nodes/VideoLinearCFGGuidance.mdx
new file mode 100644
index 000000000..195d5b0e1
--- /dev/null
+++ b/built-in-nodes/VideoLinearCFGGuidance.mdx
@@ -0,0 +1,22 @@
+---
+title: "VideoLinearCFGGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VideoLinearCFGGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VideoLinearCFGGuidance"
+icon: "circle"
+mode: wide
+---
+
+The VideoLinearCFGGuidance node applies a linear conditioning guidance scale to a video model, adjusting the influence of conditioned and unconditioned components over a specified range. This enables dynamic control over the generation process, allowing for fine-tuning of the model's output based on the desired level of conditioning.
+
+## Inputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The model parameter represents the video model to which the linear CFG guidance will be applied. It is crucial for defining the base model that will be modified with the guidance scale. |
+| `min_cfg` | `FLOAT`     | The min_cfg parameter specifies the minimum conditioning guidance scale to be applied, serving as the starting point for the linear scale adjustment. It plays a key role in determining the lower bound of the guidance scale, influencing the model's output. |
+
+## Outputs
+
+| Parameter | Data Type | Description |
+|-----------|-------------|-------------|
+| `model`   | MODEL     | The output is a modified version of the input model, with the linear CFG guidance scale applied. This adjusted model is capable of generating outputs with varying degrees of conditioning, based on the specified guidance scale. |
diff --git a/built-in-nodes/VideoTriangleCFGGuidance.mdx b/built-in-nodes/VideoTriangleCFGGuidance.mdx
new file mode 100644
index 000000000..921daa8fc
--- /dev/null
+++ b/built-in-nodes/VideoTriangleCFGGuidance.mdx
@@ -0,0 +1,23 @@
+---
+title: "VideoTriangleCFGGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VideoTriangleCFGGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VideoTriangleCFGGuidance"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VideoTriangleCFGGuidance/en.md)
+
+The VideoTriangleCFGGuidance node applies a triangular classifier-free guidance scaling pattern to video models. It modifies the conditioning scale over time using a triangular wave function that oscillates between the minimum CFG value and the original conditioning scale. This creates a dynamic guidance pattern that can help improve video generation consistency and quality.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The video model to apply triangular CFG guidance to |
+| `min_cfg` | FLOAT | Yes | 0.0 - 100.0 | The minimum CFG scale value for the triangular pattern (default: 1.0) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The modified model with triangular CFG guidance applied |
diff --git a/built-in-nodes/Vidu2ImageToVideoNode.mdx b/built-in-nodes/Vidu2ImageToVideoNode.mdx
new file mode 100644
index 000000000..05f185605
--- /dev/null
+++ b/built-in-nodes/Vidu2ImageToVideoNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "Vidu2ImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu2ImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu2ImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2ImageToVideoNode/en.md)
+
+The Vidu2 Image-to-Video Generation node creates a video sequence starting from a single input image. It uses a specified Vidu2 model to animate the scene based on an optional text prompt, controlling the video's length, resolution, and the intensity of motion.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"viduq2-pro-fast"`<br />`"viduq2-pro"`<br />`"viduq2-turbo"` | The Vidu2 model to use for video generation. Different models offer varying speed and quality trade-offs. |
+| `image` | IMAGE | Yes | - | An image to be used as the start frame of the generated video. Only one image is allowed. |
+| `prompt` | STRING | No | - | An optional text prompt for video generation (max 2000 characters). Default is an empty string. |
+| `duration` | INT | Yes | 1 to 10 | The length of the generated video in seconds. Default is 5. |
+| `seed` | INT | No | 0 to 2147483647 | A seed value for random number generation to ensure reproducible results. Default is 1. |
+| `resolution` | COMBO | Yes | `"720p"`<br />`"1080p"` | The output resolution of the generated video. |
+| `movement_amplitude` | COMBO | Yes | `"auto"`<br />`"small"`<br />`"medium"`<br />`"large"` | The movement amplitude of objects in the frame. |
+
+**Constraints:**
+
+* The `image` input must contain exactly one image.
+* The input image's aspect ratio must be between 1:4 and 4:1.
+* The `prompt` text is limited to a maximum of 2000 characters.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/Vidu2ReferenceVideoNode.mdx b/built-in-nodes/Vidu2ReferenceVideoNode.mdx
new file mode 100644
index 000000000..b634b6d18
--- /dev/null
+++ b/built-in-nodes/Vidu2ReferenceVideoNode.mdx
@@ -0,0 +1,38 @@
+---
+title: "Vidu2ReferenceVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu2ReferenceVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu2ReferenceVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2ReferenceVideoNode/en.md)
+
+The Vidu2 Reference-to-Video Generation node creates a video from a text prompt and multiple reference images. You can define up to seven subjects, each with its own set of reference images, and reference them in the prompt using `@subject{subject_id}`. The node generates a video with configurable duration, aspect ratio, and movement.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"viduq2"` | The AI model to use for video generation. |
+| `subjects` | AUTOGROW | Yes | N/A | For each subject, provide up to 3 reference images (7 images total across all subjects). Reference them in prompts via `@subject{subject_id}`. |
+| `prompt` | STRING | Yes | N/A | The text description used to guide the video generation. When the `audio` parameter is enabled, the video will include generated speech and background music based on this prompt. |
+| `audio` | BOOLEAN | No | N/A | When enabled, the video will contain generated speech and background music based on the prompt (default: `False`). |
+| `duration` | INT | No | 1 to 10 | The length of the generated video in seconds (default: `5`). |
+| `seed` | INT | No | 0 to 2147483647 | A number used to control the randomness of the generation for reproducible results (default: `1`). |
+| `aspect_ratio` | COMBO | No | `"16:9"`<br />`"9:16"`<br />`"4:3"`<br />`"3:4"`<br />`"1:1"` | The shape of the video frame. |
+| `resolution` | COMBO | No | `"720p"`<br />`"1080p"` | The pixel resolution of the output video. |
+| `movement_amplitude` | COMBO | No | `"auto"`<br />`"small"`<br />`"medium"`<br />`"large"` | Controls the movement amplitude of objects in the frame. |
+
+**Constraints:**
+
+* The `prompt` must be between 1 and 2000 characters long.
+* You can define multiple subjects, but the total number of reference images across all subjects must not exceed 7.
+* Each individual subject can have a maximum of 3 reference images.
+* Each reference image must have a width-to-height ratio between 1:4 and 4:1.
+* Each reference image must be at least 128 pixels in both width and height.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/Vidu2StartEndToVideoNode.mdx b/built-in-nodes/Vidu2StartEndToVideoNode.mdx
new file mode 100644
index 000000000..f104fa6ce
--- /dev/null
+++ b/built-in-nodes/Vidu2StartEndToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "Vidu2StartEndToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu2StartEndToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu2StartEndToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2StartEndToVideoNode/en.md)
+
+This node generates a video by interpolating between a provided start frame and an end frame, guided by a text prompt. It uses a specified Vidu model to create a smooth transition between the two images over a set duration.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"viduq2-pro-fast"`<br />`"viduq2-pro"`<br />`"viduq2-turbo"` | The Vidu model to use for video generation. |
+| `first_frame` | IMAGE | Yes | - | The starting image for the video sequence. Only a single image is allowed. |
+| `end_frame` | IMAGE | Yes | - | The ending image for the video sequence. Only a single image is allowed. |
+| `prompt` | STRING | Yes | - | A text description guiding the video generation (maximum 2000 characters). |
+| `duration` | INT | No | 2 to 8 | The length of the generated video in seconds (default: 5). |
+| `seed` | INT | No | 0 to 2147483647 | A number used to initialize the random generation for reproducible results (default: 1). |
+| `resolution` | COMBO | No | `"720p"`<br />`"1080p"` | The output resolution of the generated video. |
+| `movement_amplitude` | COMBO | No | `"auto"`<br />`"small"`<br />`"medium"`<br />`"large"` | The movement amplitude of objects in the frame. |
+
+**Note:** The `first_frame` and `end_frame` images must have similar aspect ratios. The node will validate that their aspect ratios are within a relative range of 0.8 to 1.25.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/Vidu2TextToVideoNode.mdx b/built-in-nodes/Vidu2TextToVideoNode.mdx
new file mode 100644
index 000000000..96c9e61ab
--- /dev/null
+++ b/built-in-nodes/Vidu2TextToVideoNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "Vidu2TextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu2TextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu2TextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2TextToVideoNode/en.md)
+
+The Vidu2 Text-to-Video Generation node creates a video from a text description. It connects to an external API to generate video content based on your prompt, allowing you to control the video's length, visual style, and format.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"viduq2"` | The AI model to use for video generation. Currently, only one model is available. |
+| `prompt` | STRING | Yes | - | A textual description for video generation, with a maximum length of 2000 characters. |
+| `duration` | INT | No | 1 to 10 | The length of the generated video in seconds. The value can be adjusted using a slider (default: 5). |
+| `seed` | INT | No | 0 to 2147483647 | A number used to control the randomness of the generation, allowing for reproducible results. It can be controlled after generation (default: 1). |
+| `aspect_ratio` | COMBO | No | `"16:9"`<br />`"9:16"`<br />`"3:4"`<br />`"4:3"`<br />`"1:1"` | The proportional relationship between the video's width and height. |
+| `resolution` | COMBO | No | `"720p"`<br />`"1080p"` | The pixel dimensions of the generated video. |
+| `background_music` | BOOLEAN | No | - | Whether to add background music to the generated video (default: False). |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/Vidu3ImageToVideoNode.mdx b/built-in-nodes/Vidu3ImageToVideoNode.mdx
new file mode 100644
index 000000000..66dfad604
--- /dev/null
+++ b/built-in-nodes/Vidu3ImageToVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "Vidu3ImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu3ImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu3ImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3ImageToVideoNode/en.md)
+
+The Vidu Q3 Image-to-Video Generation node creates a video sequence starting from an input image. It uses the Vidu Q3 Pro model to animate the image, optionally guided by a text prompt, and outputs a video file.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"viduq3-pro"` | Model to use for video generation. |
+| `model.resolution` | COMBO | Yes | `"720p"`<br />`"1080p"`<br />`"2K"` | Resolution of the output video. |
+| `model.duration` | INT | Yes | 1 to 16 | Duration of the output video in seconds (default: 5). |
+| `model.audio` | BOOLEAN | Yes | `True` / `False` | When enabled, outputs video with sound (including dialogue and sound effects) (default: False). |
+| `image` | IMAGE | Yes | - | An image to be used as the start frame of the generated video. |
+| `prompt` | STRING | No | - | An optional text prompt for video generation (max 2000 characters) (default: empty). |
+| `seed` | INT | No | 0 to 2147483647 | A seed value for controlling the randomness of the generation (default: 1). |
+
+**Note:** The `image` must have an aspect ratio between 1:4 and 4:1 (portrait to landscape). The `prompt` is optional but cannot exceed 2000 characters.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/Vidu3StartEndToVideoNode.mdx b/built-in-nodes/Vidu3StartEndToVideoNode.mdx
new file mode 100644
index 000000000..ccb83afe7
--- /dev/null
+++ b/built-in-nodes/Vidu3StartEndToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "Vidu3StartEndToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu3StartEndToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu3StartEndToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3StartEndToVideoNode/en.md)
+
+This node generates a video by interpolating between a provided start frame and an end frame, guided by a text prompt. It uses the Vidu Q3 model to create a seamless transition between the two images, producing a video of a specified duration and resolution.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"viduq3-pro"`<br />`"viduq3-turbo"` | The model to use for video generation. Selecting an option reveals additional configuration parameters for `resolution`, `duration`, and `audio`. |
+| `model.resolution` | COMBO | Yes | `"720p"`<br />`"1080p"` | Resolution of the output video. This parameter is revealed after selecting a `model`. |
+| `model.duration` | INT | Yes | 1 to 16 | Duration of the output video in seconds (default: 5). This parameter is revealed after selecting a `model`. |
+| `model.audio` | BOOLEAN | Yes | `True` / `False` | When enabled, outputs video with sound (including dialogue and sound effects) (default: False). This parameter is revealed after selecting a `model`. |
+| `first_frame` | IMAGE | Yes | - | The starting image for the video sequence. |
+| `end_frame` | IMAGE | Yes | - | The ending image for the video sequence. |
+| `prompt` | STRING | Yes | - | A text description guiding the video generation (maximum 2000 characters). |
+| `seed` | INT | No | 0 to 2147483647 | A seed value for controlling the randomness of the generation (default: 1). |
+
+**Note:** The `first_frame` and `end_frame` images should have similar aspect ratios for optimal results.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/Vidu3TextToVideoNode.mdx b/built-in-nodes/Vidu3TextToVideoNode.mdx
new file mode 100644
index 000000000..ea8d5d6c6
--- /dev/null
+++ b/built-in-nodes/Vidu3TextToVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "Vidu3TextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu3TextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu3TextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3TextToVideoNode/en.md)
+
+The Vidu Q3 Text-to-Video Generation node creates a video from a text description. It uses the Vidu Q3 Pro model to generate video content based on your prompt, allowing you to control the video's length, resolution, and aspect ratio.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"viduq3-pro"` | Model to use for video generation. Selecting this option reveals additional configuration parameters for aspect ratio, resolution, duration, and audio. |
+| `model.aspect_ratio` | COMBO | Yes* | `"16:9"`<br />`"9:16"`<br />`"3:4"`<br />`"4:3"`<br />`"1:1"` | The aspect ratio of the output video. This parameter is revealed when the `model` is selected. |
+| `model.resolution` | COMBO | Yes* | `"720p"`<br />`"1080p"` | Resolution of the output video. This parameter is revealed when the `model` is selected. |
+| `model.duration` | INT | Yes* | 1 to 16 | Duration of the output video in seconds (default: 5). This parameter is revealed when the `model` is selected. |
+| `model.audio` | BOOLEAN | Yes* | True/False | When enabled, outputs video with sound (including dialogue and sound effects) (default: False). This parameter is revealed when the `model` is selected. |
+| `prompt` | STRING | Yes | N/A | A textual description for video generation, with a maximum length of 2000 characters. |
+| `seed` | INT | No | 0 to 2147483647 | A seed value for controlling the randomness of the generation (default: 1). |
+
+*Note: The parameters `aspect_ratio`, `resolution`, `duration`, and `audio` are required once the `model` is selected, as they are part of its configuration.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `video` | VIDEO | The generated video file. |
diff --git a/built-in-nodes/ViduExtendVideoNode.mdx b/built-in-nodes/ViduExtendVideoNode.mdx
new file mode 100644
index 000000000..ebd6502e1
--- /dev/null
+++ b/built-in-nodes/ViduExtendVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "ViduExtendVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduExtendVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduExtendVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduExtendVideoNode/en.md)
+
+The ViduExtendVideoNode generates additional frames to extend the length of an existing video. It uses a specified AI model to create a seamless continuation based on the source video and an optional text prompt.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"viduq2-pro"`<br />`"viduq2-turbo"` | The AI model to use for video extension. Selecting a model reveals its specific duration and resolution settings. |
+| `model.duration` | INT | Yes | 1 to 7 | The duration of the extended video in seconds (default: 4). This setting appears after selecting a model. |
+| `model.resolution` | COMBO | Yes | `"720p"`<br />`"1080p"` | The resolution of the output video. This setting appears after selecting a model. |
+| `video` | VIDEO | Yes | - | The source video to extend. |
+| `prompt` | STRING | No | - | An optional text prompt to guide the content of the extended video (max 2000 characters, default: empty). |
+| `seed` | INT | No | 0 to 2147483647 | A seed value for controlling the randomness of the generation (default: 1). |
+| `end_frame` | IMAGE | No | - | An optional image to use as the target end frame for the extension. If provided, its aspect ratio must be between 1:4 and 4:1, and its dimensions must be at least 128x128 pixels. |
+
+**Note:** The source `video` must have a duration between 4 and 55 seconds.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The newly generated video file containing the extended footage. |
diff --git a/built-in-nodes/ViduImageToVideoNode.mdx b/built-in-nodes/ViduImageToVideoNode.mdx
new file mode 100644
index 000000000..70e734dc7
--- /dev/null
+++ b/built-in-nodes/ViduImageToVideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "ViduImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduImageToVideoNode/en.md)
+
+The Vidu Image To Video Generation node creates videos from a starting image and an optional text description. It uses AI models to generate video content that extends from the provided image frame. The node sends the image and parameters to an external service and returns the generated video.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `vidu_q1`<br />*Other VideoModelName options* | Model name (default: vidu_q1) |
+| `image` | IMAGE | Yes | - | An image to be used as the start frame of the generated video |
+| `prompt` | STRING | No | - | A textual description for video generation (default: empty) |
+| `duration` | INT | No | 5-5 | Duration of the output video in seconds (default: 5, fixed at 5 seconds) |
+| `seed` | INT | No | 0-2147483647 | Seed for video generation (0 for random) (default: 0) |
+| `resolution` | COMBO | No | `r_1080p`<br />*Other Resolution options* | Supported values may vary by model & duration (default: r_1080p) |
+| `movement_amplitude` | COMBO | No | `auto`<br />*Other MovementAmplitude options* | The movement amplitude of objects in the frame (default: auto) |
+
+**Constraints:**
+
+- Only one input image is allowed (cannot process multiple images)
+- The input image must have an aspect ratio between 1:4 and 4:1
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video output |
diff --git a/built-in-nodes/ViduMultiFrameVideoNode.mdx b/built-in-nodes/ViduMultiFrameVideoNode.mdx
new file mode 100644
index 000000000..969ddcc20
--- /dev/null
+++ b/built-in-nodes/ViduMultiFrameVideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "ViduMultiFrameVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduMultiFrameVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduMultiFrameVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduMultiFrameVideoNode/en.md)
+
+This node generates a video by creating transitions between multiple keyframes. It starts from an initial image and animates through a sequence of user-defined end images and prompts, producing a single video file as output.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+| :--- | :--- | :--- | :--- | :--- |
+| `model` | COMBO | Yes | `"viduq2-pro"`<br />`"viduq2-turbo"` | The Vidu model to use for video generation. |
+| `start_image` | IMAGE | Yes | - | The starting frame image. Aspect ratio must be between 1:4 and 4:1. |
+| `seed` | INT | No | 0 to 2147483647 | A seed value for random number generation to ensure reproducible results (default: 1). |
+| `resolution` | COMBO | Yes | `"720p"`<br />`"1080p"` | The resolution of the output video. |
+| `frames` | DYNAMICCOMBO | Yes | `"2"`<br />`"3"`<br />`"4"`<br />`"5"`<br />`"6"`<br />`"7"`<br />`"8"`<br />`"9"` | Number of keyframe transitions (2-9). Selecting a value dynamically reveals the required inputs for each frame. |
+
+**Frame Inputs (Dynamically Revealed):**
+When you select a value for `frames` (e.g., "3"), the node will show a corresponding set of required inputs for each transition. For each frame `i` from 1 to the selected number, you must provide:
+
+* `end_image{i}` (IMAGE): The target image for this transition. Aspect ratio must be between 1:4 and 4:1.
+* `prompt{i}` (STRING): A text description guiding the transition to this frame (maximum 2000 characters).
+* `duration{i}` (INT): The duration in seconds for this specific transition segment.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+| :--- | :--- | :--- |
+| `output` | VIDEO | The generated video file containing all the animated transitions. |
diff --git a/built-in-nodes/ViduReferenceVideoNode.mdx b/built-in-nodes/ViduReferenceVideoNode.mdx
new file mode 100644
index 000000000..7362cf0d0
--- /dev/null
+++ b/built-in-nodes/ViduReferenceVideoNode.mdx
@@ -0,0 +1,37 @@
+---
+title: "ViduReferenceVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduReferenceVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduReferenceVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduReferenceVideoNode/en.md)
+
+The Vidu Reference Video Node generates videos from multiple reference images and a text prompt. It uses AI models to create consistent video content based on the provided images and description. The node supports various video settings including duration, aspect ratio, resolution, and movement control.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"vidu_q1"` | Model name for video generation (default: "vidu_q1") |
+| `images` | IMAGE | Yes | - | Images to use as references to generate a video with consistent subjects (maximum 7 images) |
+| `prompt` | STRING | Yes | - | A textual description for video generation |
+| `duration` | INT | No | 5-5 | Duration of the output video in seconds (default: 5) |
+| `seed` | INT | No | 0-2147483647 | Seed for video generation (0 for random) (default: 0) |
+| `aspect_ratio` | COMBO | No | `"16:9"`<br />`"9:16"`<br />`"1:1"`<br />`"4:3"`<br />`"3:4"`<br />`"21:9"`<br />`"9:21"` | The aspect ratio of the output video (default: "16:9") |
+| `resolution` | COMBO | No | `"480p"`<br />`"720p"`<br />`"1080p"`<br />`"1440p"`<br />`"2160p"` | Supported values may vary by model & duration (default: "1080p") |
+| `movement_amplitude` | COMBO | No | `"auto"`<br />`"low"`<br />`"medium"`<br />`"high"` | The movement amplitude of objects in the frame (default: "auto") |
+
+**Constraints and Limitations:**
+
+- The `prompt` field is required and cannot be empty
+- Maximum of 7 images allowed for reference
+- Each image must have an aspect ratio between 1:4 and 4:1
+- Each image must have minimum dimensions of 128x128 pixels
+- Duration is fixed at 5 seconds
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video based on the reference images and prompt |
diff --git a/built-in-nodes/ViduStartEndToVideoNode.mdx b/built-in-nodes/ViduStartEndToVideoNode.mdx
new file mode 100644
index 000000000..6970c8537
--- /dev/null
+++ b/built-in-nodes/ViduStartEndToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "ViduStartEndToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduStartEndToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduStartEndToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduStartEndToVideoNode/en.md)
+
+The Vidu Start End To Video Generation node creates a video by generating frames between a starting frame and an ending frame. It uses a text prompt to guide the video generation process and supports various video models with different resolution and movement settings. The node validates that the start and end frames have compatible aspect ratios before processing.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"vidu_q1"`<br />[Other model values from VideoModelName enum] | Model name (default: "vidu_q1") |
+| `first_frame` | IMAGE | Yes | - | Start frame |
+| `end_frame` | IMAGE | Yes | - | End frame |
+| `prompt` | STRING | No | - | A textual description for video generation |
+| `duration` | INT | No | 5-5 | Duration of the output video in seconds (default: 5, fixed at 5 seconds) |
+| `seed` | INT | No | 0-2147483647 | Seed for video generation (0 for random) (default: 0) |
+| `resolution` | COMBO | No | `"1080p"`<br />[Other resolution values from Resolution enum] | Supported values may vary by model & duration (default: "1080p") |
+| `movement_amplitude` | COMBO | No | `"auto"`<br />[Other movement amplitude values from MovementAmplitude enum] | The movement amplitude of objects in the frame (default: "auto") |
+
+**Note:** The start and end frames must have compatible aspect ratios (validated with min_rel=0.8, max_rel=1.25 ratio tolerance).
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video file |
diff --git a/built-in-nodes/ViduTextToVideoNode.mdx b/built-in-nodes/ViduTextToVideoNode.mdx
new file mode 100644
index 000000000..e196c4169
--- /dev/null
+++ b/built-in-nodes/ViduTextToVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "ViduTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduTextToVideoNode/en.md)
+
+The Vidu Text To Video Generation node creates videos from text descriptions. It uses various video generation models to transform your text prompts into video content with customizable settings for duration, aspect ratio, and visual style.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `vidu_q1`<br />*Other VideoModelName options* | Model name (default: vidu_q1) |
+| `prompt` | STRING | Yes | - | A textual description for video generation |
+| `duration` | INT | No | 5-5 | Duration of the output video in seconds (default: 5) |
+| `seed` | INT | No | 0-2147483647 | Seed for video generation (0 for random) (default: 0) |
+| `aspect_ratio` | COMBO | No | `r_16_9`<br />*Other AspectRatio options* | The aspect ratio of the output video (default: r_16_9) |
+| `resolution` | COMBO | No | `r_1080p`<br />*Other Resolution options* | Supported values may vary by model & duration (default: r_1080p) |
+| `movement_amplitude` | COMBO | No | `auto`<br />*Other MovementAmplitude options* | The movement amplitude of objects in the frame (default: auto) |
+
+**Note:** The `prompt` field is required and cannot be empty. The `duration` parameter is currently fixed at 5 seconds.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video based on the text prompt |
diff --git a/built-in-nodes/VoxelToMesh.mdx b/built-in-nodes/VoxelToMesh.mdx
new file mode 100644
index 000000000..6b993060b
--- /dev/null
+++ b/built-in-nodes/VoxelToMesh.mdx
@@ -0,0 +1,24 @@
+---
+title: "VoxelToMesh - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VoxelToMesh node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VoxelToMesh"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VoxelToMesh/en.md)
+
+The VoxelToMesh node converts 3D voxel data into mesh geometry using different algorithms. It processes voxel grids and generates vertices and faces that form a 3D mesh representation. The node supports multiple conversion algorithms and allows adjusting the threshold value to control the surface extraction.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `voxel` | VOXEL | Yes | - | The input voxel data to convert to mesh geometry |
+| `algorithm` | COMBO | Yes | "surface net"<br />"basic" | The algorithm used for mesh conversion from voxel data |
+| `threshold` | FLOAT | Yes | -1.0 to 1.0 | The threshold value for surface extraction (default: 0.6) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `MESH` | MESH | The generated 3D mesh containing vertices and faces |
diff --git a/built-in-nodes/VoxelToMeshBasic.mdx b/built-in-nodes/VoxelToMeshBasic.mdx
new file mode 100644
index 000000000..5661910ba
--- /dev/null
+++ b/built-in-nodes/VoxelToMeshBasic.mdx
@@ -0,0 +1,23 @@
+---
+title: "VoxelToMeshBasic - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VoxelToMeshBasic node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VoxelToMeshBasic"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VoxelToMeshBasic/en.md)
+
+The VoxelToMeshBasic node converts 3D voxel data into mesh geometry. It processes voxel volumes by applying a threshold value to determine which parts of the volume become solid surfaces in the resulting mesh. The node outputs a complete mesh structure with vertices and faces that can be used for 3D rendering and modeling.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `voxel` | VOXEL | Yes | - | The 3D voxel data to convert into a mesh |
+| `threshold` | FLOAT | Yes | -1.0 to 1.0 | The threshold value used to determine which voxels become part of the mesh surface (default: 0.6) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `MESH` | MESH | The generated 3D mesh containing vertices and faces |
diff --git a/built-in-nodes/Wan22FunControlToVideo.mdx b/built-in-nodes/Wan22FunControlToVideo.mdx
new file mode 100644
index 000000000..7c9b32541
--- /dev/null
+++ b/built-in-nodes/Wan22FunControlToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "Wan22FunControlToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Wan22FunControlToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Wan22FunControlToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22FunControlToVideo/en.md)
+
+The Wan22FunControlToVideo node prepares conditioning and latent representations for video generation using the Wan video model architecture. It processes positive and negative conditioning inputs along with optional reference images and control videos to create the necessary latent space representations for video synthesis. The node handles spatial scaling and temporal dimensions to generate appropriate conditioning data for video models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning input for guiding the video generation |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning input for guiding the video generation |
+| `vae` | VAE | Yes | - | VAE model used for encoding images to latent space |
+| `width` | INT | No | 16 to MAX_RESOLUTION | Output video width in pixels (default: 832, step: 16) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | Output video height in pixels (default: 480, step: 16) |
+| `length` | INT | No | 1 to MAX_RESOLUTION | Number of frames in the video sequence (default: 81, step: 4) |
+| `batch_size` | INT | No | 1 to 4096 | Number of video sequences to generate (default: 1) |
+| `ref_image` | IMAGE | No | - | Optional reference image for providing visual guidance |
+| `control_video` | IMAGE | No | - | Optional control video for guiding the generation process |
+
+**Note:** The `length` parameter is processed in chunks of 4 frames, and the node automatically handles temporal scaling for the latent space. When `ref_image` is provided, it influences the conditioning through reference latents. When `control_video` is provided, it directly affects the concat latent representation used in conditioning.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Modified positive conditioning with video-specific latent data |
+| `negative` | CONDITIONING | Modified negative conditioning with video-specific latent data |
+| `latent` | LATENT | Empty latent tensor with appropriate dimensions for video generation |
diff --git a/built-in-nodes/Wan22ImageToVideoLatent.mdx b/built-in-nodes/Wan22ImageToVideoLatent.mdx
new file mode 100644
index 000000000..3e69fbdf6
--- /dev/null
+++ b/built-in-nodes/Wan22ImageToVideoLatent.mdx
@@ -0,0 +1,30 @@
+---
+title: "Wan22ImageToVideoLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Wan22ImageToVideoLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Wan22ImageToVideoLatent"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22ImageToVideoLatent/en.md)
+
+The Wan22ImageToVideoLatent node creates video latent representations from images. It generates a blank video latent space with specified dimensions and can optionally encode a starting image sequence into the beginning frames. When a start image is provided, it encodes the image into the latent space and creates a corresponding noise mask for the inpainted regions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `vae` | VAE | Yes | - | The VAE model used for encoding images into latent space |
+| `width` | INT | No | 32 to MAX_RESOLUTION | The width of the output video in pixels (default: 1280, step: 32) |
+| `height` | INT | No | 32 to MAX_RESOLUTION | The height of the output video in pixels (default: 704, step: 32) |
+| `length` | INT | No | 1 to MAX_RESOLUTION | The number of frames in the video sequence (default: 49, step: 4) |
+| `batch_size` | INT | No | 1 to 4096 | The number of batches to generate (default: 1) |
+| `start_image` | IMAGE | No | - | Optional starting image sequence to encode into the video latent |
+
+**Note:** When `start_image` is provided, the node encodes the image sequence into the beginning frames of the latent space and generates a corresponding noise mask. The width and height parameters must be divisible by 16 for proper latent space dimensions.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `samples` | LATENT | The generated video latent representation |
+| `noise_mask` | LATENT | The noise mask indicating which regions should be denoised during generation |
diff --git a/built-in-nodes/WanAnimateToVideo.mdx b/built-in-nodes/WanAnimateToVideo.mdx
new file mode 100644
index 000000000..8a11e30d9
--- /dev/null
+++ b/built-in-nodes/WanAnimateToVideo.mdx
@@ -0,0 +1,51 @@
+---
+title: "WanAnimateToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanAnimateToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanAnimateToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanAnimateToVideo/en.md)
+
+The WanAnimateToVideo node generates video content by combining multiple conditioning inputs including pose references, facial expressions, and background elements. It processes various video inputs to create coherent animated sequences while maintaining temporal consistency across frames. The node handles latent space operations and can extend existing videos by continuing motion patterns.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning for guiding the generation towards desired content |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning for steering the generation away from unwanted content |
+| `vae` | VAE | Yes | - | VAE model used for encoding and decoding image data |
+| `width` | INT | No | 16 to MAX_RESOLUTION | Output video width in pixels (default: 832, step: 16) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | Output video height in pixels (default: 480, step: 16) |
+| `length` | INT | No | 1 to MAX_RESOLUTION | Number of frames to generate (default: 77, step: 4) |
+| `batch_size` | INT | No | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | No | - | Optional CLIP vision model output for additional conditioning |
+| `reference_image` | IMAGE | No | - | Reference image used as starting point for generation |
+| `face_video` | IMAGE | No | - | Video input providing facial expression guidance |
+| `pose_video` | IMAGE | No | - | Video input providing pose and motion guidance |
+| `continue_motion_max_frames` | INT | No | 1 to MAX_RESOLUTION | Maximum number of frames to continue from previous motion (default: 5, step: 4) |
+| `background_video` | IMAGE | No | - | Background video to composite with generated content |
+| `character_mask` | MASK | No | - | Mask defining character regions for selective processing |
+| `continue_motion` | IMAGE | No | - | Previous motion sequence to continue from for temporal consistency |
+| `video_frame_offset` | INT | No | 0 to MAX_RESOLUTION | The amount of frames to seek in all the input videos. Used for generating longer videos by chunk. Connect to the video_frame_offset output of the previous node for extending a video. (default: 0, step: 1) |
+
+**Parameter Constraints:**
+
+- When `pose_video` is provided and `trim_to_pose_video` logic is active, the output length will be adjusted to match the pose video duration
+- `face_video` is automatically resized to 512x512 resolution when processed
+- `continue_motion` frames are limited by `continue_motion_max_frames` parameter
+- Input videos (`face_video`, `pose_video`, `background_video`, `character_mask`) are offset by `video_frame_offset` before processing
+- If `character_mask` contains only one frame, it will be repeated across all frames
+- When `clip_vision_output` is provided, it's applied to both positive and negative conditioning
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Modified positive conditioning with additional video context |
+| `negative` | CONDITIONING | Modified negative conditioning with additional video context |
+| `latent` | LATENT | Generated video content in latent space format |
+| `trim_latent` | INT | Latent space trimming information for downstream processing |
+| `trim_image` | INT | Image space trimming information for reference motion frames |
+| `video_frame_offset` | INT | Updated frame offset for continuing video generation in chunks |
diff --git a/built-in-nodes/WanCameraEmbedding.mdx b/built-in-nodes/WanCameraEmbedding.mdx
new file mode 100644
index 000000000..a22c98f46
--- /dev/null
+++ b/built-in-nodes/WanCameraEmbedding.mdx
@@ -0,0 +1,33 @@
+---
+title: "WanCameraEmbedding - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanCameraEmbedding node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanCameraEmbedding"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraEmbedding/en.md)
+
+The WanCameraEmbedding node generates camera trajectory embeddings using Plücker embeddings based on camera motion parameters. It creates a sequence of camera poses that simulate different camera movements and converts them into embedding tensors suitable for video generation pipelines.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `camera_pose` | COMBO | Yes | "Static"<br />"Pan Up"<br />"Pan Down"<br />"Pan Left"<br />"Pan Right"<br />"Zoom In"<br />"Zoom Out"<br />"Anti Clockwise (ACW)"<br />"ClockWise (CW)" | The type of camera movement to simulate (default: "Static") |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | The width of the output in pixels (default: 832, step: 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | The height of the output in pixels (default: 480, step: 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | The length of the camera trajectory sequence (default: 81, step: 4) |
+| `speed` | FLOAT | No | 0.0 to 10.0 | The speed of the camera movement (default: 1.0, step: 0.1) |
+| `fx` | FLOAT | No | 0.0 to 1.0 | The focal length x parameter (default: 0.5, step: 0.000000001) |
+| `fy` | FLOAT | No | 0.0 to 1.0 | The focal length y parameter (default: 0.5, step: 0.000000001) |
+| `cx` | FLOAT | No | 0.0 to 1.0 | The principal point x coordinate (default: 0.5, step: 0.01) |
+| `cy` | FLOAT | No | 0.0 to 1.0 | The principal point y coordinate (default: 0.5, step: 0.01) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `camera_embedding` | TENSOR | The generated camera embedding tensor containing the trajectory sequence |
+| `width` | INT | The width value that was used for processing |
+| `height` | INT | The height value that was used for processing |
+| `length` | INT | The length value that was used for processing |
diff --git a/built-in-nodes/WanCameraImageToVideo.mdx b/built-in-nodes/WanCameraImageToVideo.mdx
new file mode 100644
index 000000000..bdd64a608
--- /dev/null
+++ b/built-in-nodes/WanCameraImageToVideo.mdx
@@ -0,0 +1,35 @@
+---
+title: "WanCameraImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanCameraImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanCameraImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraImageToVideo/en.md)
+
+The WanCameraImageToVideo node converts images to video sequences by generating latent representations for video generation. It processes conditioning inputs and optional starting images to create video latents that can be used with video models. The node supports camera conditions and clip vision outputs for enhanced video generation control.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning prompts for video generation |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning prompts to avoid in video generation |
+| `vae` | VAE | Yes | - | VAE model for encoding images to latent space |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Output video width in pixels (default: 832, step: 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Output video height in pixels (default: 480, step: 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames in the video sequence (default: 81, step: 4) |
+| `batch_size` | INT | Yes | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | No | - | Optional CLIP vision output for additional conditioning |
+| `start_image` | IMAGE | No | - | Optional starting image to initialize the video sequence |
+| `camera_conditions` | WAN_CAMERA_EMBEDDING | No | - | Optional camera embedding conditions for video generation |
+
+**Note:** When `start_image` is provided, the node uses it to initialize the video sequence and applies masking to blend the starting frames with generated content. The `camera_conditions` and `clip_vision_output` parameters are optional but when provided, they modify the conditioning for both positive and negative prompts.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Modified positive conditioning with applied camera conditions and clip vision outputs |
+| `negative` | CONDITIONING | Modified negative conditioning with applied camera conditions and clip vision outputs |
+| `latent` | LATENT | Generated video latent representation for use with video models |
diff --git a/built-in-nodes/WanContextWindowsManual.mdx b/built-in-nodes/WanContextWindowsManual.mdx
new file mode 100644
index 000000000..e1b3b0656
--- /dev/null
+++ b/built-in-nodes/WanContextWindowsManual.mdx
@@ -0,0 +1,30 @@
+---
+title: "WanContextWindowsManual - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanContextWindowsManual node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanContextWindowsManual"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanContextWindowsManual/en.md)
+
+The WAN Context Windows (Manual) node allows you to manually configure context windows for WAN-like models with 2-dimensional processing. It applies custom context window settings during sampling by specifying the window length, overlap, scheduling method, and fusion technique. This gives you precise control over how the model processes information across different context regions.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The model to apply context windows to during sampling. |
+| `context_length` | INT | Yes | 1 to 1048576 | The length of the context window (default: 81). |
+| `context_overlap` | INT | Yes | 0 to 1048576 | The overlap of the context window (default: 30). |
+| `context_schedule` | COMBO | Yes | "static_standard"<br />"uniform_standard"<br />"uniform_looped"<br />"batched" | The stride of the context window. |
+| `context_stride` | INT | Yes | 1 to 1048576 | The stride of the context window; only applicable to uniform schedules (default: 1). |
+| `closed_loop` | BOOLEAN | Yes | - | Whether to close the context window loop; only applicable to looped schedules (default: False). |
+| `fuse_method` | COMBO | Yes | "pyramid" | The method to use to fuse the context windows (default: "pyramid"). |
+
+**Note:** The `context_stride` parameter only affects uniform schedules, and `closed_loop` only applies to looped schedules. The context length and overlap values are automatically adjusted to ensure minimum valid values during processing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The model with the applied context window configuration. |
diff --git a/built-in-nodes/WanFirstLastFrameToVideo.mdx b/built-in-nodes/WanFirstLastFrameToVideo.mdx
new file mode 100644
index 000000000..71bdd225b
--- /dev/null
+++ b/built-in-nodes/WanFirstLastFrameToVideo.mdx
@@ -0,0 +1,36 @@
+---
+title: "WanFirstLastFrameToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanFirstLastFrameToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanFirstLastFrameToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFirstLastFrameToVideo/en.md)
+
+The WanFirstLastFrameToVideo node creates video conditioning by combining start and end frames with text prompts. It generates a latent representation for video generation by encoding the first and last frames, applying masks to guide the generation process, and incorporating CLIP vision features when available. This node prepares both positive and negative conditioning for video models to generate coherent sequences between specified start and end points.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive text conditioning for guiding the video generation |
+| `negative` | CONDITIONING | Yes | - | Negative text conditioning for guiding the video generation |
+| `vae` | VAE | Yes | - | VAE model used for encoding images to latent space |
+| `width` | INT | No | 16 to MAX_RESOLUTION | Output video width (default: 832, step: 16) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | Output video height (default: 480, step: 16) |
+| `length` | INT | No | 1 to MAX_RESOLUTION | Number of frames in the video sequence (default: 81, step: 4) |
+| `batch_size` | INT | No | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `clip_vision_start_image` | CLIP_VISION_OUTPUT | No | - | CLIP vision features extracted from the start image |
+| `clip_vision_end_image` | CLIP_VISION_OUTPUT | No | - | CLIP vision features extracted from the end image |
+| `start_image` | IMAGE | No | - | Starting frame image for the video sequence |
+| `end_image` | IMAGE | No | - | Ending frame image for the video sequence |
+
+**Note:** When both `start_image` and `end_image` are provided, the node creates a video sequence that transitions between these two frames. The `clip_vision_start_image` and `clip_vision_end_image` parameters are optional but when provided, their CLIP vision features are concatenated and applied to both positive and negative conditioning.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning with applied video frame encoding and CLIP vision features |
+| `negative` | CONDITIONING | Negative conditioning with applied video frame encoding and CLIP vision features |
+| `latent` | LATENT | Empty latent tensor with dimensions matching the specified video parameters |
diff --git a/built-in-nodes/WanFunControlToVideo.mdx b/built-in-nodes/WanFunControlToVideo.mdx
new file mode 100644
index 000000000..d848c3d4a
--- /dev/null
+++ b/built-in-nodes/WanFunControlToVideo.mdx
@@ -0,0 +1,39 @@
+---
+title: "WanFunControlToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanFunControlToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanFunControlToVideo"
+icon: "circle"
+mode: wide
+---
+This node was added to support the Alibaba Wan Fun Control model for video generation, and was added after [this commit](https://github.com/comfyanonymous/ComfyUI/commit/3661c833bcc41b788a7c9f0e7bc48524f8ee5f82).
+
+- **Purpose:** Prepare the conditioning information needed for video generation, using the Wan 2.1 Fun Control model.
+
+The WanFunControlToVideo node is a ComfyUI addition designed to support Wan Fun Control models for video generation, aimed at utilizing WanFun control for video creation.
+
+This node serves as a preparation point for essential conditioning information and initializes the center point of the latent space, guiding the subsequent video generation process using the Wan 2.1 Fun model. The node's name clearly indicates its function: it accepts various inputs and converts them into a format suitable for controlling video generation within the WanFun framework.
+
+The node's position in the ComfyUI node hierarchy indicates that it operates in the early stages of the video generation pipeline, focusing on manipulating conditioning signals before actual sampling or decoding of video frames.
+
+## Inputs
+
+| Parameter Name      | Required | Data Type           | Description                                                  | Default Value |
+|:-------------------|:---------|:-------------------|:-------------------------------------------------------------|:-------------|
+| positive           | Yes      | CONDITIONING       | Standard ComfyUI positive conditioning data, typically from a "CLIP Text Encode" node. The positive prompt describes the content, subject matter, and artistic style that the user envisions for the generated video. | N/A  |
+| negative           | Yes      | CONDITIONING       | Standard ComfyUI negative conditioning data, typically generated by a "CLIP Text Encode" node. The negative prompt specifies elements, styles, or artifacts that the user wants to avoid in the generated video. | N/A  |
+| vae                | Yes      | VAE                | Requires a VAE (Variational Autoencoder) model compatible with the Wan 2.1 Fun model family, used for encoding and decoding image/video data. | N/A  |
+| width              | Yes      | INT                | The desired width of output video frames in pixels, with a default value of 832, minimum value of 16, maximum value determined by nodes.MAX_RESOLUTION, and a step size of 16. | 832  |
+| height             | Yes      | INT                | The desired height of output video frames in pixels, with a default value of 480, minimum value of 16, maximum value determined by nodes.MAX_RESOLUTION, and a step size of 16. | 480  |
+| length             | Yes      | INT                | The total number of frames in the generated video, with a default value of 81, minimum value of 1, maximum value determined by nodes.MAX_RESOLUTION, and a step size of 4. | 81   |
+| batch_size         | Yes      | INT                | The number of videos generated in a single batch, with a default value of 1, minimum value of 1, and maximum value of 4096. | 1    |
+| clip_vision_output | No       | CLIP_VISION_OUTPUT | (Optional) Visual features extracted by a CLIP vision model, allowing for visual style and content guidance. | None |
+| start_image        | No       | IMAGE              | (Optional) An initial image that influences the beginning of the generated video. | None |
+| control_video      | No       | IMAGE              | (Optional) Allows users to provide a preprocessed ControlNet reference video that will guide the motion and potential structure of the generated video.| None |
+
+## Outputs
+
+| Parameter Name      | Data Type           | Description                                                  |
+|:-------------------|:-------------------|:-------------------------------------------------------------|
+| positive           | CONDITIONING       | Provides enhanced positive conditioning data, including encoded start_image and control_video. |
+| negative           | CONDITIONING       | Provides negative conditioning data that has also been enhanced, containing the same concat_latent_image. |
+| latent             | LATENT             | A dictionary containing an empty latent tensor with the key "samples". |
diff --git a/built-in-nodes/WanFunInpaintToVideo.mdx b/built-in-nodes/WanFunInpaintToVideo.mdx
new file mode 100644
index 000000000..f2668c8bb
--- /dev/null
+++ b/built-in-nodes/WanFunInpaintToVideo.mdx
@@ -0,0 +1,33 @@
+---
+title: "WanFunInpaintToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanFunInpaintToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanFunInpaintToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFunInpaintToVideo/en.md)
+
+The WanFunInpaintToVideo node creates video sequences by inpainting between start and end images. It takes positive and negative conditioning along with optional frame images to generate video latents. The node handles video generation with configurable dimensions and length parameters.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning prompts for video generation |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning prompts to avoid in video generation |
+| `vae` | VAE | Yes | - | VAE model for encoding/decoding operations |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Output video width in pixels (default: 832, step: 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Output video height in pixels (default: 480, step: 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames in the video sequence (default: 81, step: 4) |
+| `batch_size` | INT | Yes | 1 to 4096 | Number of videos to generate in a batch (default: 1) |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | No | - | Optional CLIP vision output for additional conditioning |
+| `start_image` | IMAGE | No | - | Optional starting frame image for video generation |
+| `end_image` | IMAGE | No | - | Optional ending frame image for video generation |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Processed positive conditioning output |
+| `negative` | CONDITIONING | Processed negative conditioning output |
+| `latent` | LATENT | Generated video latent representation |
diff --git a/built-in-nodes/WanHuMoImageToVideo.mdx b/built-in-nodes/WanHuMoImageToVideo.mdx
new file mode 100644
index 000000000..0c24dc763
--- /dev/null
+++ b/built-in-nodes/WanHuMoImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "WanHuMoImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanHuMoImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanHuMoImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanHuMoImageToVideo/en.md)
+
+The WanHuMoImageToVideo node converts images to video sequences by generating latent representations for video frames. It processes conditioning inputs and can incorporate reference images and audio embeddings to influence the video generation. The node outputs modified conditioning data and latent representations suitable for video synthesis.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning input that guides the video generation toward desired content |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning input that steers the video generation away from unwanted content |
+| `vae` | VAE | Yes | - | VAE model used for encoding reference images into latent space |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Width of the output video frames in pixels (default: 832, must be divisible by 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Height of the output video frames in pixels (default: 480, must be divisible by 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames in the generated video sequence (default: 97) |
+| `batch_size` | INT | Yes | 1 to 4096 | Number of video sequences to generate simultaneously (default: 1) |
+| `audio_encoder_output` | AUDIOENCODEROUTPUT | No | - | Optional audio encoding data that can influence video generation based on audio content |
+| `ref_image` | IMAGE | No | - | Optional reference image used to guide the video generation style and content |
+
+**Note:** When a reference image is provided, it gets encoded and added to both positive and negative conditioning. When audio encoder output is provided, it gets processed and incorporated into the conditioning data.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Modified positive conditioning with reference image and/or audio embeddings incorporated |
+| `negative` | CONDITIONING | Modified negative conditioning with reference image and/or audio embeddings incorporated |
+| `latent` | LATENT | Generated latent representation containing the video sequence data |
diff --git a/built-in-nodes/WanImageToImageApi.mdx b/built-in-nodes/WanImageToImageApi.mdx
new file mode 100644
index 000000000..d84a41816
--- /dev/null
+++ b/built-in-nodes/WanImageToImageApi.mdx
@@ -0,0 +1,29 @@
+---
+title: "WanImageToImageApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanImageToImageApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanImageToImageApi"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToImageApi/en.md)
+
+The Wan Image to Image node generates an image from one or two input images and a text prompt. It transforms your input images based on the description you provide, creating a new image that maintains the aspect ratio of your original input. The output image is fixed at 1.6 megapixels regardless of the input size.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | "wan2.5-i2i-preview" | Model to use (default: "wan2.5-i2i-preview"). |
+| `image` | IMAGE | Yes | - | Single-image editing or multi-image fusion, maximum 2 images. |
+| `prompt` | STRING | Yes | - | Prompt used to describe the elements and visual features, supports English/Chinese (default: empty). |
+| `negative_prompt` | STRING | No | - | Negative text prompt to guide what to avoid (default: empty). |
+| `seed` | INT | No | 0 to 2147483647 | Seed to use for generation (default: 0). |
+| `watermark` | BOOLEAN | No | - | Whether to add an "AI generated" watermark to the result (default: true). |
+
+**Note:** This node accepts exactly 1 or 2 input images. If you provide more than 2 images or no images at all, the node will return an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The generated image based on the input images and text prompts. |
diff --git a/built-in-nodes/WanImageToVideo.mdx b/built-in-nodes/WanImageToVideo.mdx
new file mode 100644
index 000000000..748335b9b
--- /dev/null
+++ b/built-in-nodes/WanImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "WanImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToVideo/en.md)
+
+The WanImageToVideo node prepares conditioning and latent representations for video generation tasks. It creates an empty latent space for video generation and can optionally incorporate starting images and CLIP vision outputs to guide the video generation process. The node modifies both positive and negative conditioning inputs based on the provided image and vision data.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning input for guiding the generation |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning input for guiding the generation |
+| `vae` | VAE | Yes | - | VAE model for encoding images to latent space |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Width of the output video (default: 832, step: 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Height of the output video (default: 480, step: 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames in the video (default: 81, step: 4) |
+| `batch_size` | INT | Yes | 1 to 4096 | Number of videos to generate in a batch (default: 1) |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | No | - | Optional CLIP vision output for additional conditioning |
+| `start_image` | IMAGE | No | - | Optional starting image to initialize the video generation |
+
+**Note:** When `start_image` is provided, the node encodes the image sequence and applies masking to the conditioning inputs. The `clip_vision_output` parameter, when provided, adds vision-based conditioning to both positive and negative inputs.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Modified positive conditioning with image and vision data incorporated |
+| `negative` | CONDITIONING | Modified negative conditioning with image and vision data incorporated |
+| `latent` | LATENT | Empty latent space tensor ready for video generation |
diff --git a/built-in-nodes/WanImageToVideoApi.mdx b/built-in-nodes/WanImageToVideoApi.mdx
new file mode 100644
index 000000000..c4addac11
--- /dev/null
+++ b/built-in-nodes/WanImageToVideoApi.mdx
@@ -0,0 +1,38 @@
+---
+title: "WanImageToVideoApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanImageToVideoApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanImageToVideoApi"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToVideoApi/en.md)
+
+The Wan Image to Video node generates video content starting from a single input image and a text prompt. It creates video sequences by extending the initial frame according to the provided description, with options to control video quality, duration, and audio integration.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | "wan2.5-i2v-preview"<br />"wan2.5-i2v-preview" | Model to use (default: "wan2.5-i2v-preview") |
+| `image` | IMAGE | Yes | - | Input image that serves as the first frame for video generation |
+| `prompt` | STRING | Yes | - | Prompt used to describe the elements and visual features, supports English/Chinese (default: empty) |
+| `negative_prompt` | STRING | No | - | Negative text prompt to guide what to avoid (default: empty) |
+| `resolution` | COMBO | No | "480P"<br />"720P"<br />"1080P" | Video resolution quality (default: "480P") |
+| `duration` | INT | No | 5-10 | Available durations: 5 and 10 seconds (default: 5) |
+| `audio` | AUDIO | No | - | Audio must contain a clear, loud voice, without extraneous noise, background music |
+| `seed` | INT | No | 0-2147483647 | Seed to use for generation (default: 0) |
+| `generate_audio` | BOOLEAN | No | - | If there is no audio input, generate audio automatically (default: False) |
+| `prompt_extend` | BOOLEAN | No | - | Whether to enhance the prompt with AI assistance (default: True) |
+| `watermark` | BOOLEAN | No | - | Whether to add an "AI generated" watermark to the result (default: True) |
+
+**Constraints:**
+
+- Exactly one input image is required for video generation
+- Duration parameter only accepts values of 5 or 10 seconds
+- When audio is provided, it must be between 3.0 and 29.0 seconds in duration
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | Generated video based on the input image and prompt |
diff --git a/built-in-nodes/WanInfiniteTalkToVideo.mdx b/built-in-nodes/WanInfiniteTalkToVideo.mdx
new file mode 100644
index 000000000..564259cee
--- /dev/null
+++ b/built-in-nodes/WanInfiniteTalkToVideo.mdx
@@ -0,0 +1,50 @@
+---
+title: "WanInfiniteTalkToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanInfiniteTalkToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanInfiniteTalkToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanInfiniteTalkToVideo/en.md)
+
+The WanInfiniteTalkToVideo node generates video sequences from audio input. It uses a video diffusion model, conditioned on audio features extracted from one or two speakers, to produce a latent representation of a talking head video. The node can generate a new sequence or extend an existing one using previous frames for motion context.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `mode` | COMBO | Yes | `"single_speaker"`<br />`"two_speakers"` | The audio input mode. `"single_speaker"` uses one audio input. `"two_speakers"` enables inputs for a second speaker and corresponding masks. |
+| `model` | MODEL | Yes | - | The base video diffusion model. |
+| `model_patch` | MODELPATCH | Yes | - | The model patch containing audio projection layers. |
+| `positive` | CONDITIONING | Yes | - | The positive conditioning to guide the generation. |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning to guide the generation. |
+| `vae` | VAE | Yes | - | The VAE used for encoding images to and from the latent space. |
+| `width` | INT | No | 16 - MAX_RESOLUTION | The width of the output video in pixels. Must be divisible by 16. (default: 832) |
+| `height` | INT | No | 16 - MAX_RESOLUTION | The height of the output video in pixels. Must be divisible by 16. (default: 480) |
+| `length` | INT | No | 1 - MAX_RESOLUTION | The number of frames to generate. (default: 81) |
+| `clip_vision_output` | CLIPVISIONOUTPUT | No | - | Optional CLIP vision output for additional conditioning. |
+| `start_image` | IMAGE | No | - | An optional starting image to initialize the video sequence. |
+| `audio_encoder_output_1` | AUDIOENCODEROUTPUT | Yes | - | The primary audio encoder output containing features for the first speaker. |
+| `motion_frame_count` | INT | No | 1 - 33 | Number of previous frames to use as motion context when extending a sequence. (default: 9) |
+| `audio_scale` | FLOAT | No | -10.0 - 10.0 | A scaling factor applied to the audio conditioning. (default: 1.0) |
+| `previous_frames` | IMAGE | No | - | Optional previous video frames to extend from. |
+| `audio_encoder_output_2` | AUDIOENCODEROUTPUT | No | - | The second audio encoder output. Required when `mode` is set to `"two_speakers"`. |
+| `mask_1` | MASK | No | - | Mask for the first speaker, required if using two audio inputs. |
+| `mask_2` | MASK | No | - | Mask for the second speaker, required if using two audio inputs. |
+
+**Parameter Constraints:**
+
+* When `mode` is set to `"two_speakers"`, the parameters `audio_encoder_output_2`, `mask_1`, and `mask_2` become required.
+* If `audio_encoder_output_2` is provided, both `mask_1` and `mask_2` must also be provided.
+* If `mask_1` and `mask_2` are provided, `audio_encoder_output_2` must also be provided.
+* If `previous_frames` is provided, it must contain at least as many frames as specified by `motion_frame_count`.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The patched model with audio conditioning applied. |
+| `positive` | CONDITIONING | The positive conditioning, potentially modified with additional context (e.g., start image, CLIP vision). |
+| `negative` | CONDITIONING | The negative conditioning, potentially modified with additional context. |
+| `latent` | LATENT | The generated video sequence in latent space. |
+| `trim_image` | INT | The number of frames from the start of the motion context that should be trimmed when extending a sequence. |
diff --git a/built-in-nodes/WanMoveConcatTrack.mdx b/built-in-nodes/WanMoveConcatTrack.mdx
new file mode 100644
index 000000000..1b279b350
--- /dev/null
+++ b/built-in-nodes/WanMoveConcatTrack.mdx
@@ -0,0 +1,23 @@
+---
+title: "WanMoveConcatTrack - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanMoveConcatTrack node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanMoveConcatTrack"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveConcatTrack/en.md)
+
+The WanMoveConcatTrack node combines two sets of motion tracking data into a single, longer sequence. It works by joining the track paths and visibility masks from the input tracks along their respective dimensions. If only one track input is provided, it simply passes that data through unchanged.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `tracks_1` | TRACKS | Yes | | The first set of motion tracking data to be concatenated. |
+| `tracks_2` | TRACKS | No | | An optional second set of motion tracking data. If not provided, `tracks_1` is passed directly to the output. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `tracks` | TRACKS | The concatenated motion tracking data, containing the combined `track_path` and `track_visibility` from the inputs. |
diff --git a/built-in-nodes/WanMoveTrackToVideo.mdx b/built-in-nodes/WanMoveTrackToVideo.mdx
new file mode 100644
index 000000000..5201eeea2
--- /dev/null
+++ b/built-in-nodes/WanMoveTrackToVideo.mdx
@@ -0,0 +1,36 @@
+---
+title: "WanMoveTrackToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanMoveTrackToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanMoveTrackToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTrackToVideo/en.md)
+
+The WanMoveTrackToVideo node prepares conditioning and latent space data for video generation, incorporating optional motion tracking information. It encodes a starting image sequence into a latent representation and can blend in positional data from object tracks to guide the motion in the generated video. The node outputs modified positive and negative conditioning along with an empty latent tensor ready for a video model.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | The positive conditioning input to be modified. |
+| `negative` | CONDITIONING | Yes | - | The negative conditioning input to be modified. |
+| `vae` | VAE | Yes | - | The VAE model used to encode the starting image into the latent space. |
+| `tracks` | TRACKS | No | - | Optional motion tracking data containing object paths. |
+| `strength` | FLOAT | No | 0.0 - 100.0 | Strength of the track conditioning. (default: 1.0) |
+| `width` | INT | No | 16 - MAX_RESOLUTION | The width of the output video. Must be divisible by 16. (default: 832) |
+| `height` | INT | No | 16 - MAX_RESOLUTION | The height of the output video. Must be divisible by 16. (default: 480) |
+| `length` | INT | No | 1 - MAX_RESOLUTION | The number of frames in the video sequence. (default: 81) |
+| `batch_size` | INT | No | 1 - 4096 | The batch size for the latent output. (default: 1) |
+| `start_image` | IMAGE | Yes | - | The starting image or image sequence to encode. |
+| `clip_vision_output` | CLIPVISIONOUTPUT | No | - | Optional CLIP vision model output to add to the conditioning. |
+
+**Note:** The `strength` parameter only has an effect when `tracks` are provided. If `tracks` are not provided or `strength` is 0.0, the track conditioning is not applied. The `start_image` is used to create a latent image and mask for the conditioning; if it is not provided, the node only passes through the conditioning and outputs an empty latent.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | The modified positive conditioning, potentially containing `concat_latent_image`, `concat_mask`, and `clip_vision_output`. |
+| `negative` | CONDITIONING | The modified negative conditioning, potentially containing `concat_latent_image`, `concat_mask`, and `clip_vision_output`. |
+| `latent` | LATENT | An empty latent tensor with dimensions shaped by the `batch_size`, `length`, `height`, and `width` inputs. |
diff --git a/built-in-nodes/WanMoveTracksFromCoords.mdx b/built-in-nodes/WanMoveTracksFromCoords.mdx
new file mode 100644
index 000000000..ac67d9fc5
--- /dev/null
+++ b/built-in-nodes/WanMoveTracksFromCoords.mdx
@@ -0,0 +1,26 @@
+---
+title: "WanMoveTracksFromCoords - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanMoveTracksFromCoords node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanMoveTracksFromCoords"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTracksFromCoords/en.md)
+
+The WanMoveTracksFromCoords node creates a set of motion tracks from a list of coordinate points. It converts a JSON-formatted string of coordinates into a tensor format that can be used by other video processing nodes, and can optionally apply a mask to control the visibility of tracks over time.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `track_coords` | STRING | Yes | N/A | A JSON-formatted string containing the coordinate data for the tracks. The default value is an empty list (`"[]"`). |
+| `track_mask` | MASK | No | N/A | An optional mask. When provided, the node uses it to determine the visibility of each track per frame. |
+
+**Note:** The `track_coords` input expects a specific JSON structure. It should be a list of tracks, where each track is a list of frames, and each frame is an object with `x` and `y` coordinates. The number of frames must be consistent across all tracks.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `tracks` | TRACKS | The generated track data, containing the path coordinates and visibility information for each track. |
+| `track_length` | INT | The total number of frames in the generated tracks. |
diff --git a/built-in-nodes/WanMoveVisualizeTracks.mdx b/built-in-nodes/WanMoveVisualizeTracks.mdx
new file mode 100644
index 000000000..2ab702773
--- /dev/null
+++ b/built-in-nodes/WanMoveVisualizeTracks.mdx
@@ -0,0 +1,29 @@
+---
+title: "WanMoveVisualizeTracks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanMoveVisualizeTracks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanMoveVisualizeTracks"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveVisualizeTracks/en.md)
+
+The WanMoveVisualizeTracks node overlays motion tracking data onto a sequence of images or video frames. It draws visual representations of tracked points, including their movement paths and current positions, making the motion data visible and easier to analyze.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | Yes | - | The sequence of input images or video frames to visualize the tracks on. |
+| `tracks` | TRACKS | No | - | The motion tracking data containing point paths and visibility information. If not provided, the input images are passed through unchanged. |
+| `line_resolution` | INT | Yes | 1 - 1024 | The number of previous frames to use when drawing the trailing path line for each track (default: 24). |
+| `circle_size` | INT | Yes | 1 - 128 | The size of the circle drawn at the current position of each track (default: 12). |
+| `opacity` | FLOAT | Yes | 0.0 - 1.0 | The opacity of the drawn track overlays (default: 0.75). |
+| `line_width` | INT | Yes | 1 - 128 | The width of the lines used to draw the track paths (default: 16). |
+
+**Note:** If the number of input images does not match the number of frames in the provided `tracks` data, the image sequence will be repeated to match the track length.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The sequence of images with the motion tracking data visualized as overlays. If no `tracks` were provided, the original input images are returned. |
diff --git a/built-in-nodes/WanPhantomSubjectToVideo.mdx b/built-in-nodes/WanPhantomSubjectToVideo.mdx
new file mode 100644
index 000000000..72929cea0
--- /dev/null
+++ b/built-in-nodes/WanPhantomSubjectToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "WanPhantomSubjectToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanPhantomSubjectToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanPhantomSubjectToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanPhantomSubjectToVideo/en.md)
+
+The WanPhantomSubjectToVideo node generates video content by processing conditioning inputs and optional reference images. It creates latent representations for video generation and can incorporate visual guidance from input images when provided. The node prepares conditioning data with time-dimensional concatenation for video models and outputs modified conditioning along with generated latent video data.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning input for guiding video generation |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning input to avoid certain characteristics |
+| `vae` | VAE | Yes | - | VAE model for encoding images when provided |
+| `width` | INT | No | 16 to MAX_RESOLUTION | Output video width in pixels (default: 832, must be divisible by 16) |
+| `height` | INT | No | 16 to MAX_RESOLUTION | Output video height in pixels (default: 480, must be divisible by 16) |
+| `length` | INT | No | 1 to MAX_RESOLUTION | Number of frames in the generated video (default: 81, must be divisible by 4) |
+| `batch_size` | INT | No | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `images` | IMAGE | No | - | Optional reference images for time-dimensional conditioning |
+
+**Note:** When `images` are provided, they are automatically upscaled to match the specified `width` and `height`, and only the first `length` frames are used for processing.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Modified positive conditioning with time-dimensional concatenation when images are provided |
+| `negative_text` | CONDITIONING | Modified negative conditioning with time-dimensional concatenation when images are provided |
+| `negative_img_text` | CONDITIONING | Negative conditioning with zeroed time-dimensional concatenation when images are provided |
+| `latent` | LATENT | Generated latent video representation with specified dimensions and length |
diff --git a/built-in-nodes/WanReferenceVideoApi.mdx b/built-in-nodes/WanReferenceVideoApi.mdx
new file mode 100644
index 000000000..840a3d2d4
--- /dev/null
+++ b/built-in-nodes/WanReferenceVideoApi.mdx
@@ -0,0 +1,35 @@
+---
+title: "WanReferenceVideoApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanReferenceVideoApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanReferenceVideoApi"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanReferenceVideoApi/en.md)
+
+The Wan Reference to Video node uses the visual appearance and voice from one or more input reference videos, along with a text prompt, to generate a new video. It maintains consistency with the characters from the reference material while creating new content based on your description.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | `"wan2.6-r2v"` | The specific AI model to use for video generation. |
+| `prompt` | STRING | Yes | - | A description of the elements and visual features for the new video. Supports English and Chinese. Use identifiers like `character1` and `character2` to refer to the characters from the reference videos. |
+| `negative_prompt` | STRING | No | - | A description of elements or features to avoid in the generated video. |
+| `reference_videos` | AUTOGROW | Yes | - | A list of video inputs used as references for character appearance and voice. You must provide at least one video. Each video can be assigned a name like `character1`, `character2`, or `character3`. |
+| `size` | COMBO | Yes | `"720p: 1:1 (960x960)"`<br />`"720p: 16:9 (1280x720)"`<br />`"720p: 9:16 (720x1280)"`<br />`"720p: 4:3 (1088x832)"`<br />`"720p: 3:4 (832x1088)"`<br />`"1080p: 1:1 (1440x1440)"`<br />`"1080p: 16:9 (1920x1080)"`<br />`"1080p: 9:16 (1080x1920)"`<br />`"1080p: 4:3 (1632x1248)"`<br />`"1080p: 3:4 (1248x1632)"` | The resolution and aspect ratio for the output video. |
+| `duration` | INT | Yes | 5 to 10 | The length of the generated video in seconds. The value must be a multiple of 5 (default: 5). |
+| `seed` | INT | No | 0 to 2147483647 | A random seed value for reproducible results. A value of 0 will generate a random seed. |
+| `shot_type` | COMBO | Yes | `"single"`<br />`"multi"` | Specifies whether the generated video is a single continuous shot or contains multiple shots with cuts. |
+| `watermark` | BOOLEAN | No | - | When enabled, an AI-generated watermark is added to the final video (default: False). |
+
+**Constraints:**
+
+* Each video provided in `reference_videos` must be between 2 and 30 seconds in duration.
+* The `duration` parameter is limited to specific values (5 or 10 seconds).
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The newly generated video file. |
diff --git a/built-in-nodes/WanSoundImageToVideo.mdx b/built-in-nodes/WanSoundImageToVideo.mdx
new file mode 100644
index 000000000..5836af4c2
--- /dev/null
+++ b/built-in-nodes/WanSoundImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "WanSoundImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanSoundImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanSoundImageToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideo/en.md)
+
+The WanSoundImageToVideo node generates video content from images with optional audio conditioning. It takes positive and negative conditioning prompts along with a VAE model to create video latents, and can incorporate reference images, audio encoding, control videos, and motion references to guide the video generation process.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning prompts that guide what content should appear in the generated video |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning prompts that specify what content should be avoided in the generated video |
+| `vae` | VAE | Yes | - | VAE model used for encoding and decoding the video latent representations |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Width of the output video in pixels (default: 832, must be divisible by 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Height of the output video in pixels (default: 480, must be divisible by 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames in the generated video (default: 77, must be divisible by 4) |
+| `batch_size` | INT | Yes | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `audio_encoder_output` | AUDIOENCODEROUTPUT | No | - | Optional audio encoding that can influence the video generation based on sound characteristics |
+| `ref_image` | IMAGE | No | - | Optional reference image that provides visual guidance for the video content |
+| `control_video` | IMAGE | No | - | Optional control video that guides the motion and structure of the generated video |
+| `ref_motion` | IMAGE | No | - | Optional motion reference that provides guidance for movement patterns in the video |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Processed positive conditioning that has been modified for video generation |
+| `negative` | CONDITIONING | Processed negative conditioning that has been modified for video generation |
+| `latent` | LATENT | Generated video representation in latent space that can be decoded into final video frames |
diff --git a/built-in-nodes/WanSoundImageToVideoExtend.mdx b/built-in-nodes/WanSoundImageToVideoExtend.mdx
new file mode 100644
index 000000000..b8dca79ec
--- /dev/null
+++ b/built-in-nodes/WanSoundImageToVideoExtend.mdx
@@ -0,0 +1,31 @@
+---
+title: "WanSoundImageToVideoExtend - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanSoundImageToVideoExtend node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanSoundImageToVideoExtend"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideoExtend/en.md)
+
+The WanSoundImageToVideoExtend node extends image-to-video generation by incorporating audio conditioning and reference images. It takes positive and negative conditioning along with video latent data and optional audio embeddings to generate extended video sequences. The node processes these inputs to create coherent video outputs that can be synchronized with audio cues.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning prompts that guide what the video should include |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning prompts that specify what the video should avoid |
+| `vae` | VAE | Yes | - | Variational Autoencoder used for encoding and decoding video frames |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames to generate for the video sequence (default: 77, step: 4) |
+| `video_latent` | LATENT | Yes | - | Initial video latent representation that serves as the starting point for extension |
+| `audio_encoder_output` | AUDIOENCODEROUTPUT | No | - | Optional audio embeddings that can influence video generation based on sound characteristics |
+| `ref_image` | IMAGE | No | - | Optional reference image that provides visual guidance for the video generation |
+| `control_video` | IMAGE | No | - | Optional control video that can guide the motion and style of the generated video |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Processed positive conditioning with video context applied |
+| `negative` | CONDITIONING | Processed negative conditioning with video context applied |
+| `latent` | LATENT | Generated video latent representation containing the extended video sequence |
diff --git a/built-in-nodes/WanTextToImageApi.mdx b/built-in-nodes/WanTextToImageApi.mdx
new file mode 100644
index 000000000..1fbad685f
--- /dev/null
+++ b/built-in-nodes/WanTextToImageApi.mdx
@@ -0,0 +1,29 @@
+---
+title: "WanTextToImageApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanTextToImageApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanTextToImageApi"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTextToImageApi/en.md)
+
+The Wan Text to Image node generates images based on text descriptions. It uses AI models to create visual content from written prompts, supporting both English and Chinese text input. The node provides various controls to adjust the output image size, quality, and style preferences.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | "wan2.5-t2i-preview" | Model to use (default: "wan2.5-t2i-preview") |
+| `prompt` | STRING | Yes | - | Prompt used to describe the elements and visual features, supports English/Chinese (default: empty) |
+| `negative_prompt` | STRING | No | - | Negative text prompt to guide what to avoid (default: empty) |
+| `width` | INT | No | 768-1440 | Image width in pixels (default: 1024, step: 32) |
+| `height` | INT | No | 768-1440 | Image height in pixels (default: 1024, step: 32) |
+| `seed` | INT | No | 0-2147483647 | Seed to use for generation (default: 0) |
+| `prompt_extend` | BOOLEAN | No | - | Whether to enhance the prompt with AI assistance (default: True) |
+| `watermark` | BOOLEAN | No | - | Whether to add an "AI generated" watermark to the result (default: True) |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | IMAGE | The generated image based on the text prompt |
diff --git a/built-in-nodes/WanTextToVideoApi.mdx b/built-in-nodes/WanTextToVideoApi.mdx
new file mode 100644
index 000000000..014c7761b
--- /dev/null
+++ b/built-in-nodes/WanTextToVideoApi.mdx
@@ -0,0 +1,33 @@
+---
+title: "WanTextToVideoApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanTextToVideoApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanTextToVideoApi"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTextToVideoApi/en.md)
+
+The Wan Text to Video node generates video content based on text descriptions. It uses AI models to create videos from prompts and supports various video sizes, durations, and optional audio inputs. The node can automatically generate audio when needed and provides options for prompt enhancement and watermarking.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | Yes | "wan2.5-t2v-preview" | Model to use (default: "wan2.5-t2v-preview") |
+| `prompt` | STRING | Yes | - | Prompt used to describe the elements and visual features, supports English/Chinese (default: "") |
+| `negative_prompt` | STRING | No | - | Negative text prompt to guide what to avoid (default: "") |
+| `size` | COMBO | No | "480p: 1:1 (624x624)"<br />"480p: 16:9 (832x480)"<br />"480p: 9:16 (480x832)"<br />"720p: 1:1 (960x960)"<br />"720p: 16:9 (1280x720)"<br />"720p: 9:16 (720x1280)"<br />"720p: 4:3 (1088x832)"<br />"720p: 3:4 (832x1088)"<br />"1080p: 1:1 (1440x1440)"<br />"1080p: 16:9 (1920x1080)"<br />"1080p: 9:16 (1080x1920)"<br />"1080p: 4:3 (1632x1248)"<br />"1080p: 3:4 (1248x1632)" | Video resolution and aspect ratio (default: "480p: 1:1 (624x624)") |
+| `duration` | INT | No | 5-10 | Available durations: 5 and 10 seconds (default: 5) |
+| `audio` | AUDIO | No | - | Audio must contain a clear, loud voice, without extraneous noise, background music |
+| `seed` | INT | No | 0-2147483647 | Seed to use for generation (default: 0) |
+| `generate_audio` | BOOLEAN | No | - | If there is no audio input, generate audio automatically (default: False) |
+| `prompt_extend` | BOOLEAN | No | - | Whether to enhance the prompt with AI assistance (default: True) |
+| `watermark` | BOOLEAN | No | - | Whether to add an "AI generated" watermark to the result (default: True) |
+
+**Note:** The `duration` parameter only accepts values of 5 or 10 seconds, as these are the available durations. When providing audio input, it must be between 3.0 and 29.0 seconds in duration and contain clear voice without background noise or music.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The generated video based on the input parameters |
diff --git a/built-in-nodes/WanTrackToVideo.mdx b/built-in-nodes/WanTrackToVideo.mdx
new file mode 100644
index 000000000..04fe0cd57
--- /dev/null
+++ b/built-in-nodes/WanTrackToVideo.mdx
@@ -0,0 +1,37 @@
+---
+title: "WanTrackToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanTrackToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanTrackToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTrackToVideo/en.md)
+
+The WanTrackToVideo node converts motion tracking data into video sequences by processing track points and generating corresponding video frames. It takes tracking coordinates as input and produces video conditioning and latent representations that can be used for video generation. When no tracks are provided, it falls back to standard image-to-video conversion.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning for video generation |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning for video generation |
+| `vae` | VAE | Yes | - | VAE model for encoding and decoding |
+| `tracks` | STRING | Yes | - | JSON-formatted tracking data as a multiline string (default: "[]") |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Output video width in pixels (default: 832, step: 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Output video height in pixels (default: 480, step: 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames in the output video (default: 81, step: 4) |
+| `batch_size` | INT | Yes | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `temperature` | FLOAT | Yes | 1.0 to 1000.0 | Temperature parameter for motion patching (default: 220.0, step: 0.1) |
+| `topk` | INT | Yes | 1 to 10 | Top-k value for motion patching (default: 2) |
+| `start_image` | IMAGE | No | - | Starting image for video generation |
+| `clip_vision_output` | CLIPVISIONOUTPUT | No | - | CLIP vision output for additional conditioning |
+
+**Note:** When `tracks` contains valid tracking data, the node processes motion tracks to generate video. When `tracks` is empty, it switches to standard image-to-video mode. If `start_image` is provided, it initializes the first frame of the video sequence.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning with motion track information applied |
+| `negative` | CONDITIONING | Negative conditioning with motion track information applied |
+| `latent` | LATENT | Generated video latent representation |
diff --git a/built-in-nodes/WanVaceToVideo.mdx b/built-in-nodes/WanVaceToVideo.mdx
new file mode 100644
index 000000000..3989a4852
--- /dev/null
+++ b/built-in-nodes/WanVaceToVideo.mdx
@@ -0,0 +1,37 @@
+---
+title: "WanVaceToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanVaceToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanVaceToVideo"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanVaceToVideo/en.md)
+
+The WanVaceToVideo node processes video conditioning data for video generation models. It takes positive and negative conditioning inputs along with video control data and prepares latent representations for video generation. The node handles video upscaling, masking, and VAE encoding to create the appropriate conditioning structure for video models.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | Yes | - | Positive conditioning input for guiding the generation |
+| `negative` | CONDITIONING | Yes | - | Negative conditioning input for guiding the generation |
+| `vae` | VAE | Yes | - | VAE model used for encoding images and video frames |
+| `width` | INT | Yes | 16 to MAX_RESOLUTION | Output video width in pixels (default: 832, step: 16) |
+| `height` | INT | Yes | 16 to MAX_RESOLUTION | Output video height in pixels (default: 480, step: 16) |
+| `length` | INT | Yes | 1 to MAX_RESOLUTION | Number of frames in the video (default: 81, step: 4) |
+| `batch_size` | INT | Yes | 1 to 4096 | Number of videos to generate simultaneously (default: 1) |
+| `strength` | FLOAT | Yes | 0.0 to 1000.0 | Control strength for video conditioning (default: 1.0, step: 0.01) |
+| `control_video` | IMAGE | No | - | Optional input video for control conditioning |
+| `control_masks` | MASK | No | - | Optional masks for controlling which parts of the video to modify |
+| `reference_image` | IMAGE | No | - | Optional reference image for additional conditioning |
+
+**Note:** When `control_video` is provided, it will be upscaled to match the specified width and height. If `control_masks` are provided, they must match the dimensions of the control video. The `reference_image` is encoded through the VAE and prepended to the latent sequence when provided.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | Positive conditioning with video control data applied |
+| `negative` | CONDITIONING | Negative conditioning with video control data applied |
+| `latent` | LATENT | Empty latent tensor ready for video generation |
+| `trim_latent` | INT | Number of latent frames to trim when reference image is used |
diff --git a/built-in-nodes/WavespeedFlashVSRNode.mdx b/built-in-nodes/WavespeedFlashVSRNode.mdx
new file mode 100644
index 000000000..567bf7cd9
--- /dev/null
+++ b/built-in-nodes/WavespeedFlashVSRNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "WavespeedFlashVSRNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WavespeedFlashVSRNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WavespeedFlashVSRNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WavespeedFlashVSRNode/en.md)
+
+The WavespeedFlashVSRNode is a fast, high-quality video upscaler that boosts the resolution and restores clarity for low-resolution or blurry footage. It processes a video input and outputs a new video at a user-selected higher resolution.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | Yes | N/A | The input video file to be upscaled. |
+| `target_resolution` | STRING | Yes | `"720p"`<br />`"1080p"`<br />`"2K"`<br />`"4K"` | The desired resolution for the upscaled output video. |
+
+**Input Constraints:**
+
+* The input `video` file must be in the MP4 container format.
+* The duration of the input `video` must be between 5 seconds and 10 minutes (600 seconds).
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `output` | VIDEO | The upscaled video file at the selected target resolution. |
diff --git a/built-in-nodes/WavespeedImageUpscaleNode.mdx b/built-in-nodes/WavespeedImageUpscaleNode.mdx
new file mode 100644
index 000000000..7a4821ec1
--- /dev/null
+++ b/built-in-nodes/WavespeedImageUpscaleNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "WavespeedImageUpscaleNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WavespeedImageUpscaleNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WavespeedImageUpscaleNode"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WavespeedImageUpscaleNode/en.md)
+
+The WaveSpeed Image Upscale node uses an external AI service to increase the resolution and quality of an image. It takes a single input photo and upscales it to a higher target resolution, such as 2K, 4K, or 8K, producing a sharper and more detailed result.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | STRING | Yes | `"SeedVR2"`<br />`"Ultimate"` | The AI model to use for upscaling. "SeedVR2" and "Ultimate" offer different quality and pricing tiers. |
+| `image` | IMAGE | Yes | | The input image to be upscaled. |
+| `target_resolution` | STRING | Yes | `"2K"`<br />`"4K"`<br />`"8K"` | The desired output resolution for the upscaled image. |
+
+**Note:** This node requires exactly one input image. Providing a batch of images will result in an error.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `image` | IMAGE | The upscaled, high-resolution output image. |
diff --git a/built-in-nodes/WebcamCapture.mdx b/built-in-nodes/WebcamCapture.mdx
new file mode 100644
index 000000000..ada92a5b2
--- /dev/null
+++ b/built-in-nodes/WebcamCapture.mdx
@@ -0,0 +1,27 @@
+---
+title: "WebcamCapture - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WebcamCapture node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WebcamCapture"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WebcamCapture/en.md)
+
+The WebcamCapture node captures images from a webcam device and converts them into a format that can be used within ComfyUI workflows. It inherits from the LoadImage node and provides options to control the capture dimensions and timing. When enabled, the node can capture new images each time the workflow queue is processed.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `image` | WEBCAM | Yes | - | The webcam input source to capture images from |
+| `width` | INT | No | 0 to MAX_RESOLUTION | The desired width for the captured image (default: 0, uses webcam's native resolution) |
+| `height` | INT | No | 0 to MAX_RESOLUTION | The desired height for the captured image (default: 0, uses webcam's native resolution) |
+| `capture_on_queue` | BOOLEAN | No | - | When enabled, captures a new image each time the workflow queue is processed (default: True) |
+
+**Note:** When both `width` and `height` are set to 0, the node uses the webcam's native resolution. Setting either dimension to a non-zero value will resize the captured image accordingly.
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | The captured webcam image converted to ComfyUI's image format |
diff --git a/built-in-nodes/ZImageFunControlnet.mdx b/built-in-nodes/ZImageFunControlnet.mdx
new file mode 100644
index 000000000..f76d2514f
--- /dev/null
+++ b/built-in-nodes/ZImageFunControlnet.mdx
@@ -0,0 +1,32 @@
+---
+title: "ZImageFunControlnet - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ZImageFunControlnet node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ZImageFunControlnet"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ZImageFunControlnet/en.md)
+
+The ZImageFunControlnet node applies a specialized control network to influence the image generation or editing process. It uses a base model, a model patch, and a VAE, allowing you to adjust the strength of the control effect. This node can work with a base image, an inpainting image, and a mask for more targeted edits.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | - | The base model used for the generation process. |
+| `model_patch` | MODEL_PATCH | Yes | - | A specialized patch model that applies the control network's guidance. |
+| `vae` | VAE | Yes | - | The Variational Autoencoder used for encoding and decoding images. |
+| `strength` | FLOAT | Yes | -10.0 to 10.0 | The strength of the control network's influence. Positive values apply the effect, while negative values can invert it (default: 1.0). |
+| `image` | IMAGE | No | - | An optional base image to guide the generation process. |
+| `inpaint_image` | IMAGE | No | - | An optional image used specifically for inpainting areas defined by a mask. |
+| `mask` | MASK | No | - | An optional mask that defines which areas of an image should be edited or inpainted. |
+
+**Note:** The `inpaint_image` parameter is typically used in conjunction with a `mask` to specify the content for inpainting. The node's behavior may change based on which optional inputs are provided (e.g., using `image` for guidance or using `image`, `mask`, and `inpaint_image` for inpainting).
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The model with the control network patch applied, ready for use in a sampling pipeline. |
+| `positive` | CONDITIONING | The positive conditioning, potentially modified by the control network inputs. |
+| `negative` | CONDITIONING | The negative conditioning, potentially modified by the control network inputs. |
diff --git a/built-in-nodes/unCLIPCheckpointLoader.mdx b/built-in-nodes/unCLIPCheckpointLoader.mdx
new file mode 100644
index 000000000..0036d9c88
--- /dev/null
+++ b/built-in-nodes/unCLIPCheckpointLoader.mdx
@@ -0,0 +1,25 @@
+---
+title: "unCLIPCheckpointLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the unCLIPCheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "unCLIPCheckpointLoader"
+icon: "circle"
+mode: wide
+---
+This node will detect models located in the `ComfyUI/models/checkpoints` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.
+
+The unCLIPCheckpointLoader node is designed for loading checkpoints specifically tailored for unCLIP models. It facilitates the retrieval and initialization of models, CLIP vision modules, and VAEs from a specified checkpoint, streamlining the setup process for further operations or analyses.
+
+## Inputs
+
+| Field      | Comfy dtype       | Description                                                                       |
+|------------|-------------------|-----------------------------------------------------------------------------------|
+| `ckpt_name`| `COMBO[STRING]`    | Specifies the name of the checkpoint to be loaded, identifying and retrieving the correct checkpoint file from a predefined directory, determining the initialization of models and configurations. |
+
+## Outputs
+
+| Field       | Comfy dtype   | Description                                                              | Python dtype         |
+|-------------|---------------|--------------------------------------------------------------------------|---------------------|
+| `model`     | `MODEL`       | Represents the primary model loaded from the checkpoint.                   | `torch.nn.Module`   |
+| `clip`      | `CLIP`        | Represents the CLIP module loaded from the checkpoint, if available.      | `torch.nn.Module`   |
+| `vae`       | `VAE`         | Represents the VAE module loaded from the checkpoint, if available.        | `torch.nn.Module`   |
+| `clip_vision`| `CLIP_VISION` | Represents the CLIP vision module loaded from the checkpoint, if available.| `torch.nn.Module`   |
diff --git a/built-in-nodes/unCLIPConditioning.mdx b/built-in-nodes/unCLIPConditioning.mdx
new file mode 100644
index 000000000..2d377d0ac
--- /dev/null
+++ b/built-in-nodes/unCLIPConditioning.mdx
@@ -0,0 +1,24 @@
+---
+title: "unCLIPConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the unCLIPConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "unCLIPConditioning"
+icon: "circle"
+mode: wide
+---
+
+This node is designed to integrate CLIP vision outputs into the conditioning process, adjusting the influence of these outputs based on specified strength and noise augmentation parameters. It enriches the conditioning with visual context, enhancing the generation process.
+
+## Inputs
+
+| Parameter              | Comfy dtype            | Description |
+|------------------------|------------------------|-------------|
+| `conditioning`         | `CONDITIONING`         | The base conditioning data to which the CLIP vision outputs are to be added, serving as the foundation for further modifications. |
+| `clip_vision_output`   | `CLIP_VISION_OUTPUT`   | The output from a CLIP vision model, providing visual context that is integrated into the conditioning. |
+| `strength`             | `FLOAT`                | Determines the intensity of the CLIP vision output's influence on the conditioning. |
+| `noise_augmentation`   | `FLOAT`                | Specifies the level of noise augmentation to apply to the CLIP vision output before integrating it into the conditioning. |
+
+## Outputs
+
+| Parameter             | Comfy dtype            | Description |
+|-----------------------|------------------------|-------------|
+| `conditioning`         | `CONDITIONING`         | The enriched conditioning data, now containing integrated CLIP vision outputs with applied strength and noise augmentation. |
diff --git a/built-in-nodes/wanBlockSwap.mdx b/built-in-nodes/wanBlockSwap.mdx
new file mode 100644
index 000000000..961c97b66
--- /dev/null
+++ b/built-in-nodes/wanBlockSwap.mdx
@@ -0,0 +1,22 @@
+---
+title: "wanBlockSwap - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the wanBlockSwap node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "wanBlockSwap"
+icon: "circle"
+mode: wide
+---
+> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/wanBlockSwap/en.md)
+
+This node is deprecated and serves no function. It accepts a model as input and returns the same model unchanged. The description "NOP" indicates it performs no operation.
+
+## Inputs
+
+| Parameter | Data Type | Required | Range | Description |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | Yes | | The model to pass through the node. |
+
+## Outputs
+
+| Output Name | Data Type | Description |
+|-------------|-----------|-------------|
+| `model` | MODEL | The same model that was provided as input, unchanged. |
diff --git a/docs.json b/docs.json
index eb7911698..d008b9bc1 100644
--- a/docs.json
+++ b/docs.json
@@ -44,7 +44,10 @@
                   {
                     "group": "Comfy Cloud",
                     "icon": "cloud",
-                    "pages": ["get_started/cloud", "cloud/import-models"]
+                    "pages": [
+                      "get_started/cloud",
+                      "cloud/import-models"
+                    ]
                   },
                   "installation/install_custom_node",
                   "get_started/first_generation"
@@ -178,7 +181,9 @@
                       },
                       {
                         "group": "Ovis",
-                        "pages": ["tutorials/image/ovis/ovis-image"]
+                        "pages": [
+                          "tutorials/image/ovis/ovis-image"
+                        ]
                       },
                       {
                         "group": "NewBie-image",
@@ -192,7 +197,9 @@
                   },
                   {
                     "group": "3D",
-                    "pages": ["tutorials/3d/hunyuan3D-2"]
+                    "pages": [
+                      "tutorials/3d/hunyuan3D-2"
+                    ]
                   },
                   {
                     "group": "Video",
@@ -398,924 +405,3562 @@
             "pages": [
               "built-in-nodes/overview",
               {
-                "group": "conditioning",
-                "pages": [
-                  "built-in-nodes/ClipSetLastLayer",
-                  "built-in-nodes/ClipTextEncode",
-                  "built-in-nodes/ClipVisionEncode",
-                  {
-                    "group": "Video Models",
-                    "pages": [
-                      "built-in-nodes/conditioning/video-models/wan-vace-to-video"
-                    ]
-                  }
-                ]
-              },
-              {
-                "group": "Image",
-                "pages": ["built-in-nodes/Canny"]
-              },
-              {
-                "group": "Loader",
+                "group": "Nodes",
                 "pages": [
-                  "built-in-nodes/CheckpointLoaderSimple",
-                  "built-in-nodes/ClipLoader",
-                  "built-in-nodes/ClipVisionLoader"
-                ]
-              },
-              {
-                "group": "Latent",
-                "pages": ["built-in-nodes/latent/video/trim-video-latent"]
-              },
-              {
-                "group": "Advanced",
-                "pages": [
-                  "built-in-nodes/ClipMergeSimple",
-                  "built-in-nodes/ClipSave",
                   {
-                    "group": "Conditioning",
+                    "group": "3D",
                     "pages": [
-                      "built-in-nodes/ClipTextEncodeFlux",
-                      "built-in-nodes/ClipTextEncodeHunyuanDit",
-                      "built-in-nodes/ClipTextEncodeSdxl",
-                      "built-in-nodes/ClipTextEncodeSdxlRefiner"
+                      "built-in-nodes/Load3D",
+                      "built-in-nodes/Load3DAnimation",
+                      "built-in-nodes/Preview3D",
+                      "built-in-nodes/Preview3DAnimation",
+                      "built-in-nodes/SaveGLB",
+                      "built-in-nodes/VoxelToMesh",
+                      "built-in-nodes/VoxelToMeshBasic"
                     ]
-                  }
-                ]
-              },
-              {
-                "group": "Sampling",
-                "pages": [
-                  "built-in-nodes/sampling/ksampler",
-                  {
-                    "group": "Custom Sampling",
-                    "pages": ["built-in-nodes/BasicScheduler"]
-                  }
-                ]
-              },
-              {
-                "group": "3D",
-                "pages": ["built-in-nodes/Load3D"]
-              },
-              {
-                "group": "Partner Node",
-                "pages": [
+                  },
                   {
-                    "group": "Image",
+                    "group": "Advanced",
                     "pages": [
                       {
-                        "group": "BFL",
+                        "group": "Attention Experiments",
                         "pages": [
-                          "built-in-nodes/partner-node/image/bfl/flux-1-1-pro-ultra-image"
+                          "built-in-nodes/CLIPAttentionMultiply",
+                          "built-in-nodes/UNetCrossAttentionMultiply",
+                          "built-in-nodes/UNetSelfAttentionMultiply",
+                          "built-in-nodes/UNetTemporalAttentionMultiply"
                         ]
                       },
                       {
-                        "group": "Luma",
+                        "group": "Conditioning",
                         "pages": [
-                          "built-in-nodes/partner-node/image/luma/luma-reference",
-                          "built-in-nodes/partner-node/image/luma/luma-text-to-image",
-                          "built-in-nodes/partner-node/image/luma/luma-image-to-image"
+                          {
+                            "group": "Audio",
+                            "pages": [
+                              "built-in-nodes/ReferenceTimbreAudio"
+                            ]
+                          },
+                          {
+                            "group": "Edit Models",
+                            "pages": [
+                              "built-in-nodes/ReferenceLatent"
+                            ]
+                          },
+                          {
+                            "group": "Flux",
+                            "pages": [
+                              "built-in-nodes/CLIPTextEncodeFlux",
+                              "built-in-nodes/ClipTextEncodeFlux",
+                              "built-in-nodes/FluxDisableGuidance",
+                              "built-in-nodes/FluxGuidance",
+                              "built-in-nodes/FluxKontextImageScale",
+                              "built-in-nodes/FluxKontextMultiReferenceLatentMethod"
+                            ]
+                          },
+                          {
+                            "group": "Kandinsky5",
+                            "pages": [
+                              "built-in-nodes/CLIPTextEncodeKandinsky5"
+                            ]
+                          },
+                          "built-in-nodes/CLIPTextEncodeHiDream",
+                          "built-in-nodes/CLIPTextEncodeHunyuanDiT",
+                          "built-in-nodes/ClipTextEncodeHunyuanDit",
+                          "built-in-nodes/CLIPTextEncodePixArtAlpha",
+                          "built-in-nodes/CLIPTextEncodeSD3",
+                          "built-in-nodes/CLIPTextEncodeSDXL",
+                          "built-in-nodes/ClipTextEncodeSdxl",
+                          "built-in-nodes/CLIPTextEncodeSDXLRefiner",
+                          "built-in-nodes/ClipTextEncodeSdxlRefiner",
+                          "built-in-nodes/ConditioningSetTimestepRange",
+                          "built-in-nodes/ConditioningZeroOut",
+                          "built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo",
+                          "built-in-nodes/TextEncodeQwenImageEdit",
+                          "built-in-nodes/TextEncodeQwenImageEditPlus",
+                          "built-in-nodes/TextEncodeZImageOmni"
                         ]
                       },
                       {
-                        "group": "Recraft",
+                        "group": "Debug",
                         "pages": [
-                          "built-in-nodes/partner-node/image/recraft/save-svg",
-                          "built-in-nodes/partner-node/image/recraft/recraft-style-realistic-image",
-                          "built-in-nodes/partner-node/image/recraft/recraft-text-to-vector",
-                          "built-in-nodes/partner-node/image/recraft/recraft-creative-upscale",
-                          "built-in-nodes/partner-node/image/recraft/recraft-image-to-image",
-                          "built-in-nodes/partner-node/image/recraft/recraft-crisp-upscale",
-                          "built-in-nodes/partner-node/image/recraft/recraft-color-rgb",
-                          "built-in-nodes/partner-node/image/recraft/recraft-text-to-image",
-                          "built-in-nodes/partner-node/image/recraft/recraft-image-inpainting",
-                          "built-in-nodes/partner-node/image/recraft/recraft-vectorize-image",
-                          "built-in-nodes/partner-node/image/recraft/recraft-style-digital-illustration",
-                          "built-in-nodes/partner-node/image/recraft/recraft-remove-background",
-                          "built-in-nodes/partner-node/image/recraft/recraft-style-logo-raster",
-                          "built-in-nodes/partner-node/image/recraft/recraft-controls",
-                          "built-in-nodes/partner-node/image/recraft/recraft-replace-background"
+                          {
+                            "group": "Model",
+                            "pages": [
+                              "built-in-nodes/EasyCache",
+                              "built-in-nodes/LazyCache",
+                              "built-in-nodes/ModelComputeDtype"
+                            ]
+                          }
                         ]
                       },
                       {
-                        "group": "Ideogram",
+                        "group": "Guidance",
                         "pages": [
-                          "built-in-nodes/partner-node/image/ideogram/ideogram-v2",
-                          "built-in-nodes/partner-node/image/ideogram/ideogram-v3",
-                          "built-in-nodes/partner-node/image/ideogram/ideogram-v1"
+                          "built-in-nodes/CFGNorm",
+                          "built-in-nodes/CFGZeroStar",
+                          "built-in-nodes/NAGuidance",
+                          "built-in-nodes/SkipLayerGuidanceDiT",
+                          "built-in-nodes/SkipLayerGuidanceDiTSimple",
+                          "built-in-nodes/SkipLayerGuidanceSD3",
+                          "built-in-nodes/TCFG"
                         ]
                       },
                       {
-                        "group": "Stability AI",
+                        "group": "Hooks",
                         "pages": [
-                          "built-in-nodes/partner-node/image/stability-ai/stability-ai-stable-image-ultra",
-                          "built-in-nodes/partner-node/image/stability-ai/stability-ai-stable-diffusion-3-5-image"
+                          {
+                            "group": "Clip",
+                            "pages": [
+                              "built-in-nodes/SetClipHooks"
+                            ]
+                          },
+                          {
+                            "group": "Combine",
+                            "pages": [
+                              "built-in-nodes/CombineHooks",
+                              "built-in-nodes/CombineHooksEight",
+                              "built-in-nodes/CombineHooksFour"
+                            ]
+                          },
+                          {
+                            "group": "Cond Pair",
+                            "pages": [
+                              "built-in-nodes/PairConditioningCombine",
+                              "built-in-nodes/PairConditioningSetDefaultAndCombine",
+                              "built-in-nodes/PairConditioningSetProperties",
+                              "built-in-nodes/PairConditioningSetPropertiesAndCombine"
+                            ]
+                          },
+                          {
+                            "group": "Cond Single",
+                            "pages": [
+                              "built-in-nodes/ConditioningSetDefaultAndCombine",
+                              "built-in-nodes/ConditioningSetProperties",
+                              "built-in-nodes/ConditioningSetPropertiesAndCombine"
+                            ]
+                          },
+                          {
+                            "group": "Create",
+                            "pages": [
+                              "built-in-nodes/CreateHookLora",
+                              "built-in-nodes/CreateHookLoraModelOnly",
+                              "built-in-nodes/CreateHookModelAsLora",
+                              "built-in-nodes/CreateHookModelAsLoraModelOnly"
+                            ]
+                          },
+                          {
+                            "group": "Manual",
+                            "pages": [
+                              "built-in-nodes/SetModelHooksOnCond"
+                            ]
+                          },
+                          {
+                            "group": "Scheduling",
+                            "pages": [
+                              "built-in-nodes/CreateHookKeyframe",
+                              "built-in-nodes/CreateHookKeyframesFromFloats",
+                              "built-in-nodes/CreateHookKeyframesInterpolated",
+                              "built-in-nodes/SetHookKeyframes"
+                            ]
+                          },
+                          "built-in-nodes/ConditioningTimestepsRange"
                         ]
                       },
                       {
-                        "group": "OpenAI",
+                        "group": "Loaders",
                         "pages": [
-                          "built-in-nodes/partner-node/image/openai/openai-gpt-image1",
-                          "built-in-nodes/partner-node/image/openai/openai-dalle2",
-                          "built-in-nodes/partner-node/image/openai/openai-dalle3"
+                          {
+                            "group": "Deprecated",
+                            "pages": [
+                              "built-in-nodes/DiffusersLoader"
+                            ]
+                          },
+                          {
+                            "group": "Qwen",
+                            "pages": [
+                              "built-in-nodes/QwenImageDiffsynthControlnet"
+                            ]
+                          },
+                          {
+                            "group": "Zimage",
+                            "pages": [
+                              "built-in-nodes/ZImageFunControlnet"
+                            ]
+                          },
+                          "built-in-nodes/CheckpointLoader",
+                          "built-in-nodes/CLIPLoader",
+                          "built-in-nodes/ClipLoader",
+                          "built-in-nodes/DeprecatedCheckpointLoader",
+                          "built-in-nodes/DeprecatedDiffusersLoader",
+                          "built-in-nodes/DualCLIPLoader",
+                          "built-in-nodes/LTXAVTextEncoderLoader",
+                          "built-in-nodes/ModelPatchLoader",
+                          "built-in-nodes/QuadrupleCLIPLoader",
+                          "built-in-nodes/TripleCLIPLoader",
+                          "built-in-nodes/UNETLoader"
                         ]
-                      }
-                    ]
-                  },
-                  {
-                    "group": "Video",
-                    "pages": [
+                      },
                       {
-                        "group": "Google",
+                        "group": "Model",
                         "pages": [
-                          "built-in-nodes/partner-node/video/google/google-veo2-video"
+                          "built-in-nodes/ModelSamplingAuraFlow",
+                          "built-in-nodes/ModelSamplingContinuousEDM",
+                          "built-in-nodes/ModelSamplingContinuousV",
+                          "built-in-nodes/ModelSamplingDiscrete",
+                          "built-in-nodes/ModelSamplingFlux",
+                          "built-in-nodes/ModelSamplingLTXV",
+                          "built-in-nodes/ModelSamplingSD3",
+                          "built-in-nodes/ModelSamplingStableCascade",
+                          "built-in-nodes/RenormCFG",
+                          "built-in-nodes/RescaleCFG"
                         ]
                       },
                       {
-                        "group": "Kling",
+                        "group": "Model Merging",
                         "pages": [
-                          "built-in-nodes/partner-node/video/kwai_vgi/kling-camera-controls",
-                          "built-in-nodes/partner-node/video/kwai_vgi/kling-text-to-video",
-                          "built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-i2v",
-                          "built-in-nodes/partner-node/video/kwai_vgi/kling-image-to-video",
-                          "built-in-nodes/partner-node/video/kwai_vgi/kling-start-end-frame-to-video",
-                          "built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-t2v"
+                          {
+                            "group": "Model Specific",
+                            "pages": [
+                              "built-in-nodes/ModelMergeAuraflow",
+                              "built-in-nodes/ModelMergeCosmos14B",
+                              "built-in-nodes/ModelMergeCosmos7B",
+                              "built-in-nodes/ModelMergeCosmosPredict2_14B",
+                              "built-in-nodes/ModelMergeCosmosPredict2_2B",
+                              "built-in-nodes/ModelMergeFlux1",
+                              "built-in-nodes/ModelMergeLTXV",
+                              "built-in-nodes/ModelMergeMochiPreview",
+                              "built-in-nodes/ModelMergeQwenImage",
+                              "built-in-nodes/ModelMergeSD1",
+                              "built-in-nodes/ModelMergeSD35_Large",
+                              "built-in-nodes/ModelMergeSD3_2B",
+                              "built-in-nodes/ModelMergeSDXL",
+                              "built-in-nodes/ModelMergeWAN2_1"
+                            ]
+                          },
+                          "built-in-nodes/CheckpointSave",
+                          "built-in-nodes/CLIPAdd",
+                          "built-in-nodes/CLIPMergeAdd",
+                          "built-in-nodes/CLIPMergeSimple",
+                          "built-in-nodes/ClipMergeSimple",
+                          "built-in-nodes/CLIPMergeSubtract",
+                          "built-in-nodes/CLIPSave",
+                          "built-in-nodes/ClipSave",
+                          "built-in-nodes/CLIPSubtract",
+                          "built-in-nodes/ImageOnlyCheckpointSave",
+                          "built-in-nodes/LoraSave",
+                          "built-in-nodes/ModelMergeAdd",
+                          "built-in-nodes/ModelMergeBlocks",
+                          "built-in-nodes/ModelMergeSimple",
+                          "built-in-nodes/ModelMergeSubtract",
+                          "built-in-nodes/ModelSave",
+                          "built-in-nodes/SaveLoRANode",
+                          "built-in-nodes/VAESave"
                         ]
                       },
                       {
-                        "group": "Luma",
+                        "group": "Model Patches",
                         "pages": [
-                          "built-in-nodes/partner-node/video/luma/luma-text-to-video",
-                          "built-in-nodes/partner-node/video/luma/luma-image-to-video",
-                          "built-in-nodes/partner-node/video/luma/luma-concepts"
+                          {
+                            "group": "Flux",
+                            "pages": [
+                              "built-in-nodes/USOStyleReference"
+                            ]
+                          },
+                          "built-in-nodes/ScaleROPE"
                         ]
                       },
                       {
-                        "group": "MiniMax",
+                        "group": "Photomaker",
                         "pages": [
-                          "built-in-nodes/partner-node/video/minimax/minimax-image-to-video",
-                          "built-in-nodes/partner-node/video/minimax/minimax-text-to-video"
+                          "built-in-nodes/PhotoMakerEncode",
+                          "built-in-nodes/PhotoMakerLoader"
                         ]
                       },
+                      "built-in-nodes/FreSca",
+                      "built-in-nodes/TorchCompileModel"
+                    ]
+                  },
+                  {
+                    "group": "API Node",
+                    "pages": [
                       {
-                        "group": "Pika",
+                        "group": "3D",
                         "pages": [
-                          "built-in-nodes/partner-node/video/pika/pika-text-to-video",
-                          "built-in-nodes/partner-node/video/pika/pika-scenes",
-                          "built-in-nodes/partner-node/video/pika/pika-image-to-video"
+                          {
+                            "group": "Meshy",
+                            "pages": [
+                              "built-in-nodes/MeshyAnimateModelNode",
+                              "built-in-nodes/MeshyImageToModelNode",
+                              "built-in-nodes/MeshyMultiImageToModelNode",
+                              "built-in-nodes/MeshyRefineNode",
+                              "built-in-nodes/MeshyRigModelNode",
+                              "built-in-nodes/MeshyTextToModelNode",
+                              "built-in-nodes/MeshyTextureNode"
+                            ]
+                          },
+                          {
+                            "group": "Rodin",
+                            "pages": [
+                              "built-in-nodes/Rodin3D_Detail",
+                              "built-in-nodes/Rodin3D_Gen2",
+                              "built-in-nodes/Rodin3D_Regular",
+                              "built-in-nodes/Rodin3D_Sketch",
+                              "built-in-nodes/Rodin3D_Smooth"
+                            ]
+                          },
+                          {
+                            "group": "Tencent",
+                            "pages": [
+                              "built-in-nodes/Tencent3DPartNode",
+                              "built-in-nodes/Tencent3DTextureEditNode",
+                              "built-in-nodes/TencentImageToModelNode",
+                              "built-in-nodes/TencentModelTo3DUVNode",
+                              "built-in-nodes/TencentTextToModelNode"
+                            ]
+                          },
+                          {
+                            "group": "Tripo",
+                            "pages": [
+                              "built-in-nodes/TripoConversionNode",
+                              "built-in-nodes/TripoImageToModelNode",
+                              "built-in-nodes/TripoMultiviewToModelNode",
+                              "built-in-nodes/TripoRefineNode",
+                              "built-in-nodes/TripoRetargetNode",
+                              "built-in-nodes/TripoRigNode",
+                              "built-in-nodes/TripoTextToModelNode",
+                              "built-in-nodes/TripoTextureNode"
+                            ]
+                          }
                         ]
                       },
                       {
-                        "group": "PixVerse",
+                        "group": "Audio",
                         "pages": [
-                          "built-in-nodes/partner-node/video/pixverse/pixverse-template",
-                          "built-in-nodes/partner-node/video/pixverse/pixverse-text-to-video",
-                          "built-in-nodes/partner-node/video/pixverse/pixverse-transition-video",
-                          "built-in-nodes/partner-node/video/pixverse/pixverse-image-to-video"
+                          {
+                            "group": "Elevenlabs",
+                            "pages": [
+                              "built-in-nodes/ElevenLabsAudioIsolation",
+                              "built-in-nodes/ElevenLabsInstantVoiceClone",
+                              "built-in-nodes/ElevenLabsSpeechToSpeech",
+                              "built-in-nodes/ElevenLabsSpeechToText",
+                              "built-in-nodes/ElevenLabsTextToDialogue",
+                              "built-in-nodes/ElevenLabsTextToSoundEffects",
+                              "built-in-nodes/ElevenLabsTextToSpeech",
+                              "built-in-nodes/ElevenLabsVoiceSelector"
+                            ]
+                          },
+                          {
+                            "group": "Stability Ai",
+                            "pages": [
+                              "built-in-nodes/StabilityAudioInpaint",
+                              "built-in-nodes/StabilityAudioToAudio"
+                            ]
+                          }
                         ]
-                      }
-                    ]
-                  }
-                ]
-              }
-            ]
-          },
-          {
-            "tab": "Development",
-            "pages": [
-              "development/overview",
-              {
-                "group": "ComfyUI Server",
-                "icon": "code",
-                "pages": [
-                  "development/comfyui-server/comms_overview",
-                  "development/comfyui-server/comms_messages",
-                  "development/comfyui-server/comms_routes",
-                  "development/comfyui-server/execution_model_inversion_guide",
-                  "development/comfyui-server/api-key-integration"
-                ]
-              },
-              {
-                "group": "Cloud API",
-                "icon": "cloud",
-                "pages": [
-                  "development/cloud/overview",
-                  "development/cloud/api-reference",
-                  "development/cloud/openapi"
-                ]
-              },
-              {
-                "group": "CLI",
-                "pages": [
-                  "comfy-cli/getting-started",
-                  "comfy-cli/reference",
-                  "comfy-cli/troubleshooting"
-                ]
-              },
-              {
-                "group": "Develop Custom Nodes",
-                "pages": [
-                  "custom-nodes/overview",
-                  "custom-nodes/walkthrough",
-                  {
-                    "group": "Backend",
-                    "icon": "python",
-                    "pages": [
-                      "custom-nodes/backend/server_overview",
-                      "custom-nodes/backend/lifecycle",
-                      "custom-nodes/backend/datatypes",
-                      "custom-nodes/backend/images_and_masks",
-                      "custom-nodes/backend/more_on_inputs",
-                      "custom-nodes/backend/lazy_evaluation",
-                      "custom-nodes/backend/expansion",
-                      "custom-nodes/backend/lists",
-                      "custom-nodes/backend/snippets",
-                      "custom-nodes/backend/tensors",
-                      "custom-nodes/backend/node-replacement"
-                    ]
-                  },
-                  {
-                    "group": "UI",
-                    "icon": "js",
-                    "pages": [
-                      "custom-nodes/js/javascript_overview",
-                      "custom-nodes/js/javascript_hooks",
-                      "custom-nodes/js/javascript_objects_and_hijacking",
-                      "custom-nodes/js/javascript_settings",
-                      "custom-nodes/js/javascript_dialog",
-                      "custom-nodes/js/javascript_toast",
-                      "custom-nodes/js/javascript_about_panel_badges",
-                      "custom-nodes/js/javascript_bottom_panel_tabs",
-                      "custom-nodes/js/javascript_sidebar_tabs",
-                      "custom-nodes/js/javascript_selection_toolbox",
-                      "custom-nodes/js/javascript_commands_keybindings",
-                      "custom-nodes/js/javascript_topbar_menu",
-                      "custom-nodes/js/context-menu-migration",
-                      "custom-nodes/js/subgraphs",
-                      "custom-nodes/js/javascript_examples",
-                      "custom-nodes/i18n"
-                    ]
-                  },
-                  "custom-nodes/v3_migration",
-                  "custom-nodes/help_page",
-                  "custom-nodes/workflow_templates",
-                  "custom-nodes/subgraph_blueprints"
-                ]
-              },
-              {
-                "group": "Registry",
-                "pages": [
-                  "registry/overview",
-                  "registry/publishing",
-                  "registry/claim-my-node",
-                  "registry/standards",
-                  "registry/cicd",
-                  "registry/specifications"
-                ]
-              },
-              {
-                "group": "Specifications",
-                "pages": [
-                  {
-                    "group": "Workflow JSON",
-                    "pages": ["specs/workflow_json", "specs/workflow_json_0.4"]
-                  },
-                  {
-                    "group": "Node Definitions",
-                    "pages": ["specs/nodedef_json", "specs/nodedef_json_1_0"]
-                  }
-                ]
-              }
-            ]
-          },
-          {
-            "tab": "Support",
-            "pages": [
-              "support/contact-support",
-              {
-                "group": "Account Management",
-                "icon": "user",
-                "pages": [
-                  "account/create-account",
-                  "account/login",
-                  "account/delete-account"
-                ]
-              },
+                      },
+                      {
+                        "group": "Image",
+                        "pages": [
+                          {
+                            "group": "BFL",
+                            "pages": [
+                              "built-in-nodes/partner-node/image/bfl/flux-1-1-pro-ultra-image"
+                            ]
+                          },
+                          {
+                            "group": "Bfl",
+                            "pages": [
+                              "built-in-nodes/FluxProCannyNode",
+                              "built-in-nodes/FluxProDepthNode",
+                              "built-in-nodes/FluxProExpandNode",
+                              "built-in-nodes/FluxProFillNode",
+                              "built-in-nodes/FluxProImageNode",
+                              "built-in-nodes/FluxProUltraImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Bria",
+                            "pages": [
+                              "built-in-nodes/BriaImageEditNode",
+                              "built-in-nodes/BriaRemoveImageBackground"
+                            ]
+                          },
+                          {
+                            "group": "Bytedance",
+                            "pages": [
+                              "built-in-nodes/ByteDanceImageEditNode",
+                              "built-in-nodes/ByteDanceImageNode",
+                              "built-in-nodes/ByteDanceSeedreamNode"
+                            ]
+                          },
+                          {
+                            "group": "Gemini",
+                            "pages": [
+                              "built-in-nodes/GeminiImage",
+                              "built-in-nodes/GeminiImage2Node",
+                              "built-in-nodes/GeminiImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Grok",
+                            "pages": [
+                              "built-in-nodes/GrokImageEditNode",
+                              "built-in-nodes/GrokImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Hitpaw",
+                            "pages": [
+                              "built-in-nodes/HitPawGeneralImageEnhance"
+                            ]
+                          },
+                          {
+                            "group": "Ideogram",
+                            "pages": [
+                              "built-in-nodes/IdeogramV1",
+                              "built-in-nodes/IdeogramV2",
+                              "built-in-nodes/IdeogramV3"
+                            ]
+                          },
+                          {
+                            "group": "Ideogram",
+                            "pages": [
+                              "built-in-nodes/partner-node/image/ideogram/ideogram-v1",
+                              "built-in-nodes/partner-node/image/ideogram/ideogram-v2",
+                              "built-in-nodes/partner-node/image/ideogram/ideogram-v3"
+                            ]
+                          },
+                          {
+                            "group": "Kling",
+                            "pages": [
+                              "built-in-nodes/KlingImageGenerationNode",
+                              "built-in-nodes/KlingOmniProImageNode",
+                              "built-in-nodes/KlingVirtualTryOnNode"
+                            ]
+                          },
+                          {
+                            "group": "Luma",
+                            "pages": [
+                              "built-in-nodes/LumaConceptsNode",
+                              "built-in-nodes/LumaImageModifyNode",
+                              "built-in-nodes/LumaReferenceNode"
+                            ]
+                          },
+                          {
+                            "group": "Luma",
+                            "pages": [
+                              "built-in-nodes/partner-node/image/luma/luma-image-to-image",
+                              "built-in-nodes/partner-node/image/luma/luma-reference",
+                              "built-in-nodes/partner-node/image/luma/luma-text-to-image"
+                            ]
+                          },
+                          {
+                            "group": "Magnific",
+                            "pages": [
+                              "built-in-nodes/MagnificImageRelightNode",
+                              "built-in-nodes/MagnificImageSkinEnhancerNode",
+                              "built-in-nodes/MagnificImageStyleTransferNode",
+                              "built-in-nodes/MagnificImageUpscalerCreativeNode",
+                              "built-in-nodes/MagnificImageUpscalerPreciseV2Node"
+                            ]
+                          },
+                          {
+                            "group": "OpenAI",
+                            "pages": [
+                              "built-in-nodes/partner-node/image/openai/openai-dalle2",
+                              "built-in-nodes/partner-node/image/openai/openai-dalle3",
+                              "built-in-nodes/partner-node/image/openai/openai-gpt-image1"
+                            ]
+                          },
+                          {
+                            "group": "Openai",
+                            "pages": [
+                              "built-in-nodes/OpenAIDalle2",
+                              "built-in-nodes/OpenAIDalle3",
+                              "built-in-nodes/OpenAIGPTImage1"
+                            ]
+                          },
+                          {
+                            "group": "Recraft",
+                            "pages": [
+                              "built-in-nodes/RecraftColorRGB",
+                              "built-in-nodes/RecraftControls",
+                              "built-in-nodes/RecraftCreateStyleNode",
+                              "built-in-nodes/RecraftCreativeUpscaleNode",
+                              "built-in-nodes/RecraftCrispUpscaleNode",
+                              "built-in-nodes/RecraftImageInpaintingNode",
+                              "built-in-nodes/RecraftImageToImageNode",
+                              "built-in-nodes/RecraftRemoveBackgroundNode",
+                              "built-in-nodes/RecraftReplaceBackgroundNode",
+                              "built-in-nodes/RecraftStyleV3DigitalIllustration",
+                              "built-in-nodes/RecraftStyleV3InfiniteStyleLibrary",
+                              "built-in-nodes/RecraftStyleV3LogoRaster",
+                              "built-in-nodes/RecraftStyleV3RealisticImage",
+                              "built-in-nodes/RecraftStyleV3VectorIllustrationNode",
+                              "built-in-nodes/RecraftTextToImageNode",
+                              "built-in-nodes/RecraftTextToVectorNode",
+                              "built-in-nodes/RecraftV4TextToImageNode",
+                              "built-in-nodes/RecraftV4TextToVectorNode",
+                              "built-in-nodes/RecraftVectorizeImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Recraft",
+                            "pages": [
+                              "built-in-nodes/partner-node/image/recraft/recraft-color-rgb",
+                              "built-in-nodes/partner-node/image/recraft/recraft-controls",
+                              "built-in-nodes/partner-node/image/recraft/recraft-creative-upscale",
+                              "built-in-nodes/partner-node/image/recraft/recraft-crisp-upscale",
+                              "built-in-nodes/partner-node/image/recraft/recraft-image-inpainting",
+                              "built-in-nodes/partner-node/image/recraft/recraft-image-to-image",
+                              "built-in-nodes/partner-node/image/recraft/recraft-remove-background",
+                              "built-in-nodes/partner-node/image/recraft/recraft-replace-background",
+                              "built-in-nodes/partner-node/image/recraft/recraft-style-digital-illustration",
+                              "built-in-nodes/partner-node/image/recraft/recraft-style-logo-raster",
+                              "built-in-nodes/partner-node/image/recraft/recraft-style-realistic-image",
+                              "built-in-nodes/partner-node/image/recraft/recraft-text-to-image",
+                              "built-in-nodes/partner-node/image/recraft/recraft-text-to-vector",
+                              "built-in-nodes/partner-node/image/recraft/recraft-vectorize-image",
+                              "built-in-nodes/partner-node/image/recraft/save-svg"
+                            ]
+                          },
+                          {
+                            "group": "Runway",
+                            "pages": [
+                              "built-in-nodes/RunwayTextToImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Stability AI",
+                            "pages": [
+                              "built-in-nodes/partner-node/image/stability-ai/stability-ai-stable-diffusion-3-5-image",
+                              "built-in-nodes/partner-node/image/stability-ai/stability-ai-stable-image-ultra"
+                            ]
+                          },
+                          {
+                            "group": "Stability Ai",
+                            "pages": [
+                              "built-in-nodes/StabilityStableImageSD_3_5Node",
+                              "built-in-nodes/StabilityStableImageUltraNode",
+                              "built-in-nodes/StabilityTextToAudio",
+                              "built-in-nodes/StabilityUpscaleConservativeNode",
+                              "built-in-nodes/StabilityUpscaleCreativeNode",
+                              "built-in-nodes/StabilityUpscaleFastNode"
+                            ]
+                          },
+                          {
+                            "group": "Topaz",
+                            "pages": [
+                              "built-in-nodes/TopazImageEnhance"
+                            ]
+                          },
+                          {
+                            "group": "Wan",
+                            "pages": [
+                              "built-in-nodes/WanImageToImageApi",
+                              "built-in-nodes/WanTextToImageApi"
+                            ]
+                          },
+                          {
+                            "group": "Wavespeed",
+                            "pages": [
+                              "built-in-nodes/WavespeedImageUpscaleNode"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Text",
+                        "pages": [
+                          {
+                            "group": "Gemini",
+                            "pages": [
+                              "built-in-nodes/GeminiInputFiles",
+                              "built-in-nodes/GeminiNode"
+                            ]
+                          },
+                          {
+                            "group": "Openai",
+                            "pages": [
+                              "built-in-nodes/OpenAIChatConfig",
+                              "built-in-nodes/OpenAIChatNode",
+                              "built-in-nodes/OpenAIInputFiles"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Video",
+                        "pages": [
+                          {
+                            "group": "Bria",
+                            "pages": [
+                              "built-in-nodes/BriaRemoveVideoBackground"
+                            ]
+                          },
+                          {
+                            "group": "Bytedance",
+                            "pages": [
+                              "built-in-nodes/ByteDanceFirstLastFrameNode",
+                              "built-in-nodes/ByteDanceImageReferenceNode",
+                              "built-in-nodes/ByteDanceImageToVideoNode",
+                              "built-in-nodes/ByteDanceTextToVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Google",
+                            "pages": [
+                              "built-in-nodes/partner-node/video/google/google-veo2-video"
+                            ]
+                          },
+                          {
+                            "group": "Grok",
+                            "pages": [
+                              "built-in-nodes/GrokVideoEditNode",
+                              "built-in-nodes/GrokVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Hitpaw",
+                            "pages": [
+                              "built-in-nodes/HitPawVideoEnhance"
+                            ]
+                          },
+                          {
+                            "group": "Kling",
+                            "pages": [
+                              "built-in-nodes/KlingCameraControlI2VNode",
+                              "built-in-nodes/KlingCameraControls",
+                              "built-in-nodes/KlingCameraControlT2VNode",
+                              "built-in-nodes/KlingDualCharacterVideoEffectNode",
+                              "built-in-nodes/KlingFirstLastFrameNode",
+                              "built-in-nodes/KlingImage2VideoNode",
+                              "built-in-nodes/KlingImageToVideoWithAudio",
+                              "built-in-nodes/KlingLipSyncAudioToVideoNode",
+                              "built-in-nodes/KlingLipSyncTextToVideoNode",
+                              "built-in-nodes/KlingMotionControl",
+                              "built-in-nodes/KlingOmniProEditVideoNode",
+                              "built-in-nodes/KlingOmniProFirstLastFrameNode",
+                              "built-in-nodes/KlingOmniProImageToVideoNode",
+                              "built-in-nodes/KlingOmniProTextToVideoNode",
+                              "built-in-nodes/KlingOmniProVideoToVideoNode",
+                              "built-in-nodes/KlingSingleImageVideoEffectNode",
+                              "built-in-nodes/KlingStartEndFrameNode",
+                              "built-in-nodes/KlingTextToVideoNode",
+                              "built-in-nodes/KlingTextToVideoWithAudio",
+                              "built-in-nodes/KlingVideoExtendNode",
+                              "built-in-nodes/KlingVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Kling",
+                            "pages": [
+                              "built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-i2v",
+                              "built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-t2v",
+                              "built-in-nodes/partner-node/video/kwai_vgi/kling-camera-controls",
+                              "built-in-nodes/partner-node/video/kwai_vgi/kling-image-to-video",
+                              "built-in-nodes/partner-node/video/kwai_vgi/kling-start-end-frame-to-video",
+                              "built-in-nodes/partner-node/video/kwai_vgi/kling-text-to-video"
+                            ]
+                          },
+                          {
+                            "group": "Ltxv",
+                            "pages": [
+                              "built-in-nodes/LtxvApiImageToVideo",
+                              "built-in-nodes/LtxvApiTextToVideo"
+                            ]
+                          },
+                          {
+                            "group": "Luma",
+                            "pages": [
+                              "built-in-nodes/LumaImageNode",
+                              "built-in-nodes/LumaImageToVideoNode",
+                              "built-in-nodes/LumaVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Luma",
+                            "pages": [
+                              "built-in-nodes/partner-node/video/luma/luma-concepts",
+                              "built-in-nodes/partner-node/video/luma/luma-image-to-video",
+                              "built-in-nodes/partner-node/video/luma/luma-text-to-video"
+                            ]
+                          },
+                          {
+                            "group": "MiniMax",
+                            "pages": [
+                              "built-in-nodes/partner-node/video/minimax/minimax-image-to-video",
+                              "built-in-nodes/partner-node/video/minimax/minimax-text-to-video"
+                            ]
+                          },
+                          {
+                            "group": "Minimax",
+                            "pages": [
+                              "built-in-nodes/MinimaxHailuoVideoNode",
+                              "built-in-nodes/MinimaxImageToVideoNode",
+                              "built-in-nodes/MinimaxSubjectToVideoNode",
+                              "built-in-nodes/MinimaxTextToVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Moonvalley Marey",
+                            "pages": [
+                              "built-in-nodes/MoonvalleyImg2VideoNode",
+                              "built-in-nodes/MoonvalleyTxt2VideoNode",
+                              "built-in-nodes/MoonvalleyVideo2VideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Pika",
+                            "pages": [
+                              "built-in-nodes/partner-node/video/pika/pika-image-to-video",
+                              "built-in-nodes/partner-node/video/pika/pika-scenes",
+                              "built-in-nodes/partner-node/video/pika/pika-text-to-video",
+                              "built-in-nodes/Pikadditions",
+                              "built-in-nodes/Pikaffects",
+                              "built-in-nodes/PikaImageToVideoNode2_2",
+                              "built-in-nodes/PikaScenesV2_2",
+                              "built-in-nodes/PikaStartEndFrameNode2_2",
+                              "built-in-nodes/Pikaswaps",
+                              "built-in-nodes/PikaTextToVideoNode2_2"
+                            ]
+                          },
+                          {
+                            "group": "PixVerse",
+                            "pages": [
+                              "built-in-nodes/partner-node/video/pixverse/pixverse-image-to-video",
+                              "built-in-nodes/partner-node/video/pixverse/pixverse-template",
+                              "built-in-nodes/partner-node/video/pixverse/pixverse-text-to-video",
+                              "built-in-nodes/partner-node/video/pixverse/pixverse-transition-video"
+                            ]
+                          },
+                          {
+                            "group": "Pixverse",
+                            "pages": [
+                              "built-in-nodes/PixverseImageToVideoNode",
+                              "built-in-nodes/PixverseTemplateNode",
+                              "built-in-nodes/PixverseTextToVideoNode",
+                              "built-in-nodes/PixverseTransitionVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Runway",
+                            "pages": [
+                              "built-in-nodes/RunwayFirstLastFrameNode",
+                              "built-in-nodes/RunwayImageToVideoNodeGen3a",
+                              "built-in-nodes/RunwayImageToVideoNodeGen4"
+                            ]
+                          },
+                          {
+                            "group": "Sora",
+                            "pages": [
+                              "built-in-nodes/OpenAIVideoSora2"
+                            ]
+                          },
+                          {
+                            "group": "Topaz",
+                            "pages": [
+                              "built-in-nodes/TopazVideoEnhance"
+                            ]
+                          },
+                          {
+                            "group": "Veo",
+                            "pages": [
+                              "built-in-nodes/Veo3FirstLastFrameNode",
+                              "built-in-nodes/Veo3VideoGenerationNode",
+                              "built-in-nodes/VeoVideoGenerationNode"
+                            ]
+                          },
+                          {
+                            "group": "Vidu",
+                            "pages": [
+                              "built-in-nodes/Vidu2ImageToVideoNode",
+                              "built-in-nodes/Vidu2ReferenceVideoNode",
+                              "built-in-nodes/Vidu2StartEndToVideoNode",
+                              "built-in-nodes/Vidu2TextToVideoNode",
+                              "built-in-nodes/Vidu3ImageToVideoNode",
+                              "built-in-nodes/Vidu3StartEndToVideoNode",
+                              "built-in-nodes/Vidu3TextToVideoNode",
+                              "built-in-nodes/ViduExtendVideoNode",
+                              "built-in-nodes/ViduImageToVideoNode",
+                              "built-in-nodes/ViduMultiFrameVideoNode",
+                              "built-in-nodes/ViduReferenceVideoNode",
+                              "built-in-nodes/ViduStartEndToVideoNode",
+                              "built-in-nodes/ViduTextToVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Wan",
+                            "pages": [
+                              "built-in-nodes/WanImageToVideoApi",
+                              "built-in-nodes/WanReferenceVideoApi",
+                              "built-in-nodes/WanTextToVideoApi"
+                            ]
+                          },
+                          {
+                            "group": "Wavespeed",
+                            "pages": [
+                              "built-in-nodes/WavespeedFlashVSRNode"
+                            ]
+                          }
+                        ]
+                      }
+                    ]
+                  },
+                  {
+                    "group": "Audio",
+                    "pages": [
+                      "built-in-nodes/AudioAdjustVolume",
+                      "built-in-nodes/AudioConcat",
+                      "built-in-nodes/AudioEqualizer3Band",
+                      "built-in-nodes/AudioMerge",
+                      "built-in-nodes/EmptyAudio",
+                      "built-in-nodes/JoinAudioChannels",
+                      "built-in-nodes/LoadAudio",
+                      "built-in-nodes/LTXVAudioVAEDecode",
+                      "built-in-nodes/LTXVAudioVAEEncode",
+                      "built-in-nodes/LTXVAudioVAELoader",
+                      "built-in-nodes/PreviewAudio",
+                      "built-in-nodes/RecordAudio",
+                      "built-in-nodes/SaveAudio",
+                      "built-in-nodes/SaveAudioMP3",
+                      "built-in-nodes/SaveAudioOpus",
+                      "built-in-nodes/SplitAudioChannels",
+                      "built-in-nodes/TrimAudioDuration"
+                    ]
+                  },
+                  {
+                    "group": "Camera",
+                    "pages": [
+                      "built-in-nodes/WanCameraEmbedding"
+                    ]
+                  },
+                  {
+                    "group": "Conditioning",
+                    "pages": [
+                      {
+                        "group": "3D Models",
+                        "pages": [
+                          "built-in-nodes/StableZero123_Conditioning",
+                          "built-in-nodes/StableZero123_Conditioning_Batched",
+                          "built-in-nodes/SV3D_Conditioning"
+                        ]
+                      },
+                      {
+                        "group": "Controlnet",
+                        "pages": [
+                          "built-in-nodes/ControlNetApply",
+                          "built-in-nodes/ControlNetApplyAdvanced",
+                          "built-in-nodes/ControlNetApplySD3",
+                          "built-in-nodes/ControlNetInpaintingAliMamaApply",
+                          "built-in-nodes/SetUnionControlNetType"
+                        ]
+                      },
+                      {
+                        "group": "Gligen",
+                        "pages": [
+                          "built-in-nodes/GLIGENTextBoxApply"
+                        ]
+                      },
+                      {
+                        "group": "Inpaint",
+                        "pages": [
+                          "built-in-nodes/CosmosImageToVideoLatent",
+                          "built-in-nodes/CosmosPredict2ImageToVideoLatent",
+                          "built-in-nodes/InpaintModelConditioning",
+                          "built-in-nodes/Wan22ImageToVideoLatent"
+                        ]
+                      },
+                      {
+                        "group": "Instructpix2Pix",
+                        "pages": [
+                          "built-in-nodes/InstructPixToPixConditioning"
+                        ]
+                      },
+                      {
+                        "group": "Lotus",
+                        "pages": [
+                          "built-in-nodes/LotusConditioning"
+                        ]
+                      },
+                      {
+                        "group": "Stable Cascade",
+                        "pages": [
+                          "built-in-nodes/StableCascade_StageB_Conditioning",
+                          "built-in-nodes/StableCascade_SuperResolutionControlnet"
+                        ]
+                      },
+                      {
+                        "group": "Style Model",
+                        "pages": [
+                          "built-in-nodes/StyleModelApply"
+                        ]
+                      },
+                      {
+                        "group": "Upscale Diffusion",
+                        "pages": [
+                          "built-in-nodes/SD_4XUpscale_Conditioning"
+                        ]
+                      },
+                      {
+                        "group": "Video Models",
+                        "pages": [
+                          "built-in-nodes/conditioning/video-models/wan-vace-to-video",
+                          "built-in-nodes/GenerateTracks",
+                          "built-in-nodes/Hunyuan3Dv2Conditioning",
+                          "built-in-nodes/Hunyuan3Dv2ConditioningMultiView",
+                          "built-in-nodes/HunyuanImageToVideo",
+                          "built-in-nodes/HunyuanVideo15ImageToVideo",
+                          "built-in-nodes/Kandinsky5ImageToVideo",
+                          "built-in-nodes/LTXVAddGuide",
+                          "built-in-nodes/LTXVConditioning",
+                          "built-in-nodes/LTXVCropGuides",
+                          "built-in-nodes/LTXVImgToVideo",
+                          "built-in-nodes/LTXVImgToVideoInplace",
+                          "built-in-nodes/NormalizeVideoLatentStart",
+                          "built-in-nodes/Stablezero123Conditioning",
+                          "built-in-nodes/Stablezero123ConditioningBatched",
+                          "built-in-nodes/SVD_img2vid_Conditioning",
+                          "built-in-nodes/SvdImg2vidConditioning",
+                          "built-in-nodes/Wan22FunControlToVideo",
+                          "built-in-nodes/WanAnimateToVideo",
+                          "built-in-nodes/WanCameraImageToVideo",
+                          "built-in-nodes/WanFirstLastFrameToVideo",
+                          "built-in-nodes/WanFunControlToVideo",
+                          "built-in-nodes/WanFunInpaintToVideo",
+                          "built-in-nodes/WanHuMoImageToVideo",
+                          "built-in-nodes/WanImageToVideo",
+                          "built-in-nodes/WanInfiniteTalkToVideo",
+                          "built-in-nodes/WanMoveConcatTrack",
+                          "built-in-nodes/WanMoveTracksFromCoords",
+                          "built-in-nodes/WanMoveTrackToVideo",
+                          "built-in-nodes/WanMoveVisualizeTracks",
+                          "built-in-nodes/WanPhantomSubjectToVideo",
+                          "built-in-nodes/WanSoundImageToVideo",
+                          "built-in-nodes/WanSoundImageToVideoExtend",
+                          "built-in-nodes/WanTrackToVideo",
+                          "built-in-nodes/WanVaceToVideo"
+                        ]
+                      },
+                      "built-in-nodes/AudioEncoderEncode",
+                      "built-in-nodes/CLIPSetLastLayer",
+                      "built-in-nodes/ClipSetLastLayer",
+                      "built-in-nodes/CLIPTextEncode",
+                      "built-in-nodes/ClipTextEncode",
+                      "built-in-nodes/CLIPTextEncodeControlnet",
+                      "built-in-nodes/CLIPTextEncodeLumina2",
+                      "built-in-nodes/CLIPVisionEncode",
+                      "built-in-nodes/ClipVisionEncode",
+                      "built-in-nodes/ConditioningAverage",
+                      "built-in-nodes/ConditioningCombine",
+                      "built-in-nodes/ConditioningConcat",
+                      "built-in-nodes/ConditioningSetArea",
+                      "built-in-nodes/ConditioningSetAreaPercentage",
+                      "built-in-nodes/ConditioningSetAreaPercentageVideo",
+                      "built-in-nodes/ConditioningSetAreaStrength",
+                      "built-in-nodes/ConditioningSetMask",
+                      "built-in-nodes/ConditioningStableAudio",
+                      "built-in-nodes/HunyuanRefinerLatent",
+                      "built-in-nodes/PerpNeg",
+                      "built-in-nodes/Sd4xupscaleConditioning",
+                      "built-in-nodes/T5TokenizerOptions",
+                      "built-in-nodes/TextEncodeAceStepAudio",
+                      "built-in-nodes/TextEncodeAceStepAudio1.5",
+                      "built-in-nodes/unCLIPConditioning"
+                    ]
+                  },
+                  {
+                    "group": "Context",
+                    "pages": [
+                      "built-in-nodes/ContextWindowsManual",
+                      "built-in-nodes/WanContextWindowsManual"
+                    ]
+                  },
+                  {
+                    "group": "Image",
+                    "pages": [
+                      {
+                        "group": "Animation",
+                        "pages": [
+                          "built-in-nodes/SaveAnimatedPNG",
+                          "built-in-nodes/SaveAnimatedWEBP"
+                        ]
+                      },
+                      {
+                        "group": "Batch",
+                        "pages": [
+                          "built-in-nodes/ImageFromBatch",
+                          "built-in-nodes/ImageRGBToYUV",
+                          "built-in-nodes/ImageYUVToRGB",
+                          "built-in-nodes/RebatchImages",
+                          "built-in-nodes/RepeatImageBatch"
+                        ]
+                      },
+                      {
+                        "group": "Image",
+                        "pages": [
+                          "built-in-nodes/AdjustBrightness",
+                          "built-in-nodes/AdjustContrast",
+                          "built-in-nodes/CenterCropImages",
+                          "built-in-nodes/ImageDeduplication",
+                          "built-in-nodes/ImageGrid",
+                          "built-in-nodes/MergeImageLists",
+                          "built-in-nodes/NormalizeImages",
+                          "built-in-nodes/RandomCropImages",
+                          "built-in-nodes/ResizeImagesByLongerEdge",
+                          "built-in-nodes/ResizeImagesByShorterEdge",
+                          "built-in-nodes/ShuffleDataset",
+                          "built-in-nodes/ShuffleImageTextDataset"
+                        ]
+                      },
+                      {
+                        "group": "Postprocessing",
+                        "pages": [
+                          "built-in-nodes/ImageBlend",
+                          "built-in-nodes/ImageBlur",
+                          "built-in-nodes/ImageQuantize",
+                          "built-in-nodes/ImageSharpen",
+                          "built-in-nodes/Morphology"
+                        ]
+                      },
+                      {
+                        "group": "Preprocessors",
+                        "pages": [
+                          "built-in-nodes/Canny"
+                        ]
+                      },
+                      {
+                        "group": "Save",
+                        "pages": [
+                          "built-in-nodes/SaveSVGNode"
+                        ]
+                      },
+                      {
+                        "group": "Shader",
+                        "pages": [
+                          "built-in-nodes/GLSLShader"
+                        ]
+                      },
+                      {
+                        "group": "Text",
+                        "pages": [
+                          "built-in-nodes/AddTextPrefix",
+                          "built-in-nodes/AddTextSuffix",
+                          "built-in-nodes/MergeTextLists",
+                          "built-in-nodes/ReplaceText",
+                          "built-in-nodes/StripWhitespace",
+                          "built-in-nodes/TextToLowercase",
+                          "built-in-nodes/TextToUppercase",
+                          "built-in-nodes/TruncateText"
+                        ]
+                      },
+                      {
+                        "group": "Transform",
+                        "pages": [
+                          "built-in-nodes/ImageCrop",
+                          "built-in-nodes/ImageCropV2",
+                          "built-in-nodes/ImageFlip",
+                          "built-in-nodes/ImageRotate",
+                          "built-in-nodes/ImageStitch",
+                          "built-in-nodes/ResizeAndPadImage"
+                        ]
+                      },
+                      {
+                        "group": "Upscaling",
+                        "pages": [
+                          "built-in-nodes/ImageScale",
+                          "built-in-nodes/ImageScaleBy",
+                          "built-in-nodes/ImageScaleToMaxDimension",
+                          "built-in-nodes/ImageScaleToTotalPixels",
+                          "built-in-nodes/ImageUpscaleWithModel"
+                        ]
+                      },
+                      {
+                        "group": "Video",
+                        "pages": [
+                          "built-in-nodes/CreateVideo",
+                          "built-in-nodes/GetVideoComponents",
+                          "built-in-nodes/LoadVideo",
+                          "built-in-nodes/SaveVideo",
+                          "built-in-nodes/SaveWEBM",
+                          "built-in-nodes/Video Slice"
+                        ]
+                      },
+                      "built-in-nodes/BatchImagesNode",
+                      "built-in-nodes/EmptyImage",
+                      "built-in-nodes/GetImageSize",
+                      "built-in-nodes/ImageAddNoise",
+                      "built-in-nodes/ImageBatch",
+                      "built-in-nodes/ImageCompare",
+                      "built-in-nodes/ImageCompositeMasked",
+                      "built-in-nodes/ImageInvert",
+                      "built-in-nodes/ImagePadForOutpaint",
+                      "built-in-nodes/LoadImage",
+                      "built-in-nodes/LoadImageDataSetFromFolder",
+                      "built-in-nodes/LoadImageOutput",
+                      "built-in-nodes/LoadImageSetFromFolderNode",
+                      "built-in-nodes/LoadImageSetNode",
+                      "built-in-nodes/LoadImageTextDataSetFromFolder",
+                      "built-in-nodes/LoadImageTextSetFromFolderNode",
+                      "built-in-nodes/LoadTrainingDataset",
+                      "built-in-nodes/LoraLoader",
+                      "built-in-nodes/LoraLoaderModelOnly",
+                      "built-in-nodes/LTXVPreprocess",
+                      "built-in-nodes/MakeTrainingDataset",
+                      "built-in-nodes/PreviewImage",
+                      "built-in-nodes/ResizeImageMaskNode",
+                      "built-in-nodes/ResolutionBucket",
+                      "built-in-nodes/SaveImage",
+                      "built-in-nodes/SaveImageDataSetToFolder",
+                      "built-in-nodes/SaveImageTextDataSetToFolder",
+                      "built-in-nodes/SaveTrainingDataset",
+                      "built-in-nodes/WebcamCapture"
+                    ]
+                  },
+                  {
+                    "group": "Latent",
+                    "pages": [
+                      {
+                        "group": "3D",
+                        "pages": [
+                          "built-in-nodes/EmptyLatentHunyuan3Dv2",
+                          "built-in-nodes/VAEDecodeHunyuan3D"
+                        ]
+                      },
+                      {
+                        "group": "Advanced",
+                        "pages": [
+                          {
+                            "group": "Operations",
+                            "pages": [
+                              "built-in-nodes/LatentApplyOperation",
+                              "built-in-nodes/LatentApplyOperationCFG",
+                              "built-in-nodes/LatentOperationSharpen",
+                              "built-in-nodes/LatentOperationTonemapReinhard"
+                            ]
+                          },
+                          "built-in-nodes/LatentAdd",
+                          "built-in-nodes/LatentBatchSeedBehavior",
+                          "built-in-nodes/LatentConcat",
+                          "built-in-nodes/LatentCut",
+                          "built-in-nodes/LatentCutToBatch",
+                          "built-in-nodes/LatentInterpolate",
+                          "built-in-nodes/LatentMultiply",
+                          "built-in-nodes/LatentSubtract"
+                        ]
+                      },
+                      {
+                        "group": "Audio",
+                        "pages": [
+                          "built-in-nodes/EmptyAceStep1.5LatentAudio",
+                          "built-in-nodes/EmptyAceStepLatentAudio",
+                          "built-in-nodes/EmptyLatentAudio",
+                          "built-in-nodes/LTXVEmptyLatentAudio",
+                          "built-in-nodes/VAEDecodeAudio",
+                          "built-in-nodes/VAEDecodeAudioTiled",
+                          "built-in-nodes/VAEEncodeAudio"
+                        ]
+                      },
+                      {
+                        "group": "Batch",
+                        "pages": [
+                          "built-in-nodes/LatentBatch",
+                          "built-in-nodes/LatentFromBatch",
+                          "built-in-nodes/RebatchLatents",
+                          "built-in-nodes/RepeatLatentBatch",
+                          "built-in-nodes/ReplaceVideoLatentFrames"
+                        ]
+                      },
+                      {
+                        "group": "Chroma Radiance",
+                        "pages": [
+                          "built-in-nodes/EmptyChromaRadianceLatentImage"
+                        ]
+                      },
+                      {
+                        "group": "Inpaint",
+                        "pages": [
+                          "built-in-nodes/SetLatentNoiseMask",
+                          "built-in-nodes/VAEEncodeForInpaint"
+                        ]
+                      },
+                      {
+                        "group": "Qwen",
+                        "pages": [
+                          "built-in-nodes/EmptyQwenImageLayeredLatentImage"
+                        ]
+                      },
+                      {
+                        "group": "Sd3",
+                        "pages": [
+                          "built-in-nodes/EmptySD3LatentImage"
+                        ]
+                      },
+                      {
+                        "group": "Stable Cascade",
+                        "pages": [
+                          "built-in-nodes/StableCascade_EmptyLatentImage",
+                          "built-in-nodes/StableCascade_StageC_VAEEncode"
+                        ]
+                      },
+                      {
+                        "group": "Transform",
+                        "pages": [
+                          "built-in-nodes/LatentCrop",
+                          "built-in-nodes/LatentFlip",
+                          "built-in-nodes/LatentRotate"
+                        ]
+                      },
+                      {
+                        "group": "Video",
+                        "pages": [
+                          {
+                            "group": "Ltxv",
+                            "pages": [
+                              "built-in-nodes/EmptyLTXVLatentVideo",
+                              "built-in-nodes/LTXVConcatAVLatent",
+                              "built-in-nodes/LTXVSeparateAVLatent"
+                            ]
+                          },
+                          "built-in-nodes/EmptyCosmosLatentVideo",
+                          "built-in-nodes/EmptyHunyuanLatentVideo",
+                          "built-in-nodes/EmptyHunyuanVideo15Latent",
+                          "built-in-nodes/EmptyMochiLatentVideo",
+                          "built-in-nodes/latent/video/trim-video-latent",
+                          "built-in-nodes/LTXVLatentUpsampler",
+                          "built-in-nodes/TrimVideoLatent"
+                        ]
+                      },
+                      "built-in-nodes/BatchLatentsNode",
+                      "built-in-nodes/EmptyFlux2LatentImage",
+                      "built-in-nodes/EmptyHunyuanImageLatent",
+                      "built-in-nodes/EmptyLatentImage",
+                      "built-in-nodes/HunyuanVideo15LatentUpscaleWithModel",
+                      "built-in-nodes/LatentBlend",
+                      "built-in-nodes/LatentComposite",
+                      "built-in-nodes/LatentCompositeMasked",
+                      "built-in-nodes/LatentUpscale",
+                      "built-in-nodes/LatentUpscaleBy",
+                      "built-in-nodes/SaveLatent",
+                      "built-in-nodes/VAEDecode",
+                      "built-in-nodes/VAEDecodeTiled",
+                      "built-in-nodes/VAEEncode",
+                      "built-in-nodes/VAEEncodeTiled"
+                    ]
+                  },
+                  {
+                    "group": "Loader",
+                    "pages": [
+                      {
+                        "group": "Video Models",
+                        "pages": [
+                          "built-in-nodes/ImageOnlyCheckpointLoader"
+                        ]
+                      },
+                      "built-in-nodes/AudioEncoderLoader",
+                      "built-in-nodes/CheckpointLoaderSimple",
+                      "built-in-nodes/CLIPVisionLoader",
+                      "built-in-nodes/ClipVisionLoader",
+                      "built-in-nodes/ControlNetLoader",
+                      "built-in-nodes/DiffControlNetLoader",
+                      "built-in-nodes/GLIGENLoader",
+                      "built-in-nodes/HunyuanVideo15SuperResolution",
+                      "built-in-nodes/HypernetworkLoader",
+                      "built-in-nodes/LatentUpscaleModelLoader",
+                      "built-in-nodes/LoadLatent",
+                      "built-in-nodes/LoraLoaderBypass",
+                      "built-in-nodes/LoraLoaderBypassModelOnly",
+                      "built-in-nodes/LoraModelLoader",
+                      "built-in-nodes/SaveLoRA",
+                      "built-in-nodes/StyleModelLoader",
+                      "built-in-nodes/unCLIPCheckpointLoader",
+                      "built-in-nodes/UpscaleModelLoader",
+                      "built-in-nodes/VAELoader"
+                    ]
+                  },
+                  {
+                    "group": "Logic",
+                    "pages": [
+                      "built-in-nodes/AutogrowNamesTestNode",
+                      "built-in-nodes/AutogrowPrefixTestNode",
+                      "built-in-nodes/ComboOptionTestNode",
+                      "built-in-nodes/ComfySoftSwitchNode",
+                      "built-in-nodes/ComfySwitchNode",
+                      "built-in-nodes/ConvertStringToComboNode",
+                      "built-in-nodes/CreateList",
+                      "built-in-nodes/DCTestNode",
+                      "built-in-nodes/InvertBooleanNode"
+                    ]
+                  },
+                  {
+                    "group": "Mask",
+                    "pages": [
+                      {
+                        "group": "Compositing",
+                        "pages": [
+                          "built-in-nodes/JoinImageWithAlpha",
+                          "built-in-nodes/PorterDuffImageComposite",
+                          "built-in-nodes/SplitImageWithAlpha"
+                        ]
+                      },
+                      "built-in-nodes/BatchMasksNode",
+                      "built-in-nodes/CropMask",
+                      "built-in-nodes/FeatherMask",
+                      "built-in-nodes/GrowMask",
+                      "built-in-nodes/ImageColorToMask",
+                      "built-in-nodes/ImageToMask",
+                      "built-in-nodes/InvertMask",
+                      "built-in-nodes/LoadImageMask",
+                      "built-in-nodes/MaskComposite",
+                      "built-in-nodes/MaskPreview",
+                      "built-in-nodes/MaskToImage",
+                      "built-in-nodes/SolidMask",
+                      "built-in-nodes/ThresholdMask"
+                    ]
+                  },
+                  {
+                    "group": "Model Patches",
+                    "pages": [
+                      {
+                        "group": "Chroma Radiance",
+                        "pages": [
+                          "built-in-nodes/ChromaRadianceOptions"
+                        ]
+                      },
+                      {
+                        "group": "Unet",
+                        "pages": [
+                          "built-in-nodes/Epsilon Scaling",
+                          "built-in-nodes/EpsilonScaling",
+                          "built-in-nodes/FreeU",
+                          "built-in-nodes/FreeU_V2",
+                          "built-in-nodes/HyperTile",
+                          "built-in-nodes/PatchModelAddDownscale",
+                          "built-in-nodes/PerturbedAttentionGuidance",
+                          "built-in-nodes/TemporalScoreRescaling",
+                          "built-in-nodes/TomePatchModel"
+                        ]
+                      }
+                    ]
+                  },
+                  {
+                    "group": "Sampling",
+                    "pages": [
+                      {
+                        "group": "Custom Sampling",
+                        "pages": [
+                          {
+                            "group": "Guiders",
+                            "pages": [
+                              "built-in-nodes/BasicGuider",
+                              "built-in-nodes/CFGGuider",
+                              "built-in-nodes/DualCFGGuider"
+                            ]
+                          },
+                          {
+                            "group": "Noise",
+                            "pages": [
+                              "built-in-nodes/AddNoise",
+                              "built-in-nodes/DisableNoise",
+                              "built-in-nodes/RandomNoise"
+                            ]
+                          },
+                          {
+                            "group": "Samplers",
+                            "pages": [
+                              "built-in-nodes/KSamplerSelect",
+                              "built-in-nodes/SamplerDPMAdaptative",
+                              "built-in-nodes/SamplerDpmpp2mSde",
+                              "built-in-nodes/SamplerDPMPP_2M_SDE",
+                              "built-in-nodes/SamplerDPMPP_2S_Ancestral",
+                              "built-in-nodes/SamplerDPMPP_3M_SDE",
+                              "built-in-nodes/SamplerDPMPP_SDE",
+                              "built-in-nodes/SamplerDpmppSde",
+                              "built-in-nodes/SamplerER_SDE",
+                              "built-in-nodes/SamplerEulerAncestral",
+                              "built-in-nodes/SamplerEulerAncestralCFGPP",
+                              "built-in-nodes/SamplerEulerCFGpp",
+                              "built-in-nodes/SamplerLCMUpscale",
+                              "built-in-nodes/SamplerLMS",
+                              "built-in-nodes/SamplerSASolver",
+                              "built-in-nodes/SamplerSEEDS2"
+                            ]
+                          },
+                          {
+                            "group": "Schedulers",
+                            "pages": [
+                              "built-in-nodes/AlignYourStepsScheduler",
+                              "built-in-nodes/BasicScheduler",
+                              "built-in-nodes/BetaSamplingScheduler",
+                              "built-in-nodes/ExponentialScheduler",
+                              "built-in-nodes/Flux2Scheduler",
+                              "built-in-nodes/GITSScheduler",
+                              "built-in-nodes/KarrasScheduler",
+                              "built-in-nodes/LaplaceScheduler",
+                              "built-in-nodes/LTXVScheduler",
+                              "built-in-nodes/OptimalStepsScheduler",
+                              "built-in-nodes/PolyexponentialScheduler",
+                              "built-in-nodes/SDTurboScheduler",
+                              "built-in-nodes/VPScheduler"
+                            ]
+                          },
+                          {
+                            "group": "Sigmas",
+                            "pages": [
+                              "built-in-nodes/ExtendIntermediateSigmas",
+                              "built-in-nodes/FlipSigmas",
+                              "built-in-nodes/SamplingPercentToSigma",
+                              "built-in-nodes/SetFirstSigma",
+                              "built-in-nodes/SplitSigmas",
+                              "built-in-nodes/SplitSigmasDenoise"
+                            ]
+                          },
+                          "built-in-nodes/APG",
+                          "built-in-nodes/ManualSigmas",
+                          "built-in-nodes/SamplerCustom",
+                          "built-in-nodes/SamplerCustomAdvanced"
+                        ]
+                      },
+                      {
+                        "group": "Video Models",
+                        "pages": [
+                          "built-in-nodes/VideoLinearCFGGuidance",
+                          "built-in-nodes/VideoTriangleCFGGuidance"
+                        ]
+                      },
+                      "built-in-nodes/DifferentialDiffusion",
+                      "built-in-nodes/KSampler",
+                      "built-in-nodes/KSamplerAdvanced",
+                      "built-in-nodes/PerpNegGuider",
+                      "built-in-nodes/sampling/ksampler",
+                      "built-in-nodes/SelfAttentionGuidance"
+                    ]
+                  },
+                  {
+                    "group": "Textgen",
+                    "pages": [
+                      "built-in-nodes/TextGenerate",
+                      "built-in-nodes/TextGenerateLTX2Prompt"
+                    ]
+                  },
+                  {
+                    "group": "Training",
+                    "pages": [
+                      "built-in-nodes/LossGraphNode",
+                      "built-in-nodes/TrainLoraNode"
+                    ]
+                  },
+                  {
+                    "group": "Utils",
+                    "pages": [
+                      {
+                        "group": "Primitive",
+                        "pages": [
+                          "built-in-nodes/PrimitiveBoolean",
+                          "built-in-nodes/PrimitiveBoundingBox",
+                          "built-in-nodes/PrimitiveFloat",
+                          "built-in-nodes/PrimitiveInt",
+                          "built-in-nodes/PrimitiveString",
+                          "built-in-nodes/PrimitiveStringMultiline"
+                        ]
+                      },
+                      {
+                        "group": "String",
+                        "pages": [
+                          "built-in-nodes/CaseConverter",
+                          "built-in-nodes/RegexExtract",
+                          "built-in-nodes/RegexMatch",
+                          "built-in-nodes/RegexReplace",
+                          "built-in-nodes/StringCompare",
+                          "built-in-nodes/StringConcatenate",
+                          "built-in-nodes/StringContains",
+                          "built-in-nodes/StringLength",
+                          "built-in-nodes/StringReplace",
+                          "built-in-nodes/StringSubstring",
+                          "built-in-nodes/StringTrim"
+                        ]
+                      },
+                      "built-in-nodes/BatchImagesMasksLatentsNode",
+                      "built-in-nodes/ColorToRGBInt",
+                      "built-in-nodes/CustomCombo",
+                      "built-in-nodes/Mahiro",
+                      "built-in-nodes/MarkdownNote",
+                      "built-in-nodes/Note",
+                      "built-in-nodes/PreviewAny",
+                      "built-in-nodes/Reroute",
+                      "built-in-nodes/TerminalLog",
+                      "built-in-nodes/wanBlockSwap"
+                    ]
+                  }
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "Development",
+            "pages": [
+              "development/overview",
+              {
+                "group": "ComfyUI Server",
+                "icon": "code",
+                "pages": [
+                  "development/comfyui-server/comms_overview",
+                  "development/comfyui-server/comms_messages",
+                  "development/comfyui-server/comms_routes",
+                  "development/comfyui-server/execution_model_inversion_guide",
+                  "development/comfyui-server/api-key-integration"
+                ]
+              },
+              {
+                "group": "Cloud API",
+                "icon": "cloud",
+                "pages": [
+                  "development/cloud/overview",
+                  "development/cloud/api-reference",
+                  "development/cloud/openapi"
+                ]
+              },
+              {
+                "group": "CLI",
+                "pages": [
+                  "comfy-cli/getting-started",
+                  "comfy-cli/reference",
+                  "comfy-cli/troubleshooting"
+                ]
+              },
+              {
+                "group": "Develop Custom Nodes",
+                "pages": [
+                  "custom-nodes/overview",
+                  "custom-nodes/walkthrough",
+                  {
+                    "group": "Backend",
+                    "icon": "python",
+                    "pages": [
+                      "custom-nodes/backend/server_overview",
+                      "custom-nodes/backend/lifecycle",
+                      "custom-nodes/backend/datatypes",
+                      "custom-nodes/backend/images_and_masks",
+                      "custom-nodes/backend/more_on_inputs",
+                      "custom-nodes/backend/lazy_evaluation",
+                      "custom-nodes/backend/expansion",
+                      "custom-nodes/backend/lists",
+                      "custom-nodes/backend/snippets",
+                      "custom-nodes/backend/tensors",
+                      "custom-nodes/backend/node-replacement"
+                    ]
+                  },
+                  {
+                    "group": "UI",
+                    "icon": "js",
+                    "pages": [
+                      "custom-nodes/js/javascript_overview",
+                      "custom-nodes/js/javascript_hooks",
+                      "custom-nodes/js/javascript_objects_and_hijacking",
+                      "custom-nodes/js/javascript_settings",
+                      "custom-nodes/js/javascript_dialog",
+                      "custom-nodes/js/javascript_toast",
+                      "custom-nodes/js/javascript_about_panel_badges",
+                      "custom-nodes/js/javascript_bottom_panel_tabs",
+                      "custom-nodes/js/javascript_sidebar_tabs",
+                      "custom-nodes/js/javascript_selection_toolbox",
+                      "custom-nodes/js/javascript_commands_keybindings",
+                      "custom-nodes/js/javascript_topbar_menu",
+                      "custom-nodes/js/context-menu-migration",
+                      "custom-nodes/js/subgraphs",
+                      "custom-nodes/js/javascript_examples",
+                      "custom-nodes/i18n"
+                    ]
+                  },
+                  "custom-nodes/v3_migration",
+                  "custom-nodes/help_page",
+                  "custom-nodes/workflow_templates",
+                  "custom-nodes/subgraph_blueprints"
+                ]
+              },
+              {
+                "group": "Registry",
+                "pages": [
+                  "registry/overview",
+                  "registry/publishing",
+                  "registry/claim-my-node",
+                  "registry/standards",
+                  "registry/cicd",
+                  "registry/specifications"
+                ]
+              },
+              {
+                "group": "Specifications",
+                "pages": [
+                  {
+                    "group": "Workflow JSON",
+                    "pages": [
+                      "specs/workflow_json",
+                      "specs/workflow_json_0.4"
+                    ]
+                  },
+                  {
+                    "group": "Node Definitions",
+                    "pages": [
+                      "specs/nodedef_json",
+                      "specs/nodedef_json_1_0"
+                    ]
+                  }
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "Support",
+            "pages": [
+              "support/contact-support",
+              {
+                "group": "Account Management",
+                "icon": "user",
+                "pages": [
+                  "account/create-account",
+                  "account/login",
+                  "account/delete-account"
+                ]
+              },
+              {
+                "group": "Billing Support",
+                "pages": [
+                  {
+                    "group": "Subscription",
+                    "pages": [
+                      "support/subscription/subscribing",
+                      "support/subscription/managing",
+                      "support/subscription/changing-plan",
+                      "support/subscription/canceling"
+                    ]
+                  },
+                  {
+                    "group": "Payment",
+                    "pages": [
+                      "support/payment/accepted-payment-methods",
+                      "support/payment/editing-payment-information",
+                      "support/payment/payment-history",
+                      "support/payment/unsuccessful-payments",
+                      "support/payment/payment-currency",
+                      "support/payment/invoice-information"
+                    ]
+                  }
+                ]
+              },
+              {
+                "group": "Troubleshooting",
+                "icon": "bug",
+                "pages": [
+                  "troubleshooting/overview",
+                  "troubleshooting/model-issues",
+                  "troubleshooting/custom-node-issues"
+                ]
+              },
+              {
+                "group": "Community",
+                "pages": [
+                  "community/contributing",
+                  "community/links"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "Registry API Reference",
+            "openapi": "https://api.comfy.org/openapi"
+          },
+          {
+            "tab": "Cloud API Reference",
+            "openapi": {
+              "source": "openapi-cloud.yaml",
+              "directory": "api-reference/cloud"
+            }
+          }
+        ]
+      },
+      {
+        "language": "cn",
+        "tabs": [
+          {
+            "tab": "开始使用",
+            "pages": [
+              {
+                "group": "开始使用",
+                "pages": [
+                  "zh-CN/index",
+                  {
+                    "group": "本地安装",
+                    "icon": "download",
+                    "pages": [
+                      "zh-CN/installation/system_requirements",
+                      {
+                        "group": "Desktop(推荐)",
+                        "pages": [
+                          "zh-CN/installation/desktop/windows",
+                          "zh-CN/installation/desktop/macos",
+                          "zh-CN/installation/desktop/linux"
+                        ]
+                      },
+                      "zh-CN/installation/comfyui_portable_windows",
+                      "zh-CN/installation/manual_install",
+                      "zh-CN/installation/update_comfyui"
+                    ]
+                  },
+                  {
+                    "group": "Comfy Cloud",
+                    "icon": "cloud",
+                    "pages": [
+                      "zh-CN/get_started/cloud",
+                      "zh-CN/cloud/import-models"
+                    ]
+                  },
+                  "zh-CN/installation/install_custom_node",
+                  "zh-CN/get_started/first_generation"
+                ]
+              },
+              {
+                "group": "基础概念",
+                "pages": [
+                  "zh-CN/development/core-concepts/workflow",
+                  "zh-CN/development/core-concepts/nodes",
+                  "zh-CN/development/core-concepts/custom-nodes",
+                  "zh-CN/development/core-concepts/properties",
+                  "zh-CN/development/core-concepts/links",
+                  "zh-CN/development/core-concepts/models",
+                  "zh-CN/development/core-concepts/dependencies"
+                ]
+              },
+              {
+                "group": "界面指南",
+                "pages": [
+                  "zh-CN/interface/overview",
+                  "zh-CN/interface/nodes-2",
+                  "zh-CN/interface/maskeditor",
+                  "zh-CN/interface/features/template",
+                  "zh-CN/interface/features/subgraph",
+                  "zh-CN/interface/features/partial-execution",
+                  "zh-CN/interface/features/node-docs",
+                  {
+                    "group": "ComfyUI 设置",
+                    "icon": "gear",
+                    "pages": [
+                      "zh-CN/interface/settings/overview",
+                      "zh-CN/interface/user",
+                      "zh-CN/interface/credits",
+                      "zh-CN/interface/settings/comfy",
+                      "zh-CN/interface/settings/lite-graph",
+                      "zh-CN/interface/appearance",
+                      "zh-CN/interface/settings/3d",
+                      "zh-CN/interface/settings/comfy-desktop",
+                      "zh-CN/interface/settings/mask-editor",
+                      "zh-CN/interface/shortcuts",
+                      "zh-CN/interface/settings/extension",
+                      "zh-CN/interface/settings/about",
+                      "zh-CN/interface/settings/server-config"
+                    ]
+                  },
+                  {
+                    "group": "ComfyUI-Manager",
+                    "icon": "puzzle-piece",
+                    "pages": [
+                      "zh-CN/manager/overview",
+                      "zh-CN/manager/install",
+                      {
+                        "group": "自定义节点管理",
+                        "pages": [
+                          "zh-CN/manager/pack-management",
+                          "zh-CN/manager/legacy-ui"
+                        ]
+                      },
+                      "zh-CN/manager/configuration",
+                      "zh-CN/manager/troubleshooting"
+                    ]
+                  }
+                ]
+              },
+              {
+                "group": "教程示例",
+                "icon": "book",
+                "pages": [
+                  {
+                    "group": "基础示例",
+                    "pages": [
+                      "zh-CN/tutorials/basic/text-to-image",
+                      "zh-CN/tutorials/basic/image-to-image",
+                      "zh-CN/tutorials/basic/inpaint",
+                      "zh-CN/tutorials/basic/outpaint",
+                      "zh-CN/tutorials/basic/upscale",
+                      "zh-CN/tutorials/basic/lora",
+                      "zh-CN/tutorials/basic/multiple-loras"
+                    ]
+                  },
+                  {
+                    "group": "ControlNet",
+                    "pages": [
+                      "zh-CN/tutorials/controlnet/controlnet",
+                      "zh-CN/tutorials/controlnet/pose-controlnet-2-pass",
+                      "zh-CN/tutorials/controlnet/depth-controlnet",
+                      "zh-CN/tutorials/controlnet/depth-t2i-adapter",
+                      "zh-CN/tutorials/controlnet/mixing-controlnets"
+                    ]
+                  },
+                  {
+                    "group": "Image",
+                    "pages": [
+                      {
+                        "group": "Flux",
+                        "pages": [
+                          "zh-CN/tutorials/flux/flux-2-dev",
+                          "zh-CN/tutorials/flux/flux-2-klein",
+                          "zh-CN/tutorials/flux/flux1-krea-dev",
+                          "zh-CN/tutorials/flux/flux-1-kontext-dev",
+                          "zh-CN/tutorials/flux/flux-1-text-to-image",
+                          "zh-CN/tutorials/flux/flux-1-uso",
+                          "zh-CN/tutorials/flux/flux-1-fill-dev",
+                          "zh-CN/tutorials/flux/flux-1-controlnet"
+                        ]
+                      },
+                      {
+                        "group": "Qwen",
+                        "pages": [
+                          "zh-CN/tutorials/image/qwen/qwen-image",
+                          "zh-CN/tutorials/image/qwen/qwen-image-2512",
+                          "zh-CN/tutorials/image/qwen/qwen-image-edit",
+                          "zh-CN/tutorials/image/qwen/qwen-image-edit-2511",
+                          "zh-CN/tutorials/image/qwen/qwen-image-layered"
+                        ]
+                      },
+                      {
+                        "group": "Z-Image",
+                        "pages": [
+                          "zh-CN/tutorials/image/z-image/z-image",
+                          "zh-CN/tutorials/image/z-image/z-image-turbo"
+                        ]
+                      },
+                      {
+                        "group": "Ovis",
+                        "pages": [
+                          "zh-CN/tutorials/image/ovis/ovis-image"
+                        ]
+                      },
+                      {
+                        "group": "HiDream",
+                        "pages": [
+                          "zh-CN/tutorials/image/hidream/hidream-i1",
+                          "zh-CN/tutorials/image/hidream/hidream-e1"
+                        ]
+                      },
+                      {
+                        "group": "NewBie-image",
+                        "pages": [
+                          "zh-CN/tutorials/image/newbie-image/newbie-image-exp-0-1"
+                        ]
+                      },
+                      "zh-CN/tutorials/image/cosmos/cosmos-predict2-t2i",
+                      "zh-CN/tutorials/image/omnigen/omnigen2"
+                    ]
+                  },
+                  {
+                    "group": "3D",
+                    "pages": [
+                      "zh-CN/tutorials/3d/hunyuan3D-2"
+                    ]
+                  },
+                  {
+                    "group": "视频",
+                    "pages": [
+                      {
+                        "group": "LTX",
+                        "pages": [
+                          "zh-CN/tutorials/video/ltxv",
+                          "zh-CN/tutorials/video/ltx/ltx-2"
+                        ]
+                      },
+                      {
+                        "group": "万相视频",
+                        "pages": [
+                          "zh-CN/tutorials/video/wan/wan2_2",
+                          "zh-CN/tutorials/video/wan/wan2-2-animate",
+                          "zh-CN/tutorials/video/wan/wan2-2-s2v",
+                          "zh-CN/tutorials/video/wan/wan2-2-fun-inp",
+                          "zh-CN/tutorials/video/wan/wan2-2-fun-control",
+                          "zh-CN/tutorials/video/wan/wan2-2-fun-camera",
+                          {
+                            "group": "Wan2.1",
+                            "pages": [
+                              "zh-CN/tutorials/video/wan/wan-video",
+                              "zh-CN/tutorials/video/wan/vace",
+                              "zh-CN/tutorials/video/wan/wan-move",
+                              "zh-CN/tutorials/video/wan/wan-alpha",
+                              "zh-CN/tutorials/video/wan/wan-ati",
+                              "zh-CN/tutorials/video/wan/fun-control",
+                              "zh-CN/tutorials/video/wan/fun-camera",
+                              "zh-CN/tutorials/video/wan/fun-inp",
+                              "zh-CN/tutorials/video/wan/wan-flf"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "腾讯混元",
+                        "pages": [
+                          "tutorials/video/hunyuan/hunyuan-video",
+                          "tutorials/video/hunyuan/hunyuan-video-1-5"
+                        ]
+                      },
+                      {
+                        "group": "Cosmos",
+                        "pages": [
+                          "zh-CN/tutorials/video/cosmos/cosmos-predict2-video2world"
+                        ]
+                      },
+                      {
+                        "group": "Kandinsky",
+                        "pages": [
+                          "zh-CN/tutorials/video/kandinsky/kandinsky-5"
+                        ]
+                      }
+                    ]
+                  },
+                  {
+                    "group": "音频",
+                    "pages": [
+                      {
+                        "group": "ACE-Step",
+                        "pages": [
+                          "zh-CN/tutorials/audio/ace-step/ace-step-v1",
+                          "zh-CN/tutorials/audio/ace-step/ace-step-v1-5"
+                        ]
+                      }
+                    ]
+                  },
+                  {
+                    "group": "Utility",
+                    "pages": [
+                      "zh-CN/tutorials/utility/preprocessors",
+                      "zh-CN/tutorials/utility/frame-interpolation",
+                      "zh-CN/tutorials/utility/image-upscale",
+                      "zh-CN/tutorials/utility/video-upscale"
+                    ]
+                  },
+                  {
+                    "group": "合作伙伴节点",
+                    "pages": [
+                      "zh-CN/tutorials/partner-nodes/overview",
+                      "zh-CN/tutorials/partner-nodes/faq",
+                      "zh-CN/tutorials/partner-nodes/pricing",
+                      {
+                        "group": "Black Forest Labs",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/black-forest-labs/flux-1-1-pro-ultra-image",
+                          "zh-CN/tutorials/partner-nodes/black-forest-labs/flux-1-kontext"
+                        ]
+                      },
+                      {
+                        "group": "ByteDance",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/bytedance/seedream-5-lite"
+                        ]
+                      },
+                      {
+                        "group": "Google",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/google/gemini",
+                          "zh-CN/tutorials/partner-nodes/google/nano-banana-pro"
+                        ]
+                      },
+                      {
+                        "group": "Stability AI",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/stability-ai/stable-image-ultra",
+                          "zh-CN/tutorials/partner-nodes/stability-ai/stable-diffusion-3-5-image",
+                          "zh-CN/tutorials/partner-nodes/stability-ai/stable-audio"
+                        ]
+                      },
+                      {
+                        "group": "Ideogram",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/ideogram/ideogram-v3"
+                        ]
+                      },
+                      {
+                        "group": "Luma",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/luma/luma-text-to-image",
+                          "zh-CN/tutorials/partner-nodes/luma/luma-image-to-image",
+                          "zh-CN/tutorials/partner-nodes/luma/luma-text-to-video",
+                          "zh-CN/tutorials/partner-nodes/luma/luma-image-to-video"
+                        ]
+                      },
+                      {
+                        "group": "Moonvalley",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/moonvalley/moonvalley-video-generation"
+                        ]
+                      },
+                      {
+                        "group": "OpenAI",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/openai/gpt-image-1",
+                          "zh-CN/tutorials/partner-nodes/openai/dall-e-2",
+                          "zh-CN/tutorials/partner-nodes/openai/dall-e-3",
+                          "zh-CN/tutorials/partner-nodes/openai/chat"
+                        ]
+                      },
+                      {
+                        "group": "Recraft",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/recraft/recraft-v4",
+                          "zh-CN/tutorials/partner-nodes/recraft/recraft-text-to-image"
+                        ]
+                      },
+                      {
+                        "group": "Kling",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/kling/kling-3-0",
+                          "zh-CN/tutorials/partner-nodes/kling/kling-motion-control"
+                        ]
+                      },
+                      {
+                        "group": "Runway",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/runway/image-generation",
+                          "zh-CN/tutorials/partner-nodes/runway/video-generation"
+                        ]
+                      },
+                      {
+                        "group": "Rodin",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/rodin/model-generation"
+                        ]
+                      },
+                      {
+                        "group": "Tripo",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/tripo/model-generation"
+                        ]
+                      },
+                      {
+                        "group": "Hunyuan 3D",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/hunyuan3d/hunyuan3d-3-0"
+                        ]
+                      },
+                      {
+                        "group": "Meshy",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/meshy/meshy-6"
+                        ]
+                      },
+                      {
+                        "group": "Bria",
+                        "pages": [
+                          "zh-CN/tutorials/partner-nodes/bria/fibo"
+                        ]
+                      }
+                    ]
+                  }
+                ]
+              },
+              "changelog/index"
+            ]
+          },
+          {
+            "tab": "内置节点",
+            "pages": [
+              "zh-CN/built-in-nodes/overview",
               {
-                "group": "Billing Support",
+                "group": "节点",
                 "pages": [
                   {
-                    "group": "Subscription",
+                    "group": "3D",
                     "pages": [
-                      "support/subscription/subscribing",
-                      "support/subscription/managing",
-                      "support/subscription/changing-plan",
-                      "support/subscription/canceling"
+                      "zh-CN/built-in-nodes/Load3D",
+                      "zh-CN/built-in-nodes/Load3DAnimation",
+                      "zh-CN/built-in-nodes/Preview3D",
+                      "zh-CN/built-in-nodes/Preview3DAnimation",
+                      "zh-CN/built-in-nodes/SaveGLB",
+                      "zh-CN/built-in-nodes/VoxelToMesh",
+                      "zh-CN/built-in-nodes/VoxelToMeshBasic"
+                    ]
+                  },
+                  {
+                    "group": "API Node",
+                    "pages": [
+                      {
+                        "group": "3D",
+                        "pages": [
+                          {
+                            "group": "Meshy",
+                            "pages": [
+                              "zh-CN/built-in-nodes/MeshyAnimateModelNode",
+                              "zh-CN/built-in-nodes/MeshyImageToModelNode",
+                              "zh-CN/built-in-nodes/MeshyMultiImageToModelNode",
+                              "zh-CN/built-in-nodes/MeshyRefineNode",
+                              "zh-CN/built-in-nodes/MeshyRigModelNode",
+                              "zh-CN/built-in-nodes/MeshyTextToModelNode",
+                              "zh-CN/built-in-nodes/MeshyTextureNode"
+                            ]
+                          },
+                          {
+                            "group": "Rodin",
+                            "pages": [
+                              "zh-CN/built-in-nodes/Rodin3D_Detail",
+                              "zh-CN/built-in-nodes/Rodin3D_Gen2",
+                              "zh-CN/built-in-nodes/Rodin3D_Regular",
+                              "zh-CN/built-in-nodes/Rodin3D_Sketch",
+                              "zh-CN/built-in-nodes/Rodin3D_Smooth"
+                            ]
+                          },
+                          {
+                            "group": "Tencent",
+                            "pages": [
+                              "zh-CN/built-in-nodes/Tencent3DPartNode",
+                              "zh-CN/built-in-nodes/Tencent3DTextureEditNode",
+                              "zh-CN/built-in-nodes/TencentImageToModelNode",
+                              "zh-CN/built-in-nodes/TencentModelTo3DUVNode",
+                              "zh-CN/built-in-nodes/TencentTextToModelNode"
+                            ]
+                          },
+                          {
+                            "group": "Tripo",
+                            "pages": [
+                              "zh-CN/built-in-nodes/TripoConversionNode",
+                              "zh-CN/built-in-nodes/TripoImageToModelNode",
+                              "zh-CN/built-in-nodes/TripoMultiviewToModelNode",
+                              "zh-CN/built-in-nodes/TripoRefineNode",
+                              "zh-CN/built-in-nodes/TripoRetargetNode",
+                              "zh-CN/built-in-nodes/TripoRigNode",
+                              "zh-CN/built-in-nodes/TripoTextToModelNode",
+                              "zh-CN/built-in-nodes/TripoTextureNode"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Audio",
+                        "pages": [
+                          {
+                            "group": "Elevenlabs",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ElevenLabsAudioIsolation",
+                              "zh-CN/built-in-nodes/ElevenLabsInstantVoiceClone",
+                              "zh-CN/built-in-nodes/ElevenLabsSpeechToSpeech",
+                              "zh-CN/built-in-nodes/ElevenLabsSpeechToText",
+                              "zh-CN/built-in-nodes/ElevenLabsTextToDialogue",
+                              "zh-CN/built-in-nodes/ElevenLabsTextToSoundEffects",
+                              "zh-CN/built-in-nodes/ElevenLabsTextToSpeech",
+                              "zh-CN/built-in-nodes/ElevenLabsVoiceSelector"
+                            ]
+                          },
+                          {
+                            "group": "Stability Ai",
+                            "pages": [
+                              "zh-CN/built-in-nodes/StabilityAudioInpaint",
+                              "zh-CN/built-in-nodes/StabilityAudioToAudio"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Image",
+                        "pages": [
+                          {
+                            "group": "Bfl",
+                            "pages": [
+                              "zh-CN/built-in-nodes/FluxProCannyNode",
+                              "zh-CN/built-in-nodes/FluxProDepthNode",
+                              "zh-CN/built-in-nodes/FluxProExpandNode",
+                              "zh-CN/built-in-nodes/FluxProFillNode",
+                              "zh-CN/built-in-nodes/FluxProImageNode",
+                              "zh-CN/built-in-nodes/FluxProUltraImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Bria",
+                            "pages": [
+                              "zh-CN/built-in-nodes/BriaImageEditNode",
+                              "zh-CN/built-in-nodes/BriaRemoveImageBackground"
+                            ]
+                          },
+                          {
+                            "group": "Bytedance",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ByteDanceImageEditNode",
+                              "zh-CN/built-in-nodes/ByteDanceImageNode",
+                              "zh-CN/built-in-nodes/ByteDanceSeedreamNode"
+                            ]
+                          },
+                          {
+                            "group": "Gemini",
+                            "pages": [
+                              "zh-CN/built-in-nodes/GeminiImage",
+                              "zh-CN/built-in-nodes/GeminiImage2Node",
+                              "zh-CN/built-in-nodes/GeminiImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Grok",
+                            "pages": [
+                              "zh-CN/built-in-nodes/GrokImageEditNode",
+                              "zh-CN/built-in-nodes/GrokImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Hitpaw",
+                            "pages": [
+                              "zh-CN/built-in-nodes/HitPawGeneralImageEnhance"
+                            ]
+                          },
+                          {
+                            "group": "Ideogram",
+                            "pages": [
+                              "zh-CN/built-in-nodes/IdeogramV1",
+                              "zh-CN/built-in-nodes/IdeogramV2",
+                              "zh-CN/built-in-nodes/IdeogramV3"
+                            ]
+                          },
+                          {
+                            "group": "Kling",
+                            "pages": [
+                              "zh-CN/built-in-nodes/KlingImageGenerationNode",
+                              "zh-CN/built-in-nodes/KlingOmniProImageNode",
+                              "zh-CN/built-in-nodes/KlingVirtualTryOnNode"
+                            ]
+                          },
+                          {
+                            "group": "Luma",
+                            "pages": [
+                              "zh-CN/built-in-nodes/LumaConceptsNode",
+                              "zh-CN/built-in-nodes/LumaImageModifyNode",
+                              "zh-CN/built-in-nodes/LumaReferenceNode"
+                            ]
+                          },
+                          {
+                            "group": "Magnific",
+                            "pages": [
+                              "zh-CN/built-in-nodes/MagnificImageRelightNode",
+                              "zh-CN/built-in-nodes/MagnificImageSkinEnhancerNode",
+                              "zh-CN/built-in-nodes/MagnificImageStyleTransferNode",
+                              "zh-CN/built-in-nodes/MagnificImageUpscalerCreativeNode",
+                              "zh-CN/built-in-nodes/MagnificImageUpscalerPreciseV2Node"
+                            ]
+                          },
+                          {
+                            "group": "Openai",
+                            "pages": [
+                              "zh-CN/built-in-nodes/OpenAIDalle2",
+                              "zh-CN/built-in-nodes/OpenAIDalle3",
+                              "zh-CN/built-in-nodes/OpenAIGPTImage1"
+                            ]
+                          },
+                          {
+                            "group": "Recraft",
+                            "pages": [
+                              "zh-CN/built-in-nodes/RecraftColorRGB",
+                              "zh-CN/built-in-nodes/RecraftControls",
+                              "zh-CN/built-in-nodes/RecraftCreateStyleNode",
+                              "zh-CN/built-in-nodes/RecraftCreativeUpscaleNode",
+                              "zh-CN/built-in-nodes/RecraftCrispUpscaleNode",
+                              "zh-CN/built-in-nodes/RecraftImageInpaintingNode",
+                              "zh-CN/built-in-nodes/RecraftImageToImageNode",
+                              "zh-CN/built-in-nodes/RecraftRemoveBackgroundNode",
+                              "zh-CN/built-in-nodes/RecraftReplaceBackgroundNode",
+                              "zh-CN/built-in-nodes/RecraftStyleV3DigitalIllustration",
+                              "zh-CN/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary",
+                              "zh-CN/built-in-nodes/RecraftStyleV3LogoRaster",
+                              "zh-CN/built-in-nodes/RecraftStyleV3RealisticImage",
+                              "zh-CN/built-in-nodes/RecraftStyleV3VectorIllustrationNode",
+                              "zh-CN/built-in-nodes/RecraftTextToImageNode",
+                              "zh-CN/built-in-nodes/RecraftTextToVectorNode",
+                              "zh-CN/built-in-nodes/RecraftV4TextToImageNode",
+                              "zh-CN/built-in-nodes/RecraftV4TextToVectorNode",
+                              "zh-CN/built-in-nodes/RecraftVectorizeImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Runway",
+                            "pages": [
+                              "zh-CN/built-in-nodes/RunwayTextToImageNode"
+                            ]
+                          },
+                          {
+                            "group": "Stability Ai",
+                            "pages": [
+                              "zh-CN/built-in-nodes/StabilityStableImageSD_3_5Node",
+                              "zh-CN/built-in-nodes/StabilityStableImageUltraNode",
+                              "zh-CN/built-in-nodes/StabilityTextToAudio",
+                              "zh-CN/built-in-nodes/StabilityUpscaleConservativeNode",
+                              "zh-CN/built-in-nodes/StabilityUpscaleCreativeNode",
+                              "zh-CN/built-in-nodes/StabilityUpscaleFastNode"
+                            ]
+                          },
+                          {
+                            "group": "Topaz",
+                            "pages": [
+                              "zh-CN/built-in-nodes/TopazImageEnhance"
+                            ]
+                          },
+                          {
+                            "group": "Wan",
+                            "pages": [
+                              "zh-CN/built-in-nodes/WanImageToImageApi",
+                              "zh-CN/built-in-nodes/WanTextToImageApi"
+                            ]
+                          },
+                          {
+                            "group": "Wavespeed",
+                            "pages": [
+                              "zh-CN/built-in-nodes/WavespeedImageUpscaleNode"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Text",
+                        "pages": [
+                          {
+                            "group": "Gemini",
+                            "pages": [
+                              "zh-CN/built-in-nodes/GeminiInputFiles",
+                              "zh-CN/built-in-nodes/GeminiNode"
+                            ]
+                          },
+                          {
+                            "group": "Openai",
+                            "pages": [
+                              "zh-CN/built-in-nodes/OpenAIChatConfig",
+                              "zh-CN/built-in-nodes/OpenAIChatNode",
+                              "zh-CN/built-in-nodes/OpenAIInputFiles"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Video",
+                        "pages": [
+                          {
+                            "group": "Bria",
+                            "pages": [
+                              "zh-CN/built-in-nodes/BriaRemoveVideoBackground"
+                            ]
+                          },
+                          {
+                            "group": "Bytedance",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ByteDanceFirstLastFrameNode",
+                              "zh-CN/built-in-nodes/ByteDanceImageReferenceNode",
+                              "zh-CN/built-in-nodes/ByteDanceImageToVideoNode",
+                              "zh-CN/built-in-nodes/ByteDanceTextToVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Google",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/video/google/google-veo2-video"
+                            ]
+                          },
+                          {
+                            "group": "Grok",
+                            "pages": [
+                              "zh-CN/built-in-nodes/GrokVideoEditNode",
+                              "zh-CN/built-in-nodes/GrokVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Hitpaw",
+                            "pages": [
+                              "zh-CN/built-in-nodes/HitPawVideoEnhance"
+                            ]
+                          },
+                          {
+                            "group": "Kling",
+                            "pages": [
+                              "zh-CN/built-in-nodes/KlingCameraControlI2VNode",
+                              "zh-CN/built-in-nodes/KlingCameraControls",
+                              "zh-CN/built-in-nodes/KlingCameraControlT2VNode",
+                              "zh-CN/built-in-nodes/KlingDualCharacterVideoEffectNode",
+                              "zh-CN/built-in-nodes/KlingFirstLastFrameNode",
+                              "zh-CN/built-in-nodes/KlingImage2VideoNode",
+                              "zh-CN/built-in-nodes/KlingImageToVideoWithAudio",
+                              "zh-CN/built-in-nodes/KlingLipSyncAudioToVideoNode",
+                              "zh-CN/built-in-nodes/KlingLipSyncTextToVideoNode",
+                              "zh-CN/built-in-nodes/KlingMotionControl",
+                              "zh-CN/built-in-nodes/KlingOmniProEditVideoNode",
+                              "zh-CN/built-in-nodes/KlingOmniProFirstLastFrameNode",
+                              "zh-CN/built-in-nodes/KlingOmniProImageToVideoNode",
+                              "zh-CN/built-in-nodes/KlingOmniProTextToVideoNode",
+                              "zh-CN/built-in-nodes/KlingOmniProVideoToVideoNode",
+                              "zh-CN/built-in-nodes/KlingSingleImageVideoEffectNode",
+                              "zh-CN/built-in-nodes/KlingStartEndFrameNode",
+                              "zh-CN/built-in-nodes/KlingTextToVideoNode",
+                              "zh-CN/built-in-nodes/KlingTextToVideoWithAudio",
+                              "zh-CN/built-in-nodes/KlingVideoExtendNode",
+                              "zh-CN/built-in-nodes/KlingVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Kling",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-i2v",
+                              "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-t2v",
+                              "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-controls",
+                              "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-image-to-video",
+                              "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-start-end-frame-to-video",
+                              "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-text-to-video"
+                            ]
+                          },
+                          {
+                            "group": "Ltxv",
+                            "pages": [
+                              "zh-CN/built-in-nodes/LtxvApiImageToVideo",
+                              "zh-CN/built-in-nodes/LtxvApiTextToVideo"
+                            ]
+                          },
+                          {
+                            "group": "Luma",
+                            "pages": [
+                              "zh-CN/built-in-nodes/LumaImageNode",
+                              "zh-CN/built-in-nodes/LumaImageToVideoNode",
+                              "zh-CN/built-in-nodes/LumaVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Luma",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/video/luma/luma-concepts",
+                              "zh-CN/built-in-nodes/partner-node/video/luma/luma-image-to-video",
+                              "zh-CN/built-in-nodes/partner-node/video/luma/luma-text-to-video"
+                            ]
+                          },
+                          {
+                            "group": "MiniMax",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/video/minimax/minimax-image-to-video",
+                              "zh-CN/built-in-nodes/partner-node/video/minimax/minimax-text-to-video"
+                            ]
+                          },
+                          {
+                            "group": "Minimax",
+                            "pages": [
+                              "zh-CN/built-in-nodes/MinimaxHailuoVideoNode",
+                              "zh-CN/built-in-nodes/MinimaxImageToVideoNode",
+                              "zh-CN/built-in-nodes/MinimaxSubjectToVideoNode",
+                              "zh-CN/built-in-nodes/MinimaxTextToVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Moonvalley Marey",
+                            "pages": [
+                              "zh-CN/built-in-nodes/MoonvalleyImg2VideoNode",
+                              "zh-CN/built-in-nodes/MoonvalleyTxt2VideoNode",
+                              "zh-CN/built-in-nodes/MoonvalleyVideo2VideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Pika",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/video/pika/pika-image-to-video",
+                              "zh-CN/built-in-nodes/partner-node/video/pika/pika-scenes",
+                              "zh-CN/built-in-nodes/partner-node/video/pika/pika-text-to-video",
+                              "zh-CN/built-in-nodes/Pikadditions",
+                              "zh-CN/built-in-nodes/Pikaffects",
+                              "zh-CN/built-in-nodes/PikaImageToVideoNode2_2",
+                              "zh-CN/built-in-nodes/PikaScenesV2_2",
+                              "zh-CN/built-in-nodes/PikaStartEndFrameNode2_2",
+                              "zh-CN/built-in-nodes/Pikaswaps",
+                              "zh-CN/built-in-nodes/PikaTextToVideoNode2_2"
+                            ]
+                          },
+                          {
+                            "group": "PixVerse",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/video/pixverse/pixverse-image-to-video",
+                              "zh-CN/built-in-nodes/partner-node/video/pixverse/pixverse-template",
+                              "zh-CN/built-in-nodes/partner-node/video/pixverse/pixverse-text-to-video",
+                              "zh-CN/built-in-nodes/partner-node/video/pixverse/pixverse-transition-video"
+                            ]
+                          },
+                          {
+                            "group": "Pixverse",
+                            "pages": [
+                              "zh-CN/built-in-nodes/PixverseImageToVideoNode",
+                              "zh-CN/built-in-nodes/PixverseTemplateNode",
+                              "zh-CN/built-in-nodes/PixverseTextToVideoNode",
+                              "zh-CN/built-in-nodes/PixverseTransitionVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Runway",
+                            "pages": [
+                              "zh-CN/built-in-nodes/RunwayFirstLastFrameNode",
+                              "zh-CN/built-in-nodes/RunwayImageToVideoNodeGen3a",
+                              "zh-CN/built-in-nodes/RunwayImageToVideoNodeGen4"
+                            ]
+                          },
+                          {
+                            "group": "Sora",
+                            "pages": [
+                              "zh-CN/built-in-nodes/OpenAIVideoSora2"
+                            ]
+                          },
+                          {
+                            "group": "Topaz",
+                            "pages": [
+                              "zh-CN/built-in-nodes/TopazVideoEnhance"
+                            ]
+                          },
+                          {
+                            "group": "Veo",
+                            "pages": [
+                              "zh-CN/built-in-nodes/Veo3FirstLastFrameNode",
+                              "zh-CN/built-in-nodes/Veo3VideoGenerationNode",
+                              "zh-CN/built-in-nodes/VeoVideoGenerationNode"
+                            ]
+                          },
+                          {
+                            "group": "Vidu",
+                            "pages": [
+                              "zh-CN/built-in-nodes/Vidu2ImageToVideoNode",
+                              "zh-CN/built-in-nodes/Vidu2ReferenceVideoNode",
+                              "zh-CN/built-in-nodes/Vidu2StartEndToVideoNode",
+                              "zh-CN/built-in-nodes/Vidu2TextToVideoNode",
+                              "zh-CN/built-in-nodes/Vidu3ImageToVideoNode",
+                              "zh-CN/built-in-nodes/Vidu3StartEndToVideoNode",
+                              "zh-CN/built-in-nodes/Vidu3TextToVideoNode",
+                              "zh-CN/built-in-nodes/ViduExtendVideoNode",
+                              "zh-CN/built-in-nodes/ViduImageToVideoNode",
+                              "zh-CN/built-in-nodes/ViduMultiFrameVideoNode",
+                              "zh-CN/built-in-nodes/ViduReferenceVideoNode",
+                              "zh-CN/built-in-nodes/ViduStartEndToVideoNode",
+                              "zh-CN/built-in-nodes/ViduTextToVideoNode"
+                            ]
+                          },
+                          {
+                            "group": "Wan",
+                            "pages": [
+                              "zh-CN/built-in-nodes/WanImageToVideoApi",
+                              "zh-CN/built-in-nodes/WanReferenceVideoApi",
+                              "zh-CN/built-in-nodes/WanTextToVideoApi"
+                            ]
+                          },
+                          {
+                            "group": "Wavespeed",
+                            "pages": [
+                              "zh-CN/built-in-nodes/WavespeedFlashVSRNode"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "图像",
+                        "pages": [
+                          {
+                            "group": "BFL",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/image/bfl/flux-1-1-pro-ultra-image"
+                            ]
+                          },
+                          {
+                            "group": "Ideogram",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/image/ideogram/ideogram-v1",
+                              "zh-CN/built-in-nodes/partner-node/image/ideogram/ideogram-v2",
+                              "zh-CN/built-in-nodes/partner-node/image/ideogram/ideogram-v3"
+                            ]
+                          },
+                          {
+                            "group": "Luma",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/image/luma/luma-image-to-image",
+                              "zh-CN/built-in-nodes/partner-node/image/luma/luma-reference",
+                              "zh-CN/built-in-nodes/partner-node/image/luma/luma-text-to-image"
+                            ]
+                          },
+                          {
+                            "group": "OpenAI",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/image/openai/openai-dalle2",
+                              "zh-CN/built-in-nodes/partner-node/image/openai/openai-dalle3",
+                              "zh-CN/built-in-nodes/partner-node/image/openai/openai-gpt-image1"
+                            ]
+                          },
+                          {
+                            "group": "Recraft",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-color-rgb",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-controls",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-creative-upscale",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-crisp-upscale",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-image-inpainting",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-image-to-image",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-remove-background",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-replace-background",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-style-digital-illustration",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-style-logo-raster",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-style-realistic-image",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-text-to-image",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-text-to-vector",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-vectorize-image",
+                              "zh-CN/built-in-nodes/partner-node/image/recraft/save-svg"
+                            ]
+                          },
+                          {
+                            "group": "Stability AI",
+                            "pages": [
+                              "zh-CN/built-in-nodes/partner-node/image/stability-ai/stability-ai-stable-diffusion-3-5-image",
+                              "zh-CN/built-in-nodes/partner-node/image/stability-ai/stability-ai-stable-image-ultra"
+                            ]
+                          }
+                        ]
+                      }
                     ]
                   },
                   {
-                    "group": "Payment",
+                    "group": "Audio",
                     "pages": [
-                      "support/payment/accepted-payment-methods",
-                      "support/payment/editing-payment-information",
-                      "support/payment/payment-history",
-                      "support/payment/unsuccessful-payments",
-                      "support/payment/payment-currency",
-                      "support/payment/invoice-information"
+                      "zh-CN/built-in-nodes/AudioAdjustVolume",
+                      "zh-CN/built-in-nodes/AudioConcat",
+                      "zh-CN/built-in-nodes/AudioEqualizer3Band",
+                      "zh-CN/built-in-nodes/AudioMerge",
+                      "zh-CN/built-in-nodes/EmptyAudio",
+                      "zh-CN/built-in-nodes/JoinAudioChannels",
+                      "zh-CN/built-in-nodes/LoadAudio",
+                      "zh-CN/built-in-nodes/LTXVAudioVAEDecode",
+                      "zh-CN/built-in-nodes/LTXVAudioVAEEncode",
+                      "zh-CN/built-in-nodes/LTXVAudioVAELoader",
+                      "zh-CN/built-in-nodes/PreviewAudio",
+                      "zh-CN/built-in-nodes/RecordAudio",
+                      "zh-CN/built-in-nodes/SaveAudio",
+                      "zh-CN/built-in-nodes/SaveAudioMP3",
+                      "zh-CN/built-in-nodes/SaveAudioOpus",
+                      "zh-CN/built-in-nodes/SplitAudioChannels",
+                      "zh-CN/built-in-nodes/TrimAudioDuration"
                     ]
-                  }
-                ]
-              },
-              {
-                "group": "Troubleshooting",
-                "icon": "bug",
-                "pages": [
-                  "troubleshooting/overview",
-                  "troubleshooting/model-issues",
-                  "troubleshooting/custom-node-issues"
-                ]
-              },
-              {
-                "group": "Community",
-                "pages": ["community/contributing", "community/links"]
-              }
-            ]
-          },
-          {
-            "tab": "Registry API Reference",
-            "openapi": "https://api.comfy.org/openapi"
-          },
-          {
-            "tab": "Cloud API Reference",
-            "openapi": {
-              "source": "openapi-cloud.yaml",
-              "directory": "api-reference/cloud"
-            }
-          }
-        ]
-      },
-      {
-        "language": "cn",
-        "tabs": [
-          {
-            "tab": "开始使用",
-            "pages": [
-              {
-                "group": "开始使用",
-                "pages": [
-                  "zh-CN/index",
+                  },
                   {
-                    "group": "本地安装",
-                    "icon": "download",
+                    "group": "Camera",
                     "pages": [
-                      "zh-CN/installation/system_requirements",
-                      {
-                        "group": "Desktop(推荐)",
-                        "pages": [
-                          "zh-CN/installation/desktop/windows",
-                          "zh-CN/installation/desktop/macos",
-                          "zh-CN/installation/desktop/linux"
-                        ]
-                      },
-                      "zh-CN/installation/comfyui_portable_windows",
-                      "zh-CN/installation/manual_install",
-                      "zh-CN/installation/update_comfyui"
+                      "zh-CN/built-in-nodes/WanCameraEmbedding"
                     ]
                   },
                   {
-                    "group": "Comfy Cloud",
-                    "icon": "cloud",
-                    "pages": ["zh-CN/get_started/cloud", "zh-CN/cloud/import-models"]
+                    "group": "Context",
+                    "pages": [
+                      "zh-CN/built-in-nodes/ContextWindowsManual",
+                      "zh-CN/built-in-nodes/WanContextWindowsManual"
+                    ]
                   },
-                  "zh-CN/installation/install_custom_node",
-                  "zh-CN/get_started/first_generation"
-                ]
-              },
-              {
-                "group": "基础概念",
-                "pages": [
-                  "zh-CN/development/core-concepts/workflow",
-                  "zh-CN/development/core-concepts/nodes",
-                  "zh-CN/development/core-concepts/custom-nodes",
-                  "zh-CN/development/core-concepts/properties",
-                  "zh-CN/development/core-concepts/links",
-                  "zh-CN/development/core-concepts/models",
-                  "zh-CN/development/core-concepts/dependencies"
-                ]
-              },
-              {
-                "group": "界面指南",
-                "pages": [
-                  "zh-CN/interface/overview",
-                  "zh-CN/interface/nodes-2",
-                  "zh-CN/interface/maskeditor",
-                  "zh-CN/interface/features/template",
-                  "zh-CN/interface/features/subgraph",
-                  "zh-CN/interface/features/partial-execution",
-                  "zh-CN/interface/features/node-docs",
                   {
-                    "group": "ComfyUI 设置",
-                    "icon": "gear",
+                    "group": "Logic",
                     "pages": [
-                      "zh-CN/interface/settings/overview",
-                      "zh-CN/interface/user",
-                      "zh-CN/interface/credits",
-                      "zh-CN/interface/settings/comfy",
-                      "zh-CN/interface/settings/lite-graph",
-                      "zh-CN/interface/appearance",
-                      "zh-CN/interface/settings/3d",
-                      "zh-CN/interface/settings/comfy-desktop",
-                      "zh-CN/interface/settings/mask-editor",
-                      "zh-CN/interface/shortcuts",
-                      "zh-CN/interface/settings/extension",
-                      "zh-CN/interface/settings/about",
-                      "zh-CN/interface/settings/server-config"
+                      "zh-CN/built-in-nodes/AutogrowNamesTestNode",
+                      "zh-CN/built-in-nodes/AutogrowPrefixTestNode",
+                      "zh-CN/built-in-nodes/ComboOptionTestNode",
+                      "zh-CN/built-in-nodes/ComfySoftSwitchNode",
+                      "zh-CN/built-in-nodes/ComfySwitchNode",
+                      "zh-CN/built-in-nodes/ConvertStringToComboNode",
+                      "zh-CN/built-in-nodes/CreateList",
+                      "zh-CN/built-in-nodes/DCTestNode",
+                      "zh-CN/built-in-nodes/InvertBooleanNode"
                     ]
                   },
                   {
-                    "group": "ComfyUI-Manager",
-                    "icon": "puzzle-piece",
+                    "group": "Mask",
                     "pages": [
-                      "zh-CN/manager/overview",
-                      "zh-CN/manager/install",
                       {
-                        "group": "自定义节点管理",
+                        "group": "Compositing",
                         "pages": [
-                          "zh-CN/manager/pack-management",
-                          "zh-CN/manager/legacy-ui"
+                          "zh-CN/built-in-nodes/JoinImageWithAlpha",
+                          "zh-CN/built-in-nodes/PorterDuffImageComposite",
+                          "zh-CN/built-in-nodes/SplitImageWithAlpha"
                         ]
                       },
-                      "zh-CN/manager/configuration",
-                      "zh-CN/manager/troubleshooting"
+                      "zh-CN/built-in-nodes/BatchMasksNode",
+                      "zh-CN/built-in-nodes/CropMask",
+                      "zh-CN/built-in-nodes/FeatherMask",
+                      "zh-CN/built-in-nodes/GrowMask",
+                      "zh-CN/built-in-nodes/ImageColorToMask",
+                      "zh-CN/built-in-nodes/ImageToMask",
+                      "zh-CN/built-in-nodes/InvertMask",
+                      "zh-CN/built-in-nodes/LoadImageMask",
+                      "zh-CN/built-in-nodes/MaskComposite",
+                      "zh-CN/built-in-nodes/MaskPreview",
+                      "zh-CN/built-in-nodes/MaskToImage",
+                      "zh-CN/built-in-nodes/SolidMask",
+                      "zh-CN/built-in-nodes/ThresholdMask"
                     ]
-                  }
-                ]
-              },
-              {
-                "group": "教程示例",
-                "icon": "book",
-                "pages": [
+                  },
                   {
-                    "group": "基础示例",
+                    "group": "Textgen",
                     "pages": [
-                      "zh-CN/tutorials/basic/text-to-image",
-                      "zh-CN/tutorials/basic/image-to-image",
-                      "zh-CN/tutorials/basic/inpaint",
-                      "zh-CN/tutorials/basic/outpaint",
-                      "zh-CN/tutorials/basic/upscale",
-                      "zh-CN/tutorials/basic/lora",
-                      "zh-CN/tutorials/basic/multiple-loras"
+                      "zh-CN/built-in-nodes/TextGenerate",
+                      "zh-CN/built-in-nodes/TextGenerateLTX2Prompt"
                     ]
                   },
                   {
-                    "group": "ControlNet",
+                    "group": "Training",
                     "pages": [
-                      "zh-CN/tutorials/controlnet/controlnet",
-                      "zh-CN/tutorials/controlnet/pose-controlnet-2-pass",
-                      "zh-CN/tutorials/controlnet/depth-controlnet",
-                      "zh-CN/tutorials/controlnet/depth-t2i-adapter",
-                      "zh-CN/tutorials/controlnet/mixing-controlnets"
+                      "zh-CN/built-in-nodes/LossGraphNode",
+                      "zh-CN/built-in-nodes/TrainLoraNode"
                     ]
                   },
                   {
-                    "group": "Image",
+                    "group": "加载器",
                     "pages": [
                       {
-                        "group": "Flux",
+                        "group": "Video Models",
                         "pages": [
-                          "zh-CN/tutorials/flux/flux-2-dev",
-                          "zh-CN/tutorials/flux/flux-2-klein",
-                          "zh-CN/tutorials/flux/flux1-krea-dev",
-                          "zh-CN/tutorials/flux/flux-1-kontext-dev",
-                          "zh-CN/tutorials/flux/flux-1-text-to-image",
-                          "zh-CN/tutorials/flux/flux-1-uso",
-                          "zh-CN/tutorials/flux/flux-1-fill-dev",
-                          "zh-CN/tutorials/flux/flux-1-controlnet"
+                          "zh-CN/built-in-nodes/ImageOnlyCheckpointLoader"
                         ]
                       },
+                      "zh-CN/built-in-nodes/AudioEncoderLoader",
+                      "zh-CN/built-in-nodes/CheckpointLoaderSimple",
+                      "zh-CN/built-in-nodes/CLIPVisionLoader",
+                      "zh-CN/built-in-nodes/ClipVisionLoader",
+                      "zh-CN/built-in-nodes/ControlNetLoader",
+                      "zh-CN/built-in-nodes/DiffControlNetLoader",
+                      "zh-CN/built-in-nodes/GLIGENLoader",
+                      "zh-CN/built-in-nodes/HunyuanVideo15SuperResolution",
+                      "zh-CN/built-in-nodes/HypernetworkLoader",
+                      "zh-CN/built-in-nodes/LatentUpscaleModelLoader",
+                      "zh-CN/built-in-nodes/LoadLatent",
+                      "zh-CN/built-in-nodes/LoraLoaderBypass",
+                      "zh-CN/built-in-nodes/LoraLoaderBypassModelOnly",
+                      "zh-CN/built-in-nodes/LoraModelLoader",
+                      "zh-CN/built-in-nodes/SaveLoRA",
+                      "zh-CN/built-in-nodes/StyleModelLoader",
+                      "zh-CN/built-in-nodes/unCLIPCheckpointLoader",
+                      "zh-CN/built-in-nodes/UpscaleModelLoader",
+                      "zh-CN/built-in-nodes/VAELoader"
+                    ]
+                  },
+                  {
+                    "group": "图像",
+                    "pages": [
                       {
-                        "group": "Qwen",
+                        "group": "Animation",
                         "pages": [
-                          "zh-CN/tutorials/image/qwen/qwen-image",
-                          "zh-CN/tutorials/image/qwen/qwen-image-2512",
-                          "zh-CN/tutorials/image/qwen/qwen-image-edit",
-                          "zh-CN/tutorials/image/qwen/qwen-image-edit-2511",
-                          "zh-CN/tutorials/image/qwen/qwen-image-layered"
+                          "zh-CN/built-in-nodes/SaveAnimatedPNG",
+                          "zh-CN/built-in-nodes/SaveAnimatedWEBP"
                         ]
                       },
                       {
-                        "group": "Z-Image",
+                        "group": "Batch",
                         "pages": [
-                          "zh-CN/tutorials/image/z-image/z-image",
-                          "zh-CN/tutorials/image/z-image/z-image-turbo"
+                          "zh-CN/built-in-nodes/ImageFromBatch",
+                          "zh-CN/built-in-nodes/ImageRGBToYUV",
+                          "zh-CN/built-in-nodes/ImageYUVToRGB",
+                          "zh-CN/built-in-nodes/RebatchImages",
+                          "zh-CN/built-in-nodes/RepeatImageBatch"
                         ]
                       },
                       {
-                        "group": "Ovis",
-                        "pages": ["zh-CN/tutorials/image/ovis/ovis-image"]
+                        "group": "Image",
+                        "pages": [
+                          "zh-CN/built-in-nodes/AdjustBrightness",
+                          "zh-CN/built-in-nodes/AdjustContrast",
+                          "zh-CN/built-in-nodes/CenterCropImages",
+                          "zh-CN/built-in-nodes/ImageDeduplication",
+                          "zh-CN/built-in-nodes/ImageGrid",
+                          "zh-CN/built-in-nodes/MergeImageLists",
+                          "zh-CN/built-in-nodes/NormalizeImages",
+                          "zh-CN/built-in-nodes/RandomCropImages",
+                          "zh-CN/built-in-nodes/ResizeImagesByLongerEdge",
+                          "zh-CN/built-in-nodes/ResizeImagesByShorterEdge",
+                          "zh-CN/built-in-nodes/ShuffleDataset",
+                          "zh-CN/built-in-nodes/ShuffleImageTextDataset"
+                        ]
                       },
                       {
-                        "group": "HiDream",
+                        "group": "Postprocessing",
                         "pages": [
-                          "zh-CN/tutorials/image/hidream/hidream-i1",
-                          "zh-CN/tutorials/image/hidream/hidream-e1"
+                          "zh-CN/built-in-nodes/ImageBlend",
+                          "zh-CN/built-in-nodes/ImageBlur",
+                          "zh-CN/built-in-nodes/ImageQuantize",
+                          "zh-CN/built-in-nodes/ImageSharpen",
+                          "zh-CN/built-in-nodes/Morphology"
                         ]
                       },
                       {
-                        "group": "NewBie-image",
+                        "group": "Preprocessors",
                         "pages": [
-                          "zh-CN/tutorials/image/newbie-image/newbie-image-exp-0-1"
+                          "zh-CN/built-in-nodes/Canny"
                         ]
                       },
-                      "zh-CN/tutorials/image/cosmos/cosmos-predict2-t2i",
-                      "zh-CN/tutorials/image/omnigen/omnigen2"
-                    ]
-                  },
-                  {
-                    "group": "3D",
-                    "pages": ["zh-CN/tutorials/3d/hunyuan3D-2"]
-                  },
-                  {
-                    "group": "视频",
-                    "pages": [
                       {
-                        "group": "LTX",
+                        "group": "Save",
                         "pages": [
-                          "zh-CN/tutorials/video/ltxv",
-                          "zh-CN/tutorials/video/ltx/ltx-2"
+                          "zh-CN/built-in-nodes/SaveSVGNode"
                         ]
                       },
                       {
-                        "group": "万相视频",
+                        "group": "Shader",
                         "pages": [
-                          "zh-CN/tutorials/video/wan/wan2_2",
-                          "zh-CN/tutorials/video/wan/wan2-2-animate",
-                          "zh-CN/tutorials/video/wan/wan2-2-s2v",
-                          "zh-CN/tutorials/video/wan/wan2-2-fun-inp",
-                          "zh-CN/tutorials/video/wan/wan2-2-fun-control",
-                          "zh-CN/tutorials/video/wan/wan2-2-fun-camera",
-                          {
-                            "group": "Wan2.1",
-                            "pages": [
-                              "zh-CN/tutorials/video/wan/wan-video",
-                              "zh-CN/tutorials/video/wan/vace",
-                              "zh-CN/tutorials/video/wan/wan-move",
-                              "zh-CN/tutorials/video/wan/wan-alpha",
-                              "zh-CN/tutorials/video/wan/wan-ati",
-                              "zh-CN/tutorials/video/wan/fun-control",
-                              "zh-CN/tutorials/video/wan/fun-camera",
-                              "zh-CN/tutorials/video/wan/fun-inp",
-                              "zh-CN/tutorials/video/wan/wan-flf"
-                            ]
-                          }
+                          "zh-CN/built-in-nodes/GLSLShader"
                         ]
                       },
-
                       {
-                        "group": "腾讯混元",
+                        "group": "Text",
+                        "pages": [
+                          "zh-CN/built-in-nodes/AddTextPrefix",
+                          "zh-CN/built-in-nodes/AddTextSuffix",
+                          "zh-CN/built-in-nodes/MergeTextLists",
+                          "zh-CN/built-in-nodes/ReplaceText",
+                          "zh-CN/built-in-nodes/StripWhitespace",
+                          "zh-CN/built-in-nodes/TextToLowercase",
+                          "zh-CN/built-in-nodes/TextToUppercase",
+                          "zh-CN/built-in-nodes/TruncateText"
+                        ]
+                      },
+                      {
+                        "group": "Transform",
                         "pages": [
-                          "tutorials/video/hunyuan/hunyuan-video",
-                          "tutorials/video/hunyuan/hunyuan-video-1-5"
+                          "zh-CN/built-in-nodes/ImageCrop",
+                          "zh-CN/built-in-nodes/ImageCropV2",
+                          "zh-CN/built-in-nodes/ImageFlip",
+                          "zh-CN/built-in-nodes/ImageRotate",
+                          "zh-CN/built-in-nodes/ImageStitch",
+                          "zh-CN/built-in-nodes/ResizeAndPadImage"
                         ]
                       },
                       {
-                        "group": "Cosmos",
+                        "group": "Upscaling",
                         "pages": [
-                          "zh-CN/tutorials/video/cosmos/cosmos-predict2-video2world"
+                          "zh-CN/built-in-nodes/ImageScale",
+                          "zh-CN/built-in-nodes/ImageScaleBy",
+                          "zh-CN/built-in-nodes/ImageScaleToMaxDimension",
+                          "zh-CN/built-in-nodes/ImageScaleToTotalPixels",
+                          "zh-CN/built-in-nodes/ImageUpscaleWithModel"
                         ]
                       },
                       {
-                        "group": "Kandinsky",
+                        "group": "Video",
                         "pages": [
-                          "zh-CN/tutorials/video/kandinsky/kandinsky-5"
+                          "zh-CN/built-in-nodes/CreateVideo",
+                          "zh-CN/built-in-nodes/GetVideoComponents",
+                          "zh-CN/built-in-nodes/LoadVideo",
+                          "zh-CN/built-in-nodes/SaveVideo",
+                          "zh-CN/built-in-nodes/SaveWEBM",
+                          "zh-CN/built-in-nodes/Video Slice"
                         ]
-                      }
+                      },
+                      "zh-CN/built-in-nodes/BatchImagesNode",
+                      "zh-CN/built-in-nodes/EmptyImage",
+                      "zh-CN/built-in-nodes/GetImageSize",
+                      "zh-CN/built-in-nodes/ImageAddNoise",
+                      "zh-CN/built-in-nodes/ImageBatch",
+                      "zh-CN/built-in-nodes/ImageCompare",
+                      "zh-CN/built-in-nodes/ImageCompositeMasked",
+                      "zh-CN/built-in-nodes/ImageInvert",
+                      "zh-CN/built-in-nodes/ImagePadForOutpaint",
+                      "zh-CN/built-in-nodes/LoadImage",
+                      "zh-CN/built-in-nodes/LoadImageDataSetFromFolder",
+                      "zh-CN/built-in-nodes/LoadImageOutput",
+                      "zh-CN/built-in-nodes/LoadImageSetFromFolderNode",
+                      "zh-CN/built-in-nodes/LoadImageSetNode",
+                      "zh-CN/built-in-nodes/LoadImageTextDataSetFromFolder",
+                      "zh-CN/built-in-nodes/LoadImageTextSetFromFolderNode",
+                      "zh-CN/built-in-nodes/LoadTrainingDataset",
+                      "zh-CN/built-in-nodes/LoraLoader",
+                      "zh-CN/built-in-nodes/LoraLoaderModelOnly",
+                      "zh-CN/built-in-nodes/LTXVPreprocess",
+                      "zh-CN/built-in-nodes/MakeTrainingDataset",
+                      "zh-CN/built-in-nodes/PreviewImage",
+                      "zh-CN/built-in-nodes/ResizeImageMaskNode",
+                      "zh-CN/built-in-nodes/ResolutionBucket",
+                      "zh-CN/built-in-nodes/SaveImage",
+                      "zh-CN/built-in-nodes/SaveImageDataSetToFolder",
+                      "zh-CN/built-in-nodes/SaveImageTextDataSetToFolder",
+                      "zh-CN/built-in-nodes/SaveTrainingDataset",
+                      "zh-CN/built-in-nodes/WebcamCapture"
                     ]
                   },
                   {
-                    "group": "音频",
+                    "group": "实用工具",
                     "pages": [
                       {
-                        "group": "ACE-Step",
+                        "group": "Primitive",
                         "pages": [
-                          "zh-CN/tutorials/audio/ace-step/ace-step-v1",
-                          "zh-CN/tutorials/audio/ace-step/ace-step-v1-5"
+                          "zh-CN/built-in-nodes/PrimitiveBoolean",
+                          "zh-CN/built-in-nodes/PrimitiveBoundingBox",
+                          "zh-CN/built-in-nodes/PrimitiveFloat",
+                          "zh-CN/built-in-nodes/PrimitiveInt",
+                          "zh-CN/built-in-nodes/PrimitiveString",
+                          "zh-CN/built-in-nodes/PrimitiveStringMultiline"
                         ]
-                      }
-                    ]
-                  },
-                  {
-                    "group": "Utility",
-                    "pages": [
-                      "zh-CN/tutorials/utility/preprocessors",
-                      "zh-CN/tutorials/utility/frame-interpolation",
-                      "zh-CN/tutorials/utility/image-upscale",
-                      "zh-CN/tutorials/utility/video-upscale"
+                      },
+                      {
+                        "group": "String",
+                        "pages": [
+                          "zh-CN/built-in-nodes/CaseConverter",
+                          "zh-CN/built-in-nodes/RegexExtract",
+                          "zh-CN/built-in-nodes/RegexMatch",
+                          "zh-CN/built-in-nodes/RegexReplace",
+                          "zh-CN/built-in-nodes/StringCompare",
+                          "zh-CN/built-in-nodes/StringConcatenate",
+                          "zh-CN/built-in-nodes/StringContains",
+                          "zh-CN/built-in-nodes/StringLength",
+                          "zh-CN/built-in-nodes/StringReplace",
+                          "zh-CN/built-in-nodes/StringSubstring",
+                          "zh-CN/built-in-nodes/StringTrim"
+                        ]
+                      },
+                      "zh-CN/built-in-nodes/BatchImagesMasksLatentsNode",
+                      "zh-CN/built-in-nodes/ColorToRGBInt",
+                      "zh-CN/built-in-nodes/CustomCombo",
+                      "zh-CN/built-in-nodes/Mahiro",
+                      "zh-CN/built-in-nodes/MarkdownNote",
+                      "zh-CN/built-in-nodes/Note",
+                      "zh-CN/built-in-nodes/PreviewAny",
+                      "zh-CN/built-in-nodes/Reroute",
+                      "zh-CN/built-in-nodes/TerminalLog",
+                      "zh-CN/built-in-nodes/wanBlockSwap"
                     ]
                   },
                   {
-                    "group": "合作伙伴节点",
+                    "group": "条件",
                     "pages": [
-                      "zh-CN/tutorials/partner-nodes/overview",
-                      "zh-CN/tutorials/partner-nodes/faq",
-                      "zh-CN/tutorials/partner-nodes/pricing",
                       {
-                        "group": "Black Forest Labs",
+                        "group": "3D Models",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/black-forest-labs/flux-1-1-pro-ultra-image",
-                          "zh-CN/tutorials/partner-nodes/black-forest-labs/flux-1-kontext"
+                          "zh-CN/built-in-nodes/StableZero123_Conditioning",
+                          "zh-CN/built-in-nodes/StableZero123_Conditioning_Batched",
+                          "zh-CN/built-in-nodes/SV3D_Conditioning"
                         ]
                       },
                       {
-                        "group": "ByteDance",
+                        "group": "Controlnet",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/bytedance/seedream-5-lite"
+                          "zh-CN/built-in-nodes/ControlNetApply",
+                          "zh-CN/built-in-nodes/ControlNetApplyAdvanced",
+                          "zh-CN/built-in-nodes/ControlNetApplySD3",
+                          "zh-CN/built-in-nodes/ControlNetInpaintingAliMamaApply",
+                          "zh-CN/built-in-nodes/SetUnionControlNetType"
                         ]
                       },
                       {
-                        "group": "Google",
+                        "group": "Gligen",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/google/gemini",
-                          "zh-CN/tutorials/partner-nodes/google/nano-banana-pro"
+                          "zh-CN/built-in-nodes/GLIGENTextBoxApply"
                         ]
                       },
                       {
-                        "group": "Stability AI",
+                        "group": "Inpaint",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/stability-ai/stable-image-ultra",
-                          "zh-CN/tutorials/partner-nodes/stability-ai/stable-diffusion-3-5-image",
-                          "zh-CN/tutorials/partner-nodes/stability-ai/stable-audio"
+                          "zh-CN/built-in-nodes/CosmosImageToVideoLatent",
+                          "zh-CN/built-in-nodes/CosmosPredict2ImageToVideoLatent",
+                          "zh-CN/built-in-nodes/InpaintModelConditioning",
+                          "zh-CN/built-in-nodes/Wan22ImageToVideoLatent"
                         ]
                       },
                       {
-                        "group": "Ideogram",
+                        "group": "Instructpix2Pix",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/ideogram/ideogram-v3"
+                          "zh-CN/built-in-nodes/InstructPixToPixConditioning"
                         ]
                       },
                       {
-                        "group": "Luma",
+                        "group": "Lotus",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/luma/luma-text-to-image",
-                          "zh-CN/tutorials/partner-nodes/luma/luma-image-to-image",
-                          "zh-CN/tutorials/partner-nodes/luma/luma-text-to-video",
-                          "zh-CN/tutorials/partner-nodes/luma/luma-image-to-video"
+                          "zh-CN/built-in-nodes/LotusConditioning"
                         ]
                       },
                       {
-                        "group": "Moonvalley",
+                        "group": "Stable Cascade",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/moonvalley/moonvalley-video-generation"
+                          "zh-CN/built-in-nodes/StableCascade_StageB_Conditioning",
+                          "zh-CN/built-in-nodes/StableCascade_SuperResolutionControlnet"
                         ]
                       },
                       {
-                        "group": "OpenAI",
+                        "group": "Style Model",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/openai/gpt-image-1",
-                          "zh-CN/tutorials/partner-nodes/openai/dall-e-2",
-                          "zh-CN/tutorials/partner-nodes/openai/dall-e-3",
-                          "zh-CN/tutorials/partner-nodes/openai/chat"
+                          "zh-CN/built-in-nodes/StyleModelApply"
                         ]
                       },
                       {
-                        "group": "Recraft",
+                        "group": "Upscale Diffusion",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/recraft/recraft-v4",
-                          "zh-CN/tutorials/partner-nodes/recraft/recraft-text-to-image"
+                          "zh-CN/built-in-nodes/SD_4XUpscale_Conditioning"
                         ]
                       },
                       {
-                        "group": "Kling",
+                        "group": "Video Models",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/kling/kling-3-0",
-                          "zh-CN/tutorials/partner-nodes/kling/kling-motion-control"
+                          "zh-CN/built-in-nodes/conditioning/video-models/wan-vace-to-video",
+                          "zh-CN/built-in-nodes/GenerateTracks",
+                          "zh-CN/built-in-nodes/Hunyuan3Dv2Conditioning",
+                          "zh-CN/built-in-nodes/Hunyuan3Dv2ConditioningMultiView",
+                          "zh-CN/built-in-nodes/HunyuanImageToVideo",
+                          "zh-CN/built-in-nodes/HunyuanVideo15ImageToVideo",
+                          "zh-CN/built-in-nodes/Kandinsky5ImageToVideo",
+                          "zh-CN/built-in-nodes/LTXVAddGuide",
+                          "zh-CN/built-in-nodes/LTXVConditioning",
+                          "zh-CN/built-in-nodes/LTXVCropGuides",
+                          "zh-CN/built-in-nodes/LTXVImgToVideo",
+                          "zh-CN/built-in-nodes/LTXVImgToVideoInplace",
+                          "zh-CN/built-in-nodes/NormalizeVideoLatentStart",
+                          "zh-CN/built-in-nodes/Stablezero123Conditioning",
+                          "zh-CN/built-in-nodes/Stablezero123ConditioningBatched",
+                          "zh-CN/built-in-nodes/SVD_img2vid_Conditioning",
+                          "zh-CN/built-in-nodes/SvdImg2vidConditioning",
+                          "zh-CN/built-in-nodes/Wan22FunControlToVideo",
+                          "zh-CN/built-in-nodes/WanAnimateToVideo",
+                          "zh-CN/built-in-nodes/WanCameraImageToVideo",
+                          "zh-CN/built-in-nodes/WanFirstLastFrameToVideo",
+                          "zh-CN/built-in-nodes/WanFunControlToVideo",
+                          "zh-CN/built-in-nodes/WanFunInpaintToVideo",
+                          "zh-CN/built-in-nodes/WanHuMoImageToVideo",
+                          "zh-CN/built-in-nodes/WanImageToVideo",
+                          "zh-CN/built-in-nodes/WanInfiniteTalkToVideo",
+                          "zh-CN/built-in-nodes/WanMoveConcatTrack",
+                          "zh-CN/built-in-nodes/WanMoveTracksFromCoords",
+                          "zh-CN/built-in-nodes/WanMoveTrackToVideo",
+                          "zh-CN/built-in-nodes/WanMoveVisualizeTracks",
+                          "zh-CN/built-in-nodes/WanPhantomSubjectToVideo",
+                          "zh-CN/built-in-nodes/WanSoundImageToVideo",
+                          "zh-CN/built-in-nodes/WanSoundImageToVideoExtend",
+                          "zh-CN/built-in-nodes/WanTrackToVideo",
+                          "zh-CN/built-in-nodes/WanVaceToVideo"
                         ]
                       },
+                      "zh-CN/built-in-nodes/AudioEncoderEncode",
+                      "zh-CN/built-in-nodes/CLIPSetLastLayer",
+                      "zh-CN/built-in-nodes/ClipSetLastLayer",
+                      "zh-CN/built-in-nodes/CLIPTextEncode",
+                      "zh-CN/built-in-nodes/ClipTextEncode",
+                      "zh-CN/built-in-nodes/CLIPTextEncodeControlnet",
+                      "zh-CN/built-in-nodes/CLIPTextEncodeLumina2",
+                      "zh-CN/built-in-nodes/CLIPVisionEncode",
+                      "zh-CN/built-in-nodes/ClipVisionEncode",
+                      "zh-CN/built-in-nodes/ConditioningAverage",
+                      "zh-CN/built-in-nodes/ConditioningCombine",
+                      "zh-CN/built-in-nodes/ConditioningConcat",
+                      "zh-CN/built-in-nodes/ConditioningSetArea",
+                      "zh-CN/built-in-nodes/ConditioningSetAreaPercentage",
+                      "zh-CN/built-in-nodes/ConditioningSetAreaPercentageVideo",
+                      "zh-CN/built-in-nodes/ConditioningSetAreaStrength",
+                      "zh-CN/built-in-nodes/ConditioningSetMask",
+                      "zh-CN/built-in-nodes/ConditioningStableAudio",
+                      "zh-CN/built-in-nodes/HunyuanRefinerLatent",
+                      "zh-CN/built-in-nodes/PerpNeg",
+                      "zh-CN/built-in-nodes/Sd4xupscaleConditioning",
+                      "zh-CN/built-in-nodes/T5TokenizerOptions",
+                      "zh-CN/built-in-nodes/TextEncodeAceStepAudio",
+                      "zh-CN/built-in-nodes/TextEncodeAceStepAudio1.5",
+                      "zh-CN/built-in-nodes/unCLIPConditioning"
+                    ]
+                  },
+                  {
+                    "group": "模型补丁",
+                    "pages": [
                       {
-                        "group": "Runway",
+                        "group": "Chroma Radiance",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/runway/image-generation",
-                          "zh-CN/tutorials/partner-nodes/runway/video-generation"
+                          "zh-CN/built-in-nodes/ChromaRadianceOptions"
                         ]
                       },
                       {
-                        "group": "Rodin",
+                        "group": "Unet",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/rodin/model-generation"
+                          "zh-CN/built-in-nodes/Epsilon Scaling",
+                          "zh-CN/built-in-nodes/EpsilonScaling",
+                          "zh-CN/built-in-nodes/FreeU",
+                          "zh-CN/built-in-nodes/FreeU_V2",
+                          "zh-CN/built-in-nodes/HyperTile",
+                          "zh-CN/built-in-nodes/PatchModelAddDownscale",
+                          "zh-CN/built-in-nodes/PerturbedAttentionGuidance",
+                          "zh-CN/built-in-nodes/TemporalScoreRescaling",
+                          "zh-CN/built-in-nodes/TomePatchModel"
+                        ]
+                      }
+                    ]
+                  },
+                  {
+                    "group": "潜变量",
+                    "pages": [
+                      {
+                        "group": "3D",
+                        "pages": [
+                          "zh-CN/built-in-nodes/EmptyLatentHunyuan3Dv2",
+                          "zh-CN/built-in-nodes/VAEDecodeHunyuan3D"
                         ]
                       },
                       {
-                        "group": "Tripo",
+                        "group": "Advanced",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/tripo/model-generation"
+                          {
+                            "group": "Operations",
+                            "pages": [
+                              "zh-CN/built-in-nodes/LatentApplyOperation",
+                              "zh-CN/built-in-nodes/LatentApplyOperationCFG",
+                              "zh-CN/built-in-nodes/LatentOperationSharpen",
+                              "zh-CN/built-in-nodes/LatentOperationTonemapReinhard"
+                            ]
+                          },
+                          "zh-CN/built-in-nodes/LatentAdd",
+                          "zh-CN/built-in-nodes/LatentBatchSeedBehavior",
+                          "zh-CN/built-in-nodes/LatentConcat",
+                          "zh-CN/built-in-nodes/LatentCut",
+                          "zh-CN/built-in-nodes/LatentCutToBatch",
+                          "zh-CN/built-in-nodes/LatentInterpolate",
+                          "zh-CN/built-in-nodes/LatentMultiply",
+                          "zh-CN/built-in-nodes/LatentSubtract"
                         ]
                       },
                       {
-                        "group": "Hunyuan 3D",
+                        "group": "Audio",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/hunyuan3d/hunyuan3d-3-0"
+                          "zh-CN/built-in-nodes/EmptyAceStep1.5LatentAudio",
+                          "zh-CN/built-in-nodes/EmptyAceStepLatentAudio",
+                          "zh-CN/built-in-nodes/EmptyLatentAudio",
+                          "zh-CN/built-in-nodes/LTXVEmptyLatentAudio",
+                          "zh-CN/built-in-nodes/VAEDecodeAudio",
+                          "zh-CN/built-in-nodes/VAEDecodeAudioTiled",
+                          "zh-CN/built-in-nodes/VAEEncodeAudio"
                         ]
                       },
                       {
-                        "group": "Meshy",
+                        "group": "Batch",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/meshy/meshy-6"
+                          "zh-CN/built-in-nodes/LatentBatch",
+                          "zh-CN/built-in-nodes/LatentFromBatch",
+                          "zh-CN/built-in-nodes/RebatchLatents",
+                          "zh-CN/built-in-nodes/RepeatLatentBatch",
+                          "zh-CN/built-in-nodes/ReplaceVideoLatentFrames"
                         ]
                       },
                       {
-                        "group": "Bria",
+                        "group": "Chroma Radiance",
                         "pages": [
-                          "zh-CN/tutorials/partner-nodes/bria/fibo"
+                          "zh-CN/built-in-nodes/EmptyChromaRadianceLatentImage"
                         ]
-                      }
-                    ]
-                  }
-                ]
-              },
-              "changelog/index"
-            ]
-          },
-          {
-            "tab": "内置节点",
-            "pages": [
-              "zh-CN/built-in-nodes/overview",
-              {
-                "group": "条件",
-                "pages": [
-                  "zh-CN/built-in-nodes/ClipSetLastLayer",
-                  "zh-CN/built-in-nodes/ClipTextEncode",
-                  "zh-CN/built-in-nodes/ClipVisionEncode",
-                  {
-                    "group": "视频模型",
-                    "pages": [
-                      "zh-CN/built-in-nodes/conditioning/video-models/wan-vace-to-video"
-                    ]
-                  }
-                ]
-              },
-              {
-                "group": "图像",
-                "pages": ["zh-CN/built-in-nodes/Canny"]
-              },
-              {
-                "group": "加载器",
-                "pages": [
-                  "zh-CN/built-in-nodes/CheckpointLoaderSimple",
-                  "zh-CN/built-in-nodes/ClipLoader",
-                  "zh-CN/built-in-nodes/ClipVisionLoader"
-                ]
-              },
-              {
-                "group": "潜变量",
-                "pages": ["zh-CN/built-in-nodes/latent/video/trim-video-latent"]
-              },
-              {
-                "group": "高级",
-                "pages": [
-                  "zh-CN/built-in-nodes/ClipMergeSimple",
-                  "zh-CN/built-in-nodes/ClipSave",
-                  {
-                    "group": "条件",
-                    "pages": [
-                      "zh-CN/built-in-nodes/ClipTextEncodeFlux",
-                      "zh-CN/built-in-nodes/ClipTextEncodeHunyuanDit",
-                      "zh-CN/built-in-nodes/ClipTextEncodeSdxl",
-                      "zh-CN/built-in-nodes/ClipTextEncodeSdxlRefiner"
-                    ]
-                  }
-                ]
-              },
-              {
-                "group": "采样",
-                "pages": [
-                  "zh-CN/built-in-nodes/sampling/ksampler",
-                  {
-                    "group": "自定义采样",
-                    "pages": ["zh-CN/built-in-nodes/BasicScheduler"]
-                  }
-                ]
-              },
-              {
-                "group": "3D",
-                "pages": ["zh-CN/built-in-nodes/Load3D"]
-              },
-              {
-                "group": "合作伙伴节点",
-                "pages": [
-                  {
-                    "group": "图像",
-                    "pages": [
+                      },
                       {
-                        "group": "BFL",
+                        "group": "Inpaint",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/image/bfl/flux-1-1-pro-ultra-image"
+                          "zh-CN/built-in-nodes/SetLatentNoiseMask",
+                          "zh-CN/built-in-nodes/VAEEncodeForInpaint"
                         ]
                       },
                       {
-                        "group": "Luma",
+                        "group": "Qwen",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/image/luma/luma-reference",
-                          "zh-CN/built-in-nodes/partner-node/image/luma/luma-text-to-image",
-                          "zh-CN/built-in-nodes/partner-node/image/luma/luma-image-to-image"
+                          "zh-CN/built-in-nodes/EmptyQwenImageLayeredLatentImage"
                         ]
                       },
                       {
-                        "group": "Recraft",
+                        "group": "Sd3",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/save-svg",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-style-realistic-image",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-text-to-vector",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-creative-upscale",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-image-to-image",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-crisp-upscale",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-color-rgb",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-text-to-image",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-image-inpainting",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-vectorize-image",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-style-digital-illustration",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-remove-background",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-style-logo-raster",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-controls",
-                          "zh-CN/built-in-nodes/partner-node/image/recraft/recraft-replace-background"
+                          "zh-CN/built-in-nodes/EmptySD3LatentImage"
                         ]
                       },
                       {
-                        "group": "Ideogram",
+                        "group": "Stable Cascade",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/image/ideogram/ideogram-v2",
-                          "zh-CN/built-in-nodes/partner-node/image/ideogram/ideogram-v3",
-                          "zh-CN/built-in-nodes/partner-node/image/ideogram/ideogram-v1"
+                          "zh-CN/built-in-nodes/StableCascade_EmptyLatentImage",
+                          "zh-CN/built-in-nodes/StableCascade_StageC_VAEEncode"
                         ]
                       },
                       {
-                        "group": "Stability AI",
+                        "group": "Transform",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/image/stability-ai/stability-ai-stable-image-ultra",
-                          "zh-CN/built-in-nodes/partner-node/image/stability-ai/stability-ai-stable-diffusion-3-5-image"
+                          "zh-CN/built-in-nodes/LatentCrop",
+                          "zh-CN/built-in-nodes/LatentFlip",
+                          "zh-CN/built-in-nodes/LatentRotate"
                         ]
                       },
                       {
-                        "group": "OpenAI",
+                        "group": "Video",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/image/openai/openai-gpt-image1",
-                          "zh-CN/built-in-nodes/partner-node/image/openai/openai-dalle2",
-                          "zh-CN/built-in-nodes/partner-node/image/openai/openai-dalle3"
+                          {
+                            "group": "Ltxv",
+                            "pages": [
+                              "zh-CN/built-in-nodes/EmptyLTXVLatentVideo",
+                              "zh-CN/built-in-nodes/LTXVConcatAVLatent",
+                              "zh-CN/built-in-nodes/LTXVSeparateAVLatent"
+                            ]
+                          },
+                          "zh-CN/built-in-nodes/EmptyCosmosLatentVideo",
+                          "zh-CN/built-in-nodes/EmptyHunyuanLatentVideo",
+                          "zh-CN/built-in-nodes/EmptyHunyuanVideo15Latent",
+                          "zh-CN/built-in-nodes/EmptyMochiLatentVideo",
+                          "zh-CN/built-in-nodes/latent/video/trim-video-latent",
+                          "zh-CN/built-in-nodes/LTXVLatentUpsampler",
+                          "zh-CN/built-in-nodes/TrimVideoLatent"
                         ]
-                      }
+                      },
+                      "zh-CN/built-in-nodes/BatchLatentsNode",
+                      "zh-CN/built-in-nodes/EmptyFlux2LatentImage",
+                      "zh-CN/built-in-nodes/EmptyHunyuanImageLatent",
+                      "zh-CN/built-in-nodes/EmptyLatentImage",
+                      "zh-CN/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel",
+                      "zh-CN/built-in-nodes/LatentBlend",
+                      "zh-CN/built-in-nodes/LatentComposite",
+                      "zh-CN/built-in-nodes/LatentCompositeMasked",
+                      "zh-CN/built-in-nodes/LatentUpscale",
+                      "zh-CN/built-in-nodes/LatentUpscaleBy",
+                      "zh-CN/built-in-nodes/SaveLatent",
+                      "zh-CN/built-in-nodes/VAEDecode",
+                      "zh-CN/built-in-nodes/VAEDecodeTiled",
+                      "zh-CN/built-in-nodes/VAEEncode",
+                      "zh-CN/built-in-nodes/VAEEncodeTiled"
                     ]
                   },
                   {
-                    "group": "Video",
+                    "group": "采样",
                     "pages": [
                       {
-                        "group": "MiniMax",
+                        "group": "Custom Sampling",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/video/minimax/minimax-image-to-video",
-                          "zh-CN/built-in-nodes/partner-node/video/minimax/minimax-text-to-video"
+                          {
+                            "group": "Guiders",
+                            "pages": [
+                              "zh-CN/built-in-nodes/BasicGuider",
+                              "zh-CN/built-in-nodes/CFGGuider",
+                              "zh-CN/built-in-nodes/DualCFGGuider"
+                            ]
+                          },
+                          {
+                            "group": "Noise",
+                            "pages": [
+                              "zh-CN/built-in-nodes/AddNoise",
+                              "zh-CN/built-in-nodes/DisableNoise",
+                              "zh-CN/built-in-nodes/RandomNoise"
+                            ]
+                          },
+                          {
+                            "group": "Samplers",
+                            "pages": [
+                              "zh-CN/built-in-nodes/KSamplerSelect",
+                              "zh-CN/built-in-nodes/SamplerDPMAdaptative",
+                              "zh-CN/built-in-nodes/SamplerDpmpp2mSde",
+                              "zh-CN/built-in-nodes/SamplerDPMPP_2M_SDE",
+                              "zh-CN/built-in-nodes/SamplerDPMPP_2S_Ancestral",
+                              "zh-CN/built-in-nodes/SamplerDPMPP_3M_SDE",
+                              "zh-CN/built-in-nodes/SamplerDPMPP_SDE",
+                              "zh-CN/built-in-nodes/SamplerDpmppSde",
+                              "zh-CN/built-in-nodes/SamplerER_SDE",
+                              "zh-CN/built-in-nodes/SamplerEulerAncestral",
+                              "zh-CN/built-in-nodes/SamplerEulerAncestralCFGPP",
+                              "zh-CN/built-in-nodes/SamplerEulerCFGpp",
+                              "zh-CN/built-in-nodes/SamplerLCMUpscale",
+                              "zh-CN/built-in-nodes/SamplerLMS",
+                              "zh-CN/built-in-nodes/SamplerSASolver",
+                              "zh-CN/built-in-nodes/SamplerSEEDS2"
+                            ]
+                          },
+                          {
+                            "group": "Schedulers",
+                            "pages": [
+                              "zh-CN/built-in-nodes/AlignYourStepsScheduler",
+                              "zh-CN/built-in-nodes/BasicScheduler",
+                              "zh-CN/built-in-nodes/BetaSamplingScheduler",
+                              "zh-CN/built-in-nodes/ExponentialScheduler",
+                              "zh-CN/built-in-nodes/Flux2Scheduler",
+                              "zh-CN/built-in-nodes/GITSScheduler",
+                              "zh-CN/built-in-nodes/KarrasScheduler",
+                              "zh-CN/built-in-nodes/LaplaceScheduler",
+                              "zh-CN/built-in-nodes/LTXVScheduler",
+                              "zh-CN/built-in-nodes/OptimalStepsScheduler",
+                              "zh-CN/built-in-nodes/PolyexponentialScheduler",
+                              "zh-CN/built-in-nodes/SDTurboScheduler",
+                              "zh-CN/built-in-nodes/VPScheduler"
+                            ]
+                          },
+                          {
+                            "group": "Sigmas",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ExtendIntermediateSigmas",
+                              "zh-CN/built-in-nodes/FlipSigmas",
+                              "zh-CN/built-in-nodes/SamplingPercentToSigma",
+                              "zh-CN/built-in-nodes/SetFirstSigma",
+                              "zh-CN/built-in-nodes/SplitSigmas",
+                              "zh-CN/built-in-nodes/SplitSigmasDenoise"
+                            ]
+                          },
+                          "zh-CN/built-in-nodes/APG",
+                          "zh-CN/built-in-nodes/ManualSigmas",
+                          "zh-CN/built-in-nodes/SamplerCustom",
+                          "zh-CN/built-in-nodes/SamplerCustomAdvanced"
                         ]
                       },
                       {
-                        "group": "Google",
+                        "group": "Video Models",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/video/google/google-veo2-video"
+                          "zh-CN/built-in-nodes/VideoLinearCFGGuidance",
+                          "zh-CN/built-in-nodes/VideoTriangleCFGGuidance"
                         ]
                       },
+                      "zh-CN/built-in-nodes/DifferentialDiffusion",
+                      "zh-CN/built-in-nodes/KSampler",
+                      "zh-CN/built-in-nodes/KSamplerAdvanced",
+                      "zh-CN/built-in-nodes/PerpNegGuider",
+                      "zh-CN/built-in-nodes/sampling/ksampler",
+                      "zh-CN/built-in-nodes/SelfAttentionGuidance"
+                    ]
+                  },
+                  {
+                    "group": "高级",
+                    "pages": [
                       {
-                        "group": "Kling",
+                        "group": "Attention Experiments",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-controls",
-                          "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-text-to-video",
-                          "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-i2v",
-                          "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-image-to-video",
-                          "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-start-end-frame-to-video",
-                          "zh-CN/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-t2v"
+                          "zh-CN/built-in-nodes/CLIPAttentionMultiply",
+                          "zh-CN/built-in-nodes/UNetCrossAttentionMultiply",
+                          "zh-CN/built-in-nodes/UNetSelfAttentionMultiply",
+                          "zh-CN/built-in-nodes/UNetTemporalAttentionMultiply"
                         ]
                       },
                       {
-                        "group": "Luma",
+                        "group": "Conditioning",
+                        "pages": [
+                          {
+                            "group": "Audio",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ReferenceTimbreAudio"
+                            ]
+                          },
+                          {
+                            "group": "Edit Models",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ReferenceLatent"
+                            ]
+                          },
+                          {
+                            "group": "Flux",
+                            "pages": [
+                              "zh-CN/built-in-nodes/CLIPTextEncodeFlux",
+                              "zh-CN/built-in-nodes/ClipTextEncodeFlux",
+                              "zh-CN/built-in-nodes/FluxDisableGuidance",
+                              "zh-CN/built-in-nodes/FluxGuidance",
+                              "zh-CN/built-in-nodes/FluxKontextImageScale",
+                              "zh-CN/built-in-nodes/FluxKontextMultiReferenceLatentMethod"
+                            ]
+                          },
+                          {
+                            "group": "Kandinsky5",
+                            "pages": [
+                              "zh-CN/built-in-nodes/CLIPTextEncodeKandinsky5"
+                            ]
+                          },
+                          "zh-CN/built-in-nodes/CLIPTextEncodeHiDream",
+                          "zh-CN/built-in-nodes/CLIPTextEncodeHunyuanDiT",
+                          "zh-CN/built-in-nodes/ClipTextEncodeHunyuanDit",
+                          "zh-CN/built-in-nodes/CLIPTextEncodePixArtAlpha",
+                          "zh-CN/built-in-nodes/CLIPTextEncodeSD3",
+                          "zh-CN/built-in-nodes/CLIPTextEncodeSDXL",
+                          "zh-CN/built-in-nodes/ClipTextEncodeSdxl",
+                          "zh-CN/built-in-nodes/CLIPTextEncodeSDXLRefiner",
+                          "zh-CN/built-in-nodes/ClipTextEncodeSdxlRefiner",
+                          "zh-CN/built-in-nodes/ConditioningSetTimestepRange",
+                          "zh-CN/built-in-nodes/ConditioningZeroOut",
+                          "zh-CN/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo",
+                          "zh-CN/built-in-nodes/TextEncodeQwenImageEdit",
+                          "zh-CN/built-in-nodes/TextEncodeQwenImageEditPlus",
+                          "zh-CN/built-in-nodes/TextEncodeZImageOmni"
+                        ]
+                      },
+                      {
+                        "group": "Debug",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/video/luma/luma-text-to-video",
-                          "zh-CN/built-in-nodes/partner-node/video/luma/luma-image-to-video",
-                          "zh-CN/built-in-nodes/partner-node/video/luma/luma-concepts"
+                          {
+                            "group": "Model",
+                            "pages": [
+                              "zh-CN/built-in-nodes/EasyCache",
+                              "zh-CN/built-in-nodes/LazyCache",
+                              "zh-CN/built-in-nodes/ModelComputeDtype"
+                            ]
+                          }
                         ]
                       },
                       {
-                        "group": "Pika",
+                        "group": "Guidance",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/video/pika/pika-text-to-video",
-                          "zh-CN/built-in-nodes/partner-node/video/pika/pika-scenes",
-                          "zh-CN/built-in-nodes/partner-node/video/pika/pika-image-to-video"
+                          "zh-CN/built-in-nodes/CFGNorm",
+                          "zh-CN/built-in-nodes/CFGZeroStar",
+                          "zh-CN/built-in-nodes/NAGuidance",
+                          "zh-CN/built-in-nodes/SkipLayerGuidanceDiT",
+                          "zh-CN/built-in-nodes/SkipLayerGuidanceDiTSimple",
+                          "zh-CN/built-in-nodes/SkipLayerGuidanceSD3",
+                          "zh-CN/built-in-nodes/TCFG"
                         ]
                       },
                       {
-                        "group": "PixVerse",
+                        "group": "Hooks",
                         "pages": [
-                          "zh-CN/built-in-nodes/partner-node/video/pixverse/pixverse-template",
-                          "zh-CN/built-in-nodes/partner-node/video/pixverse/pixverse-text-to-video",
-                          "zh-CN/built-in-nodes/partner-node/video/pixverse/pixverse-transition-video",
-                          "zh-CN/built-in-nodes/partner-node/video/pixverse/pixverse-image-to-video"
+                          {
+                            "group": "Clip",
+                            "pages": [
+                              "zh-CN/built-in-nodes/SetClipHooks"
+                            ]
+                          },
+                          {
+                            "group": "Combine",
+                            "pages": [
+                              "zh-CN/built-in-nodes/CombineHooks",
+                              "zh-CN/built-in-nodes/CombineHooksEight",
+                              "zh-CN/built-in-nodes/CombineHooksFour"
+                            ]
+                          },
+                          {
+                            "group": "Cond Pair",
+                            "pages": [
+                              "zh-CN/built-in-nodes/PairConditioningCombine",
+                              "zh-CN/built-in-nodes/PairConditioningSetDefaultAndCombine",
+                              "zh-CN/built-in-nodes/PairConditioningSetProperties",
+                              "zh-CN/built-in-nodes/PairConditioningSetPropertiesAndCombine"
+                            ]
+                          },
+                          {
+                            "group": "Cond Single",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ConditioningSetDefaultAndCombine",
+                              "zh-CN/built-in-nodes/ConditioningSetProperties",
+                              "zh-CN/built-in-nodes/ConditioningSetPropertiesAndCombine"
+                            ]
+                          },
+                          {
+                            "group": "Create",
+                            "pages": [
+                              "zh-CN/built-in-nodes/CreateHookLora",
+                              "zh-CN/built-in-nodes/CreateHookLoraModelOnly",
+                              "zh-CN/built-in-nodes/CreateHookModelAsLora",
+                              "zh-CN/built-in-nodes/CreateHookModelAsLoraModelOnly"
+                            ]
+                          },
+                          {
+                            "group": "Manual",
+                            "pages": [
+                              "zh-CN/built-in-nodes/SetModelHooksOnCond"
+                            ]
+                          },
+                          {
+                            "group": "Scheduling",
+                            "pages": [
+                              "zh-CN/built-in-nodes/CreateHookKeyframe",
+                              "zh-CN/built-in-nodes/CreateHookKeyframesFromFloats",
+                              "zh-CN/built-in-nodes/CreateHookKeyframesInterpolated",
+                              "zh-CN/built-in-nodes/SetHookKeyframes"
+                            ]
+                          },
+                          "zh-CN/built-in-nodes/ConditioningTimestepsRange"
                         ]
-                      }
+                      },
+                      {
+                        "group": "Loaders",
+                        "pages": [
+                          {
+                            "group": "Deprecated",
+                            "pages": [
+                              "zh-CN/built-in-nodes/DiffusersLoader"
+                            ]
+                          },
+                          {
+                            "group": "Qwen",
+                            "pages": [
+                              "zh-CN/built-in-nodes/QwenImageDiffsynthControlnet"
+                            ]
+                          },
+                          {
+                            "group": "Zimage",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ZImageFunControlnet"
+                            ]
+                          },
+                          "zh-CN/built-in-nodes/CheckpointLoader",
+                          "zh-CN/built-in-nodes/CLIPLoader",
+                          "zh-CN/built-in-nodes/ClipLoader",
+                          "zh-CN/built-in-nodes/DeprecatedCheckpointLoader",
+                          "zh-CN/built-in-nodes/DeprecatedDiffusersLoader",
+                          "zh-CN/built-in-nodes/DualCLIPLoader",
+                          "zh-CN/built-in-nodes/LTXAVTextEncoderLoader",
+                          "zh-CN/built-in-nodes/ModelPatchLoader",
+                          "zh-CN/built-in-nodes/QuadrupleCLIPLoader",
+                          "zh-CN/built-in-nodes/TripleCLIPLoader",
+                          "zh-CN/built-in-nodes/UNETLoader"
+                        ]
+                      },
+                      {
+                        "group": "Model",
+                        "pages": [
+                          "zh-CN/built-in-nodes/ModelSamplingAuraFlow",
+                          "zh-CN/built-in-nodes/ModelSamplingContinuousEDM",
+                          "zh-CN/built-in-nodes/ModelSamplingContinuousV",
+                          "zh-CN/built-in-nodes/ModelSamplingDiscrete",
+                          "zh-CN/built-in-nodes/ModelSamplingFlux",
+                          "zh-CN/built-in-nodes/ModelSamplingLTXV",
+                          "zh-CN/built-in-nodes/ModelSamplingSD3",
+                          "zh-CN/built-in-nodes/ModelSamplingStableCascade",
+                          "zh-CN/built-in-nodes/RenormCFG",
+                          "zh-CN/built-in-nodes/RescaleCFG"
+                        ]
+                      },
+                      {
+                        "group": "Model Merging",
+                        "pages": [
+                          {
+                            "group": "Model Specific",
+                            "pages": [
+                              "zh-CN/built-in-nodes/ModelMergeAuraflow",
+                              "zh-CN/built-in-nodes/ModelMergeCosmos14B",
+                              "zh-CN/built-in-nodes/ModelMergeCosmos7B",
+                              "zh-CN/built-in-nodes/ModelMergeCosmosPredict2_14B",
+                              "zh-CN/built-in-nodes/ModelMergeCosmosPredict2_2B",
+                              "zh-CN/built-in-nodes/ModelMergeFlux1",
+                              "zh-CN/built-in-nodes/ModelMergeLTXV",
+                              "zh-CN/built-in-nodes/ModelMergeMochiPreview",
+                              "zh-CN/built-in-nodes/ModelMergeQwenImage",
+                              "zh-CN/built-in-nodes/ModelMergeSD1",
+                              "zh-CN/built-in-nodes/ModelMergeSD35_Large",
+                              "zh-CN/built-in-nodes/ModelMergeSD3_2B",
+                              "zh-CN/built-in-nodes/ModelMergeSDXL",
+                              "zh-CN/built-in-nodes/ModelMergeWAN2_1"
+                            ]
+                          },
+                          "zh-CN/built-in-nodes/CheckpointSave",
+                          "zh-CN/built-in-nodes/CLIPAdd",
+                          "zh-CN/built-in-nodes/CLIPMergeAdd",
+                          "zh-CN/built-in-nodes/CLIPMergeSimple",
+                          "zh-CN/built-in-nodes/ClipMergeSimple",
+                          "zh-CN/built-in-nodes/CLIPMergeSubtract",
+                          "zh-CN/built-in-nodes/CLIPSave",
+                          "zh-CN/built-in-nodes/ClipSave",
+                          "zh-CN/built-in-nodes/CLIPSubtract",
+                          "zh-CN/built-in-nodes/ImageOnlyCheckpointSave",
+                          "zh-CN/built-in-nodes/LoraSave",
+                          "zh-CN/built-in-nodes/ModelMergeAdd",
+                          "zh-CN/built-in-nodes/ModelMergeBlocks",
+                          "zh-CN/built-in-nodes/ModelMergeSimple",
+                          "zh-CN/built-in-nodes/ModelMergeSubtract",
+                          "zh-CN/built-in-nodes/ModelSave",
+                          "zh-CN/built-in-nodes/SaveLoRANode",
+                          "zh-CN/built-in-nodes/VAESave"
+                        ]
+                      },
+                      {
+                        "group": "Model Patches",
+                        "pages": [
+                          {
+                            "group": "Flux",
+                            "pages": [
+                              "zh-CN/built-in-nodes/USOStyleReference"
+                            ]
+                          },
+                          "zh-CN/built-in-nodes/ScaleROPE"
+                        ]
+                      },
+                      {
+                        "group": "Photomaker",
+                        "pages": [
+                          "zh-CN/built-in-nodes/PhotoMakerEncode",
+                          "zh-CN/built-in-nodes/PhotoMakerLoader"
+                        ]
+                      },
+                      "zh-CN/built-in-nodes/FreSca",
+                      "zh-CN/built-in-nodes/TorchCompileModel"
                     ]
                   }
                 ]
@@ -1595,7 +4240,12 @@
     ]
   },
   "contextual": {
-    "options": ["copy", "view", "chatgpt", "claude"]
+    "options": [
+      "copy",
+      "view",
+      "chatgpt",
+      "claude"
+    ]
   },
   "integrations": {
     "ga4": {
@@ -1692,4 +4342,4 @@
       "destination": "/zh-CN/custom-nodes/backend/expansion"
     }
   ]
-}
+}
\ No newline at end of file
diff --git a/images/built-in-nodes/canny/compare.webp b/images/built-in-nodes/Canny/compare.webp
similarity index 100%
rename from images/built-in-nodes/canny/compare.webp
rename to images/built-in-nodes/Canny/compare.webp
diff --git a/images/built-in-nodes/canny/input.webp b/images/built-in-nodes/Canny/input.webp
similarity index 100%
rename from images/built-in-nodes/canny/input.webp
rename to images/built-in-nodes/Canny/input.webp
diff --git a/images/built-in-nodes/ConditioningAverage/example.webp b/images/built-in-nodes/ConditioningAverage/example.webp
new file mode 100644
index 000000000..f2b1af5bd
Binary files /dev/null and b/images/built-in-nodes/ConditioningAverage/example.webp differ
diff --git a/images/built-in-nodes/ConditioningCombine/compare.jpg b/images/built-in-nodes/ConditioningCombine/compare.jpg
new file mode 100644
index 000000000..1c115b3c1
Binary files /dev/null and b/images/built-in-nodes/ConditioningCombine/compare.jpg differ
diff --git a/images/built-in-nodes/ImageStitch/output-1.webp b/images/built-in-nodes/ImageStitch/output-1.webp
new file mode 100644
index 000000000..ceca52882
Binary files /dev/null and b/images/built-in-nodes/ImageStitch/output-1.webp differ
diff --git a/images/built-in-nodes/ImageStitch/output-2.webp b/images/built-in-nodes/ImageStitch/output-2.webp
new file mode 100644
index 000000000..6e5702283
Binary files /dev/null and b/images/built-in-nodes/ImageStitch/output-2.webp differ
diff --git a/images/built-in-nodes/ImageStitch/workflow.webp b/images/built-in-nodes/ImageStitch/workflow.webp
new file mode 100644
index 000000000..96d944944
Binary files /dev/null and b/images/built-in-nodes/ImageStitch/workflow.webp differ
diff --git a/images/built-in-nodes/Load3D/load3d_outputs.webp b/images/built-in-nodes/Load3D/load3d_outputs.webp
new file mode 100644
index 000000000..f37d20686
Binary files /dev/null and b/images/built-in-nodes/Load3D/load3d_outputs.webp differ
diff --git a/images/built-in-nodes/Load3D/load3d_ui.jpg b/images/built-in-nodes/Load3D/load3d_ui.jpg
new file mode 100644
index 000000000..46c22cdc0
Binary files /dev/null and b/images/built-in-nodes/Load3D/load3d_ui.jpg differ
diff --git a/images/built-in-nodes/Load3D/menu.webp b/images/built-in-nodes/Load3D/menu.webp
new file mode 100644
index 000000000..4cbbb4b2e
Binary files /dev/null and b/images/built-in-nodes/Load3D/menu.webp differ
diff --git a/images/built-in-nodes/Load3D/menu_camera.webp b/images/built-in-nodes/Load3D/menu_camera.webp
new file mode 100644
index 000000000..20b2f7bc7
Binary files /dev/null and b/images/built-in-nodes/Load3D/menu_camera.webp differ
diff --git a/images/built-in-nodes/Load3D/menu_export.webp b/images/built-in-nodes/Load3D/menu_export.webp
new file mode 100644
index 000000000..51cc9fa81
Binary files /dev/null and b/images/built-in-nodes/Load3D/menu_export.webp differ
diff --git a/images/built-in-nodes/Load3D/menu_light.webp b/images/built-in-nodes/Load3D/menu_light.webp
new file mode 100644
index 000000000..9d39adf8f
Binary files /dev/null and b/images/built-in-nodes/Load3D/menu_light.webp differ
diff --git a/images/built-in-nodes/Load3D/menu_model.webp b/images/built-in-nodes/Load3D/menu_model.webp
new file mode 100644
index 000000000..263e28262
Binary files /dev/null and b/images/built-in-nodes/Load3D/menu_model.webp differ
diff --git a/images/built-in-nodes/Load3D/menu_scene.webp b/images/built-in-nodes/Load3D/menu_scene.webp
new file mode 100644
index 000000000..070a024af
Binary files /dev/null and b/images/built-in-nodes/Load3D/menu_scene.webp differ
diff --git a/images/built-in-nodes/Load3D/view_operations.mp4 b/images/built-in-nodes/Load3D/view_operations.mp4
new file mode 100644
index 000000000..77af5b9ab
Binary files /dev/null and b/images/built-in-nodes/Load3D/view_operations.mp4 differ
diff --git a/images/built-in-nodes/Load3DAnimation/load3d_outputs.webp b/images/built-in-nodes/Load3DAnimation/load3d_outputs.webp
new file mode 100644
index 000000000..f37d20686
Binary files /dev/null and b/images/built-in-nodes/Load3DAnimation/load3d_outputs.webp differ
diff --git a/images/built-in-nodes/Load3DAnimation/load3d_ui.jpg b/images/built-in-nodes/Load3DAnimation/load3d_ui.jpg
new file mode 100644
index 000000000..46c22cdc0
Binary files /dev/null and b/images/built-in-nodes/Load3DAnimation/load3d_ui.jpg differ
diff --git a/images/built-in-nodes/Load3DAnimation/recording.mp4 b/images/built-in-nodes/Load3DAnimation/recording.mp4
new file mode 100644
index 000000000..5f077f4d4
Binary files /dev/null and b/images/built-in-nodes/Load3DAnimation/recording.mp4 differ
diff --git a/images/built-in-nodes/Preview3D/preview3d_canvas.jpg b/images/built-in-nodes/Preview3D/preview3d_canvas.jpg
new file mode 100644
index 000000000..6fcbf7be1
Binary files /dev/null and b/images/built-in-nodes/Preview3D/preview3d_canvas.jpg differ
diff --git a/images/built-in-nodes/Preview3DAnimation/preview3d_canvas.jpg b/images/built-in-nodes/Preview3DAnimation/preview3d_canvas.jpg
new file mode 100644
index 000000000..6fcbf7be1
Binary files /dev/null and b/images/built-in-nodes/Preview3DAnimation/preview3d_canvas.jpg differ
diff --git a/tutorials/partner-nodes/pricing.mdx b/tutorials/partner-nodes/pricing.mdx
index 2078ce6c2..428c50048 100644
--- a/tutorials/partner-nodes/pricing.mdx
+++ b/tutorials/partner-nodes/pricing.mdx
@@ -1,16 +1,14 @@
 ---
 title: "Pricing"
-description: "This article lists the pricing of the current Partner Nodes."
+description: "This article lists the pricing of the current Partner Nodes. All prices are in credits (211 credits = 1 USD)."
 sidebarTitle: "Pricing"
 mode: wide
 ---
 
-The following table lists the pricing of the current Partner Nodes. All prices are in credits. 
+The following table lists the pricing of the current Partner Nodes. All prices are in credits.
 
 211 credits = 1 USD
 
-> Please refer to the prices shown in the ComfyUI interface for the actual pricing.
-
 ## BFL
 
 | Product Name               | Configuration              | Credits     | Category |
@@ -29,9 +27,11 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 
 ## Bria
 
-| Product Name    | Configuration                        | Credits    | Category |
-| :-------------- | :----------------------------------- | :--------- | :------- |
-| Bria Image Edit | endpoint: v2/image/edit, model: fibo | 8.44 / run | Image    |
+| Product Name                 | Configuration                             | Credits     | Category |
+| :--------------------------- | :---------------------------------------- | :---------- | :------- |
+| Bria Image Edit              | endpoint: v2/image/edit, model: fibo      | 8.44 / run  | Image    |
+| Bria Image Remove Background | endpoint: v2/image/edit/remove_background | 3.8 / run   | Image    |
+| Bria Video Remove Background | endpoint: v2/video/edit/remove_background | 29.54 / sec | Video    |
 
 ## ByteDance
 
@@ -41,7 +41,7 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | BytePlus Image Generation Product                    | model: seedream-3-0-t2i-250415                                  | 6.33 / run        | Image    |
 | BytePlus Image Generation Product                    | model: seedream-4-0-250828                                      | 6.33 / run        | Image    |
 | BytePlus Image Generation Product                    | model: seedream-4-5-251128                                      | 8.44 / run        | Image    |
-| BytePlus Image Generation Product                    | model: seedream-5-0-lite                                        | 7.4 / run         | Image    |
+| BytePlus Image Generation Product                    | model: seedream-5-0-260128                                      | 7.39 / run        | Image    |
 | BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-lite-i2v-250428, video_type: image-to-video | 379.8 / 1M tokens | Video    |
 | BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-lite-t2v-250428, video_type: text-to-video  | 379.8 / 1M tokens | Video    |
 | BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-250528, video_type: image-to-video      | 527.5 / 1M tokens | Video    |
@@ -52,6 +52,21 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | BytePlus Video Generation With Audio (Per 1M tokens) | generate_audio: false, model: seedance-1-5-pro-251215           | 253.2 / 1M tokens | Video    |
 | BytePlus Video Generation With Audio (Per 1M tokens) | generate_audio: true, model: seedance-1-5-pro-251215            | 506.4 / 1M tokens | Video    |
 
+## ElevenLabs
+
+| Product Name                           | Configuration                                              | Credits     | Category |
+| :------------------------------------- | :--------------------------------------------------------- | :---------- | :------- |
+| 11labs Text-to-Speech                  | endpoint: v1/text-to-dialogue, model: eleven_v3            | 50.64 / run | Audio    |
+| 11labs Text-to-Speech                  | endpoint: v1/text-to-speech, model: eleven_multilingual_v2 | 50.64 / run | Audio    |
+| 11labs Text-to-Speech                  | endpoint: v1/text-to-speech, model: eleven_v3              | 50.64 / run | Audio    |
+| 11labs Speech-to-Text                  | endpoint: v1/speech-to-text, model: scribe_v2              | 92.84 / run | Audio    |
+| 11labs Speech-to-Text Keyterm          | endpoint: v1/speech-to-text, model: scribe_v2              | 18.57 / run | Audio    |
+| 11labs Speech-to-Text Entity Detection | endpoint: scribe_v2, model: v1/speech-to-text              | 27.85 / run | Audio    |
+| 11labs Speech-to-Speech Per Minute     | endpoint: v1/speech-to-speech                              | 50.64 / min | Audio    |
+| 11labs Sound Generation Per Minute     | endpoint: v1/sound-generation                              | 29.54 / min | Audio    |
+| 11labs Audio Isolation Per Minute      | endpoint: v1/audio-isolation                               | 50.64 / min | Audio    |
+| 11labs Add Voice                       | endpoint: v1/voices/add                                    | 31.65 / run | Audio    |
+
 ## Freepik
 
 | Product Name                 | Configuration                     | Credits     | Category |
@@ -61,6 +76,7 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Freepik Image Per Generation | endpoint: skin-enhancer-creative  | 61.19 / run | Image    |
 | Freepik Image Per Generation | endpoint: skin-enhancer-faithful  | 78.07 / run | Image    |
 | Freepik Image Per Generation | endpoint: skin-enhancer-flexible  | 94.95 / run | Image    |
+| Freepik Image Cost           | NA                                | 211 / run   | Image    |
 
 ## Google
 
@@ -74,6 +90,8 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Text     |
 | Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Text     |
 | Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-3.1-flash-image-preview                      | 105.5 / 1M tokens  | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-3.1-pro-preview                              | 422 / 1M tokens    | Text     |
 | Gemini Input Text Tokens (per 1M) Product   | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Text     |
 | Gemini Input Text Tokens (per 1M) Product   | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Text     |
 | Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 527.5 / 1M tokens  | Text     |
@@ -82,6 +100,8 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 527.5 / 1M tokens  | Text     |
 | Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 2110 / 1M tokens   | Text     |
 | Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 2110 / 1M tokens   | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-3.1-flash-image-preview                      | 633 / 1M tokens    | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-3.1-pro-preview                              | 2532 / 1M tokens   | Text     |
 | Gemini Output Text Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 2532 / 1M tokens   | Text     |
 | Gemini Output Text Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 2532 / 1M tokens   | Text     |
 | Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 63.3 / 1M tokens   | Image    |
@@ -90,12 +110,16 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Image    |
 | Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Image    |
 | Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-3.1-flash-image-preview                      | 105.5 / 1M tokens  | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-3.1-pro-preview                              | 422 / 1M tokens    | Image    |
 | Gemini Input Image Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Image    |
 | Gemini Input Image Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Image    |
 | Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-image                              | 6330 / 1M tokens   | Image    |
 | Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-image-preview                      | 6330 / 1M tokens   | Image    |
 | Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 3165 / 1M tokens   | Image    |
 | Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-pro-preview-05-06                        | 7385 / 1M tokens   | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-3.1-flash-image-preview                      | 12660 / 1M tokens  | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-3.1-pro-preview                              | 25320 / 1M tokens  | Image    |
 | Gemini Output Image Tokens (per 1M) Product | model: gemini-3-pro-image-preview                          | 25320 / 1M tokens  | Image    |
 | Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 63.3 / 1M tokens   | Video    |
 | Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 63.3 / 1M tokens   | Video    |
@@ -103,6 +127,7 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Video    |
 | Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Video    |
 | Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-3.1-pro-preview                              | 422 / 1M tokens    | Video    |
 | Gemini Input Video Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Video    |
 | Gemini Input Video Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Video    |
 | Gemini Output Video Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 4220 / 1M tokens   | Video    |
@@ -113,6 +138,7 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 211 / 1M tokens    | Audio    |
 | Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Audio    |
 | Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-3.1-pro-preview                              | 422 / 1M tokens    | Audio    |
 | Gemini Input Audio Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Audio    |
 | Gemini Input Audio Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Audio    |
 | Gemini Output Audio Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 3165 / 1M tokens   | Audio    |
@@ -130,6 +156,8 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Google Veo3                                 | generateAudio: true, model: veo-3.0-generate-001           | 84.4 / run         | Image    |
 | Google Veo3                                 | generateAudio: true, model: veo-3.1-fast-generate-preview  | 31.65 / run        | Image    |
 | Google Veo3                                 | generateAudio: true, model: veo-3.1-generate-preview       | 84.4 / run         | Image    |
+| Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3.1-flash-image-preview                      | 633 / 1M tokens    | Text     |
+| Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3.1-pro-preview                              | 2532 / 1M tokens   | Text     |
 | Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3-pro-image-preview                          | 2532 / 1M tokens   | Text     |
 | Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3-pro-preview                                | 2532 / 1M tokens   | Text     |
 
@@ -220,6 +248,8 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Kling Video Generation with Sound Product | mode: pro, model: kling-v2-6, sound: on                      | 29.54 / sec  | Video    |
 | Kling Motion Control Product              | mode: pro, model: kling-v2-6                                 | 23.63 / run  | Image    |
 | Kling Motion Control Product              | mode: std, model: kling-v2-6                                 | 14.77 / run  | Image    |
+| Kling Credits                             | type: image                                                  | 0.74 / run   | Image    |
+| Kling Credits                             | type: video                                                  | 29.54 / run  | Image    |
 
 ## Lightricks
 
@@ -473,6 +503,9 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Tencent 3D Face Count       | custom_face_count: true, endpoint: hunyuan/3d-pro | 42.2 / run  | 3D       |
 | Tencent 3D PBR              | enable_pbr: true, endpoint: hunyuan/3d-pro        | 42.2 / run  | 3D       |
 | Tencent 3D Multiview Images | endpoint: hunyuan/3d-pro, multi_view: true        | 42.2 / run  | Image    |
+| Tencent 3D                  | endpoint: hunyuan/3d-part                         | 126.6 / run | 3D       |
+| Tencent 3D                  | endpoint: hunyuan/3d-texture-edit                 | 126.6 / run | 3D       |
+| Tencent 3D                  | endpoint: hunyuan/3d-uv                           | 42.2 / run  | 3D       |
 
 ## Topaz
 
@@ -525,15 +558,6 @@ The following table lists the pricing of the current Partner Nodes. All prices a
 | Tripo V1-4 Generation Product            | type: text_to_model                                                       | 42.2 / run  | 3D       |
 | Tripo Geometry Quality Product           | geometry_quality: detailed                                                | 42.2 / run  | 3D       |
 
-## Vidu
-
-| Model(Node name)        | Category | Parameters that affect price | Parameter combo | Price (Credits) |
-| ----------------------- | -------- | ---------------------------- | --------------- | ------- |
-| ViduImageToVideoNode    | Video    | NA                           | NA              | 84.4 |
-| ViduReferenceVideoNode  | Video    | NA                           | NA              | 84.4 |
-| ViduStartEndToVideoNode | Video    | NA                           | NA              | 84.4 |
-| ViduTextToVideoNode     | Video    | NA                           | NA              | 84.4 |
-
 ## WAN
 
 | Product Name                 | Configuration                                | Credits     | Category |
@@ -575,5 +599,4 @@ Video endpoints charge for moderated content.
 | xAI Video Generation Output Video Per Second | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 720p                       | 38.19 / sec | Video    |
 | xAI Video Generation Input Image             | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 480p, type: image-to-video | 0.42 / sec  | Video    |
 | xAI Video Generation Input Image             | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 720p, type: image-to-video | 0.42 / sec  | Video    |
-| xAI Video Edit Input+Output Video Per Second | endpoint: v1/videos/edits, model: grok-imagine-video-beta, resolution: 480p                             | 40.3 / sec  | Video    |
-
+| xAI Video Edit Input+Output Video Per Second | endpoint: v1/videos/edits, model: grok-imagine-video-beta, resolution: 480p                             | 40.3 / sec  | Video    |
\ No newline at end of file
diff --git a/zh-CN/built-in-nodes/APG.mdx b/zh-CN/built-in-nodes/APG.mdx
new file mode 100644
index 000000000..7c182be8c
--- /dev/null
+++ b/zh-CN/built-in-nodes/APG.mdx
@@ -0,0 +1,25 @@
+---
+title: "APG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the APG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "APG"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/APG/zh.md)
+
+APG（自适应投影引导）节点通过调整扩散过程中引导应用的方式，来修改采样过程。它将引导向量分离为相对于条件输出的平行和正交分量，从而实现更可控的图像生成。该节点提供了用于缩放引导、归一化其幅度以及应用动量以实现扩散步骤间更平滑过渡的参数。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | 必选 | - | - | 要应用自适应投影引导的扩散模型 |
+| `eta` | FLOAT | 必选 | 1.0 | -10.0 到 10.0 | 控制平行引导向量的缩放比例。设置为 1 时为默认的 CFG 行为。 |
+| `norm_threshold` | FLOAT | 必选 | 5.0 | 0.0 到 50.0 | 将引导向量归一化到此值，设置为 0 时禁用归一化。 |
+| `momentum` | FLOAT | 必选 | 0.0 | -5.0 到 1.0 | 控制扩散过程中引导的滑动平均值，设置为 0 时禁用。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 返回已在其采样过程中应用了自适应投影引导的修改后模型 |
diff --git a/zh-CN/built-in-nodes/AddNoise.mdx b/zh-CN/built-in-nodes/AddNoise.mdx
new file mode 100644
index 000000000..bc669c310
--- /dev/null
+++ b/zh-CN/built-in-nodes/AddNoise.mdx
@@ -0,0 +1,31 @@
+---
+title: "AddNoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AddNoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AddNoise"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddNoise/zh.md)
+
+# AddNoise
+
+此节点使用指定的噪声参数和 sigma 值向潜在图像添加受控噪声。它通过模型的采样系统处理输入，以应用适合给定 sigma 范围的噪声缩放。
+
+## 工作原理
+
+该节点接收一个潜在图像，并根据提供的噪声生成器和 sigma 值向其添加噪声。它首先检查是否提供了任何 sigmas - 如果没有，则返回未经更改的原始潜在图像。然后，该节点使用模型的采样系统处理潜在图像并应用缩放后的噪声。当提供多个 sigmas 时，噪声缩放由第一个和最后一个 sigma 值之间的差异决定；当仅提供一个 sigma 时，则由单个 sigma 值决定。空的潜在图像（仅包含零值）在处理过程中不会被偏移。最终输出是带有应用噪声的新潜在表示，任何 NaN 或无限值都会被转换为零以确保稳定性。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-------|-----------|------------|---------|-------|-------------|
+| `模型` | MODEL | 必填 | - | - | 包含采样参数和处理函数的模型 |
+| `噪波` | NOISE | 必填 | - | - | 产生基础噪声模式的噪声生成器 |
+| `Sigmas` | SIGMAS | 必填 | - | - | 控制噪声缩放强度的 sigma 值 |
+| `Latent` | LATENT | 必填 | - | - | 将要添加噪声的输入潜在表示 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-----------|-----------|-------------|
+| `LATENT` | LATENT | 带有添加噪声的修改后潜在表示 |
diff --git a/zh-CN/built-in-nodes/AddTextPrefix.mdx b/zh-CN/built-in-nodes/AddTextPrefix.mdx
new file mode 100644
index 000000000..b18019d8d
--- /dev/null
+++ b/zh-CN/built-in-nodes/AddTextPrefix.mdx
@@ -0,0 +1,23 @@
+---
+title: "AddTextPrefix - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AddTextPrefix node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AddTextPrefix"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextPrefix/zh.md)
+
+Add Text Prefix 节点通过在每个输入文本的开头添加指定字符串来修改文本。它接收文本和前缀作为输入，然后返回组合后的结果。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | 是 | | 需要添加前缀的文本。 |
+| `prefix` | STRING | 否 | | 要添加到文本开头的字符串（默认值：""）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `text` | STRING | 将前缀添加到开头后得到的文本。 |
diff --git a/zh-CN/built-in-nodes/AddTextSuffix.mdx b/zh-CN/built-in-nodes/AddTextSuffix.mdx
new file mode 100644
index 000000000..7e14a8b7a
--- /dev/null
+++ b/zh-CN/built-in-nodes/AddTextSuffix.mdx
@@ -0,0 +1,23 @@
+---
+title: "AddTextSuffix - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AddTextSuffix node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AddTextSuffix"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextSuffix/zh.md)
+
+此节点将指定的后缀追加到输入文本字符串的末尾。它接收原始文本和后缀作为输入，然后返回组合后的结果。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | 是 | | 将要添加后缀的原始文本。 |
+| `suffix` | STRING | 否 | | 要添加到文本的后缀（默认值：""）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `text` | STRING | 后缀追加后得到的最终文本。 |
diff --git a/zh-CN/built-in-nodes/AdjustBrightness.mdx b/zh-CN/built-in-nodes/AdjustBrightness.mdx
new file mode 100644
index 000000000..2e677bfe0
--- /dev/null
+++ b/zh-CN/built-in-nodes/AdjustBrightness.mdx
@@ -0,0 +1,23 @@
+---
+title: "AdjustBrightness - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AdjustBrightness node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AdjustBrightness"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustBrightness/zh.md)
+
+此节点通过将输入图像的每个像素值乘以指定系数来调整图像亮度，并确保结果值保持在有效范围内。系数为 1.0 时图像保持不变，低于 1.0 会使图像变暗，高于 1.0 会使图像变亮。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待调整的输入图像。 |
+| `factor` | FLOAT | 否 | 0.0 - 2.0 | 亮度系数。1.0 = 无变化，&lt;1.0 = 变暗，>1.0 = 变亮。（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 调整亮度后的输出图像。 |
diff --git a/zh-CN/built-in-nodes/AdjustContrast.mdx b/zh-CN/built-in-nodes/AdjustContrast.mdx
new file mode 100644
index 000000000..bd59fe934
--- /dev/null
+++ b/zh-CN/built-in-nodes/AdjustContrast.mdx
@@ -0,0 +1,23 @@
+---
+title: "AdjustContrast - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AdjustContrast node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AdjustContrast"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustContrast/zh.md)
+
+调整对比度节点用于修改输入图像的对比度水平。它通过调整图像明暗区域之间的差异来实现。系数为 1.0 时图像保持不变，低于 1.0 的值会降低对比度，高于 1.0 的值则会增强对比度。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 需要进行对比度调整的输入图像。 |
+| `factor` | FLOAT | 否 | 0.0 - 2.0 | 对比度系数。1.0 = 无变化，&lt;1.0 = 降低对比度，>1.0 = 增强对比度。（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 调整对比度后的结果图像。 |
diff --git a/zh-CN/built-in-nodes/AlignYourStepsScheduler.mdx b/zh-CN/built-in-nodes/AlignYourStepsScheduler.mdx
new file mode 100644
index 000000000..e5dead9f0
--- /dev/null
+++ b/zh-CN/built-in-nodes/AlignYourStepsScheduler.mdx
@@ -0,0 +1,24 @@
+---
+title: "AlignYourStepsScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AlignYourStepsScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AlignYourStepsScheduler"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献您的力量！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AlignYourStepsScheduler/zh.md)
+
+AlignYourStepsScheduler 节点根据不同的模型类型生成用于去噪过程的 sigma 值。它计算采样过程每个步骤的适当噪声水平，并根据去噪参数调整总步数。这有助于将采样步骤与不同扩散模型的特定要求对齐。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `模型类型` | STRING | 下拉选项 | - | SD1, SDXL, SVD | 指定用于 sigma 计算的模型类型 |
+| `步数` | INT | 整数 | 10 | 1-10000 | 要生成的采样步骤总数 |
+| `降噪` | FLOAT | 浮点数 | 1.0 | 0.0-1.0 | 控制图像的去噪程度，1.0 使用所有步骤，较低值使用较少步骤 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | 返回为去噪过程计算的 sigma 值 |
diff --git a/zh-CN/built-in-nodes/AudioAdjustVolume.mdx b/zh-CN/built-in-nodes/AudioAdjustVolume.mdx
new file mode 100644
index 000000000..f1468a1e1
--- /dev/null
+++ b/zh-CN/built-in-nodes/AudioAdjustVolume.mdx
@@ -0,0 +1,23 @@
+---
+title: "AudioAdjustVolume - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioAdjustVolume node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioAdjustVolume"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioAdjustVolume/zh.md)
+
+AudioAdjustVolume 节点通过以分贝为单位进行音量调整来修改音频的响度。它接收音频输入，并根据指定的音量级别应用增益系数，其中正值增加音量，负值减小音量。该节点返回处理后的音频，其采样率与原始音频相同。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-------|-----------|------------|---------|-------|-------------|
+| `audio` | AUDIO | 必填 | - | - | 待处理的音频输入 |
+| `volume` | INT | 必填 | 1.0 | -100 到 100 | 以分贝为单位的音量调整。0 = 无变化，+6 = 加倍，-6 = 减半等 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 经过音量调整处理后的音频 |
diff --git a/zh-CN/built-in-nodes/AudioConcat.mdx b/zh-CN/built-in-nodes/AudioConcat.mdx
new file mode 100644
index 000000000..20ecfb831
--- /dev/null
+++ b/zh-CN/built-in-nodes/AudioConcat.mdx
@@ -0,0 +1,24 @@
+---
+title: "AudioConcat - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioConcat node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioConcat"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioConcat/zh.md)
+
+AudioConcat 节点通过将两个音频输入连接在一起来合并它们。它接收两个音频输入，并按照您指定的顺序连接它们，可以将第二个音频放置在第一个音频之前或之后。该节点通过将单声道音频转换为立体声并匹配两个输入之间的采样率，自动处理不同的音频格式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|------|-----------|------------|---------|-------|-------------|
+| `audio1` | AUDIO | 必填 | - | - | 要连接的第一个音频输入 |
+| `audio2` | AUDIO | 必填 | - | - | 要连接的第二个音频输入 |
+| `direction` | COMBO | 必填 | after | ['after', 'before'] | 将 audio2 附加在 audio1 之后还是之前 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `AUDIO` | AUDIO | 包含两个输入音频文件连接在一起的组合音频 |
diff --git a/zh-CN/built-in-nodes/AudioEncoderEncode.mdx b/zh-CN/built-in-nodes/AudioEncoderEncode.mdx
new file mode 100644
index 000000000..e60e60085
--- /dev/null
+++ b/zh-CN/built-in-nodes/AudioEncoderEncode.mdx
@@ -0,0 +1,23 @@
+---
+title: "AudioEncoderEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioEncoderEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioEncoderEncode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioEncoderEncode/zh.md)
+
+AudioEncoderEncode 节点通过使用音频编码器模型对音频数据进行编码处理。它接收音频输入并将其转换为编码表示，可在条件处理流程中用于进一步处理。该节点将原始音频波形转换为适合基于音频的机器学习应用的格式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-------|-----------|------------|---------|-------|-------------|
+| `audio_encoder` | AUDIO_ENCODER | 必填 | - | - | 用于处理音频输入的音频编码器模型 |
+| `audio` | AUDIO | 必填 | - | - | 包含波形和采样率信息的音频数据 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-----------|-----------|-------------|
+| `output` | AUDIO_ENCODER_OUTPUT | 由音频编码器生成的编码音频表示 |
diff --git a/zh-CN/built-in-nodes/AudioEncoderLoader.mdx b/zh-CN/built-in-nodes/AudioEncoderLoader.mdx
new file mode 100644
index 000000000..8aa09286e
--- /dev/null
+++ b/zh-CN/built-in-nodes/AudioEncoderLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "AudioEncoderLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioEncoderLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioEncoderLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献您的力量！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioEncoderLoader/zh.md)
+
+AudioEncoderLoader 节点从您可用的音频编码器文件中加载音频编码器模型。它接收音频编码器文件名作为输入，并返回一个已加载的音频编码器模型，该模型可在工作流中用于音频处理任务。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|--------|----------|----------|---------|----------|------|
+| `audio_encoder_name` | STRING | COMBO | - | 可用的音频编码器文件 | 选择要从 audio_encoders 文件夹加载的音频编码器模型文件 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|----------|------|
+| `audio_encoder` | AUDIO_ENCODER | 返回已加载的音频编码器模型，用于音频处理工作流 |
diff --git a/zh-CN/built-in-nodes/AudioEqualizer3Band.mdx b/zh-CN/built-in-nodes/AudioEqualizer3Band.mdx
new file mode 100644
index 000000000..6dc24d46c
--- /dev/null
+++ b/zh-CN/built-in-nodes/AudioEqualizer3Band.mdx
@@ -0,0 +1,31 @@
+---
+title: "AudioEqualizer3Band - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioEqualizer3Band node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioEqualizer3Band"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioEqualizer3Band/zh.md)
+
+音频均衡器（3段）节点允许您调整音频波形的低频、中频和高频。它应用三个独立的滤波器：用于低频的低架滤波器、用于中频的峰值滤波器以及用于高频的高架滤波器。每个频段都可以通过增益、频率和带宽设置进行独立控制。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | 是 | - | 包含波形和采样率的输入音频数据。 |
+| `low_gain_dB` | FLOAT | 否 | -24.0 到 24.0 | 低频（低音）增益。正值提升，负值削减。（默认值：0.0） |
+| `low_freq` | INT | 否 | 20 到 500 | 低架滤波器的截止频率，单位为赫兹（Hz）。（默认值：100） |
+| `mid_gain_dB` | FLOAT | 否 | -24.0 到 24.0 | 中频增益。正值提升，负值削减。（默认值：0.0） |
+| `mid_freq` | INT | 否 | 200 到 4000 | 中频峰值滤波器的中心频率，单位为赫兹（Hz）。（默认值：1000） |
+| `mid_q` | FLOAT | 否 | 0.1 到 10.0 | 中频峰值滤波器的 Q 因子（带宽）。值越低频带越宽，值越高频带越窄。（默认值：0.707） |
+| `high_gain_dB` | FLOAT | 否 | -24.0 到 24.0 | 高频（高音）增益。正值提升，负值削减。（默认值：0.0） |
+| `high_freq` | INT | 否 | 1000 到 15000 | 高架滤波器的截止频率，单位为赫兹（Hz）。（默认值：5000） |
+
+**注意：** 仅当 `low_gain_dB`、`mid_gain_dB` 和 `high_gain_dB` 参数的值不为零时，才会应用它们。如果增益设置为 0.0，则会跳过相应的滤波器阶段。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 应用了均衡处理后的音频数据，包含修改后的波形和原始采样率。 |
diff --git a/zh-CN/built-in-nodes/AudioMerge.mdx b/zh-CN/built-in-nodes/AudioMerge.mdx
new file mode 100644
index 000000000..2a9fdd203
--- /dev/null
+++ b/zh-CN/built-in-nodes/AudioMerge.mdx
@@ -0,0 +1,24 @@
+---
+title: "AudioMerge - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AudioMerge node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AudioMerge"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioMerge/zh.md)
+
+AudioMerge 节点通过叠加两个音频轨道的波形来合并它们。该节点会自动匹配两个音频输入的采样率，并在合并前调整它们的长度使其相等。该节点提供了多种数学方法来合并音频信号，并确保输出保持在可接受的音量水平内。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|------|-----------|------------|---------|-------|-------------|
+| `audio1` | AUDIO | 必选 | - | - | 要合并的第一个音频输入 |
+| `audio2` | AUDIO | 必选 | - | - | 要合并的第二个音频输入 |
+| `merge_method` | COMBO | 必选 | - | ["add", "mean", "subtract", "multiply"] | 用于合并音频波形的方法 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | 合并后的音频输出，包含组合后的波形和采样率 |
diff --git a/zh-CN/built-in-nodes/AutogrowNamesTestNode.mdx b/zh-CN/built-in-nodes/AutogrowNamesTestNode.mdx
new file mode 100644
index 000000000..1fef9d7ef
--- /dev/null
+++ b/zh-CN/built-in-nodes/AutogrowNamesTestNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "AutogrowNamesTestNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AutogrowNamesTestNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AutogrowNamesTestNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AutogrowNamesTestNode/zh.md)
+
+此节点用于测试 Autogrow 输入功能。它接收动态数量的浮点数输入，每个输入都带有特定名称标签，并将它们的值组合成一个逗号分隔的字符串。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `autogrow` | FLOAT | 是 | N/A | 一个动态输入组。您可以添加多个浮点数输入，每个输入使用预定义列表中的名称："a"、"b" 或 "c"。节点将接受这些命名输入的任意组合。 |
+
+**注意：** `autogrow` 输入是动态的。您可以根据工作流程需要添加或移除单个浮点数输入（命名为 "a"、"b" 或 "c"）。节点将处理所有提供的值。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 一个包含所有提供的浮点数输入值的字符串，这些值用逗号连接在一起。 |
diff --git a/zh-CN/built-in-nodes/AutogrowPrefixTestNode.mdx b/zh-CN/built-in-nodes/AutogrowPrefixTestNode.mdx
new file mode 100644
index 000000000..609b3772d
--- /dev/null
+++ b/zh-CN/built-in-nodes/AutogrowPrefixTestNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "AutogrowPrefixTestNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the AutogrowPrefixTestNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "AutogrowPrefixTestNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AutogrowPrefixTestNode/zh.md)
+
+AutogrowPrefixTestNode 是一个用于测试自动增长输入功能的逻辑节点。它接受动态数量的浮点数输入，将这些值组合成逗号分隔的字符串，并输出该字符串。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `autogrow` | AUTOGROW | 是 | 1 到 10 个输入 | 一个动态输入组，可以接受 1 到 10 个浮点数值。组中的每个输入都是 FLOAT 类型。 |
+
+**注意：** `autogrow` 输入是一个特殊的动态输入。您可以向此组添加多个浮点数输入，最多 10 个。节点将处理所有提供的值。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 一个包含所有输入浮点数值的字符串，数值之间用逗号分隔。 |
diff --git a/zh-CN/built-in-nodes/BasicGuider.mdx b/zh-CN/built-in-nodes/BasicGuider.mdx
new file mode 100644
index 000000000..efa1acead
--- /dev/null
+++ b/zh-CN/built-in-nodes/BasicGuider.mdx
@@ -0,0 +1,23 @@
+---
+title: "BasicGuider - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BasicGuider node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BasicGuider"
+icon: "circle"
+mode: wide
+---
+> 本文档由AI生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BasicGuider/zh.md)
+
+BasicGuider 节点为采样过程创建一个简单的引导机制。它接收模型和条件数据作为输入，并生成一个引导器对象，该对象可在采样过程中用于引导生成过程。此节点提供了受控生成所需的基础引导功能。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `模型` | MODEL | 必填 | - | - | 用于引导的模型 |
+| `条件` | CONDITIONING | 必填 | - | - | 引导生成过程的条件数据 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `GUIDER` | GUIDER | 可在采样过程中用于引导生成的引导器对象 |
diff --git a/zh-CN/built-in-nodes/BasicScheduler.mdx b/zh-CN/built-in-nodes/BasicScheduler.mdx
index e0520ab59..c4e506e7d 100644
--- a/zh-CN/built-in-nodes/BasicScheduler.mdx
+++ b/zh-CN/built-in-nodes/BasicScheduler.mdx
@@ -1,10 +1,10 @@
 ---
-title: "BasicScheduler - ComfyUI 原生节点文档"
-description: "`BasicScheduler` 节点旨在根据提供的调度器、模型和去噪参数为扩散模型计算一系列 sigma 值。它根据去噪因子动态调整总步骤数，以微调扩散过程，在一些需要精细控制的高级的采样过程"
+title: "BasicScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BasicScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
 sidebarTitle: "BasicScheduler"
 icon: "circle"
+mode: wide
 ---
-
 `BasicScheduler` 节点旨在根据提供的调度器、模型和去噪参数为扩散模型计算一系列 sigma 值。它根据去噪因子动态调整总步骤数，以微调扩散过程，在一些需要精细控制的高级的采样过程（比如分步采样）等等提供了精细的不同阶段的“配方”
 
 ## 输入
diff --git a/zh-CN/built-in-nodes/BatchImagesMasksLatentsNode.mdx b/zh-CN/built-in-nodes/BatchImagesMasksLatentsNode.mdx
new file mode 100644
index 000000000..ed3b6c78b
--- /dev/null
+++ b/zh-CN/built-in-nodes/BatchImagesMasksLatentsNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "BatchImagesMasksLatentsNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BatchImagesMasksLatentsNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BatchImagesMasksLatentsNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchImagesMasksLatentsNode/zh.md)
+
+Batch Images/Masks/Latents 节点将多个相同类型的输入组合成一个批次。它会自动检测输入是图像、遮罩还是潜在表示，并使用适当的批处理方法。这对于为接受批量输入的节点准备多个处理项非常有用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `inputs` | IMAGE、MASK 或 LATENT | 是 | 1 到 50 个输入 | 一个动态输入列表，将被组合成一个批次。您可以添加 1 到 50 个项目。所有项目必须是相同类型（全部是图像、全部是遮罩或全部是潜在表示）。 |
+
+**注意：** 该节点根据 `inputs` 列表中的第一个项目自动确定数据类型（IMAGE、MASK 或 LATENT）。所有后续项目必须与此类型匹配。如果您尝试混合不同的数据类型，节点将失败。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE、MASK 或 LATENT | 一个单一的批处理输出。数据类型与输入类型匹配（批处理的 IMAGE、批处理的 MASK 或批处理的 LATENT）。 |
diff --git a/zh-CN/built-in-nodes/BatchImagesNode.mdx b/zh-CN/built-in-nodes/BatchImagesNode.mdx
new file mode 100644
index 000000000..979983524
--- /dev/null
+++ b/zh-CN/built-in-nodes/BatchImagesNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "BatchImagesNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BatchImagesNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BatchImagesNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchImagesNode/zh.md)
+
+Batch Images 节点将多个独立图像合并为单个批次。它接收可变数量的图像输入，并将它们输出为一个批处理图像张量，以便在后续节点中统一处理。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | 2 到 50 个输入 | 一个动态的图像输入列表。您可以添加 2 到 50 张图像以合并为一个批次。节点界面允许您根据需要添加更多图像输入槽位。 |
+
+**注意：** 必须连接至少两张图像节点才能正常工作。第一个输入槽位始终是必需的，您可以使用节点界面中出现的 "+" 按钮添加更多输入槽位。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 一个包含所有输入图像堆叠在一起的批处理图像张量。 |
diff --git a/zh-CN/built-in-nodes/BatchLatentsNode.mdx b/zh-CN/built-in-nodes/BatchLatentsNode.mdx
new file mode 100644
index 000000000..06afde894
--- /dev/null
+++ b/zh-CN/built-in-nodes/BatchLatentsNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "BatchLatentsNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BatchLatentsNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BatchLatentsNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchLatentsNode/zh.md)
+
+此节点将多个潜在表示输入合并为一个批次。它接收可变数量的潜在样本，并沿批次维度将它们合并，使它们能够在后续节点中一起处理。这对于在单次操作中生成或处理多张图像非常有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `latents` | LATENT | 是 | N/A | 要包含在批次中的第一个潜在样本。 |
+| `latent_2` 至 `latent_50` | LATENT | 否 | N/A | 要包含在批次中的其他潜在样本。总共可以添加 2 到 50 个潜在输入。 |
+
+**注意：** 必须至少提供两个潜在输入，节点才能正常工作。当您连接更多潜在表示时，节点会自动创建输入槽，最多可达 50 个。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | LATENT | 一个单一的潜在输出，包含所有输入潜在表示合并后的批次。 |
diff --git a/zh-CN/built-in-nodes/BatchMasksNode.mdx b/zh-CN/built-in-nodes/BatchMasksNode.mdx
new file mode 100644
index 000000000..0c5a0829f
--- /dev/null
+++ b/zh-CN/built-in-nodes/BatchMasksNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "BatchMasksNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BatchMasksNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BatchMasksNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchMasksNode/zh.md)
+
+Batch Masks 节点将多个独立的遮罩输入合并为单个批次。它接收可变数量的遮罩输入，并将它们作为单个批处理的遮罩张量输出，以便在后续节点中对遮罩进行批处理。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `mask_0` | MASK | 是 | - | 第一个遮罩输入。 |
+| `mask_1` | MASK | 是 | - | 第二个遮罩输入。 |
+| `mask_2` 至 `mask_49` | MASK | 否 | - | 额外的可选遮罩输入。该节点总共最少可接受 2 个，最多可接受 50 个遮罩。 |
+
+**注意：** 此节点使用自动增长的输入模板。您必须至少连接两个遮罩（`mask_0` 和 `mask_1`）。您最多可以再添加 48 个可选遮罩输入（`mask_2` 至 `mask_49`），总共 50 个遮罩。所有已连接的遮罩将被合并为一个批次。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | MASK | 一个包含所有输入遮罩堆叠在一起的单个批处理遮罩。 |
diff --git a/zh-CN/built-in-nodes/BetaSamplingScheduler.mdx b/zh-CN/built-in-nodes/BetaSamplingScheduler.mdx
new file mode 100644
index 000000000..582d02c55
--- /dev/null
+++ b/zh-CN/built-in-nodes/BetaSamplingScheduler.mdx
@@ -0,0 +1,25 @@
+---
+title: "BetaSamplingScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BetaSamplingScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BetaSamplingScheduler"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献您的力量！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BetaSamplingScheduler/zh.md)
+
+BetaSamplingScheduler 节点使用 beta 调度算法为采样过程生成一系列噪声水平（sigmas）。它接收模型和配置参数，创建自定义的噪声调度，用于控制图像生成过程中的去噪流程。该调度器允许通过 alpha 和 beta 参数微调降噪轨迹。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-------|-----------|------------|---------|-------|-------------|
+| `模型` | MODEL | 必选 | - | - | 用于采样的模型，提供模型采样对象 |
+| `步数` | INT | 必选 | 20 | 1-10000 | 生成 sigmas 的采样步数 |
+| `阿尔法` | FLOAT | 必选 | 0.6 | 0.0-50.0 | Beta 调度器的 alpha 参数，控制调度曲线形状 |
+| `贝塔` | FLOAT | 必选 | 0.6 | 0.0-50.0 | Beta 调度器的 beta 参数，控制调度曲线形状 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `SIGMAS` | SIGMAS | 用于采样过程的噪声水平序列 |
diff --git a/zh-CN/built-in-nodes/BriaImageEditNode.mdx b/zh-CN/built-in-nodes/BriaImageEditNode.mdx
new file mode 100644
index 000000000..8d6e9d57d
--- /dev/null
+++ b/zh-CN/built-in-nodes/BriaImageEditNode.mdx
@@ -0,0 +1,38 @@
+---
+title: "BriaImageEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BriaImageEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BriaImageEditNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaImageEditNode/zh.md)
+
+Bria FIBO 图像编辑节点允许您通过文本指令修改现有图像。它会将图像和您的提示发送至 Bria API，该 API 使用 FIBO 模型根据您的要求生成新的编辑后图像版本。您也可以提供蒙版，以将编辑限制在特定区域。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"FIBO"` | 用于图像编辑的模型版本。 |
+| `image` | IMAGE | 是 | - | 您想要编辑的输入图像。 |
+| `prompt` | STRING | 否 | - | 描述如何编辑图像的文本指令（默认：空）。 |
+| `negative_prompt` | STRING | 否 | - | 描述您不希望出现在编辑后图像中的内容的文本（默认：空）。 |
+| `structured_prompt` | STRING | 否 | - | 一个包含 JSON 格式结构化编辑提示的字符串。使用此参数代替常规提示，以实现精确的程序化控制（默认：空）。 |
+| `seed` | INT | 是 | 1 至 2147483647 | 用于初始化随机生成的数字，确保结果可复现（默认：1）。 |
+| `guidance_scale` | FLOAT | 是 | 3.0 至 5.0 | 控制生成图像遵循提示的紧密程度。值越高，遵循度越强（默认：3.0）。 |
+| `steps` | INT | 是 | 20 至 50 | 模型将执行的去噪步骤数（默认：50）。 |
+| `moderation` | DYNAMICCOMBO | 是 | `"true"`<br />`"false"` | 启用或禁用内容审核。选择 `"true"` 会显示额外的审核选项。 |
+| `mask` | MASK | 否 | - | 可选的蒙版图像。如果提供，编辑将仅应用于图像的蒙版区域。 |
+
+**重要限制：**
+
+* 您必须至少提供 `prompt` 或 `structured_prompt` 输入之一。两者不能同时为空。
+* 恰好需要一个 `image` 输入。
+* 当 `moderation` 参数设置为 `"true"` 时，会额外出现三个布尔值输入：`prompt_content_moderation`、`visual_input_moderation` 和 `visual_output_moderation`。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | Bria API 返回的编辑后图像。 |
+| `structured_prompt` | STRING | 在编辑过程中使用或生成的结构化提示。 |
diff --git a/zh-CN/built-in-nodes/BriaRemoveImageBackground.mdx b/zh-CN/built-in-nodes/BriaRemoveImageBackground.mdx
new file mode 100644
index 000000000..3467ebb0a
--- /dev/null
+++ b/zh-CN/built-in-nodes/BriaRemoveImageBackground.mdx
@@ -0,0 +1,28 @@
+---
+title: "BriaRemoveImageBackground - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BriaRemoveImageBackground node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BriaRemoveImageBackground"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaRemoveImageBackground/zh.md)
+
+此节点使用 Bria RMBG 2.0 服务移除图像的背景。它会将图像发送到外部 API 进行处理，并返回移除背景后的结果。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 需要移除背景的输入图像。 |
+| `moderation` | COMBO | 否 | `"false"`<br />`"true"` | 内容审核设置。当设置为 `"true"` 时，会启用额外的审核选项。 |
+| `visual_input_moderation` | BOOLEAN | 否 | - | 对输入图像启用视觉内容审核。此参数仅在 `moderation` 设置为 `"true"` 时可用。默认值：`False`。 |
+| `visual_output_moderation` | BOOLEAN | 否 | - | 对输出图像启用视觉内容审核。此参数仅在 `moderation` 设置为 `"true"` 时可用。默认值：`True`。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 控制节点是否应重新运行的种子值。无论种子值如何，结果都是非确定性的。默认值：`0`。 |
+
+**注意：** `visual_input_moderation` 和 `visual_output_moderation` 参数依赖于 `moderation` 参数。它们仅在 `moderation` 设置为 `"true"` 时才被激活且为必需。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 经过处理、背景已被移除的图像。 |
diff --git a/zh-CN/built-in-nodes/BriaRemoveVideoBackground.mdx b/zh-CN/built-in-nodes/BriaRemoveVideoBackground.mdx
new file mode 100644
index 000000000..a853829bc
--- /dev/null
+++ b/zh-CN/built-in-nodes/BriaRemoveVideoBackground.mdx
@@ -0,0 +1,26 @@
+---
+title: "BriaRemoveVideoBackground - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the BriaRemoveVideoBackground node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "BriaRemoveVideoBackground"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaRemoveVideoBackground/zh.md)
+
+此节点使用 Bria AI 服务移除视频背景。它会处理输入视频，并将原始背景替换为您选择的纯色背景。该操作通过外部 API 执行，结果以新的视频文件形式返回。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | 是 | N/A | 将被移除背景的输入视频文件。 |
+| `background_color` | STRING | 是 | `"Black"`<br />`"White"`<br />`"Gray"`<br />`"Red"`<br />`"Green"`<br />`"Blue"`<br />`"Yellow"`<br />`"Cyan"`<br />`"Magenta"`<br />`"Orange"` | 用作输出视频新背景的纯色。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 控制节点是否应重新运行的种子值。无论种子值如何，结果都是非确定性的。（默认值：0） |
+
+**注意：** 输入视频的时长必须不超过 60 秒。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 经过处理的视频文件，背景已被移除并替换为所选颜色。 |
diff --git a/zh-CN/built-in-nodes/ByteDanceFirstLastFrameNode.mdx b/zh-CN/built-in-nodes/ByteDanceFirstLastFrameNode.mdx
new file mode 100644
index 000000000..17a13b76e
--- /dev/null
+++ b/zh-CN/built-in-nodes/ByteDanceFirstLastFrameNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "ByteDanceFirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceFirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceFirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceFirstLastFrameNode/zh.md)
+
+该节点通过文本提示词结合首尾帧图像生成视频。它根据您的描述和两个关键帧创建完整的视频序列，实现帧与帧之间的过渡。该节点提供多种选项来控制视频的分辨率、宽高比、时长及其他生成参数。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|--------|-----------|------------|---------|-------|-------------|
+| `model` | COMBO | 下拉选项 | seedance_1_lite | seedance_1_lite | 模型名称 |
+| `prompt` | STRING | 字符串 | - | - | 用于生成视频的文本提示词 |
+| `first_frame` | IMAGE | 图像 | - | - | 视频使用的首帧图像 |
+| `last_frame` | IMAGE | 图像 | - | - | 视频使用的尾帧图像 |
+| `resolution` | COMBO | 下拉选项 | - | 480p, 720p, 1080p | 输出视频的分辨率 |
+| `aspect_ratio` | COMBO | 下拉选项 | - | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | 输出视频的宽高比 |
+| `duration` | INT | 滑块 | 5 | 3-12 | 输出视频的时长（单位：秒） |
+| `seed` | INT | 数值 | 0 | 0-2147483647 | 生成时使用的随机种子（可选） |
+| `camera_fixed` | BOOLEAN | 布尔值 | False | - | 指定是否固定摄像机。平台会在提示词后附加固定摄像机的指令，但不保证实际效果（可选） |
+| `watermark` | BOOLEAN | 布尔值 | True | - | 是否为视频添加"AI生成"水印（可选） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/ByteDanceImageEditNode.mdx b/zh-CN/built-in-nodes/ByteDanceImageEditNode.mdx
new file mode 100644
index 000000000..8eaaae1ef
--- /dev/null
+++ b/zh-CN/built-in-nodes/ByteDanceImageEditNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "ByteDanceImageEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceImageEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceImageEditNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageEditNode/zh.md)
+
+字节跳动图像编辑节点允许您通过 API 使用字节跳动的 AI 模型来修改图像。您提供输入图像和描述所需更改的文本提示，节点会根据您的指令处理图像。该节点会自动处理 API 通信并返回编辑后的图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | COMBO | seededit_3 | Image2ImageModelName 选项 | 模型名称 |
+| `image` | IMAGE | IMAGE | - | - | 要编辑的基础图像 |
+| `prompt` | STRING | STRING | "" | - | 编辑图像的指令 |
+| `seed` | INT | INT | 0 | 0-2147483647 | 生成使用的随机种子 |
+| `guidance_scale` | FLOAT | FLOAT | 5.5 | 1.0-10.0 | 数值越高，图像越紧密遵循提示 |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | 是否在图像上添加"AI 生成"水印 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 从字节跳动 API 返回的编辑后图像 |
diff --git a/zh-CN/built-in-nodes/ByteDanceImageNode.mdx b/zh-CN/built-in-nodes/ByteDanceImageNode.mdx
new file mode 100644
index 000000000..ffaa8e689
--- /dev/null
+++ b/zh-CN/built-in-nodes/ByteDanceImageNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "ByteDanceImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageNode/zh.md)
+
+## 概述
+
+ByteDance Image 节点通过基于文本提示的 API 使用字节跳动模型生成图像。它允许您选择不同的模型，指定图像尺寸，并控制各种生成参数，如种子值和引导尺度。该节点连接到字节跳动的图像生成服务并返回创建的图像。
+
+## 输入
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | COMBO | seedream_3 | Text2ImageModelName 选项 | 模型名称 |
+| `prompt` | STRING | STRING | - | - | 用于生成图像的文本提示 |
+| `size_preset` | STRING | COMBO | - | RECOMMENDED_PRESETS 标签 | 选择推荐尺寸。选择 Custom 以使用下方的宽度和高度 |
+| `width` | INT | INT | 1024 | 512-2048（步长 64） | 图像的自定义宽度。仅当 `size_preset` 设置为 `Custom` 时生效 |
+| `height` | INT | INT | 1024 | 512-2048（步长 64） | 图像的自定义高度。仅当 `size_preset` 设置为 `Custom` 时生效 |
+| `seed` | INT | INT | 0 | 0-2147483647（步长 1） | 用于生成的种子值（可选） |
+| `guidance_scale` | FLOAT | FLOAT | 2.5 | 1.0-10.0（步长 0.01） | 值越高，图像越紧密遵循提示（可选） |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | 是否在图像上添加"AI 生成"水印（可选） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 从字节跳动 API 生成的图像 |
diff --git a/zh-CN/built-in-nodes/ByteDanceImageReferenceNode.mdx b/zh-CN/built-in-nodes/ByteDanceImageReferenceNode.mdx
new file mode 100644
index 000000000..51910d700
--- /dev/null
+++ b/zh-CN/built-in-nodes/ByteDanceImageReferenceNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "ByteDanceImageReferenceNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceImageReferenceNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceImageReferenceNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageReferenceNode/zh.md)
+
+字节跳动图像参考节点使用文本提示和一到四张参考图像来生成视频。它将图像和提示发送到外部 API 服务，该服务会根据您的描述创建视频，同时融入参考图像的视觉风格和内容。该节点提供了视频分辨率、宽高比、时长和其他生成参数的各种控制选项。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | COMBO | seedance_1_lite | seedance_1_lite | 模型名称 |
+| `prompt` | STRING | STRING | - | - | 用于生成视频的文本提示。 |
+| `images` | IMAGE | IMAGE | - | - | 一到四张图像。 |
+| `resolution` | STRING | COMBO | - | 480p, 720p | 输出视频的分辨率。 |
+| `aspect_ratio` | STRING | COMBO | - | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | 输出视频的宽高比。 |
+| `duration` | INT | INT | 5 | 3-12 | 输出视频的时长（单位：秒）。 |
+| `seed` | INT | INT | 0 | 0-2147483647 | 用于生成的随机种子。 |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | 是否在视频上添加"AI生成"水印。 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 基于输入提示和参考图像生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/ByteDanceImageToVideoNode.mdx b/zh-CN/built-in-nodes/ByteDanceImageToVideoNode.mdx
new file mode 100644
index 000000000..841a79ab4
--- /dev/null
+++ b/zh-CN/built-in-nodes/ByteDanceImageToVideoNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "ByteDanceImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageToVideoNode/zh.md)
+
+## 概述
+
+ByteDance Image to Video 节点通过 API 使用字节跳动模型，基于输入图像和文本提示生成视频。该节点接收起始图像帧，并根据提供的描述创建视频序列。节点提供多种自定义选项，包括视频分辨率、宽高比、时长和其他生成参数。
+
+## 输入
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|------|-----------|------------|---------|-------|-------------|
+| `model` | STRING | COMBO | seedance_1_pro | Image2VideoModelName 选项 | 模型名称 |
+| `prompt` | STRING | STRING | - | - | 用于生成视频的文本提示。 |
+| `image` | IMAGE | IMAGE | - | - | 用作视频起始帧的图像。 |
+| `resolution` | STRING | COMBO | - | ["480p", "720p", "1080p"] | 输出视频的分辨率。 |
+| `aspect_ratio` | STRING | COMBO | - | ["adaptive", "16:9", "4:3", "1:1", "3:4", "9:16", "21:9"] | 输出视频的宽高比。 |
+| `duration` | INT | INT | 5 | 3-12 | 输出视频的时长（单位：秒）。 |
+| `seed` | INT | INT | 0 | 0-2147483647 | 生成视频时使用的随机种子。 |
+| `camera_fixed` | BOOLEAN | BOOLEAN | False | - | 是否固定摄像机。平台会在您的提示词后附加固定摄像机的指令，但不保证实际效果。 |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | 是否在视频中添加“AI生成”水印。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `output` | VIDEO | 基于输入图像和提示参数生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/ByteDanceSeedreamNode.mdx b/zh-CN/built-in-nodes/ByteDanceSeedreamNode.mdx
new file mode 100644
index 000000000..3aa9b9afd
--- /dev/null
+++ b/zh-CN/built-in-nodes/ByteDanceSeedreamNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "ByteDanceSeedreamNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceSeedreamNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceSeedreamNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedreamNode/zh.md)
+
+字节跳动 Seedream 4 节点提供统一的文生图功能和高达 4K 分辨率的精准单句编辑能力。它可以根据文本提示创建新图像，或使用文本指令编辑现有图像。该节点支持单张图像生成和连续生成多张相关图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | COMBO | "seedream-4-0-250828" | ["seedream-4-0-250828"] | 模型名称 |
+| `prompt` | STRING | STRING | "" | - | 用于创建或编辑图像的文本提示 |
+| `image` | IMAGE | IMAGE | - | - | 用于图生图的输入图像。单参考或多参考生成时，可输入1-10张图像列表 |
+| `size_preset` | STRING | COMBO | RECOMMENDED_PRESETS_SEEDREAM_4 的第一个预设 | RECOMMENDED_PRESETS_SEEDREAM_4 的所有标签 | 选择推荐尺寸。选择"自定义"可使用下方的宽度和高度 |
+| `width` | INT | INT | 2048 | 1024-4096 (步长64) | 图像的自定义宽度。仅当 `size_preset` 设置为 `Custom` 时生效 |
+| `height` | INT | INT | 2048 | 1024-4096 (步长64) | 图像的自定义高度。仅当 `size_preset` 设置为 `Custom` 时生效 |
+| `sequential_image_generation` | STRING | COMBO | "disabled" | ["disabled", "auto"] | 分组图像生成模式。"disabled"生成单张图像。"auto"让模型决定是否生成多张相关图像（如故事场景、角色变体） |
+| `max_images` | INT | INT | 1 | 1-15 | 当 sequential_image_generation='auto' 时生成的最大图像数量。总图像数（输入+生成）不能超过15张 |
+| `seed` | INT | INT | 0 | 0-2147483647 | 用于生成的随机种子 |
+| `watermark` | BOOLEAN | BOOLEAN | True | - | 是否在图像上添加"AI生成"水印 |
+| `fail_on_partial` | BOOLEAN | BOOLEAN | True | - | 如果启用，当任何请求的图像缺失或返回错误时将中止执行 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 基于输入参数和提示生成的图像 |
diff --git a/zh-CN/built-in-nodes/ByteDanceTextToVideoNode.mdx b/zh-CN/built-in-nodes/ByteDanceTextToVideoNode.mdx
new file mode 100644
index 000000000..26e9d0c7f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ByteDanceTextToVideoNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "ByteDanceTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ByteDanceTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ByteDanceTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceTextToVideoNode/zh.md)
+
+字节跳动文生视频节点通过基于文本提示的 API 使用字节跳动模型生成视频。它接收文本描述和各种视频设置作为输入，然后创建符合所提供规格的视频。该节点负责处理 API 通信，并将生成的视频作为输出返回。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | STRING | 下拉选项 | seedance_1_pro | Text2VideoModelName 选项 | 模型名称 |
+| `prompt` | STRING | 字符串 | - | - | 用于生成视频的文本提示。 |
+| `resolution` | STRING | 下拉选项 | - | ["480p", "720p", "1080p"] | 输出视频的分辨率。 |
+| `aspect_ratio` | STRING | 下拉选项 | - | ["16:9", "4:3", "1:1", "3:4", "9:16", "21:9"] | 输出视频的宽高比。 |
+| `duration` | INT | 整数 | 5 | 3-12 | 输出视频的时长（单位：秒）。 |
+| `seed` | INT | 整数 | 0 | 0-2147483647 | 用于生成的随机种子。（可选） |
+| `camera_fixed` | BOOLEAN | 布尔值 | False | - | 指定是否固定摄像机。平台会在您的提示词后附加固定摄像机的指令，但不保证实际效果。（可选） |
+| `watermark` | BOOLEAN | 布尔值 | True | - | 是否在视频上添加"AI生成"水印。（可选） |
+
+**参数约束：**
+
+- `prompt` 参数在去除空白字符后必须至少包含 1 个字符
+- `prompt` 参数不能包含以下文本参数："resolution"、"ratio"、"duration"、"seed"、"camerafixed"、"watermark"
+- `duration` 参数限制在 3 到 12 秒之间的值
+- `seed` 参数接受 0 到 2,147,483,647 之间的值
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/CFGGuider.mdx b/zh-CN/built-in-nodes/CFGGuider.mdx
new file mode 100644
index 000000000..cc7a7bc5a
--- /dev/null
+++ b/zh-CN/built-in-nodes/CFGGuider.mdx
@@ -0,0 +1,25 @@
+---
+title: "CFGGuider - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CFGGuider node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CFGGuider"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGGuider/zh.md)
+
+CFGGuider 节点创建了一个用于控制图像生成采样过程的引导系统。它接收一个模型以及正向和负向条件输入，然后应用无分类器引导尺度来引导生成过程朝向期望内容，同时避免不需要的元素。该节点输出一个引导器对象，可供采样节点使用以控制图像生成方向。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `模型` | MODEL | 必填 | - | - | 用于引导的模型 |
+| `正面条件` | CONDITIONING | 必填 | - | - | 正向条件，引导生成过程朝向期望内容 |
+| `负面条件` | CONDITIONING | 必填 | - | - | 负向条件，使生成过程远离不需要的内容 |
+| `CFG` | FLOAT | 必填 | 8.0 | 0.0 - 100.0 | 无分类器引导尺度，控制条件对生成过程的影响强度 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `GUIDER` | GUIDER | 引导器对象，可传递给采样节点以控制生成过程 |
diff --git a/zh-CN/built-in-nodes/CFGNorm.mdx b/zh-CN/built-in-nodes/CFGNorm.mdx
new file mode 100644
index 000000000..174aa7877
--- /dev/null
+++ b/zh-CN/built-in-nodes/CFGNorm.mdx
@@ -0,0 +1,23 @@
+---
+title: "CFGNorm - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CFGNorm node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CFGNorm"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGNorm/zh.md)
+
+CFGNorm 节点对扩散模型中的无分类器引导（CFG）过程应用归一化技术。它通过比较条件输出和无条件输出的范数来调整去噪预测的尺度，然后应用强度乘数来控制效果。这有助于通过防止引导缩放中的极端值来稳定生成过程。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | 必填 | - | - | 要应用 CFG 归一化的扩散模型 |
+| `strength` | FLOAT | 必填 | 1.0 | 0.0 - 100.0 | 控制应用于 CFG 缩放的归一化效果的强度 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | 返回经过修改的模型，其采样过程已应用 CFG 归一化 |
diff --git a/zh-CN/built-in-nodes/CFGZeroStar.mdx b/zh-CN/built-in-nodes/CFGZeroStar.mdx
new file mode 100644
index 000000000..5067809f4
--- /dev/null
+++ b/zh-CN/built-in-nodes/CFGZeroStar.mdx
@@ -0,0 +1,22 @@
+---
+title: "CFGZeroStar - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CFGZeroStar node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CFGZeroStar"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGZeroStar/zh.md)
+
+CFGZeroStar 节点对扩散模型应用了一种专门的引导缩放技术。它通过基于条件预测和无条件预测之间的差异计算优化比例因子，从而修改无分类器引导过程。这种方法调整最终输出，在保持模型稳定性的同时，为生成过程提供增强的控制能力。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | 必选 | - | - | 需要使用 CFGZeroStar 引导缩放技术进行修改的扩散模型 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | 应用了 CFGZeroStar 引导缩放技术后的修改模型 |
diff --git a/zh-CN/built-in-nodes/CLIPAdd.mdx b/zh-CN/built-in-nodes/CLIPAdd.mdx
new file mode 100644
index 000000000..3d9f5d6b3
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPAdd.mdx
@@ -0,0 +1,25 @@
+---
+title: "CLIPAdd - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPAdd node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPAdd"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPAdd/zh.md)
+
+## 概述
+
+CLIPAdd 节点通过合并两个 CLIP 模型的关键补丁来组合它们。它会创建第一个 CLIP 模型的副本，然后添加第二个模型中的大部分关键补丁（不包括位置 ID 和对数尺度参数）。这使您能够融合不同 CLIP 模型的特征，同时保留第一个模型的结构。
+
+## 输入
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip1` | CLIP | 必选 | - | - | 作为合并基础的主 CLIP 模型 |
+| `clip2` | CLIP | 必选 | - | - | 提供待添加补丁的次要 CLIP 模型 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | 返回合并后的 CLIP 模型，包含两个输入模型的特征 |
diff --git a/zh-CN/built-in-nodes/CLIPAttentionMultiply.mdx b/zh-CN/built-in-nodes/CLIPAttentionMultiply.mdx
new file mode 100644
index 000000000..37d4e7cc4
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPAttentionMultiply.mdx
@@ -0,0 +1,28 @@
+---
+title: "CLIPAttentionMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPAttentionMultiply"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPAttentionMultiply/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPAttentionMultiply/en.md)
+
+CLIPAttentionMultiply 节点允许您通过为自注意力层的不同组件应用乘法因子来调整 CLIP 模型中的注意力机制。它通过修改 CLIP 模型注意力机制中的查询、键、值和输出投影权重及偏置来实现。这个实验性节点会创建一个应用了指定缩放因子的输入 CLIP 模型的修改副本。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip` | CLIP | 必选 | - | - | 要修改的 CLIP 模型 |
+| `q` | FLOAT | 必选 | 1.0 | 0.0 - 10.0 | 查询投影权重和偏置的乘法因子 |
+| `k` | FLOAT | 必选 | 1.0 | 0.0 - 10.0 | 键投影权重和偏置的乘法因子 |
+| `v` | FLOAT | 必选 | 1.0 | 0.0 - 10.0 | 值投影权重和偏置的乘法因子 |
+| `输出` | FLOAT | 必选 | 1.0 | 0.0 - 10.0 | 输出投影权重和偏置的乘法因子 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | 返回应用了指定注意力缩放因子的修改后 CLIP 模型 |
diff --git a/zh-CN/built-in-nodes/CLIPMergeAdd.mdx b/zh-CN/built-in-nodes/CLIPMergeAdd.mdx
new file mode 100644
index 000000000..e0359a5f6
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPMergeAdd.mdx
@@ -0,0 +1,23 @@
+---
+title: "CLIPMergeAdd - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPMergeAdd node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPMergeAdd"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPMergeAdd/zh.md)
+
+CLIPMergeAdd 节点通过将第二个 CLIP 模型中的补丁添加到第一个模型来合并两个 CLIP 模型。它会创建第一个 CLIP 模型的副本，并选择性地整合第二个模型中的关键补丁，同时排除位置 ID 和对数尺度参数。这使您能够在保留基础模型结构的同时合并 CLIP 模型组件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip1` | CLIP | 是 | - | 基础 CLIP 模型，将被克隆并作为合并的基础 |
+| `clip2` | CLIP | 是 | - | 次要 CLIP 模型，提供要添加到基础模型的关键补丁 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | 合并后的 CLIP 模型，包含基础模型结构并添加了次要模型的补丁 |
diff --git a/zh-CN/built-in-nodes/CLIPMergeSubtract.mdx b/zh-CN/built-in-nodes/CLIPMergeSubtract.mdx
new file mode 100644
index 000000000..d7954f146
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPMergeSubtract.mdx
@@ -0,0 +1,28 @@
+---
+title: "CLIPMergeSubtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPMergeSubtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPMergeSubtract"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPMergeSubtract/zh.md)
+
+> 本文档由 AI 生成，如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPMergeSubtract/en.md)
+
+CLIPMergeSubtract 节点通过从一个 CLIP 模型中减去另一个 CLIP 模型的权重来执行模型合并。它通过克隆第一个模型，然后减去第二个模型的关键补丁（附带可调节的乘数来控制减法强度）来创建新的 CLIP 模型。这允许通过从基础模型中移除特定特征来实现精细调整的模型混合。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip1` | CLIP | 是 | - | 将被克隆和修改的基础 CLIP 模型 |
+| `clip2` | CLIP | 是 | - | 其关键补丁将从基础模型中减去的 CLIP 模型 |
+| `乘数` | FLOAT | 是 | -10.0 到 10.0 | 控制减法操作强度的乘数（默认值：1.0） |
+
+**注意：** 无论乘数值如何，该节点都会从减法操作中排除 `.position_ids` 和 `.logit_scale` 参数。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `clip` | CLIP | 从第一个模型减去第二个模型权重后得到的 CLIP 模型 |
diff --git a/zh-CN/built-in-nodes/CLIPSubtract.mdx b/zh-CN/built-in-nodes/CLIPSubtract.mdx
new file mode 100644
index 000000000..6919de7f2
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPSubtract.mdx
@@ -0,0 +1,24 @@
+---
+title: "CLIPSubtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPSubtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPSubtract"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPSubtract/zh.md)
+
+CLIPSubtract 节点在两个 CLIP 模型之间执行减法操作。它以第一个 CLIP 模型为基础，从第二个 CLIP 模型中减去关键补丁，并通过可选乘数控制减法强度。这允许通过从一个模型中移除另一个模型的特定特征来实现精细调整的模型混合。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip1` | CLIP | 必需 | - | - | 将被修改的基础 CLIP 模型 |
+| `clip2` | CLIP | 必需 | - | - | 其关键补丁将从基础模型中减去的 CLIP 模型 |
+| `multiplier` | FLOAT | 必需 | 1.0 | -10.0 到 10.0，步长 0.01 | 控制减法操作的强度 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | 减法操作后得到的 CLIP 模型 |
diff --git a/zh-CN/built-in-nodes/CLIPTextEncodeControlnet.mdx b/zh-CN/built-in-nodes/CLIPTextEncodeControlnet.mdx
new file mode 100644
index 000000000..6fd3e7806
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPTextEncodeControlnet.mdx
@@ -0,0 +1,26 @@
+---
+title: "CLIPTextEncodeControlnet - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeControlnet node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeControlnet"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeControlnet/zh.md)
+
+CLIPTextEncodeControlnet 节点使用 CLIP 模型处理文本输入，并将其与现有的条件数据相结合，为 controlnet 应用创建增强的条件输出。该节点将输入文本进行标记化处理，通过 CLIP 模型进行编码，并将生成的嵌入作为交叉注意力 controlnet 参数添加到提供的条件数据中。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 数值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip` | CLIP | 必需 | - | - | 用于文本标记化和编码的 CLIP 模型 |
+| `条件` | CONDITIONING | 必需 | - | - | 需要通过 controlnet 参数增强的现有条件数据 |
+| `文本` | STRING | 多行文本，动态提示 | - | - | 由 CLIP 模型处理的文本输入 |
+
+**注意：** 此节点需要同时提供 `clip` 和 `conditioning` 输入才能正常工作。`text` 输入支持动态提示和多行文本，以实现灵活的文本处理。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 添加了 controlnet 交叉注意力参数的增强条件数据 |
diff --git a/zh-CN/built-in-nodes/CLIPTextEncodeHiDream.mdx b/zh-CN/built-in-nodes/CLIPTextEncodeHiDream.mdx
new file mode 100644
index 000000000..c72b901ef
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPTextEncodeHiDream.mdx
@@ -0,0 +1,28 @@
+---
+title: "CLIPTextEncodeHiDream - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeHiDream node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeHiDream"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeHiDream/zh.md)
+
+CLIPTextEncodeHiDream 节点使用不同的语言模型处理多个文本输入，并将它们组合成单一的条件输出。该节点对来自四个不同来源（CLIP-L、CLIP-G、T5-XXL 和 LLaMA）的文本进行标记化，并使用调度编码方法对它们进行编码。通过同时利用多个语言模型，这允许进行更复杂的文本条件控制。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 数值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip` | CLIP | 必需输入 | - | - | 用于标记化和编码的 CLIP 模型 |
+| `clip_l` | STRING | 多行文本 | - | - | 用于 CLIP-L 模型处理的文本输入 |
+| `clip_g` | STRING | 多行文本 | - | - | 用于 CLIP-G 模型处理的文本输入 |
+| `t5xxl` | STRING | 多行文本 | - | - | 用于 T5-XXL 模型处理的文本输入 |
+| `llama` | STRING | 多行文本 | - | - | 用于 LLaMA 模型处理的文本输入 |
+
+**注意：** 所有文本输入都支持动态提示和多行文本输入。该节点需要提供所有四个文本参数才能正常运行，因为每个参数都通过调度编码过程为最终的条件输出做出贡献。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 来自所有已处理文本输入的组合条件输出 |
diff --git a/zh-CN/built-in-nodes/CLIPTextEncodeKandinsky5.mdx b/zh-CN/built-in-nodes/CLIPTextEncodeKandinsky5.mdx
new file mode 100644
index 000000000..c4f18d982
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPTextEncodeKandinsky5.mdx
@@ -0,0 +1,24 @@
+---
+title: "CLIPTextEncodeKandinsky5 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeKandinsky5 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeKandinsky5"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeKandinsky5/zh.md)
+
+该节点为 Kandinsky 5 模型准备文本提示。它接收两个独立的文本输入，使用提供的 CLIP 模型对其进行分词处理，并将它们组合成单个条件输出。此输出用于指导图像生成过程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | | 用于对文本提示进行分词和编码的 CLIP 模型。 |
+| `clip_l` | STRING | 是 | | 主文本提示。此输入支持多行文本和动态提示。 |
+| `qwen25_7b` | STRING | 是 | | 辅助文本提示。此输入支持多行文本和动态提示。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 由两个文本提示生成的组合条件数据，准备输入到 Kandinsky 5 模型以进行图像生成。 |
diff --git a/zh-CN/built-in-nodes/CLIPTextEncodeLumina2.mdx b/zh-CN/built-in-nodes/CLIPTextEncodeLumina2.mdx
new file mode 100644
index 000000000..491bb54d5
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPTextEncodeLumina2.mdx
@@ -0,0 +1,28 @@
+---
+title: "CLIPTextEncodeLumina2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeLumina2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeLumina2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeLumina2/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeLumina2/en.md)
+
+CLIP Text Encode for Lumina2 节点使用 CLIP 模型将系统提示和用户提示编码为嵌入向量，该向量可以指导扩散模型生成特定图像。它将预定义的系统提示与您的自定义文本提示相结合，并通过 CLIP 模型进行处理，以创建用于图像生成的条件数据。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `system_prompt` | STRING | COMBO | - | "superior", "alignment" | Lumina2 提供两种类型的系统提示：Superior：您是一个旨在根据文本提示或用户提示生成具有卓越图文对齐度的优质图像的助手。Alignment：您是一个旨在根据文本提示生成具有最高图文对齐度的高质量图像的助手。 |
+| `user_prompt` | STRING | STRING | - | - | 需要编码的文本。 |
+| `clip` | CLIP | CLIP | - | - | 用于文本编码的 CLIP 模型。 |
+
+**注意：** `clip` 输入是必需的，不能为 None。如果 clip 输入无效，节点将引发错误，提示检查点可能不包含有效的 CLIP 或文本编码器模型。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 包含嵌入文本的条件数据，用于指导扩散模型。 |
diff --git a/zh-CN/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx b/zh-CN/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx
new file mode 100644
index 000000000..59fb68745
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx
@@ -0,0 +1,27 @@
+---
+title: "CLIPTextEncodePixArtAlpha - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodePixArtAlpha node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodePixArtAlpha"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodePixArtAlpha/zh.md)
+
+## 概述
+
+对文本进行编码并为 PixArt Alpha 设置分辨率条件。此节点处理文本输入并添加宽度和高度信息，以创建专门用于 PixArt Alpha 模型的条件数据。它不适用于 PixArt Sigma 模型。
+
+## 输入
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `宽度` | INT | 输入 | 1024 | 0 到 MAX_RESOLUTION | 用于分辨率条件的宽度维度 |
+| `高度` | INT | 输入 | 1024 | 0 到 MAX_RESOLUTION | 用于分辨率条件的高度维度 |
+| `文本` | STRING | 输入 | - | - | 要编码的文本输入，支持多行输入和动态提示 |
+| `剪辑` | CLIP | 输入 | - | - | 用于标记化和编码的 CLIP 模型 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 包含文本标记和分辨率信息的编码条件数据 |
diff --git a/zh-CN/built-in-nodes/CLIPTextEncodeSD3.mdx b/zh-CN/built-in-nodes/CLIPTextEncodeSD3.mdx
new file mode 100644
index 000000000..e699e7172
--- /dev/null
+++ b/zh-CN/built-in-nodes/CLIPTextEncodeSD3.mdx
@@ -0,0 +1,32 @@
+---
+title: "CLIPTextEncodeSD3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeSD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeSD3"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodeSD3/zh.md)
+
+CLIPTextEncodeSD3 节点通过使用不同的 CLIP 模型对多个文本提示进行编码，为 Stable Diffusion 3 模型处理文本输入。它处理三个独立的文本输入（clip_g、clip_l 和 t5xxl），并提供管理空文本填充的选项。该节点确保不同文本输入之间的正确令牌对齐，并返回适用于 SD3 生成流程的条件数据。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 参数说明 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `clip` | CLIP | 必需 | - | - | 用于文本编码的 CLIP 模型 |
+| `clip_l` | STRING | 多行文本，动态提示 | - | - | 本地 CLIP 模型的文本输入 |
+| `clip_g` | STRING | 多行文本，动态提示 | - | - | 全局 CLIP 模型的文本输入 |
+| `t5xxl` | STRING | 多行文本，动态提示 | - | - | T5-XXL 模型的文本输入 |
+| `空白填充` | COMBO | 选择 | - | ["none", "empty_prompt"] | 控制如何处理空文本输入 |
+
+**参数约束：**
+
+- 当 `empty_padding` 设置为 "none" 时，`clip_g`、`clip_l` 或 `t5xxl` 的空文本输入将产生空令牌列表而不是填充
+- 当长度不同时，节点通过用空令牌填充较短的那个，自动平衡 `clip_l` 和 `clip_g` 输入之间的令牌长度
+- 所有文本输入都支持动态提示和多行文本输入
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 输出说明 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 已编码的文本条件数据，准备用于 SD3 生成流程 |
diff --git a/zh-CN/built-in-nodes/Canny.mdx b/zh-CN/built-in-nodes/Canny.mdx
index 4c473932d..29251931a 100644
--- a/zh-CN/built-in-nodes/Canny.mdx
+++ b/zh-CN/built-in-nodes/Canny.mdx
@@ -1,10 +1,10 @@
 ---
-title: "Canny - ComfyUI 原生节点文档"
-description: "Canny 节点是 ComfyUI 中用于提取图像边缘的节点。"
+title: "Canny - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Canny node in ComfyUI. Learn its inputs, outputs, parameters and usage."
 sidebarTitle: "Canny"
 icon: "circle"
+mode: wide
 ---
-
 从照片中提取所有边缘线条，就像用钢笔为照片描边一样，把物体的轮廓和细节边界都画出来。
 
 ## 工作原理
@@ -35,9 +35,9 @@ icon: "circle"
 
 ## 参数对比
 
-![原图](/images/built-in-nodes/canny/input.webp)
+![原图](/images/built-in-nodes/Canny/input.webp)
 
-![参数对比](/images/built-in-nodes/canny/compare.webp)
+![参数对比](/images/built-in-nodes/Canny/compare.webp)
 
 **常见问题：**
 
diff --git a/zh-CN/built-in-nodes/CaseConverter.mdx b/zh-CN/built-in-nodes/CaseConverter.mdx
new file mode 100644
index 000000000..45333bfdf
--- /dev/null
+++ b/zh-CN/built-in-nodes/CaseConverter.mdx
@@ -0,0 +1,25 @@
+---
+title: "CaseConverter - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CaseConverter node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CaseConverter"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CaseConverter/zh.md)
+
+## 概述
+
+Case Converter 节点可将文本字符串转换为不同的字母大小写格式。它接收输入字符串并根据所选模式进行转换，生成应用了指定大小写格式的输出字符串。该节点支持四种不同的大小写转换选项，用于修改文本的大小写格式。
+
+## 输入
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `string` | STRING | 字符串 | - | - | 需要转换为不同大小写格式的文本字符串 |
+| `mode` | STRING | 下拉选项 | - | ["UPPERCASE", "lowercase", "Capitalize", "Title Case"] | 要应用的大小写转换模式：UPPERCASE 将所有字母转换为大写，lowercase 将所有字母转换为小写，Capitalize 仅首字母大写，Title Case 将每个单词的首字母大写 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 已转换为指定大小写格式的输入字符串 |
diff --git a/zh-CN/built-in-nodes/CenterCropImages.mdx b/zh-CN/built-in-nodes/CenterCropImages.mdx
new file mode 100644
index 000000000..0dee5953e
--- /dev/null
+++ b/zh-CN/built-in-nodes/CenterCropImages.mdx
@@ -0,0 +1,24 @@
+---
+title: "CenterCropImages - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CenterCropImages node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CenterCropImages"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CenterCropImages/zh.md)
+
+Center Crop Images 节点将图像从中心裁剪至指定的宽度和高度。它会计算输入图像的中心区域，并提取出指定尺寸的矩形区域。如果请求的裁剪尺寸大于图像本身，裁剪区域将被限制在图像的边界内。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待裁剪的输入图像。 |
+| `width` | INT | 否 | 1 至 8192 | 裁剪区域的宽度（默认值：512）。 |
+| `height` | INT | 否 | 1 至 8192 | 裁剪区域的高度（默认值：512）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 经过中心裁剪操作后得到的图像。 |
diff --git a/zh-CN/built-in-nodes/CheckpointLoader.mdx b/zh-CN/built-in-nodes/CheckpointLoader.mdx
new file mode 100644
index 000000000..09740b230
--- /dev/null
+++ b/zh-CN/built-in-nodes/CheckpointLoader.mdx
@@ -0,0 +1,31 @@
+---
+title: "CheckpointLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CheckpointLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CheckpointLoader/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CheckpointLoader/en.md)
+
+CheckpointLoader 节点加载预训练的模型检查点及其配置文件。它接收配置文件和检查点文件作为输入，并返回已加载的模型组件，包括主模型、CLIP 模型和 VAE 模型，以供工作流使用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-------|-----------|------------|---------|-------|-------------|
+| `配置名称` | STRING | 下拉选择 | - | 可用的配置文件 | 定义模型架构和设置的配置文件 |
+| `Checkpoint名称` | STRING | 下拉选择 | - | 可用的检查点文件 | 包含训练好的模型权重和参数的检查点文件 |
+
+**注意：** 此节点需要同时选择配置文件和检查点文件。配置文件必须与要加载的检查点文件的架构匹配。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | 已加载的主模型组件，准备进行推理 |
+| `CLIP` | CLIP | 已加载的 CLIP 模型组件，用于文本编码 |
+| `VAE` | VAE | 已加载的 VAE 模型组件，用于图像编码和解码 |
+
+**重要提示：** 此节点已被标记为弃用，可能在未来的版本中被移除。对于新的工作流，请考虑使用替代的加载节点。
diff --git a/zh-CN/built-in-nodes/CheckpointLoaderSimple.mdx b/zh-CN/built-in-nodes/CheckpointLoaderSimple.mdx
index 69a366487..59dce1ec5 100644
--- a/zh-CN/built-in-nodes/CheckpointLoaderSimple.mdx
+++ b/zh-CN/built-in-nodes/CheckpointLoaderSimple.mdx
@@ -1,10 +1,10 @@
 ---
-title: "CheckpointLoaderSimple - ComfyUI 原生节点文档"
-description: "CheckpointLoaderSimple 节点是 ComfyUI 中用于加载模型的节点。"
+title: "CheckpointLoaderSimple - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CheckpointLoaderSimple node in ComfyUI. Learn its inputs, outputs, parameters and usage."
 sidebarTitle: "CheckpointLoaderSimple"
 icon: "circle"
+mode: wide
 ---
-
 这是一个模型加载器节点，用于从指定位置加载模型文件，并将其分解为三个核心组件：主模型、文本编码器和图像编解码器。
 
 这个节点会自动检测`ComfyUI/models/checkpoints`文件夹下的所有模型文件，以及你在extra_model_paths.yaml文件中配置的额外路径。
@@ -26,4 +26,3 @@ icon: "circle"
 | 模型 | MODEL | 用于图像去噪生成的主要扩散模型，是AI绘画的核心组件 |
 | CLIP | CLIP | 用于编码文本提示词的模型，将文字描述转换为AI能理解的信息 |
 | VAE | VAE | 用于图像编解码的模型，负责在像素空间和潜在空间之间转换 |
-
diff --git a/zh-CN/built-in-nodes/CheckpointSave.mdx b/zh-CN/built-in-nodes/CheckpointSave.mdx
index 18d64925f..10be57aa4 100644
--- a/zh-CN/built-in-nodes/CheckpointSave.mdx
+++ b/zh-CN/built-in-nodes/CheckpointSave.mdx
@@ -1,11 +1,10 @@
 ---
-title: "保存Checkpoint - ComfyUI 原生节点文档"
-description: "保存Checkpoint 节点是 ComfyUI 中用于保存模型的节点。"
-sidebarTitle: "保存Checkpoint"
+title: "CheckpointSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CheckpointSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CheckpointSave"
 icon: "circle"
+mode: wide
 ---
-
-
 `保存Checkpoint` 节点的作用是将完整的 Stable Diffusion 模型（包括 UNet、CLIP 和 VAE 组件）保存为 **.safetensors** 格式的检查点文件。
 
 CheckpointSave 主要用于模型合并工作流中，当你通过 `ModelMergeSimple`、`ModelMergeBlocks` 等节点创建了新的合并模型后，可以使用此节点将结果保存为可重复使用的检查点文件。
@@ -36,4 +35,3 @@ CheckpointSave 主要用于模型合并工作流中，当你通过 `ModelMergeSi
 ## 相关链接
 
 相关源码: [nodes_model_merging.py#L227](https://github.com/comfyanonymous/ComfyUI/blob/master/comfy_extras/nodes_model_merging.py#L227)
-
diff --git a/zh-CN/built-in-nodes/ChromaRadianceOptions.mdx b/zh-CN/built-in-nodes/ChromaRadianceOptions.mdx
new file mode 100644
index 000000000..36c95e660
--- /dev/null
+++ b/zh-CN/built-in-nodes/ChromaRadianceOptions.mdx
@@ -0,0 +1,28 @@
+---
+title: "ChromaRadianceOptions - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ChromaRadianceOptions node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ChromaRadianceOptions"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ChromaRadianceOptions/zh.md)
+
+ChromaRadianceOptions 节点允许您配置 Chroma Radiance 模型的高级设置。它封装现有模型，并在去噪过程中根据 sigma 值应用特定选项，从而实现对 NeRF 图块大小和其他辐射相关参数的精细控制。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `model` | MODEL | 必填 | - | - | 要应用 Chroma Radiance 选项的模型 |
+| `preserve_wrapper` | BOOLEAN | 可选 | True | - | 启用时，如果存在现有模型函数包装器，将委托给该包装器。通常应保持启用状态。 |
+| `start_sigma` | FLOAT | 可选 | 1.0 | 0.0 - 1.0 | 这些选项开始生效的第一个 sigma 值。 |
+| `end_sigma` | FLOAT | 可选 | 0.0 | 0.0 - 1.0 | 这些选项停止生效的最后一个 sigma 值。 |
+| `nerf_tile_size` | INT | 可选 | -1 | -1 及以上 | 允许覆盖默认的 NeRF 图块大小。-1 表示使用默认值（32）。0 表示使用非分块模式（可能需要大量显存）。 |
+
+**注意：** 仅当当前 sigma 值介于 `end_sigma` 和 `start_sigma` 之间（含边界值）时，Chroma Radiance 选项才会生效。`nerf_tile_size` 参数仅在设置为 0 或更高值时才会被应用。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 应用了 Chroma Radiance 选项的修改后模型 |
diff --git a/zh-CN/built-in-nodes/ClipLoader.mdx b/zh-CN/built-in-nodes/ClipLoader.mdx
index 5fd0b58d2..40652dfb6 100644
--- a/zh-CN/built-in-nodes/ClipLoader.mdx
+++ b/zh-CN/built-in-nodes/ClipLoader.mdx
@@ -1,10 +1,10 @@
 ---
-title: "加载CLIP - ComfyUI 原生节点文档"
-description: "`加载CLIP ` 节点主要用于单独加载 CLIP 文本编码器模型。"
-sidebarTitle: "加载CLIP"
+title: "CLIPLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPLoader"
 icon: "circle"
+mode: wide
 ---
-
 该节点主要用于单独加载 CLIP 文本编码器模型。
 支持检测以下路径的模型文件检测：
 
@@ -76,4 +76,4 @@ CPU 运行会比 GPU 运行慢很多，但可以节省宝贵的 GPU 内存供其
 
 ## 其它扩展
 
-CLIP 模型在 ComfyUI 中扮演着文本编码器的核心角色，负责将文本提示转换为可供扩散模型理解的数值表示，你可以把它理解成翻译官，负责将你的文本翻译成大模型可以理解的语言，当然不同模型也存在着 “方言” ，所以在不同架构的模型之间需要不同的 CLIP 模型来完成文本编码的这一过程。
+CLIP 模型在 ComfyUI 中扮演着文本编码器的核心角色，负责将文本提示转换为可供扩散模型理解的数值表示，你可以把它理解成翻译官，负责讲你的文本翻译成大模型可以理解语言，当然不同模型也存在着 “方言” ，所以在不同架构的模型之间需要不同的 CLIP 编码器来完成文本编码的这一过程。
diff --git a/zh-CN/built-in-nodes/ClipMergeSimple.mdx b/zh-CN/built-in-nodes/ClipMergeSimple.mdx
index a934c8495..91416ae4f 100644
--- a/zh-CN/built-in-nodes/ClipMergeSimple.mdx
+++ b/zh-CN/built-in-nodes/ClipMergeSimple.mdx
@@ -1,10 +1,10 @@
 ---
-title: "CLIP融合简易 - ComfyUI 原生节点文档"
-description: "`CLIP融合简易` 是一个高级模型合并节点，用于将两个 CLIP 文本编码器模型按指定比例进行合并."
-sidebarTitle: "CLIP融合简易"
+title: "CLIPMergeSimple - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPMergeSimple node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPMergeSimple"
 icon: "circle"
+mode: wide
 ---
-
 `CLIP融合简易` 是一个高级模型合并节点，用于将两个 CLIP 文本编码器模型按指定比例进行合并.
 
 此节点专门用于根据指定比例合并两个CLIP模型，有效地混合它们的特性。它有选择性地将一个模型的补丁应用到另一个模型上，排除像位置ID和对数尺度这样的特定组件，以创建一个结合了两个源模型特征的混合模型。
@@ -32,7 +32,7 @@ icon: "circle"
 1. **克隆基础模型**: 首先克隆 `clip1` 作为基础模型
 2. **获取补丁**: 从 `clip2` 获取所有键值补丁 (key patches)
 3. **过滤特殊键**: 跳过 `.position_ids` 和 `.logit_scale` 结尾的键
-4. **应用加权合并**: 使用公式 `(1.0 - 比例) * clip1 + 比例 * clip2` 
+4. **应用加权合并**: 使用公式 `(1.0 - 比例) * clip1 + 比例 * clip2`
 
 ### 比例 参数说明
 
diff --git a/zh-CN/built-in-nodes/ClipSave.mdx b/zh-CN/built-in-nodes/ClipSave.mdx
index 1d738d5d1..7107b0004 100644
--- a/zh-CN/built-in-nodes/ClipSave.mdx
+++ b/zh-CN/built-in-nodes/ClipSave.mdx
@@ -1,10 +1,10 @@
 ---
-title: "保存CLIP - ComfyUI 原生节点文档"
-description: "`CLIP保存` 节点用于将 CLIP 文本编码器模型保存为 SafeTensors 格式文件, 该节点属于高级模型合并工作流的一部分，通常与 `CLIPMergeSimple`、`CLIPMergeAdd` 等节点配合使用。保存的文件采用 SafeTensors 格式，确保安全性和兼容性。"
-sidebarTitle: "保存CLIP"
+title: "CLIPSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPSave"
 icon: "circle"
+mode: wide
 ---
-
 `CLIP保存` 节点用于将 CLIP 文本编码器模型保存为 SafeTensors 格式文件, 该节点属于高级模型合并工作流的一部分，通常与 `CLIPMergeSimple`、`CLIPMergeAdd` 等节点配合使用。保存的文件采用 SafeTensors 格式，确保安全性和兼容性。
 
 ## 输入
diff --git a/zh-CN/built-in-nodes/ClipSetLastLayer.mdx b/zh-CN/built-in-nodes/ClipSetLastLayer.mdx
index 3b4e0648a..ecf37125d 100644
--- a/zh-CN/built-in-nodes/ClipSetLastLayer.mdx
+++ b/zh-CN/built-in-nodes/ClipSetLastLayer.mdx
@@ -1,10 +1,10 @@
 ---
-title: "设置CLIP最后一层 - ComfyUI 原生节点文档"
-description: "`设置CLIP最后一层` 是 ComfyUI 中用于控制 CLIP 模型处理深度的核心节点。"
-sidebarTitle: "设置CLIP最后一层"
+title: "CLIPSetLastLayer - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPSetLastLayer node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPSetLastLayer"
 icon: "circle"
+mode: wide
 ---
-
 `设置CLIP最后一层` 是 ComfyUI 中用于控制 CLIP 模型处理深度的核心节点。它允许用户精确控制 CLIP 文本编码器在哪一层停止处理，从而影响文本理解的深度和生成图像的风格。
 
 想象 CLIP 模型是一个24层的智能大脑：
@@ -13,7 +13,7 @@ icon: "circle"
 - 中层 (9-16层)：理解语法、句子结构
 - 深层 (17-24层)：掌握抽象概念、复杂语义
 
-`设置CLIP最后一层` 就像一个 **"思考深度调节器"**：
+`设置CLIP最后一层` 就像一个**"思考深度调节器"**：
 
 -1: 使用全部24层（最完整理解）
 -2: 停在第23层（稍微简化）
@@ -38,4 +38,3 @@ icon: "circle"
 - **性能优化**：就像不需要博士学位来理解简单句子一样，有时浅层理解就够了，速度更快
 - **风格控制**：不同层次的理解会产生不同的艺术风格
 - **兼容性**：某些模型可能在特定层次上表现更好
-
diff --git a/zh-CN/built-in-nodes/ClipTextEncode.mdx b/zh-CN/built-in-nodes/ClipTextEncode.mdx
index 18894fa18..633f371db 100644
--- a/zh-CN/built-in-nodes/ClipTextEncode.mdx
+++ b/zh-CN/built-in-nodes/ClipTextEncode.mdx
@@ -1,54 +1,74 @@
 ---
-title: "CLIP文本编码 - ComfyUI 原生节点文档"
-description: "`CLIP文本编码` 这个节点就像一位翻译官，它能将你用文字描述的创作想法转换成AI能够理解的特殊语言，帮助AI准确理解你想要创作的图像内容。"
-sidebarTitle: "CLIP文本编码"
+title: "CLIPTextEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncode"
 icon: "circle"
+mode: wide
 ---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncode/zh.md)
 
-`CLIP文本编码 (CLIPTextEncode)` 这个节点就像一位翻译官，它能将你用文字描述的创作想法转换成AI能够理解的特殊"语言"，帮助AI准确理解你想要创作的图像内容。
+`CLIP Text Encode (CLIPTextEncode)` 节点充当翻译器的角色，将您的文本描述转换为 AI 能够理解的格式。这有助于 AI 理解您的输入并生成期望的图像。
 
-想象你在和一位外国画家沟通，你需要一位翻译来帮助你准确传达你想要的画作效果。这个节点就像那位翻译，它使用CLIP模型（一个经过大量图文训练的AI模型）来理解你的文字描述，并将其转换成AI绘画模型能理解的"语言指令"。
+可以将其想象成与一位说不同语言的艺术家交流。CLIP 模型经过海量图像-文本对的训练，通过将您的描述转换为 AI 模型可以遵循的"指令"，从而弥合了这种沟通鸿沟。
 
-## 输入
+## 输入参数
 
-| 参数名称 | 数据类型 | 输入方式 | 默认值 | 取值范围 | 功能说明 |
-|----------|----------|----------|---------|----------|----------|
-| text | STRING | 文本输入框 | 空 | 任意文本 | 就像给画家的详细说明，在这里输入你想要生成的图像的文字描述。支持多行文本，可以非常详细地描述你想要的效果。 |
-| clip | CLIP | 模型选择 | 无 | 已加载的CLIP模型 | 相当于选择特定的翻译官，不同的CLIP模型就像不同的翻译官，他们对艺术风格的理解略有不同。 |
+| 参数 | 数据类型 | 输入方式 | 默认值 | 范围 | 描述 |
+|-----------|-----------|--------------|---------|--------|-------------|
+| text | STRING | 文本输入 | 空 | 任意文本 | 输入您想要创建的图像的描述（提示词）。支持多行输入以进行详细描述。 |
+| clip | CLIP | 模型选择 | 无 | 已加载的 CLIP 模型 | 选择用于将您的描述翻译成 AI 模型指令的 CLIP 模型。 |
 
-## 输出
+## 输出参数
 
-| 输出名称 | 数据类型 | 说明 |
-|----------|----------|------|
-| 条件 | CONDITIONING | 这是转换后的"绘画指令"，包含了AI能够理解的详细创作指引。这些指令会告诉AI模型应该如何绘制符合你描述的图像。 |
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| CONDITIONING | CONDITIONING | 经过处理的描述"指令"，用于在生成图像时引导 AI 模型。 |
 
-## 使用建议
+## 提示词特性
 
-1. **文本提示的基本用法**
-   - 可以像写作文一样详细描述你想要的图像
-   - 越具体的描述，生成的图像越符合预期
-   - 可以使用英文逗号分隔不同的描述要素
+### 嵌入模型
 
-2. **特殊功能：使用Embedding模型**
-   - Embedding模型就像预设的艺术风格包，可以快速应用特定的艺术效果
-   - 目前支持 .safetensors、.pt、.bin 这三种文件格式，你不一定需要在使用的时候用完整的模型名称
-   - 使用方法：
-     1. 将embedding模型文件(.pt格式)放入`ComfyUI/models/embeddings`文件夹
-     2. 在文本中使用`embedding:模型名称`来调用
-     例如：如果你有一个叫`EasyNegative.pt`的模型，可以这样使用：
+嵌入模型允许您应用特定的艺术效果或风格。支持的格式包括 `.safetensors`、`.pt` 和 `.bin`。要使用嵌入模型：
 
-     ```
-     a beautiful landscape, embedding:EasyNegative, high quality
-     ```
+1. 将文件放置在 `ComfyUI/models/embeddings` 文件夹中。
+2. 在您的文本中使用 `embedding:模型名称` 来引用它。
 
-3. **提示词权重调整**
-   - 可以用括号来调整某些描述的重要程度
-   - 例如：`(beautiful:1.2)`会让"beautiful"这个特征更突出
-   - 普通括号`()`的默认权重是1.1
-   - 使用键盘快捷键 `ctrl + 上/下方向键` 头可以快速调整权重
-   - 对应权重快速调整步长可以在设置中进行修改
+示例：如果您在 `ComfyUI/models/embeddings` 文件夹中有一个名为 `EasyNegative.pt` 的模型，则可以像这样使用它：
 
-4. **注意事项**
-   - 确保CLIP模型已正确加载
-   - 文本描述尽量使用正面、明确的词语
-   - 如果使用embedding模型，确保文件名称输入正确并且和当前主模型的架构吻合
+```
+worst quality, embedding:EasyNegative, bad quality
+```
+
+**重要提示**：使用嵌入模型时，请验证文件名是否匹配且与您的模型架构兼容。例如，为 SD1.5 设计的嵌入模型将无法在 SDXL 模型上正常工作。
+
+### 提示词权重调整
+
+您可以使用括号来调整描述中某些部分的重要性。例如：
+
+- `(beautiful:1.2)` 增加 "beautiful" 的权重。
+- `(beautiful:0.8)` 降低 "beautiful" 的权重。
+- 普通括号 `(beautiful)` 将应用默认权重 1.1。
+
+您可以使用键盘快捷键 `ctrl + 上/下箭头` 来快速调整权重。权重调整的步长可以在设置中修改。
+
+如果您想在提示词中包含字面意义上的括号而不改变权重，可以使用反斜杠进行转义，例如 `\(word\)`。
+
+### 通配符/动态提示词
+
+使用 `{}` 创建动态提示词。例如，`{day|night|morning}` 将在每次处理提示词时随机选择一个选项。
+
+如果您想在提示词中包含字面意义上的花括号而不触发动态行为，可以使用反斜杠进行转义，例如 `\{word\}`。
+
+### 提示词中的注释
+
+您可以通过以下方式添加在提示词中被排除的注释：
+
+- `//` 用于注释单行。
+- `/* */` 用于注释一个部分或多行。
+
+示例：
+
+```
+// 这一行不会包含在提示词中。
+a beautiful landscape, /* 这部分被忽略 */ high quality
+```
diff --git a/zh-CN/built-in-nodes/ClipTextEncodeFlux.mdx b/zh-CN/built-in-nodes/ClipTextEncodeFlux.mdx
index f371447ba..0427a26e8 100644
--- a/zh-CN/built-in-nodes/ClipTextEncodeFlux.mdx
+++ b/zh-CN/built-in-nodes/ClipTextEncodeFlux.mdx
@@ -1,13 +1,14 @@
 ---
-title: "CLIP文本编码Flux - ComfyUI 原生节点文档"
-description: "CLIP文本编码Flux 节点是 ComfyUI 中专为 Flux 架构设计的高级文本编码节点。"
-sidebarTitle: "CLIP文本编码Flux"
+title: "CLIPTextEncodeFlux - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeFlux node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeFlux"
 icon: "circle"
+mode: wide
 ---
-
 `CLIP文本编码Flux` 是 ComfyUI 中专为 Flux 架构设计的高级文本编码节点。它采用双文本编码器（CLIP-L 与 T5XXL）协同机制，能够同时处理结构化关键词和详细自然语言描述，为 Flux 模型提供更精准、更丰富的文本理解能力，提升文本到图像的生成质量。
 
 该节点基于双编码器协作机制：
+
 1. `clip_l` 输入会被 CLIP-L 编码器处理，提取风格、主题等关键词特征，适合简洁描述。
 2. `t5xxl` 输入由 T5XXL 编码器处理，擅长理解复杂、细致的自然语言场景描述。
 3. 两路编码结果融合后，结合"引导"参数，生成统一的条件嵌入（CONDITIONING），用于下游的 Flux 采样器节点，控制生成内容与文本描述的契合度。
diff --git a/zh-CN/built-in-nodes/ClipTextEncodeHunyuanDit.mdx b/zh-CN/built-in-nodes/ClipTextEncodeHunyuanDit.mdx
index 926e30e8e..6f8700883 100644
--- a/zh-CN/built-in-nodes/ClipTextEncodeHunyuanDit.mdx
+++ b/zh-CN/built-in-nodes/ClipTextEncodeHunyuanDit.mdx
@@ -1,10 +1,10 @@
 ---
-title: "CLIP文本编码混元DiT - ComfyUI内置节点文档"
-description: "CLIP文本编码混元DiT节点用于将文本提示编码为HunyuanDiT兼容的条件嵌入。"
-sidebarTitle: "CLIP文本编码混元DiT"
+title: "CLIPTextEncodeHunyuanDiT - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeHunyuanDiT node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeHunyuanDiT"
 icon: "circle"
+mode: wide
 ---
-
 `CLIP文本编码混元DiT` 节点的主要功能是将输入的文本转换为模型可以理解的形式。是一个高级条件化节点，专门用于 HunyuanDiT 模型的双文本编码器架构。
 主要作用它就像一个翻译器，可以将我们的文字描述转换成 AI 模型能理解的"机器语言"。其中 `bert` 和 `mt5xl` 偏好不同类型的提示词输入
 
diff --git a/zh-CN/built-in-nodes/ClipTextEncodeSdxl.mdx b/zh-CN/built-in-nodes/ClipTextEncodeSdxl.mdx
index 90fbfd65c..82502c4d7 100644
--- a/zh-CN/built-in-nodes/ClipTextEncodeSdxl.mdx
+++ b/zh-CN/built-in-nodes/ClipTextEncodeSdxl.mdx
@@ -1,10 +1,10 @@
 ---
-title: "CLIP文本编码SDXL - ComfyUI内置节点文档"
-description: "CLIP文本编码SDXL节点用于将文本提示编码为SDXL兼容的条件嵌入。"
-sidebarTitle: "CLIP文本编码SDXL"
+title: "CLIPTextEncodeSDXL - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeSDXL node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeSDXL"
 icon: "circle"
+mode: wide
 ---
-
 此节点设计使用特别为SDXL架构定制的CLIP模型对文本输入进行编码。它使用双编码器系统（CLIP-L和CLIP-G）来处理文本描述，从而生成更准确的图像。
 
 ## 输入
@@ -18,8 +18,8 @@ icon: "circle"
 | `裁剪高` | `INT`    | 裁剪区域的高度（以像素为单位），默认0。                                                                     |
 | `目标宽度` | `INT`  | 输出图像的目标宽度，默认1024。                                                                             |
 | `目标高度` | `INT`  | 输出图像的目标高度，默认1024。                                                                             |
-| `text_g` | `STRING` | 全局文本描述，用于整体场景描述。                                                                            |
-| `text_l` | `STRING` | 局部文本描述，用于细节描述。                                                                                |
+| `文本_g` | `STRING` | 全局文本描述，用于整体场景描述。                                                                            |
+| `文本_l` | `STRING` | 局部文本描述，用于细节描述。                                                                                |
 
 ## 输出
 
diff --git a/zh-CN/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx b/zh-CN/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx
index 4a6afaf26..8018d924b 100644
--- a/zh-CN/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx
+++ b/zh-CN/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx
@@ -1,10 +1,10 @@
 ---
-title: "CLIP文本编码SDXL精炼器 - ComfyUI内置节点文档"
-description: "CLIP文本编码SDXL精炼器节点用于将文本提示编码为SDXL精炼兼容的条件嵌入。"
-sidebarTitle: "CLIP文本编码SDXL精炼器"
+title: "CLIPTextEncodeSDXLRefiner - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPTextEncodeSDXLRefiner node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPTextEncodeSDXLRefiner"
 icon: "circle"
+mode: wide
 ---
-
 此节点专门为 SDXL Refiner 模型设计，用于将文本提示转换为条件信息，通过纳入审美得分和维度信息来增强生成任务的条件，从而提升最终的精炼效果。它就像是一位专业的艺术指导，不仅传达您的创作意图，还能为作品注入精确的美学标准和规格要求。
 
 ## 工作原理
@@ -16,6 +16,7 @@ SDXL Refiner 是一个专门的精炼模型，它在 SDXL 基础模型的基础
 3. 最后，它专注于处理图像的高频细节，提升整体质量
 
 Refiner 可以通过两种方式使用：
+
 - 作为独立的精炼步骤，对基础模型生成的图像进行后期处理
 - 作为专家集成系统的一部分，在生成过程的低噪声阶段接管处理
 
@@ -27,7 +28,7 @@ Refiner 可以通过两种方式使用：
 | `美学分数` | FLOAT | 可选 | 6.0 | 0.0-1000.0 | 控制生成图像的视觉质量和美观程度，类似于为艺术作品设定质量标准：<br/>- 高分值(7.5-8.5)：追求更精美、细节丰富的效果<br/>- 中等分值(6.0-7.0)：平衡的质量控制<br/>- 低分值(2.0-3.0)：适用于负面提示 |
 | `宽度` | INT | 必需 | 1024 | 64-16384 | 指定输出图像的宽度（像素），需要是 8 的倍数。SDXL 在总像素量接近 1024×1024 (约100万像素) 时效果最佳 |
 | `高度` | INT | 必需 | 1024 | 64-16384 | 指定输出图像的高度（像素），需要是 8 的倍数。SDXL 在总像素量接近 1024×1024 (约100万像素) 时效果最佳 |
-| `text` | STRING | 必需 | - | - | 文本提示描述，支持多行输入和动态提示语法。在 Refiner 中，文本提示应更注重描述期望的视觉质量和细节特征 |
+| `文本` | STRING | 必需 | - | - | 文本提示描述，支持多行输入和动态提示语法。在 Refiner 中，文本提示应更注重描述期望的视觉质量和细节特征 |
 
 ## 输出
 
diff --git a/zh-CN/built-in-nodes/ClipVisionEncode.mdx b/zh-CN/built-in-nodes/ClipVisionEncode.mdx
index 7fbf33f2f..c7cc5881a 100644
--- a/zh-CN/built-in-nodes/ClipVisionEncode.mdx
+++ b/zh-CN/built-in-nodes/ClipVisionEncode.mdx
@@ -1,10 +1,10 @@
 ---
-title: "CLIP视觉编码 - ComfyUI内置节点文档"
-description: "CLIP视觉编码节点用于将输入图像通过CLIP Vision模型转换为视觉特征向量。"
-sidebarTitle: "CLIP视觉编码"
+title: "CLIPVisionEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPVisionEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPVisionEncode"
 icon: "circle"
+mode: wide
 ---
-
 `CLIP视觉编码` 节点是 ComfyUI 中的图像编码节点，用于将输入图像通过 CLIP Vision 模型转换为视觉特征向量。该节点是连接图像和文本理解的重要桥梁，广泛用于各种 AI 图像生成和处理工作流中。
 
 **节点功能**
@@ -12,6 +12,7 @@ icon: "circle"
 - **图像特征提取**：将输入图像转换为高维特征向量
 - **多模态桥接**：为图像和文本的联合处理提供基础
 - **条件生成**：为基于图像的条件生成提供视觉条件
+
 ## 输入参数
 
 | 参数名          | 类型         | 说明                                         |
@@ -27,7 +28,8 @@ icon: "circle"
 | CLIP视觉输出             | CLIP_VISION_OUTPUT   |编码后的视觉特征                |
 
 这个输出对象包含:
+
 - `last_hidden_state`: 最后一层的隐藏状态  
 - `image_embeds`: 图像嵌入向量  
 - `penultimate_hidden_states`: 倒数第二层的隐藏状态  
-- `mm_projected`: 多模态投影结果（如果可用）  
\ No newline at end of file
+- `mm_projected`: 多模态投影结果（如果可用）  
diff --git a/zh-CN/built-in-nodes/ClipVisionLoader.mdx b/zh-CN/built-in-nodes/ClipVisionLoader.mdx
index 4aa679f2f..deec8052c 100644
--- a/zh-CN/built-in-nodes/ClipVisionLoader.mdx
+++ b/zh-CN/built-in-nodes/ClipVisionLoader.mdx
@@ -1,10 +1,10 @@
 ---
-title: "加载CLIP视觉 - ComfyUI内置节点文档"
-description: "加载CLIP视觉节点用于从 `ComfyUI/models/clip_vision` 文件夹中加载 CLIP Vision 模型。"
-sidebarTitle: "加载CLIP视觉"
+title: "CLIPVisionLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CLIPVisionLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CLIPVisionLoader"
 icon: "circle"
+mode: wide
 ---
-
 该节点会检测位于 `ComfyUI/models/clip_vision` 文件夹下的模型，同时也会读取在 `extra_model_paths.yaml` 文件中配置的额外路径的模型，如果你的模型是在 ComfyUI 启动后才添加的，请 **刷新 ComfyUI 界面** 保证前端能够获取到最新的模型文件列表
 
 ## 输入
diff --git a/zh-CN/built-in-nodes/ColorToRGBInt.mdx b/zh-CN/built-in-nodes/ColorToRGBInt.mdx
new file mode 100644
index 000000000..8a64b2ebd
--- /dev/null
+++ b/zh-CN/built-in-nodes/ColorToRGBInt.mdx
@@ -0,0 +1,24 @@
+---
+title: "ColorToRGBInt - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ColorToRGBInt node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ColorToRGBInt"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ColorToRGBInt/zh.md)
+
+该节点将十六进制格式指定的颜色转换为单个整数值。它接收类似 `#FF5733` 的颜色字符串，并通过组合红、绿、蓝分量来计算相应的 RGB 整数。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `color` | STRING | 是 | 不适用 | 十六进制格式 `#RRGGBB` 的颜色值。 |
+
+**注意：** 输入的 `color` 字符串必须恰好为 7 个字符长，并以 `#` 符号开头，后跟六个十六进制数字（例如，红色为 `#FF0000`）。如果格式不正确，节点将引发错误。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `rgb_int` | INT | 计算得到的 RGB 整数值。该值由公式 `(Red * 65536) + (Green * 256) + Blue` 推导得出。 |
diff --git a/zh-CN/built-in-nodes/CombineHooks.mdx b/zh-CN/built-in-nodes/CombineHooks.mdx
new file mode 100644
index 000000000..385af5fc0
--- /dev/null
+++ b/zh-CN/built-in-nodes/CombineHooks.mdx
@@ -0,0 +1,27 @@
+---
+title: "CombineHooks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CombineHooks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CombineHooks"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CombineHooks/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CombineHooks/en.md)
+
+Combine Hooks [2] 节点将两个钩子组合并为一个组合钩子组。它接收两个可选的钩子输入，并使用 ComfyUI 的钩子组合功能将它们合并。这使您可以整合多个钩子配置以实现流线型处理。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|------|-----------|------------|---------|-------|-------------|
+| `hooks_A` | HOOKS | 可选 | 无 | - | 要合并的第一个钩子组 |
+| `hooks_B` | HOOKS | 可选 | 无 | - | 要合并的第二个钩子组 |
+
+**注意：** 两个输入都是可选的，但必须至少提供一个钩子组才能使节点正常工作。如果只提供一个钩子组，它将原样返回。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `hooks` | HOOKS | 包含两个输入组中所有钩子的组合钩子组 |
diff --git a/zh-CN/built-in-nodes/CombineHooksEight.mdx b/zh-CN/built-in-nodes/CombineHooksEight.mdx
new file mode 100644
index 000000000..24ebe4c77
--- /dev/null
+++ b/zh-CN/built-in-nodes/CombineHooksEight.mdx
@@ -0,0 +1,31 @@
+---
+title: "CombineHooksEight - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CombineHooksEight node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CombineHooksEight"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CombineHooksEight/zh.md)
+
+组合钩子 [8] 节点可将最多八个不同的钩子组合并为一个统一的钩子组。它接收多个钩子输入，并使用 ComfyUI 的钩子组合功能将它们合并。这使您能够整合多个钩子配置，在高级工作流中实现简化处理。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 数值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `hooks_A` | HOOKS | 可选 | None | - | 要组合的第一个钩子组 |
+| `hooks_B` | HOOKS | 可选 | None | - | 要组合的第二个钩子组 |
+| `hooks_C` | HOOKS | 可选 | None | - | 要组合的第三个钩子组 |
+| `hooks_D` | HOOKS | 可选 | None | - | 要组合的第四个钩子组 |
+| `hooks_E` | HOOKS | 可选 | None | - | 要组合的第五个钩子组 |
+| `hooks_F` | HOOKS | 可选 | None | - | 要组合的第六个钩子组 |
+| `hooks_G` | HOOKS | 可选 | None | - | 要组合的第七个钩子组 |
+| `hooks_H` | HOOKS | 可选 | None | - | 要组合的第八个钩子组 |
+
+**注意：** 所有输入参数均为可选。该节点仅会组合已提供的钩子组，忽略任何留空的输入。您可以选择提供一至八个钩子组进行组合。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `HOOKS` | HOOKS | 包含所有已提供钩子配置的单一组合钩子组 |
diff --git a/zh-CN/built-in-nodes/CombineHooksFour.mdx b/zh-CN/built-in-nodes/CombineHooksFour.mdx
new file mode 100644
index 000000000..386ca0e0d
--- /dev/null
+++ b/zh-CN/built-in-nodes/CombineHooksFour.mdx
@@ -0,0 +1,29 @@
+---
+title: "CombineHooksFour - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CombineHooksFour node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CombineHooksFour"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CombineHooksFour/zh.md)
+
+## 概述
+
+Combine Hooks [4] 节点可将最多四个独立的钩子组合并为一个统一的钩子组。该节点接收四个可用钩子输入中的任意组合，并使用 ComfyUI 的钩子组合系统进行合并。通过此功能，您可以在高级工作流中整合多个钩子配置，实现简化的处理流程。
+
+## 输入
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|------|-----------|------------|---------|----------|-------------|
+| `hooks_A` | HOOKS | 可选 | 无 | - | 要合并的第一个钩子组 |
+| `hooks_B` | HOOKS | 可选 | 无 | - | 要合并的第二个钩子组 |
+| `hooks_C` | HOOKS | 可选 | 无 | - | 要合并的第三个钩子组 |
+| `hooks_D` | HOOKS | 可选 | 无 | - | 要合并的第四个钩子组 |
+
+**注意：** 所有四个钩子输入均为可选。该节点仅会合并已连接的钩子组，如果未连接任何输入，将返回空钩子组。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `HOOKS` | HOOKS | 包含所有已提供钩子配置的合并钩子组 |
diff --git a/zh-CN/built-in-nodes/ComboOptionTestNode.mdx b/zh-CN/built-in-nodes/ComboOptionTestNode.mdx
new file mode 100644
index 000000000..1a344caa8
--- /dev/null
+++ b/zh-CN/built-in-nodes/ComboOptionTestNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "ComboOptionTestNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ComboOptionTestNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ComboOptionTestNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComboOptionTestNode/zh.md)
+
+ComboOptionTestNode 是一个逻辑节点，用于测试并透传下拉框选择。它接收两个下拉框输入，每个输入都包含一组预定义的选项，并直接输出所选值而不进行修改。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `combo` | COMBO | 是 | `"option1"`<br />`"option2"`<br />`"option3"` | 从三个测试选项集合中的第一个选择。 |
+| `combo2` | COMBO | 是 | `"option4"`<br />`"option5"`<br />`"option6"` | 从另一组三个测试选项集合中的第二个选择。 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output_1` | COMBO | 输出从第一个下拉框 (`combo`) 中选择的值。 |
+| `output_2` | COMBO | 输出从第二个下拉框 (`combo2`) 中选择的值。 |
diff --git a/zh-CN/built-in-nodes/ComfySoftSwitchNode.mdx b/zh-CN/built-in-nodes/ComfySoftSwitchNode.mdx
new file mode 100644
index 000000000..5e9440128
--- /dev/null
+++ b/zh-CN/built-in-nodes/ComfySoftSwitchNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "ComfySoftSwitchNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ComfySoftSwitchNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ComfySoftSwitchNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfySoftSwitchNode/zh.md)
+
+Soft Switch 节点根据一个布尔条件在两个可能的输入值之间进行选择。当 `switch` 为真时，它输出 `on_true` 输入的值；当 `switch` 为假时，它输出 `on_false` 输入的值。此节点设计为惰性求值，意味着它仅根据开关状态评估所需的输入。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `switch` | BOOLEAN | 是 | | 决定传递哪个输入的布尔条件。为真时，选择 `on_true` 输入。为假时，选择 `on_false` 输入。 |
+| `on_false` | MATCH_TYPE | 否 | | 当 `switch` 条件为假时要输出的值。此输入是可选的，但 `on_false` 和 `on_true` 中至少必须连接一个。 |
+| `on_true` | MATCH_TYPE | 否 | | 当 `switch` 条件为真时要输出的值。此输入是可选的，但 `on_false` 和 `on_true` 中至少必须连接一个。 |
+
+**注意：** `on_false` 和 `on_true` 输入必须是相同的数据类型，由节点的内部模板定义。这两个输入中至少必须连接一个，节点才能正常工作。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | MATCH_TYPE | 被选中的值。其数据类型将与所连接的 `on_false` 或 `on_true` 输入的数据类型相匹配。 |
diff --git a/zh-CN/built-in-nodes/ComfySwitchNode.mdx b/zh-CN/built-in-nodes/ComfySwitchNode.mdx
new file mode 100644
index 000000000..66aa6ede8
--- /dev/null
+++ b/zh-CN/built-in-nodes/ComfySwitchNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "ComfySwitchNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ComfySwitchNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ComfySwitchNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfySwitchNode/zh.md)
+
+Switch 节点根据布尔条件在两个可能的输入之间进行选择。当 `switch` 启用时，它输出 `on_true` 输入；当 `switch` 禁用时，它输出 `on_false` 输入。这允许你在工作流中创建条件逻辑并选择不同的数据路径。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `switch` | BOOLEAN | 是 | | 一个布尔条件，用于决定传递哪个输入。当启用（true）时，选择 `on_true` 输入。当禁用（false）时，选择 `on_false` 输入。 |
+| `on_false` | MATCH_TYPE | 否 | | 当 `switch` 禁用（false）时传递给输出的数据。仅当 `switch` 为 false 时才需要此输入。 |
+| `on_true` | MATCH_TYPE | 否 | | 当 `switch` 启用（true）时传递给输出的数据。仅当 `switch` 为 true 时才需要此输入。 |
+
+**关于输入要求的说明：** `on_false` 和 `on_true` 输入是条件性必填的。节点仅在 `switch` 为 true 时请求 `on_true` 输入，仅在 `switch` 为 false 时请求 `on_false` 输入。两个输入必须是相同的数据类型。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | MATCH_TYPE | 被选中的数据。如果 `switch` 为 true，则输出 `on_true` 输入的值；如果 `switch` 为 false，则输出 `on_false` 输入的值。 |
diff --git a/zh-CN/built-in-nodes/ConditioningAverage.mdx b/zh-CN/built-in-nodes/ConditioningAverage.mdx
new file mode 100644
index 000000000..48bdbaa8f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningAverage.mdx
@@ -0,0 +1,38 @@
+---
+title: "ConditioningAverage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningAverage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningAverage"
+icon: "circle"
+mode: wide
+---
+`条件平均` 节点用于将两组不同的条件（如文本提示/Prompt）按照指定权重进行加权平均，生成介于两者之间的新条件。通过调整权重参数，可以灵活控制不同条件对最终结果的影响，非常适合于提示词插值、风格融合等高级用例。
+
+如下图，通过调节`条件到` 的强度，可以输出介于两个条件之间的结果
+
+![example](/images/built-in-nodes/ConditioningAverage/example.webp)
+
+**示例说明**
+`conditioning_to` 为 `条件到`
+`conditioning_fro` 为 `条件从`
+`Strength` 为 `条件到强度`
+
+## 输入
+
+| 参数名称 | 数据类型 | 说明 |
+| --- | --- | --- |
+| `条件到` | `CONDITIONING` | 目标条件向量，作为加权平均的主要基础。 |
+| `条件从` | `CONDITIONING` | 源条件向量，将以一定权重混合到目标条件中。 |
+| `条件到强度` | `FLOAT` | 目标条件的强度权重，范围 0.0-1.0，默认 1.0，步长 0.01。|
+
+## 输出
+
+| 参数名称 | 数据类型 | 说明 |
+| --- | --- | --- |
+| `条件` | `CONDITIONING` | 返回混合后的条件向量，反映加权平均结果。 |
+
+## 典型应用场景
+
+- **Prompt 插值**：在两个不同文本提示之间平滑过渡，生成中间风格或语义的内容。
+- **风格融合**：结合不同艺术风格或语义条件，创造新颖效果。
+- **强度调节**：通过调整权重，精确控制某一条件对结果的影响程度。
+- **创意探索**：探索不同提示组合带来的多样化生成效果。
diff --git a/zh-CN/built-in-nodes/ConditioningCombine.mdx b/zh-CN/built-in-nodes/ConditioningCombine.mdx
new file mode 100644
index 000000000..248c246a4
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningCombine.mdx
@@ -0,0 +1,35 @@
+---
+title: "ConditioningCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningCombine"
+icon: "circle"
+mode: wide
+---
+此节点将两个条件输入组合成单个输出，有效地合并它们的信息， 两个条件使用列表拼接相加
+
+## 输入
+
+| 参数名称 | 数据类型       | 作用                                                             |
+| -------- | -------------- | ---------------------------------------------------------------- |
+| `条件_1` | `CONDITIONING` | 要组合的第一个条件输入。在组合过程中与 `条件_2` 同等重要。 |
+| `条件_2` | `CONDITIONING` | 要组合的第二个条件输入。在组合过程中与 `条件_1`同等重要。   |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `条件` | CONDITIONING | 组合`条件_1`和 `条件_2`的结果，封装了合并后的信息。 |
+
+## 使用场景
+
+对比下面的两组对比，左边是使用了 ConditioningCombine 节点，而右侧则是正常输出
+
+![Compare](/images/built-in-nodes/ConditioningCombine/compare.jpg)
+
+在这个示例中，使用了 `条件合并` 的两个条件，他们之间的重要性是等效的，因而你可以将将画面风格、主体特征等采用不同的文本编码，从而使得提示词的特征能够更完整地输出, 而第二个提示词使用了组合后的完整提示词，但语义理解可能编码出了完全不同的条件
+
+使用这个节点你可以实现：
+
+- 基础文本合并：将两个 `CLIP文本编码` 节点的输出连接到 `条件合并` 的两个输入端口
+- 复杂提示组合：结合正面和负面提示，或者将主要描述与风格描述分开编码后再合并
+- 条件链式组合：多个 `条件合并` 节点可以串联使用，实现多个条件的逐步合并
diff --git a/zh-CN/built-in-nodes/ConditioningConcat.mdx b/zh-CN/built-in-nodes/ConditioningConcat.mdx
new file mode 100644
index 000000000..a704c9dde
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningConcat.mdx
@@ -0,0 +1,21 @@
+---
+title: "ConditioningConcat - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningConcat node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningConcat"
+icon: "circle"
+mode: wide
+---
+此节点设计用于连接条件向量，特别是将'conditioning_from'向量合并到'conditioning_to'向量中。在需要将来自两个源的条件信息组合成单一、统一表示的场景中，此操作是基础。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `条件到` | `CONDITIONING` | 表示'conditioning_from'向量将被连接到的主要条件向量集。它作为连接过程的基础。 |
+| `条件从` | `CONDITIONING` | 包含要连接到'conditioning_to'向量的条件向量。此参数允许将额外的条件信息集成到现有的集。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 输出是统一的条件向量集，由'conditioning_from'向量连接到'conditioning_to'向量的结果。 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetArea.mdx b/zh-CN/built-in-nodes/ConditioningSetArea.mdx
new file mode 100644
index 000000000..f4097f497
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetArea.mdx
@@ -0,0 +1,25 @@
+---
+title: "ConditioningSetArea - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetArea node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetArea"
+icon: "circle"
+mode: wide
+---
+此节点设计用于通过在条件上下文中设置特定区域来修改条件信息。它允许对条件元素进行精确的空间操作，根据指定的尺寸和强度实现有针对性的调整和增强。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 要修改的条件数据。它作为应用空间调整的基础。 |
+| `宽度` | `INT` | 指定要在条件上下文中设置的区域的宽度，影响调整的水平范围。 |
+| `高度` | `INT` | 确定要设置的区域的高度，影响条件修改的垂直范围。 |
+| `x` | `INT` | 要设置的区域的水平起始点，定位条件上下文中的调整。 |
+| `y` | `INT` | 区域调整的垂直起始点，确定其在条件上下文中的位置。 |
+| `强度` | `FLOAT` | 定义指定区域内条件修改的强度，允许对调整的影响进行精细控制。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 修改后的条件数据，反映了指定区域设置和调整。 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetAreaPercentage.mdx b/zh-CN/built-in-nodes/ConditioningSetAreaPercentage.mdx
new file mode 100644
index 000000000..f5f59eefa
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetAreaPercentage.mdx
@@ -0,0 +1,25 @@
+---
+title: "ConditioningSetAreaPercentage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetAreaPercentage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetAreaPercentage"
+icon: "circle"
+mode: wide
+---
+条件采样区域百分比设置节点专门用于根据百分比值调整条件元素的影响区域。它允许指定区域的尺寸和位置作为总图像尺寸的百分比，以及一个强度参数来调节条件效果的强度。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 表示要修改的条件元素，作为应用区域和强度调整的基础。 |
+| `宽度` | `FLOAT` | 指定区域的宽度，作为总图像宽度的百分比，影响条件水平上影响图像的程度。 |
+| `高度` | `FLOAT` | 确定区域的高度，作为总图像高度的百分比，影响条件影响的垂直范围。 |
+| `x` | `FLOAT` | 表示区域的水平起始点，作为总图像宽度的百分比，定位条件效果。 |
+| `y` | `FLOAT` | 指定区域的垂直起始点，作为总图像高度的百分比，定位条件效果。 |
+| `强度` | `FLOAT` | 控制指定区域内条件效果的强度，允许微调其影响。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 返回具有更新的区域和强度参数的修改后条件元素，准备进行进一步处理或应用。 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx b/zh-CN/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx
new file mode 100644
index 000000000..071bc9012
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx
@@ -0,0 +1,29 @@
+---
+title: "ConditioningSetAreaPercentageVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetAreaPercentageVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetAreaPercentageVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetAreaPercentageVideo/zh.md)
+
+ConditioningSetAreaPercentageVideo 节点通过定义视频生成的特定区域和时域范围来修改条件数据。它允许您使用相对于整体尺寸的百分比值来设置条件应用区域的位置、大小和持续时间。这对于将生成过程聚焦在视频序列的特定部分非常有用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|--------|-----------|------------|---------|-------|-------------|
+| `调节` | CONDITIONING | 必填 | - | - | 待修改的条件数据 |
+| `宽度` | FLOAT | 必填 | 1.0 | 0.0 - 1.0 | 区域宽度占总宽度的百分比 |
+| `高度` | FLOAT | 必填 | 1.0 | 0.0 - 1.0 | 区域高度占总高度的百分比 |
+| `时间` | FLOAT | 必填 | 1.0 | 0.0 - 1.0 | 区域持续时间占总视频长度的百分比 |
+| `x` | FLOAT | 必填 | 0.0 | 0.0 - 1.0 | 区域水平起始位置的百分比 |
+| `y` | FLOAT | 必填 | 0.0 | 0.0 - 1.0 | 区域垂直起始位置的百分比 |
+| `z` | FLOAT | 必填 | 0.0 | 0.0 - 1.0 | 区域在视频时间轴上的起始位置百分比 |
+| `强度` | FLOAT | 必填 | 1.0 | 0.0 - 10.0 | 在定义区域内应用于条件数据的强度乘数 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `调节` | CONDITIONING | 应用了指定区域和强度设置的修改后条件数据 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetAreaStrength.mdx b/zh-CN/built-in-nodes/ConditioningSetAreaStrength.mdx
new file mode 100644
index 000000000..55e72f854
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetAreaStrength.mdx
@@ -0,0 +1,21 @@
+---
+title: "ConditioningSetAreaStrength - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetAreaStrength node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetAreaStrength"
+icon: "circle"
+mode: wide
+---
+此节点旨在修改给定条件集的强度属性，允许调整条件对生成过程的影响或强度。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `CONDITIONING` | CONDITIONING | 要修改的条件集，代表影响生成过程的当前条件状态。       |
+| `强度` | `FLOAT` | 要应用于条件集的强度值，决定其影响的强度。               |
+
+## 输出
+
+| 参数名称     | 数据类型     | 作用                                       |
+|--------------|--------------|--------------------------------------------|
+| `CONDITIONING` | CONDITIONING | 修改后的条件集，每个元素的强度值已更新。 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetDefaultAndCombine.mdx b/zh-CN/built-in-nodes/ConditioningSetDefaultAndCombine.mdx
new file mode 100644
index 000000000..0f3ff73d9
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetDefaultAndCombine.mdx
@@ -0,0 +1,26 @@
+---
+title: "ConditioningSetDefaultAndCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetDefaultAndCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetDefaultAndCombine"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetDefaultAndCombine/zh.md)
+
+## 概述
+
+该节点使用基于钩子的系统将条件数据与默认条件数据相结合。它接收一个主要条件输入和一个默认条件输入，然后根据指定的钩子配置将它们合并。最终输出一个融合了两种来源的单一条件数据。
+
+## 输入
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `cond` | CONDITIONING | 必填 | - | - | 待处理的主要条件输入 |
+| `cond_DEFAULT` | CONDITIONING | 必填 | - | - | 将与主要条件数据合并的默认条件数据 |
+| `hooks` | HOOKS | 可选 | - | - | 控制条件数据处理和合并方式的可选钩子配置 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 合并主要和默认条件输入后得到的组合条件数据 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetMask.mdx b/zh-CN/built-in-nodes/ConditioningSetMask.mdx
new file mode 100644
index 000000000..074e8f8f9
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetMask.mdx
@@ -0,0 +1,23 @@
+---
+title: "ConditioningSetMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetMask"
+icon: "circle"
+mode: wide
+---
+此节点设计通过应用具有指定强度的遮罩来修改生成模型的条件，允许对条件内的特定区域进行有针对性的调整，从而实现对生成过程更精确的控制。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 要修改的条件数据。它作为应用遮罩和强度调整的基础。 |
+| `遮罩` | `MASK` | 一个遮罩张量，指定要在其中修改的条件区域。 |
+| `强度` | `FLOAT` | 遮罩对条件的影响强度，允许对应用的修改进行微调。 |
+| `设置条件区域` | COMBO[STRING] | 确定遮罩的效果是应用于默认区域还是由遮罩本身限定，提供在定位特定区域方面的灵活性。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 应用了遮罩和强度调整的修改后条件数据。 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetProperties.mdx b/zh-CN/built-in-nodes/ConditioningSetProperties.mdx
new file mode 100644
index 000000000..492d1a22b
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetProperties.mdx
@@ -0,0 +1,31 @@
+---
+title: "ConditioningSetProperties - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetProperties node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetProperties"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetProperties/zh.md)
+
+> 本文档由 AI 生成，如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetProperties/en.md)
+
+ConditioningSetProperties 节点通过调整强度、区域设置以及应用可选遮罩或时间步范围来修改条件数据的属性。它允许您通过设置特定参数来控制条件数据在图像生成过程中的应用方式，从而影响条件调节对生成过程的作用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `新条件` | CONDITIONING | 必填 | - | - | 要修改的条件数据 |
+| `强度` | FLOAT | 必填 | 1.0 | 0.0-10.0 | 控制条件调节效果的强度 |
+| `设置条件区域` | STRING | 必填 | default | ["default", "mask bounds"] | 决定条件区域的应用方式 |
+| `遮罩` | MASK | 可选 | - | - | 用于限制条件调节应用区域的可选遮罩 |
+| `约束` | HOOKS | 可选 | - | - | 用于自定义处理的可选钩子函数 |
+| `间隔` | TIMESTEPS_RANGE | 可选 | - | - | 用于限制条件调节生效时间范围的可选时间步范围 |
+
+**注意：** 当提供 `mask` 时，`set_cond_area` 参数可设置为 "mask bounds"，以将条件调节应用限制在遮罩区域内。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 具有更新属性的修改后条件数据 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx b/zh-CN/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx
new file mode 100644
index 000000000..7cc1f2d54
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx
@@ -0,0 +1,32 @@
+---
+title: "ConditioningSetPropertiesAndCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetPropertiesAndCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetPropertiesAndCombine"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetPropertiesAndCombine/zh.md)
+
+# ConditioningSetPropertiesAndCombine 节点
+
+ConditioningSetPropertiesAndCombine 节点通过将新条件输入中的属性应用到现有条件输入来修改条件数据。它结合了两个条件集，同时控制新条件的强度并指定条件区域的应用方式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `条件` | CONDITIONING | 必填 | - | - | 待修改的原始条件数据 |
+| `新条件` | CONDITIONING | 必填 | - | - | 提供要应用属性的新条件数据 |
+| `强度` | FLOAT | 必填 | 1.0 | 0.0 - 10.0 | 控制新条件属性的强度 |
+| `设置条件区域` | STRING | 必填 | default | ["default", "mask bounds"] | 决定条件区域的应用方式 |
+| `遮罩` | MASK | 可选 | - | - | 用于定义特定条件区域的可选遮罩 |
+| `约束` | HOOKS | 可选 | - | - | 用于自定义处理的可选钩子函数 |
+| `间隔` | TIMESTEPS_RANGE | 可选 | - | - | 用于控制条件应用时机的可选时间步范围 |
+
+**注意：** 当提供 `mask` 时，`set_cond_area` 参数可以使用 "mask bounds" 将条件应用限制在遮罩区域内。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 具有修改后属性的组合条件数据 |
diff --git a/zh-CN/built-in-nodes/ConditioningSetTimestepRange.mdx b/zh-CN/built-in-nodes/ConditioningSetTimestepRange.mdx
new file mode 100644
index 000000000..d7a88dff4
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningSetTimestepRange.mdx
@@ -0,0 +1,22 @@
+---
+title: "ConditioningSetTimestepRange - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningSetTimestepRange node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningSetTimestepRange"
+icon: "circle"
+mode: wide
+---
+此节点设计用于通过设置特定时间步范围来调整条件的时序方面。它允许对条件过程的起始和结束点进行精确控制，从而实现更有针对性的高效生成。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `条件` | `CONDITIONING` | 条件输入代表生成过程的当前状态，此节点通过设置特定时间步范围来修改它。 |
+| `开始` | `FLOAT` | `开始`参数指定时间步范围的起始点，作为总生成过程的百分比，允许对条件效果开始的时间进行微调控制。 |
+| `结束` | `FLOAT` | `结束`参数定义时间步范围的终点作为百分比，使您能够精确控制条件效果的持续时间和结束。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `条件` | `CONDITIONING` | 输出是应用了指定时间步范围的修改后条件，已准备好进行进一步的处理或生成。 |
diff --git a/zh-CN/built-in-nodes/ConditioningStableAudio.mdx b/zh-CN/built-in-nodes/ConditioningStableAudio.mdx
new file mode 100644
index 000000000..3b0661751
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningStableAudio.mdx
@@ -0,0 +1,28 @@
+---
+title: "ConditioningStableAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningStableAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningStableAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningStableAudio/zh.md)
+
+## 概述
+
+ConditioningStableAudio 节点为音频生成的正负条件输入添加时序信息。它设置开始时间和总时长参数，有助于控制音频内容的生成起始时间和持续时间。该节点通过附加音频特定的时序元数据来修改现有条件数据。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正面条件` | CONDITIONING | 是 | - | 需要添加音频时序信息的正条件输入 |
+| `负面条件` | CONDITIONING | 是 | - | 需要添加音频时序信息的负条件输入 |
+| `开始秒数` | FLOAT | 是 | 0.0 至 1000.0 | 音频生成的起始时间（单位：秒，默认值：0.0） |
+| `总秒数` | FLOAT | 是 | 0.0 至 1000.0 | 音频生成的总时长（单位：秒，默认值：47.0） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 已应用音频时序信息的修改后正条件 |
+| `负面条件` | CONDITIONING | 已应用音频时序信息的修改后负条件 |
diff --git a/zh-CN/built-in-nodes/ConditioningTimestepsRange.mdx b/zh-CN/built-in-nodes/ConditioningTimestepsRange.mdx
new file mode 100644
index 000000000..953811e5e
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningTimestepsRange.mdx
@@ -0,0 +1,25 @@
+---
+title: "ConditioningTimestepsRange - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningTimestepsRange node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningTimestepsRange"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningTimestepsRange/zh.md)
+
+ConditioningTimestepsRange 节点创建三个不同的时间步范围，用于控制在生成过程中应用条件效果的时机。它接收起始和结束百分比值，并将整个时间步范围（0.0 到 1.0）划分为三个区段：指定百分比之间的主范围、起始百分比之前的范围以及结束百分比之后的范围。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `开始百分比` | FLOAT | 是 | 0.0 - 1.0 | 时间步范围的起始百分比（默认值：0.0） |
+| `结束百分比` | FLOAT | 是 | 0.0 - 1.0 | 时间步范围的结束百分比（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `范围前` | TIMESTEPS_RANGE | 由 start_percent 和 end_percent 定义的主时间步范围 |
+| `范围后` | TIMESTEPS_RANGE | 从 0.0 到 start_percent 的时间步范围 |
+| `AFTER_RANGE` | TIMESTEPS_RANGE | 从 end_percent 到 1.0 的时间步范围 |
diff --git a/zh-CN/built-in-nodes/ConditioningZeroOut.mdx b/zh-CN/built-in-nodes/ConditioningZeroOut.mdx
new file mode 100644
index 000000000..9ad9a0e52
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConditioningZeroOut.mdx
@@ -0,0 +1,20 @@
+---
+title: "ConditioningZeroOut - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConditioningZeroOut node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConditioningZeroOut"
+icon: "circle"
+mode: wide
+---
+此节点设计用于将条件数据结构中的特定元素置零，有效中和它们在后续处理步骤中的影响。它适用于需要直接操作条件内部表示的高级条件操作。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `条件` | `CONDITIONING` | 要被修改的条件数据结构。如果存在，此节点将每个条件条目内的'pooled_output'元素置零。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `条件` | `CONDITIONING` | 修改后的条件数据结构，其中适用的'pooled_output'元素已被设置为零。 |
diff --git a/zh-CN/built-in-nodes/ContextWindowsManual.mdx b/zh-CN/built-in-nodes/ContextWindowsManual.mdx
new file mode 100644
index 000000000..3f8344737
--- /dev/null
+++ b/zh-CN/built-in-nodes/ContextWindowsManual.mdx
@@ -0,0 +1,35 @@
+---
+title: "ContextWindowsManual - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ContextWindowsManual node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ContextWindowsManual"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ContextWindowsManual/zh.md)
+
+Context Windows (Manual) 节点允许您在采样过程中手动配置模型的上下文窗口。它通过创建具有指定长度、重叠度和调度模式的重叠上下文片段，将数据处理为可管理的块，同时保持片段之间的连续性。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 在采样过程中应用上下文窗口的模型。 |
+| `context_length` | INT | 否 | 1+ | 上下文窗口的长度（默认值：16）。 |
+| `context_overlap` | INT | 否 | 0+ | 上下文窗口的重叠度（默认值：4）。 |
+| `context_schedule` | COMBO | 否 | `STATIC_STANDARD`<br />`UNIFORM_STANDARD`<br />`UNIFORM_LOOPED`<br />`BATCHED` | 上下文窗口的步进调度模式。 |
+| `context_stride` | INT | 否 | 1+ | 上下文窗口的步长；仅适用于均匀调度模式（默认值：1）。 |
+| `closed_loop` | BOOLEAN | 否 | - | 是否闭合上下文窗口循环；仅适用于循环调度模式（默认值：False）。 |
+| `fuse_method` | COMBO | 否 | `PYRAMID`<br />`LIST_STATIC` | 用于融合上下文窗口的方法（默认值：PYRAMID）。 |
+| `dim` | INT | 否 | 0-5 | 应用上下文窗口的维度（默认值：0）。 |
+
+**参数约束条件：**
+
+- `context_stride` 仅在选择了均匀调度模式时使用
+- `closed_loop` 仅适用于循环调度模式
+- `dim` 必须在 0 到 5 之间（包含边界值）
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 在采样过程中应用了上下文窗口的模型。 |
diff --git a/zh-CN/built-in-nodes/ControlNetApply.mdx b/zh-CN/built-in-nodes/ControlNetApply.mdx
new file mode 100644
index 000000000..d44384e02
--- /dev/null
+++ b/zh-CN/built-in-nodes/ControlNetApply.mdx
@@ -0,0 +1,34 @@
+---
+title: "ControlNetApply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetApply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetApply"
+icon: "circle"
+mode: wide
+---
+目前文档是原来 `Apply ControlNet(Advanced)`节点的说明，最早的 `Apply ControlNet` 节点已被重命名为 `Apply ControlNet(Old)`，但 comfyui.org 为了保证兼容性，在你下载到的许多工作流文件夹里应该还可以看到 `Apply ControlNet(Old)` 节点，但是目前你已经无法通过搜索或者节点列表看到 `Apply ControlNet(Old)` 节点，所以请使用 `Apply ControlNet` 节点。
+
+此节点将 ControlNet 应用于给定的图像和条件，根据控制网络的参数和指定的强度调整图像的属性，比如 Depth、OpenPose、Canny、HED等等。
+
+使用 controlNet 要求对输入图像进行预处理，由于ComfyUI 初始节点不带处理器和 controlNet 模型，所以请先安装ContrlNet预处理器[这里下载与处理器](https://github.com/Fannovel16/comfy_controlnet_preprocessors)和contrlNet 对应的模型。
+
+## Apply ControlNet 输入类型
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `positive` | `CONDITIONING` | 正向条件数据，来自 `CLIP文本编码器`或者其它条件输入|
+| `negative` | `CONDITIONING` | 负向条件数据，来自 `CLIP文本编码器`或者其它条件输入|
+| `ControlNet` | `CONTROL_NET` | 要应用的controlNet模型，通常输入来自 `controlNt加载器` |
+| `图像` | `IMAGE` | 用于 controlNet 应用的图片，需要经过预处理器处理 |
+| `vae` | `VAE` | Vae模型输入|
+| `强度` | `FLOAT` | 用来控制网络调整的强度，取值0～10。建议取值在0.5～1.5之间比较合理，越小则模型会发挥越高的自由度，越大则会被限制得越严格,过高会出现很诡异的画面。你也可以通过自己测试来调整这个值，用来微调控制网络对图像产生的影响。 |
+| `start_percent` | `FLOAT` | 取值 0.000～1.000，确定开始应用controlNet的百分比，比如取值0.2，意味着ControlNet的引导将在扩散过程完成20%时开始影响图像生成|
+| `end_percent` | `FLOAT` | 取值 0.000～1.000，确定结束应用controlNet的百分比，比如取值0.8，意味着ControlNet的引导将在扩散过程完成80%时停止影响图像生成|
+
+## Apply ControlNet 输出类型
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `positive` | `CONDITIONING` | 经过ControlNet 处理后的正向条件数据，可以输出到下一个ControlNet 或者 K采样器等节点 |
+| `negative` | `CONDITIONING` | 经过ControlNet 处理后的负向条件数据，可以输出到下一个ControlNet 或者 K采样器等节点 |
+
+如果要使用**T2IAdaptor样式模型**，请改用`Apply Style Model`节点
diff --git a/zh-CN/built-in-nodes/ControlNetApplyAdvanced.mdx b/zh-CN/built-in-nodes/ControlNetApplyAdvanced.mdx
new file mode 100644
index 000000000..d1e4cc828
--- /dev/null
+++ b/zh-CN/built-in-nodes/ControlNetApplyAdvanced.mdx
@@ -0,0 +1,29 @@
+---
+title: "ControlNetApplyAdvanced - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetApplyAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetApplyAdvanced"
+icon: "circle"
+mode: wide
+---
+这个节点在新的 ComfyUI 版本中已被重命名为 Apply ControlNet 取代了旧版本 Apply ControlNet (OLD) 的名称,由于  原先的Apply ControlNet (OLD) 目前有点类似启用状态，所以关于本节点的最新文档已经调整到 `Apply ControlNet` 来进行说明
+
+此节点基于图像和控制网模型对条件数据应用高级控制网变换。它允许对控制网对生成内容的影响进行微调调整，从而对条件进行更精确和多样化的修改。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `正面条件` | `CONDITIONING` | 将应用控制网变换的正面条件数据。它代表在生成内容中增强或保持的期望属性或特征。 |
+| `负面条件` | `CONDITIONING` | 负面条件数据，代表要从生成内容中减少或移除的属性或特征。控制网变换也应用于这些数据，允许平衡调整内容的特性。 |
+| `ControlNet` | `CONTROL_NET` | 控制网模型对于定义条件数据的具体调整和增强至关重要。它解释参考图像和强度参数以应用变换，通过修改正面和负面条件数据中的属性，显著影响最终输出。 |
+| `图像` | `IMAGE` | 作为控制网变换的参考图像。它影响控制网对条件数据的调整，引导特定特征的增强或抑制。 |
+| `强度` | `FLOAT` | 标量值，确定控制网对条件数据的影响强度。更高的值会导致更显著的调整。 |
+| `开始百分比` | `FLOAT` | 控制网效果的起始百分比，允许在指定范围内逐步应用变换。 |
+| `结束百分比` | `FLOAT` | 控制网效果的结束百分比，定义变换应用的范围。这允许对调整过程进行更微妙的控制。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `负面条件` | `CONDITIONING` | 应用控制网变换后的修改正面条件数据，反映了基于输入参数所做增强。 |
+| `负面条件` | `CONDITIONING` | 应用控制网变换后的修改负面条件数据，反映了基于输入参数对特定特征的抑制或移除。 |
diff --git a/zh-CN/built-in-nodes/ControlNetApplySD3.mdx b/zh-CN/built-in-nodes/ControlNetApplySD3.mdx
new file mode 100644
index 000000000..87f39fecc
--- /dev/null
+++ b/zh-CN/built-in-nodes/ControlNetApplySD3.mdx
@@ -0,0 +1,34 @@
+---
+title: "ControlNetApplySD3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetApplySD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetApplySD3"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetApplySD3/zh.md)
+
+## 概述
+
+该节点将 ControlNet 引导应用于 Stable Diffusion 3 的条件输入。它接收正向和负向条件输入，以及 ControlNet 模型和图像，然后通过可调节的强度和时间参数来应用控制引导，从而影响生成过程。
+
+**注意：** 此节点已被标记为弃用，可能在未来的版本中被移除。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正面条件` | CONDITIONING | 是 | - | 要应用 ControlNet 引导的正向条件输入 |
+| `负面条件` | CONDITIONING | 是 | - | 要应用 ControlNet 引导的负向条件输入 |
+| `ControlNet` | CONTROL_NET | 是 | - | 用于引导的 ControlNet 模型 |
+| `vae` | VAE | 是 | - | 过程中使用的 VAE 模型 |
+| `图像` | IMAGE | 是 | - | ControlNet 将用作引导的输入图像 |
+| `强度` | FLOAT | 是 | 0.0 - 10.0 | ControlNet 效果的强度（默认值：1.0） |
+| `开始百分比` | FLOAT | 是 | 0.0 - 1.0 | ControlNet 开始应用的生成过程起始点（默认值：0.0） |
+| `结束百分比` | FLOAT | 是 | 0.0 - 1.0 | ControlNet 停止应用的生成过程结束点（默认值：1.0） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 应用了 ControlNet 引导的修改后正向条件输入 |
+| `负面条件` | CONDITIONING | 应用了 ControlNet 引导的修改后负向条件输入 |
diff --git a/zh-CN/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx b/zh-CN/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx
new file mode 100644
index 000000000..cccdd1ad8
--- /dev/null
+++ b/zh-CN/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx
@@ -0,0 +1,33 @@
+---
+title: "ControlNetInpaintingAliMamaApply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetInpaintingAliMamaApply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetInpaintingAliMamaApply"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetInpaintingAliMamaApply/zh.md)
+
+ControlNetInpaintingAliMamaApply 节点通过将正向和负向条件与控制图像及蒙版相结合，为修复任务应用 ControlNet 条件处理。该节点会处理输入图像和蒙版，创建经过修改的条件来指导生成过程，从而实现对图像修复区域的精确控制。该节点支持强度调整和时序控制，可在生成过程的不同阶段微调 ControlNet 的影响程度。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `正面条件` | CONDITIONING | 是 | - | 引导生成朝向期望内容的正向条件 |
+| `负面条件` | CONDITIONING | 是 | - | 引导生成远离不需要内容的负向条件 |
+| `ControlNet` | CONTROL_NET | 是 | - | 提供对生成过程额外控制的 ControlNet 模型 |
+| `vae` | VAE | 是 | - | 用于图像编码和解码的变分自编码器 |
+| `图像` | IMAGE | 是 | - | 作为 ControlNet 控制引导的输入图像 |
+| `遮罩` | MASK | 是 | - | 定义图像中哪些区域需要修复的蒙版 |
+| `强度` | FLOAT | 是 | 0.0 到 10.0 | ControlNet 效果的强度（默认值：1.0） |
+| `开始百分比` | FLOAT | 是 | 0.0 到 1.0 | ControlNet 影响在生成过程中开始的时间点（百分比）（默认值：0.0） |
+| `结束百分比` | FLOAT | 是 | 0.0 到 1.0 | ControlNet 影响在生成过程中停止的时间点（百分比）（默认值：1.0） |
+
+**注意：** 当 ControlNet 启用 `concat_mask` 时，蒙版会在处理前进行反转并应用到图像上，同时该蒙版会包含在发送给 ControlNet 的额外拼接数据中。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `负面条件` | CONDITIONING | 应用了 ControlNet 修复功能的修改后正向条件 |
+| `负面条件` | CONDITIONING | 应用了 ControlNet 修复功能的修改后负向条件 |
diff --git a/zh-CN/built-in-nodes/ControlNetLoader.mdx b/zh-CN/built-in-nodes/ControlNetLoader.mdx
new file mode 100644
index 000000000..9546a5db2
--- /dev/null
+++ b/zh-CN/built-in-nodes/ControlNetLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "ControlNetLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ControlNetLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ControlNetLoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/controlnet` 文件夹下的模型，同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+`ControlNetLoader`节点设计用于从指定路径加载一个ControlNet模型。它在初始化ControlNet模型中扮演着至关重要的角色，这些模型对于在生成内容或根据控制信号修改现有内容时应用控制机制是必不可少的。
+
+## 输入
+
+| 字段               | Comfy dtype        | 描述                                                                            |
+|------------------|-------------------|-----------------------------------------------------------------------------------|
+| `ControlNet名称`| `COMBO[STRING]`    | 指定要加载的ControlNet模型的名称，用于在预定义的目录结构中定位模型文件。 |
+
+## 输出
+
+| 字段            | Comfy dtype      | 描述                                                                   |
+|---------------|-----------------|----------------------------------------------------------------------|
+| `control_net` | `CONTROL_NET`   | 返回加载的ControlNet模型，准备用于控制或修改内容生成过程。 |
diff --git a/zh-CN/built-in-nodes/ConvertStringToComboNode.mdx b/zh-CN/built-in-nodes/ConvertStringToComboNode.mdx
new file mode 100644
index 000000000..aa0b8ccde
--- /dev/null
+++ b/zh-CN/built-in-nodes/ConvertStringToComboNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "ConvertStringToComboNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ConvertStringToComboNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ConvertStringToComboNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertStringToComboNode/zh.md)
+
+Convert String to Combo 节点接收一个文本字符串作为输入，并将其转换为 COMBO 数据类型。这允许您将文本值用作其他需要 COMBO 输入的节点的选择项。它只是原封不动地传递字符串值，但会更改其数据类型。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | 是 | N/A | 要转换为 COMBO 类型的文本字符串。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | COMBO | 输入的字符串，现在格式化为 COMBO 数据类型。 |
diff --git a/zh-CN/built-in-nodes/CosmosImageToVideoLatent.mdx b/zh-CN/built-in-nodes/CosmosImageToVideoLatent.mdx
new file mode 100644
index 000000000..9b64cb14b
--- /dev/null
+++ b/zh-CN/built-in-nodes/CosmosImageToVideoLatent.mdx
@@ -0,0 +1,30 @@
+---
+title: "CosmosImageToVideoLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CosmosImageToVideoLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CosmosImageToVideoLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CosmosImageToVideoLatent/zh.md)
+
+CosmosImageToVideoLatent 节点可从输入图像创建视频潜空间表示。它会生成一个空白视频潜空间，并可选地将起始图像和/或结束图像编码到视频序列的开端和/或末尾帧。当提供图像时，它还会创建相应的噪声掩码，以指示在生成过程中应保留潜空间的哪些部分。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `vae` | VAE | 是 | - | 用于将图像编码到潜空间的 VAE 模型 |
+| `宽度` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频的宽度（像素）（默认值：1280） |
+| `高度` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频的高度（像素）（默认值：704） |
+| `长度` | INT | 否 | 1 至 MAX_RESOLUTION | 视频序列的帧数（默认值：121） |
+| `批量大小` | INT | 否 | 1 至 4096 | 要生成的潜空间批次数量（默认值：1） |
+| `开始图像` | IMAGE | 否 | - | 可选，在视频序列开头编码的图像 |
+| `结束图像` | IMAGE | 否 | - | 可选，在视频序列末尾编码的图像 |
+
+**注意：** 当既未提供 `start_image` 也未提供 `end_image` 时，节点将返回一个空白潜空间且不带任何噪声掩码。当提供任一图像时，潜空间的相应部分会被编码并生成对应的掩码。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `latent` | LATENT | 生成的视频潜空间表示，包含可选的编码图像及相应的噪声掩码 |
diff --git a/zh-CN/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx b/zh-CN/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx
new file mode 100644
index 000000000..da957358f
--- /dev/null
+++ b/zh-CN/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx
@@ -0,0 +1,31 @@
+---
+title: "CosmosPredict2ImageToVideoLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CosmosPredict2ImageToVideoLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CosmosPredict2ImageToVideoLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CosmosPredict2ImageToVideoLatent/zh.md)
+
+CosmosPredict2ImageToVideoLatent 节点可从图像创建视频潜在表示以用于视频生成。它能够生成空白视频潜在表示，或结合起始和结束图像来创建具有指定尺寸和时长的视频序列。该节点负责将图像编码为适用于视频处理的潜在空间格式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `vae` | VAE | 是 | - | 用于将图像编码到潜在空间的 VAE 模型 |
+| `width` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频的宽度（单位：像素，默认值：848，必须能被 16 整除） |
+| `height` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频的高度（单位：像素，默认值：480，必须能被 16 整除） |
+| `length` | INT | 否 | 1 至 MAX_RESOLUTION | 视频序列的帧数（默认值：93，步长：4） |
+| `batch_size` | INT | 否 | 1 至 4096 | 要生成的视频序列数量（默认值：1） |
+| `start_image` | IMAGE | 否 | - | 视频序列的可选起始图像 |
+| `end_image` | IMAGE | 否 | - | 视频序列的可选结束图像 |
+
+**注意：** 当未提供 `start_image` 和 `end_image` 时，节点将生成空白视频潜在表示。当提供图像时，它们会被编码并放置在视频序列的起始和/或结束位置，并应用相应的遮罩。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `samples` | LATENT | 生成的视频潜在表示，包含编码后的视频序列 |
+| `noise_mask` | LATENT | 指示在生成过程中应保留潜在表示哪些部分的遮罩 |
diff --git a/zh-CN/built-in-nodes/CreateHookKeyframe.mdx b/zh-CN/built-in-nodes/CreateHookKeyframe.mdx
new file mode 100644
index 000000000..53d02cb11
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateHookKeyframe.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateHookKeyframe - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookKeyframe node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookKeyframe"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframe/zh.md)
+
+Create Hook Keyframe 节点允许您在生成过程中定义钩子行为发生变化的具体时间点。它会创建关键帧，在生成进度的特定百分比处修改钩子的强度，这些关键帧可以链接在一起以创建复杂的调度模式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `强度倍数` | FLOAT | 是 | -20.0 到 20.0 | 此关键帧处钩子强度的乘数（默认值：1.0） |
+| `开始百分比` | FLOAT | 是 | 0.0 到 1.0 | 生成过程中此关键帧生效的百分比点（默认值：0.0） |
+| `前一个约束关键帧` | HOOK_KEYFRAMES | 否 | - | 可选的先前钩子关键帧组，用于将当前关键帧添加到该组中 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `HOOK_KF` | HOOK_KEYFRAMES | 包含新创建关键帧的一组钩子关键帧 |
diff --git a/zh-CN/built-in-nodes/CreateHookKeyframesFromFloats.mdx b/zh-CN/built-in-nodes/CreateHookKeyframesFromFloats.mdx
new file mode 100644
index 000000000..0ee2d223c
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateHookKeyframesFromFloats.mdx
@@ -0,0 +1,28 @@
+---
+title: "CreateHookKeyframesFromFloats - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookKeyframesFromFloats node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookKeyframesFromFloats"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesFromFloats/zh.md)
+
+该节点根据一系列浮点数强度值创建钩子关键帧，并将这些关键帧均匀分布在指定的起始百分比和结束百分比之间。它会生成一个关键帧序列，其中每个强度值都被分配到动画时间轴中的特定百分比位置。该节点可以创建新的关键帧组，也可以添加到现有的关键帧组中，并提供了一个选项用于打印生成的关键帧以便调试。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `浮点强度` | FLOATS | 是 | -1 到 ∞ | 表示关键帧强度值的单个浮点数或浮点数列表（默认值：-1） |
+| `开始百分比` | FLOAT | 是 | 0.0 到 1.0 | 时间轴中第一个关键帧的起始百分比位置（默认值：0.0） |
+| `结束百分比` | FLOAT | 是 | 0.0 到 1.0 | 时间轴中最后一个关键帧的结束百分比位置（默认值：1.0） |
+| `打印关键帧` | BOOLEAN | 是 | True/False | 启用时，将生成的关键帧信息打印到控制台（默认值：False） |
+| `前一个约束关键帧` | HOOK_KEYFRAMES | 否 | - | 要添加新关键帧的现有钩子关键帧组，如未提供则创建新组 |
+
+**注意：** `floats_strength` 参数接受单个浮点数或可迭代的浮点数列表。关键帧会根据提供的强度值数量，在 `start_percent` 和 `end_percent` 之间线性分布。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `HOOK_KF` | HOOK_KEYFRAMES | 包含新创建关键帧的钩子关键帧组，可以是新组或附加到输入关键帧组的组 |
diff --git a/zh-CN/built-in-nodes/CreateHookKeyframesInterpolated.mdx b/zh-CN/built-in-nodes/CreateHookKeyframesInterpolated.mdx
new file mode 100644
index 000000000..9bb91512d
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateHookKeyframesInterpolated.mdx
@@ -0,0 +1,29 @@
+---
+title: "CreateHookKeyframesInterpolated - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookKeyframesInterpolated node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookKeyframesInterpolated"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesInterpolated/zh.md)
+
+创建一个包含起始点和结束点之间插值强度值的钩子关键帧序列。该节点生成多个关键帧，在生成过程的指定百分比范围内平滑过渡强度参数，使用各种插值方法来控制过渡曲线。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `开始强度` | FLOAT | 是 | 0.0 - 10.0 | 插值序列的起始强度值（默认：1.0） |
+| `结束强度` | FLOAT | 是 | 0.0 - 10.0 | 插值序列的结束强度值（默认：1.0） |
+| `插值` | COMBO | 是 | 多个选项可用 | 用于在强度值之间过渡的插值方法 |
+| `开始百分比` | FLOAT | 是 | 0.0 - 1.0 | 生成过程中的起始百分比位置（默认：0.0） |
+| `结束百分比` | FLOAT | 是 | 0.0 - 1.0 | 生成过程中的结束百分比位置（默认：1.0） |
+| `关键帧数量` | INT | 是 | 2 - 100 | 插值序列中要生成的关键帧数量（默认：5） |
+| `打印关键帧` | BOOLEAN | 是 | True/False | 是否将生成的关键帧信息打印到日志中（默认：False） |
+| `前一个约束关键帧` | HOOK_KEYFRAMES | 否 | - | 可选的先前钩子关键帧组，用于追加到其中 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `HOOK_KF` | HOOK_KEYFRAMES | 包含插值序列的生成钩子关键帧组 |
diff --git a/zh-CN/built-in-nodes/CreateHookLora.mdx b/zh-CN/built-in-nodes/CreateHookLora.mdx
new file mode 100644
index 000000000..be7d4b7eb
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateHookLora.mdx
@@ -0,0 +1,30 @@
+---
+title: "CreateHookLora - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookLora node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookLora"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookLora/zh.md)
+
+Create Hook LoRA 节点用于生成钩子对象，以便对模型应用 LoRA（低秩自适应）修改。它会加载指定的 LoRA 文件并创建可调整模型和 CLIP 强度的钩子，然后将这些钩子与传入的任何现有钩子进行组合。该节点通过缓存先前加载的 LoRA 文件来避免重复操作，从而高效管理 LoRA 加载流程。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|--------|-----------|------|----------|------|
+| `LoRA名称` | STRING | 是 | 支持多选项 | 从 loras 目录加载的 LoRA 文件名 |
+| `模型强度` | FLOAT | 是 | -20.0 至 20.0 | 模型调整的强度乘数（默认值：1.0） |
+| `CLIP强度` | FLOAT | 是 | -20.0 至 20.0 | CLIP 调整的强度乘数（默认值：1.0） |
+| `前一个约束` | HOOKS | 否 | 不适用 | 可选的现有钩子组，将与新创建的 LoRA 钩子组合 |
+
+**参数约束：**
+
+- 当 `strength_model` 和 `strength_clip` 同时设置为 0 时，节点将跳过创建新 LoRA 钩子并直接返回现有钩子
+- 节点会缓存最后加载的 LoRA 文件，在重复使用相同 LoRA 时优化性能
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `HOOKS` | HOOKS | 包含组合后的 LoRA 钩子及原有钩子的钩子组 |
diff --git a/zh-CN/built-in-nodes/CreateHookLoraModelOnly.mdx b/zh-CN/built-in-nodes/CreateHookLoraModelOnly.mdx
new file mode 100644
index 000000000..f71746ec3
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateHookLoraModelOnly.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateHookLoraModelOnly - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookLoraModelOnly node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookLoraModelOnly"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookLoraModelOnly/zh.md)
+
+此节点创建一个仅应用于模型组件的 LoRA（低秩适应）钩子，允许您修改模型行为而不影响 CLIP 组件。它会加载一个 LoRA 文件，并以指定的强度应用于模型，同时保持 CLIP 组件不变。该节点可以与先前的钩子链接，以创建复杂的修改流水线。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `LoRA名称` | STRING | 是 | 提供多个选项 | 要从 loras 文件夹加载的 LoRA 文件名 |
+| `模型强度` | FLOAT | 是 | -20.0 到 20.0 | 将 LoRA 应用于模型组件的强度乘数（默认值：1.0） |
+| `前一个约束` | HOOKS | 否 | - | 可选的先前钩子，用于与此钩子链接 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `hooks` | HOOKS | 创建的 LoRA 钩子，可应用于模型处理 |
diff --git a/zh-CN/built-in-nodes/CreateHookModelAsLora.mdx b/zh-CN/built-in-nodes/CreateHookModelAsLora.mdx
new file mode 100644
index 000000000..0a70c2b70
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateHookModelAsLora.mdx
@@ -0,0 +1,34 @@
+---
+title: "CreateHookModelAsLora - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookModelAsLora node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookModelAsLora"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookModelAsLora/zh.md)
+
+> 本文档由 AI 生成，如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookModelAsLora/en.md)
+
+此节点通过加载检查点权重并对模型和 CLIP 组件应用强度调整，创建一个作为 LoRA（低秩自适应）的钩子模型。它允许您通过基于钩子的方法对现有模型应用 LoRA 风格的修改，实现微调和自适应而无需永久更改模型。该节点可以与之前的钩子组合使用，并缓存已加载的权重以提高效率。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|------|-----------|------|------|-------------|
+| `Checkpoint名称` | COMBO | 是 | 多个可用选项 | 用于加载权重的检查点文件（从可用检查点中选择） |
+| `模型强度` | FLOAT | 是 | -20.0 到 20.0 | 应用于模型权重的强度乘数（默认：1.0） |
+| `CLIP强度` | FLOAT | 是 | -20.0 到 20.0 | 应用于 CLIP 权重的强度乘数（默认：1.0） |
+| `前一个约束` | HOOKS | 否 | - | 可选的先前钩子，用于与新创建的 LoRA 钩子组合 |
+
+**参数约束：**
+
+- `ckpt_name` 参数从可用检查点文件夹加载检查点
+- 两个强度参数接受从 -20.0 到 20.0 的值，步长为 0.01
+- 当未提供 `prev_hooks` 时，节点会创建新的钩子组
+- 节点会缓存已加载的权重，避免多次重新加载同一检查点
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `HOOKS` | HOOKS | 创建的 LoRA 钩子，如果提供了先前钩子则会与之组合 |
diff --git a/zh-CN/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx b/zh-CN/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx
new file mode 100644
index 000000000..cbc124afc
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateHookModelAsLoraModelOnly - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateHookModelAsLoraModelOnly node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateHookModelAsLoraModelOnly"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookModelAsLoraModelOnly/zh.md)
+
+此节点创建一个钩子，用于应用 LoRA（低秩适应）模型来仅修改神经网络的模型组件。它会加载一个检查点文件，并以指定的强度应用于模型，同时保持 CLIP 组件不变。这是一个实验性节点，扩展了基础 CreateHookModelAsLora 类的功能。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Checkpoint名称` | STRING | 是 | 提供多个选项 | 要作为 LoRA 模型加载的检查点文件。可用选项取决于 checkpoints 文件夹中的内容。 |
+| `模型强度` | FLOAT | 是 | -20.0 至 20.0 | 将 LoRA 应用于模型组件的强度乘数（默认值：1.0） |
+| `前一个约束` | HOOKS | 否 | - | 可选的先前钩子，用于与此钩子链接 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `hooks` | HOOKS | 创建的钩子组，包含 LoRA 模型修改 |
diff --git a/zh-CN/built-in-nodes/CreateList.mdx b/zh-CN/built-in-nodes/CreateList.mdx
new file mode 100644
index 000000000..8d3f3a900
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateList.mdx
@@ -0,0 +1,24 @@
+---
+title: "CreateList - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateList node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateList"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateList/zh.md)
+
+此节点将多个输入合并为一个顺序列表。它接收任意数量的相同数据类型输入，并按连接顺序将它们串联起来。该节点适用于准备批量数据（如图像或文本），以便在工作流中被其他节点处理。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `input_*` | 可变 | 是 | 任意 | 可变数量的输入槽。可通过点击加号 (+) 图标添加更多输入。所有输入必须为相同数据类型（例如，全部为 IMAGE 或全部为 STRING）。 |
+
+**注意：** 当您连接项目时，节点将自动创建新的输入槽。所有已连接的输入必须共享相同的数据类型，节点才能正常工作。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `list` | 可变 | 一个包含所有连接输入项的单一列表，按提供顺序串联。输出数据类型与输入数据类型匹配。 |
diff --git a/zh-CN/built-in-nodes/CreateVideo.mdx b/zh-CN/built-in-nodes/CreateVideo.mdx
new file mode 100644
index 000000000..b2fc48cd8
--- /dev/null
+++ b/zh-CN/built-in-nodes/CreateVideo.mdx
@@ -0,0 +1,26 @@
+---
+title: "CreateVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CreateVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CreateVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateVideo/zh.md)
+
+## 概述
+
+Create Video 节点能够将一系列图像合成为视频文件。您可以通过设置帧率参数来指定视频播放速度，并可选地为视频添加音频轨道。该节点会将输入的图像序列按照指定帧率合成为可播放的视频格式。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 用于生成视频的输入图像序列 |
+| `帧率` | FLOAT | 是 | 1.0 - 120.0 | 视频播放的帧率参数（默认值：30.0） |
+| `音频` | AUDIO | 否 | - | 可为视频添加的音频轨道 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件，包含输入图像序列及可选的音频轨道 |
diff --git a/zh-CN/built-in-nodes/CropMask.mdx b/zh-CN/built-in-nodes/CropMask.mdx
new file mode 100644
index 000000000..325685074
--- /dev/null
+++ b/zh-CN/built-in-nodes/CropMask.mdx
@@ -0,0 +1,24 @@
+---
+title: "CropMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CropMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CropMask"
+icon: "circle"
+mode: wide
+---
+裁剪遮罩节点用于从给定的遮罩中裁剪出指定的区域。它允许用户通过指定坐标和尺寸来定义感兴趣区域，有效地提取遮罩的一部分以进行进一步的处理或分析。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `遮罩` | MASK | 遮罩输入，代表要裁剪的遮罩图像。它对于根据指定的坐标和尺寸定义要提取的区域至关重要。 |
+| `x` | INT | x坐标指定水平轴上裁剪应开始的起始点。 |
+| `y` | INT | y坐标确定裁剪操作在垂直轴上的起始点。 |
+| `宽度` | INT | 宽度定义从起始点开始裁剪区域的水平范围。 |
+| `高度` | INT | 高度指定从起始点开始裁剪区域的垂直范围。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `遮罩` | MASK | 输出是裁剪后的遮罩，它是根据指定的坐标和尺寸定义的原始遮罩的一部分。 |
diff --git a/zh-CN/built-in-nodes/CustomCombo.mdx b/zh-CN/built-in-nodes/CustomCombo.mdx
new file mode 100644
index 000000000..a34e9fae8
--- /dev/null
+++ b/zh-CN/built-in-nodes/CustomCombo.mdx
@@ -0,0 +1,24 @@
+---
+title: "CustomCombo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the CustomCombo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "CustomCombo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CustomCombo/zh.md)
+
+Custom Combo 节点允许您创建一个包含自定义文本选项列表的下拉菜单。这是一个侧重于前端的节点，它提供了一个后端表示形式，以确保在您的工作流中的兼容性。当您从下拉菜单中选择一个选项时，该节点会将该文本作为字符串输出。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `choice` | COMBO | 是 | 用户自定义 | 从自定义下拉菜单中选择的文本选项。可用选项列表由用户在节点的前端界面中定义。 |
+
+**注意：** 此节点输入的验证功能被有意禁用。这允许您在前端定义任何您想要的自定义文本选项，而无需后端检查您的选择是否来自预定义的列表。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 从自定义组合框中选择的选项的文本字符串。 |
diff --git a/zh-CN/built-in-nodes/DCTestNode.mdx b/zh-CN/built-in-nodes/DCTestNode.mdx
new file mode 100644
index 000000000..e8c41219e
--- /dev/null
+++ b/zh-CN/built-in-nodes/DCTestNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "DCTestNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DCTestNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DCTestNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DCTestNode/zh.md)
+
+DCTestNode 是一个逻辑节点，根据用户从动态组合框中的选择返回不同类型的数据。它充当条件路由器，所选选项决定了哪个输入字段处于活动状态以及节点将输出何种类型的值。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `combo` | COMBO | 是 | `"option1"`<br />`"option2"`<br />`"option3"`<br />`"option4"` | 主要选择项，决定哪个输入字段处于活动状态以及节点将输出什么。 |
+| `string` | STRING | 否 | - | 文本输入字段。仅当 `combo` 设置为 `"option1"` 时，此字段才处于活动状态且为必填项。 |
+| `integer` | INT | 否 | - | 整数输入字段。仅当 `combo` 设置为 `"option2"` 时，此字段才处于活动状态且为必填项。 |
+| `image` | IMAGE | 否 | - | 图像输入字段。仅当 `combo` 设置为 `"option3"` 时，此字段才处于活动状态且为必填项。 |
+| `subcombo` | COMBO | 否 | `"opt1"`<br />`"opt2"` | 当 `combo` 设置为 `"option4"` 时出现的次级选择项。它决定哪些嵌套输入字段处于活动状态。 |
+| `float_x` | FLOAT | 否 | - | 小数输入。仅当 `combo` 设置为 `"option4"` 且 `subcombo` 设置为 `"opt1"` 时，此字段才处于活动状态且为必填项。 |
+| `float_y` | FLOAT | 否 | - | 小数输入。仅当 `combo` 设置为 `"option4"` 且 `subcombo` 设置为 `"opt1"` 时，此字段才处于活动状态且为必填项。 |
+| `mask1` | MASK | 否 | - | 遮罩输入字段。仅当 `combo` 设置为 `"option4"` 且 `subcombo` 设置为 `"opt2"` 时，此字段才处于活动状态。它是可选的。 |
+
+**参数约束：**
+
+* `combo` 参数控制所有其他输入字段的可见性和必填性。只有与所选 `combo` 选项关联的输入才会显示，并且是必填的（`mask1` 除外，它是可选的）。
+* 当 `combo` 设置为 `"option4"` 时，`subcombo` 参数变为必填项，并控制第二组嵌套输入（`float_x`/`float_y` 或 `mask1`）。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | ANYTYPE | 输出取决于所选的 `combo` 选项。它可以是 STRING（`"option1"`）、INT（`"option2"`）、IMAGE（`"option3"`）或 `subcombo` 字典的字符串表示形式（`"option4"`）。 |
diff --git a/zh-CN/built-in-nodes/DeprecatedCheckpointLoader.mdx b/zh-CN/built-in-nodes/DeprecatedCheckpointLoader.mdx
new file mode 100644
index 000000000..6b32297eb
--- /dev/null
+++ b/zh-CN/built-in-nodes/DeprecatedCheckpointLoader.mdx
@@ -0,0 +1,23 @@
+---
+title: "DeprecatedCheckpointLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DeprecatedCheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DeprecatedCheckpointLoader"
+icon: "circle"
+mode: wide
+---
+CheckpointLoader 节点旨在进行高级加载操作，特别是加载模型检查点及其配置。它方便检索初始化和运行生成模型所需的模型组件，包括来自指定目录的配置和检查点。
+
+## 输入
+
+| 参数名称     | 数据类型 | 描述                                                         |
+| ------------ | -------- | ------------------------------------------------------------ |
+| `config_name` | COMBO[STRING] | 指定要使用的配置文件的名称。这对于确定模型的参数和设置至关重要，会影响模型的行为和性能。 |
+| `ckpt_name`  | COMBO[STRING] | 指示要加载的检查点文件的名称。这直接影响初始化的模型状态，影响其初始权重和偏差。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 描述                                       |
+| -------- | -------- | ------------------------------------------ |
+| `model`  | MODEL    | 表示从检查点加载的主要模型，准备进行进一步操作或推理。 |
+| `clip`   | CLIP     | 如果可用并被请求，提供从检查点加载的 CLIP 模型组件。 |
+| `vae`    | VAE      | 如果可用并被请求，提供从检查点加载的 VAE 模型组件。 |
diff --git a/zh-CN/built-in-nodes/DeprecatedDiffusersLoader.mdx b/zh-CN/built-in-nodes/DeprecatedDiffusersLoader.mdx
new file mode 100644
index 000000000..8760708d7
--- /dev/null
+++ b/zh-CN/built-in-nodes/DeprecatedDiffusersLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "DeprecatedDiffusersLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DeprecatedDiffusersLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DeprecatedDiffusersLoader"
+icon: "circle"
+mode: wide
+---
+DiffusersLoader 节点旨在从 diffusers 库加载模型，特别处理基于提供的模型路径加载 UNet、CLIP 和 VAE 模型。它促进了这些模型与 ComfyUI 框架的集成，使得能够实现文本到图像生成、图像操作等高级功能。
+
+## 输入
+
+| 参数名称 | 数据类型 | 描述                                                         |
+| -------- | -------- | ------------------------------------------------------------ |
+| `model_path` | COMBO[STRING] | 指定要加载的模型的路径。该路径至关重要，因为它决定了后续操作将使用哪个模型，影响节点的输出和功能。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 描述                                       |
+| -------- | -------- | ------------------------------------------ |
+| `model`  | MODEL    | 加载的 UNet 模型，是输出元组的一部分。此模型对于 ComfyUI 框架内的图像合成和操作任务至关重要。 |
+| `clip`   | CLIP     | 加载的 CLIP 模型，如果被请求则包含在输出元组中。此模型能够实现高级文本和图像理解及操作功能。 |
+| `vae`    | VAE      | 加载的 VAE 模型，如果被请求则包含在输出元组中。此模型对于涉及潜在空间操作和图像生成的任务至关重要。 |
diff --git a/zh-CN/built-in-nodes/DiffControlNetLoader.mdx b/zh-CN/built-in-nodes/DiffControlNetLoader.mdx
new file mode 100644
index 000000000..db2e906a3
--- /dev/null
+++ b/zh-CN/built-in-nodes/DiffControlNetLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "DiffControlNetLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DiffControlNetLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DiffControlNetLoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/controlnet` 文件夹下的模型，
+同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，
+有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+控制网络加载节点旨在从指定路径加载一个ControlNet模型。它在初始化ControlNet模型中扮演着关键角色，这些模型对于在生成内容上应用控制机制或基于控制信号修改现有内容至关重要。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `ControlNet名称` | COMBO[STRING] | 指定要加载的ControlNet模型的名称。此名称用于在预定义的目录结构中定位模型文件。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `control_net` | CONTROL_NET | 返回加载的ControlNet模型，准备用于控制或修改内容生成过程。 |
+
+---
diff --git a/zh-CN/built-in-nodes/DifferentialDiffusion.mdx b/zh-CN/built-in-nodes/DifferentialDiffusion.mdx
new file mode 100644
index 000000000..f97daa7ec
--- /dev/null
+++ b/zh-CN/built-in-nodes/DifferentialDiffusion.mdx
@@ -0,0 +1,25 @@
+---
+title: "DifferentialDiffusion - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DifferentialDiffusion node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DifferentialDiffusion"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DifferentialDiffusion/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DifferentialDiffusion/en.md)
+
+Differential Diffusion 节点通过基于时间步阈值应用二值掩码来修改去噪过程。它会创建一个在原始去噪掩码和基于阈值的二值掩码之间进行混合的掩码，从而允许对扩散过程强度进行受控调整。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要修改的扩散模型 |
+| `strength` | FLOAT | 否 | 0.0 - 1.0 | 控制原始去噪掩码与二值阈值掩码之间的混合强度（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 带有更新后去噪掩码函数的修改版扩散模型 |
diff --git a/zh-CN/built-in-nodes/DiffusersLoader.mdx b/zh-CN/built-in-nodes/DiffusersLoader.mdx
new file mode 100644
index 000000000..b28b1975e
--- /dev/null
+++ b/zh-CN/built-in-nodes/DiffusersLoader.mdx
@@ -0,0 +1,24 @@
+---
+title: "DiffusersLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DiffusersLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DiffusersLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DiffusersLoader/zh.md)
+
+DiffusersLoader 节点从 diffusers 格式加载预训练模型。它会搜索包含 model_index.json 文件的有效 diffusers 模型目录，并将其加载为 MODEL、CLIP 和 VAE 组件以供流程使用。此节点属于已弃用的加载器类别，提供与 Hugging Face diffusers 模型的兼容性。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型路径` | STRING | 是 | 提供多个选项<br />（自动从 diffusers 文件夹填充） | 要加载的 diffusers 模型目录路径。该节点会自动扫描配置的 diffusers 文件夹中的有效 diffusers 模型，并列出可用选项。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | 从 diffusers 格式加载的模型组件 |
+| `CLIP` | CLIP | 从 diffusers 格式加载的 CLIP 模型组件 |
+| `VAE` | VAE | 从 diffusers 格式加载的 VAE（变分自编码器）组件 |
diff --git a/zh-CN/built-in-nodes/DisableNoise.mdx b/zh-CN/built-in-nodes/DisableNoise.mdx
new file mode 100644
index 000000000..4a2c5a6b0
--- /dev/null
+++ b/zh-CN/built-in-nodes/DisableNoise.mdx
@@ -0,0 +1,22 @@
+---
+title: "DisableNoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DisableNoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DisableNoise"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DisableNoise/zh.md)
+
+DisableNoise 节点提供了一个空的噪声配置，可用于在采样过程中禁用噪声生成。它返回一个不包含任何噪声数据的特殊噪声对象，当其他节点连接到此输出时，可以跳过与噪声相关的操作。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| *无输入参数* | - | - | - | 此节点不需要任何输入参数。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `NOISE` | NOISE | 返回一个空的噪声配置，可用于在采样过程中禁用噪声生成。 |
diff --git a/zh-CN/built-in-nodes/DualCFGGuider.mdx b/zh-CN/built-in-nodes/DualCFGGuider.mdx
new file mode 100644
index 000000000..8e2f337af
--- /dev/null
+++ b/zh-CN/built-in-nodes/DualCFGGuider.mdx
@@ -0,0 +1,28 @@
+---
+title: "DualCFGGuider - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DualCFGGuider node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DualCFGGuider"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DualCFGGuider/zh.md)
+
+DualCFGGuider 节点为双分类器自由引导采样创建了一个引导系统。它将两个正向条件输入与一个负向条件输入相结合，对每个条件对应用不同的引导尺度，以控制每个提示词对生成输出的影响程度。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 用于引导的模型 |
+| `条件1` | CONDITIONING | 是 | - | 第一个正向条件输入 |
+| `条件2` | CONDITIONING | 是 | - | 第二个正向条件输入 |
+| `负面条件` | CONDITIONING | 是 | - | 负向条件输入 |
+| `cfg_条件1` | FLOAT | 是 | 0.0 - 100.0 | 第一个正向条件的引导尺度（默认值：8.0） |
+| `cfg_条件2_负面` | FLOAT | 是 | 0.0 - 100.0 | 第二个正向和负向条件的引导尺度（默认值：8.0） |
+| `style` | COMBO | 是 | "regular"<br />"nested" | 要应用的引导样式（默认值："regular"） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `GUIDER` | GUIDER | 已配置的引导系统，准备用于采样 |
diff --git a/zh-CN/built-in-nodes/DualCLIPLoader.mdx b/zh-CN/built-in-nodes/DualCLIPLoader.mdx
new file mode 100644
index 000000000..045f9568b
--- /dev/null
+++ b/zh-CN/built-in-nodes/DualCLIPLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "DualCLIPLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the DualCLIPLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "DualCLIPLoader"
+icon: "circle"
+mode: wide
+---
+DualCLIPLoader 节点旨在同时加载两个 CLIP 模型，便于执行需要整合或比较这两个模型特征的操作。
+
+该节点会自动检测位于 `ComfyUI/models/text_encoders` 文件夹中的模型。
+
+## 输入
+
+| 参数名称      | 数据类型          | 作用                                                         |
+| ------------ | --------------- | ------------------------------------------------------------ |
+| `CLIP名称1` | COMBO[STRING] | 指定要加载的第一个 CLIP 模型的名称。此参数对于从预定义的可用 CLIP 模型列表中识别和检索正确的模型至关重要。 |
+| `CLIP名称2` | COMBO[STRING] | 指定要加载的第二个 CLIP 模型的名称。此参数允许加载第二个不同的 CLIP 模型，以便与第一个模型一起进行比较或整合分析。 |
+| `类型`       | `选项`           |  从"sdxl", "sd3", "flux"中选择一个，用来适应不同模型下的工作流 |
+
+* 加载的顺序不会影响输出效果
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                       |
+| -------- | -------- | ------------------------------------------ |
+| `clip`   | CLIP     | 输出是一个整合了两个指定 CLIP 模型特征或功能的组合 CLIP 模型。 |
diff --git a/zh-CN/built-in-nodes/EasyCache.mdx b/zh-CN/built-in-nodes/EasyCache.mdx
new file mode 100644
index 000000000..2802c312c
--- /dev/null
+++ b/zh-CN/built-in-nodes/EasyCache.mdx
@@ -0,0 +1,26 @@
+---
+title: "EasyCache - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EasyCache node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EasyCache"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EasyCache/zh.md)
+
+EasyCache 节点为模型实现了原生缓存系统，通过在采样过程中复用先前计算过的步骤来提升性能。该节点可为模型添加 EasyCache 功能，并支持配置在采样时间线中开始和停止使用缓存的阈值。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要添加 EasyCache 功能的模型。 |
+| `reuse_threshold` | FLOAT | 否 | 0.0 - 3.0 | 复用缓存步骤的阈值（默认值：0.2）。 |
+| `start_percent` | FLOAT | 否 | 0.0 - 1.0 | 开始使用 EasyCache 的相对采样步数（默认值：0.15）。 |
+| `end_percent` | FLOAT | 否 | 0.0 - 1.0 | 停止使用 EasyCache 的相对采样步数（默认值：0.95）。 |
+| `verbose` | BOOLEAN | 否 | - | 是否输出详细日志信息（默认值：False）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 已添加 EasyCache 功能的模型。 |
diff --git a/zh-CN/built-in-nodes/ElevenLabsAudioIsolation.mdx b/zh-CN/built-in-nodes/ElevenLabsAudioIsolation.mdx
new file mode 100644
index 000000000..27592cd1c
--- /dev/null
+++ b/zh-CN/built-in-nodes/ElevenLabsAudioIsolation.mdx
@@ -0,0 +1,22 @@
+---
+title: "ElevenLabsAudioIsolation - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsAudioIsolation node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsAudioIsolation"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsAudioIsolation/zh.md)
+
+此节点可从音频文件中去除背景噪音，实现人声或语音的分离。它会将音频发送至 ElevenLabs API 进行处理，并返回降噪后的音频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | 是 | | 需要进行背景噪音去除处理的音频。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 经过处理、已去除背景噪音的音频。 |
diff --git a/zh-CN/built-in-nodes/ElevenLabsInstantVoiceClone.mdx b/zh-CN/built-in-nodes/ElevenLabsInstantVoiceClone.mdx
new file mode 100644
index 000000000..b190cb8c1
--- /dev/null
+++ b/zh-CN/built-in-nodes/ElevenLabsInstantVoiceClone.mdx
@@ -0,0 +1,25 @@
+---
+title: "ElevenLabsInstantVoiceClone - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsInstantVoiceClone node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsInstantVoiceClone"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsInstantVoiceClone/zh.md)
+
+ElevenLabs Instant Voice Clone 节点通过分析 1 到 8 段人声录音来创建一个新的、独特的语音模型。它会将这些样本发送到 ElevenLabs API，API 将处理这些样本以生成可用于文本转语音合成的语音克隆。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio_*` | AUDIO | 是 | 1 到 8 个文件 | 用于语音克隆的音频录音。您必须提供 1 到 8 个音频文件。 |
+| `remove_background_noise` | BOOLEAN | 否 | True / False | 使用音频隔离技术从语音样本中去除背景噪音。（默认值：False） |
+
+**注意：** 您必须提供至少一个音频文件，最多可提供八个。节点将根据您添加的音频文件自动创建输入槽。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `voice` | ELEVENLABS_VOICE | 新创建的克隆语音模型的唯一标识符。此输出可以连接到其他 ElevenLabs 文本转语音节点。 |
diff --git a/zh-CN/built-in-nodes/ElevenLabsSpeechToSpeech.mdx b/zh-CN/built-in-nodes/ElevenLabsSpeechToSpeech.mdx
new file mode 100644
index 000000000..877091271
--- /dev/null
+++ b/zh-CN/built-in-nodes/ElevenLabsSpeechToSpeech.mdx
@@ -0,0 +1,28 @@
+---
+title: "ElevenLabsSpeechToSpeech - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsSpeechToSpeech node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsSpeechToSpeech"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToSpeech/zh.md)
+
+ElevenLabs 语音转语音节点可将输入的音频文件从一种声音转换为另一种声音。它利用 ElevenLabs API 进行语音转换，同时保留音频的原始内容和情感基调。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `voice` | CUSTOM | 是 | - | 转换的目标声音。请从 Voice Selector 或 Instant Voice Clone 节点连接。 |
+| `audio` | AUDIO | 是 | - | 待转换的源音频。 |
+| `stability` | FLOAT | 否 | 0.0 - 1.0 | 语音稳定性。较低的值提供更广的情感范围，较高的值产生更一致但可能单调的语音（默认值：0.5）。 |
+| `model` | DYNAMICCOMBO | 否 | `eleven_multilingual_sts_v2`<br />`eleven_english_sts_v2` | 用于语音转语音转换的模型。每个选项提供一组特定的语音设置（similarity_boost、style、use_speaker_boost、speed）。 |
+| `output_format` | COMBO | 否 | `"mp3_44100_192"`<br />`"opus_48000_192"` | 音频输出格式（默认值："mp3_44100_192"）。 |
+| `seed` | INT | 否 | 0 - 4294967295 | 用于确保结果可复现的随机种子（默认值：0）。 |
+| `remove_background_noise` | BOOLEAN | 否 | - | 使用音频隔离技术去除输入音频中的背景噪音（默认值：False）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 转换后的音频文件，格式为指定的输出格式。 |
diff --git a/zh-CN/built-in-nodes/ElevenLabsSpeechToText.mdx b/zh-CN/built-in-nodes/ElevenLabsSpeechToText.mdx
new file mode 100644
index 000000000..5edd0add0
--- /dev/null
+++ b/zh-CN/built-in-nodes/ElevenLabsSpeechToText.mdx
@@ -0,0 +1,35 @@
+---
+title: "ElevenLabsSpeechToText - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsSpeechToText node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsSpeechToText"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToText/zh.md)
+
+ElevenLabs 语音转文本节点可将音频文件转录为文本。它利用 ElevenLabs 的 API 将语音转换为文字记录，支持自动语言检测、识别不同说话者以及标记非语音声音（如音乐或笑声）等功能。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | 是 | - | 待转录的音频。 |
+| `model` | COMBO | 是 | `"scribe_v2"` | 用于转录的模型。选择此模型会显示额外参数。 |
+| `tag_audio_events` | BOOLEAN | 否 | - | 在转录文本中标注如（笑声）、（音乐）等声音。此参数在选择 `"scribe_v2"` 模型时显示。（默认值：False） |
+| `diarize` | BOOLEAN | 否 | - | 标注当前说话的说话者。此参数在选择 `"scribe_v2"` 模型时显示。（默认值：False） |
+| `diarization_threshold` | FLOAT | 否 | 0.1 - 0.4 | 说话者分离敏感度。数值越低对说话者变化越敏感。此参数在选择 `"scribe_v2"` 模型且启用 `diarize` 时显示。（默认值：0.22） |
+| `temperature` | FLOAT | 否 | 0.0 - 2.0 | 随机性控制。0.0 使用模型默认值。数值越高随机性越大。此参数在选择 `"scribe_v2"` 模型时显示。（默认值：0.0） |
+| `timestamps_granularity` | COMBO | 否 | `"word"`<br />`"character"`<br />`"none"` | 转录文本中单词的时间戳精度。此参数在选择 `"scribe_v2"` 模型时显示。（默认值："word"） |
+| `language_code` | STRING | 否 | - | ISO-639-1 或 ISO-639-3 语言代码（例如 'en'、'es'、'fra'）。留空则自动检测。（默认值：""） |
+| `num_speakers` | INT | 否 | 0 - 32 | 预测的最大说话者数量。设置为 0 则自动检测。（默认值：0） |
+| `seed` | INT | 否 | 0 - 2147483647 | 用于结果可复现性的种子值（不保证完全确定性）。（默认值：1） |
+
+**注意：** 启用 `diarize` 选项时，`num_speakers` 参数不能设置为大于 0 的值。您必须禁用 `diarize` 或将 `num_speakers` 设置为 0。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `text` | STRING | 从音频转录得到的文本。 |
+| `language_code` | STRING | 检测到的音频语言代码。 |
+| `words_json` | STRING | JSON 格式的字符串，包含详细的词级信息，如启用则包括时间戳和说话者标签。 |
diff --git a/zh-CN/built-in-nodes/ElevenLabsTextToDialogue.mdx b/zh-CN/built-in-nodes/ElevenLabsTextToDialogue.mdx
new file mode 100644
index 000000000..de7f7897c
--- /dev/null
+++ b/zh-CN/built-in-nodes/ElevenLabsTextToDialogue.mdx
@@ -0,0 +1,30 @@
+---
+title: "ElevenLabsTextToDialogue - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsTextToDialogue node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsTextToDialogue"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToDialogue/zh.md)
+
+ElevenLabs 文本转对话节点可从文本生成多说话人音频对话。它允许您通过为每个参与者指定不同的文本行和独特音色来创建对话。该节点将对话请求发送至 ElevenLabs API 并返回生成的音频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `stability` | FLOAT | 否 | 0.0 - 1.0 | 音色稳定性。数值越低情感范围越广，数值越高语音越一致但可能单调。（默认：0.5） |
+| `apply_text_normalization` | COMBO | 否 | `"auto"`<br />`"on"`<br />`"off"` | 文本归一化模式。'auto' 由系统决定，'on' 始终应用归一化，'off' 跳过归一化。 |
+| `model` | COMBO | 否 | `"eleven_v3"` | 用于对话生成的模型。 |
+| `inputs` | DYNAMICCOMBO | 是 | `"1"`<br />`"2"`<br />`"3"`<br />`"4"`<br />`"5"`<br />`"6"`<br />`"7"`<br />`"8"`<br />`"9"`<br />`"10"` | 对话条目数量。选择数字将生成相应数量的文本和音色输入字段。 |
+| `language_code` | STRING | 否 | - | ISO-639-1 或 ISO-639-3 语言代码（如 'en'、'es'、'fra'）。留空则自动检测。（默认：空） |
+| `seed` | INT | 否 | 0 - 4294967295 | 用于可重现性的随机种子。（默认：1） |
+| `output_format` | COMBO | 否 | `"mp3_44100_192"`<br />`"opus_48000_192"` | 音频输出格式。 |
+
+**注意：** `inputs` 参数是动态的。当您选择一个数字（例如 "3"）时，节点将显示三个对应的 `text` 和 `voice` 输入字段（例如 `text1`、`voice1`、`text2`、`voice2`、`text3`、`voice3`）。每个 `text` 字段必须包含至少一个字符。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 以选定输出格式生成的多说话人对话音频。 |
diff --git a/zh-CN/built-in-nodes/ElevenLabsTextToSoundEffects.mdx b/zh-CN/built-in-nodes/ElevenLabsTextToSoundEffects.mdx
new file mode 100644
index 000000000..d9c574335
--- /dev/null
+++ b/zh-CN/built-in-nodes/ElevenLabsTextToSoundEffects.mdx
@@ -0,0 +1,30 @@
+---
+title: "ElevenLabsTextToSoundEffects - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsTextToSoundEffects node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsTextToSoundEffects"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToSoundEffects/zh.md)
+
+ElevenLabs 文本转音效节点可根据文本描述生成音频音效。它利用 ElevenLabs API 基于您的提示创建音效，允许您控制音效的持续时间、循环行为以及音效与文本描述的贴合程度。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | 是 | 不适用 | 要生成的音效的文本描述。此为必填字段。 |
+| `model` | COMBO | 是 | `"eleven_sfx_v2"` | 用于音效生成的模型。选择此模型会显示额外参数：`duration`（默认值：5.0，范围：0.5 至 30.0 秒）、`loop`（默认值：False）和 `prompt_influence`（默认值：0.3，范围：0.0 至 1.0）。 |
+| `output_format` | COMBO | 是 | `"mp3_44100_192"`<br />`"opus_48000_192"` | 音频输出格式。 |
+
+**参数详情：**
+
+* **`model["duration"]`**：生成音效的持续时间（秒）。默认值为 5.0，最小值为 0.5，最大值为 30.0。
+* **`model["loop"]`**：启用后，将创建平滑循环的音效。默认值为 False。
+* **`model["prompt_influence"]`**：控制生成结果与文本提示的贴合程度。数值越高，音效越贴合文本。默认值为 0.3，取值范围为 0.0 至 1.0。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 生成的音效音频文件。 |
diff --git a/zh-CN/built-in-nodes/ElevenLabsTextToSpeech.mdx b/zh-CN/built-in-nodes/ElevenLabsTextToSpeech.mdx
new file mode 100644
index 000000000..0fa9a114f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ElevenLabsTextToSpeech.mdx
@@ -0,0 +1,42 @@
+---
+title: "ElevenLabsTextToSpeech - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsTextToSpeech node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsTextToSpeech"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToSpeech/zh.md)
+
+ElevenLabs 文本转语音节点利用 ElevenLabs API 将书面文本转换为语音音频。它允许您选择特定的语音，并微调各种语音特性，如稳定性、速度和风格，以生成定制的音频输出。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `voice` | CUSTOM | 是 | N/A | 用于语音合成的语音。从 Voice Selector 或 Instant Voice Clone 节点连接。 |
+| `text` | STRING | 是 | N/A | 要转换为语音的文本。 |
+| `stability` | FLOAT | 否 | 0.0 - 1.0 | 语音稳定性。较低的值提供更广的情感范围，较高的值产生更一致但可能单调的语音（默认：0.5）。 |
+| `apply_text_normalization` | COMBO | 否 | `"auto"`<br />`"on"`<br />`"off"` | 文本规范化模式。'auto' 由系统决定，'on' 始终应用规范化，'off' 跳过规范化。 |
+| `model` | DYNAMICCOMBO | 否 | `"eleven_multilingual_v2"`<br />`"eleven_v3"` | 用于文本转语音的模型。选择模型会显示其特定参数。 |
+| `language_code` | STRING | 否 | N/A | ISO-639-1 或 ISO-639-3 语言代码（例如 'en'、'es'、'fra'）。留空以自动检测（默认：""）。 |
+| `seed` | INT | 否 | 0 - 2147483647 | 用于可重复性的种子（不保证确定性）（默认：1）。 |
+| `output_format` | COMBO | 否 | `"mp3_44100_192"`<br />`"opus_48000_192"` | 音频输出格式。 |
+
+**模型特定参数：**
+当 `model` 参数设置为 `"eleven_multilingual_v2"` 时，以下附加参数变为可用：
+
+* `speed`： 语速。1.0 为正常，&lt;1.0 更慢，>1.0 更快（默认：1.0，范围：0.7 - 1.3）。
+* `similarity_boost`： 相似度增强。值越高，语音与原始语音越相似（默认：0.75，范围：0.0 - 1.0）。
+* `use_speaker_boost`： 增强与原始说话者语音的相似度（默认：False）。
+* `style`： 风格夸张度。值越高，风格表达越强，但可能降低稳定性（默认：0.0，范围：0.0 - 0.2）。
+
+当 `model` 参数设置为 `"eleven_v3"` 时，以下附加参数变为可用：
+
+* `speed`： 语速。1.0 为正常，&lt;1.0 更慢，>1.0 更快（默认：1.0，范围：0.7 - 1.3）。
+* `similarity_boost`： 相似度增强。值越高，语音与原始语音越相似（默认：0.75，范围：0.0 - 1.0）。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 文本转语音转换生成的音频。 |
diff --git a/zh-CN/built-in-nodes/ElevenLabsVoiceSelector.mdx b/zh-CN/built-in-nodes/ElevenLabsVoiceSelector.mdx
new file mode 100644
index 000000000..7a0b7fa79
--- /dev/null
+++ b/zh-CN/built-in-nodes/ElevenLabsVoiceSelector.mdx
@@ -0,0 +1,22 @@
+---
+title: "ElevenLabsVoiceSelector - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ElevenLabsVoiceSelector node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ElevenLabsVoiceSelector"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsVoiceSelector/zh.md)
+
+ElevenLabs 语音选择器节点允许您从预定义的 ElevenLabs 文本转语音语音列表中选择特定语音。它接收一个语音名称作为输入，并输出音频生成所需的对应语音标识符。此节点简化了为其他 ElevenLabs 音频节点选择兼容语音的过程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `voice` | STRING | 是 | `"Adam"`<br />`"Antoni"`<br />`"Arnold"`<br />`"Bella"`<br />`"Domi"`<br />`"Elli"`<br />`"Josh"`<br />`"Rachel"`<br />`"Sam"` | 从预定义的 ElevenLabs 语音中选择一个语音。 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `voice` | STRING | 所选 ElevenLabs 语音的唯一标识符，可传递给其他节点用于文本转语音生成。 |
diff --git a/zh-CN/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx b/zh-CN/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx
new file mode 100644
index 000000000..7e884ea16
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx
@@ -0,0 +1,25 @@
+---
+title: "EmptyAceStep1.5LatentAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyAceStep1.5LatentAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyAceStep1.5LatentAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyAceStep1.5LatentAudio/zh.md)
+
+## 概述
+
+Empty Ace Step 1.5 Latent Audio 节点创建一个专为音频处理设计的空潜在张量。它生成指定时长和批次大小的静音音频潜在表示，可作为 ComfyUI 中音频生成工作流的起点。该节点根据输入的秒数和固定的采样率计算潜在长度。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `seconds` | FLOAT | 否 | 1.0 - 1000.0 | 要生成的音频时长，单位为秒（默认值：120.0）。 |
+| `batch_size` | INT | 否 | 1 - 4096 | 批次中的潜在图像数量（默认值：1）。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 一个代表静音音频的空潜在张量，其类型标识符为 "audio"。 |
diff --git a/zh-CN/built-in-nodes/EmptyAceStepLatentAudio.mdx b/zh-CN/built-in-nodes/EmptyAceStepLatentAudio.mdx
new file mode 100644
index 000000000..4942173e8
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyAceStepLatentAudio.mdx
@@ -0,0 +1,23 @@
+---
+title: "EmptyAceStepLatentAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyAceStepLatentAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyAceStepLatentAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyAceStepLatentAudio/zh.md)
+
+EmptyAceStepLatentAudio 节点可创建指定时长的空潜空间音频样本。该节点会生成一批全零的静音潜空间音频，其长度根据输入的秒数和音频处理参数计算得出。此节点适用于需要潜空间表示的音频处理工作流的初始化操作。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `seconds` | FLOAT | 否 | 1.0 - 1000.0 | 音频时长（单位：秒），默认值：120.0 |
+| `batch_size` | INT | 否 | 1 - 4096 | 批次中的潜空间图像数量，默认值：1 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | LATENT | 返回全零的空潜空间音频样本 |
diff --git a/zh-CN/built-in-nodes/EmptyAudio.mdx b/zh-CN/built-in-nodes/EmptyAudio.mdx
new file mode 100644
index 000000000..72c41ac4b
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyAudio.mdx
@@ -0,0 +1,26 @@
+---
+title: "EmptyAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyAudio/zh.md)
+
+## 概述
+
+EmptyAudio 节点可生成具有指定时长、采样率和声道配置的静音音频片段。它会创建一个包含全零值的波形，在给定时长内产生完全静音的效果。该节点适用于创建占位音频或在音频工作流中生成静音片段。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `duration` | FLOAT | 是 | 0.0 至 1.8446744073709552e+19 | 静音音频片段的时长（单位：秒）（默认值：60.0） |
+| `sample_rate` | INT | 是 | - | 静音音频片段的采样率（默认值：44100） |
+| `channels` | INT | 是 | 1 至 2 | 音频声道数（1 表示单声道，2 表示立体声）（默认值：2） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | 生成的静音音频片段，包含波形数据和采样率信息 |
diff --git a/zh-CN/built-in-nodes/EmptyChromaRadianceLatentImage.mdx b/zh-CN/built-in-nodes/EmptyChromaRadianceLatentImage.mdx
new file mode 100644
index 000000000..3c63a7506
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyChromaRadianceLatentImage.mdx
@@ -0,0 +1,24 @@
+---
+title: "EmptyChromaRadianceLatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyChromaRadianceLatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyChromaRadianceLatentImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyChromaRadianceLatentImage/zh.md)
+
+EmptyChromaRadianceLatentImage 节点创建一个具有指定尺寸的空白潜空间图像，用于色度辐射工作流程。它生成一个填充零值的张量，作为潜空间操作的起点。该节点允许您定义空白潜空间图像的宽度、高度和批次大小。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | 是 | 16 到 MAX_RESOLUTION | 潜空间图像的宽度（单位：像素，默认值：1024，必须能被16整除） |
+| `height` | INT | 是 | 16 到 MAX_RESOLUTION | 潜空间图像的高度（单位：像素，默认值：1024，必须能被16整除） |
+| `batch_size` | INT | 否 | 1 到 4096 | 批次中生成的潜空间图像数量（默认值：1） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 生成的具有指定尺寸的空白潜空间图像张量 |
diff --git a/zh-CN/built-in-nodes/EmptyCosmosLatentVideo.mdx b/zh-CN/built-in-nodes/EmptyCosmosLatentVideo.mdx
new file mode 100644
index 000000000..368d5e5a3
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyCosmosLatentVideo.mdx
@@ -0,0 +1,25 @@
+---
+title: "EmptyCosmosLatentVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyCosmosLatentVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyCosmosLatentVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyCosmosLatentVideo/zh.md)
+
+EmptyCosmosLatentVideo 节点可创建具有指定尺寸的空潜视频张量。它生成一个填充零值的潜表示，可作为视频生成工作流程的起点，并支持可配置的宽度、高度、长度和批次大小参数。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `宽度` | INT | 是 | 16 至 MAX_RESOLUTION | 潜视频的宽度（单位：像素），默认值：1280，必须能被16整除 |
+| `高度` | INT | 是 | 16 至 MAX_RESOLUTION | 潜视频的高度（单位：像素），默认值：704，必须能被16整除 |
+| `长度` | INT | 是 | 1 至 MAX_RESOLUTION | 潜视频的帧数，默认值：121 |
+| `批量大小` | INT | 否 | 1 至 4096 | 单批次生成的潜视频数量，默认值：1 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 生成的空潜视频张量，其数值均为零 |
diff --git a/zh-CN/built-in-nodes/EmptyFlux2LatentImage.mdx b/zh-CN/built-in-nodes/EmptyFlux2LatentImage.mdx
new file mode 100644
index 000000000..713d7f6af
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyFlux2LatentImage.mdx
@@ -0,0 +1,26 @@
+---
+title: "EmptyFlux2LatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyFlux2LatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyFlux2LatentImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyFlux2LatentImage/zh.md)
+
+EmptyFlux2LatentImage 节点创建一个空白的潜在表示。它生成一个填充零值的张量，作为 Flux 模型去噪过程的起点。潜在表示的维度由输入的宽度和高度决定，并按 16 的比例因子进行缩放。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | 是 | 16 至 8192 | 要生成的最终图像的宽度。潜在宽度将是此值除以 16。默认值为 1024。 |
+| `height` | INT | 是 | 16 至 8192 | 要生成的最终图像的高度。潜在高度将是此值除以 16。默认值为 1024。 |
+| `batch_size` | INT | 否 | 1 至 4096 | 单批次中要生成的潜在样本数量。默认值为 1。 |
+
+**注意：** `width` 和 `height` 输入值必须能被 16 整除，因为节点内部会将这些值除以 16 以创建潜在维度。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 一个填充零值的潜在张量。其形状为 `[batch_size, 128, height // 16, width // 16]`。 |
diff --git a/zh-CN/built-in-nodes/EmptyHunyuanImageLatent.mdx b/zh-CN/built-in-nodes/EmptyHunyuanImageLatent.mdx
new file mode 100644
index 000000000..a9e0b2c09
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyHunyuanImageLatent.mdx
@@ -0,0 +1,26 @@
+---
+title: "EmptyHunyuanImageLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyHunyuanImageLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyHunyuanImageLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyHunyuanImageLatent/zh.md)
+
+## 概述
+
+EmptyHunyuanImageLatent 节点创建一个具有特定维度的空潜在张量，用于混元图像生成模型。它生成一个空白的起始点，可以在工作流中通过后续节点进行处理。该节点允许您指定潜在空间的宽度、高度和批次大小。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | 是 | 64 到 MAX_RESOLUTION | 生成潜在图像的宽度，单位为像素（默认值：2048，步长：32） |
+| `height` | INT | 是 | 64 到 MAX_RESOLUTION | 生成潜在图像的高度，单位为像素（默认值：2048，步长：32） |
+| `batch_size` | INT | 是 | 1 到 4096 | 批次中生成的潜在样本数量（默认值：1） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 具有指定维度的空潜在张量，用于混元图像处理 |
diff --git a/zh-CN/built-in-nodes/EmptyHunyuanLatentVideo.mdx b/zh-CN/built-in-nodes/EmptyHunyuanLatentVideo.mdx
new file mode 100644
index 000000000..800e2ded5
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyHunyuanLatentVideo.mdx
@@ -0,0 +1,21 @@
+---
+title: "EmptyHunyuanLatentVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyHunyuanLatentVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyHunyuanLatentVideo"
+icon: "circle"
+mode: wide
+---
+## 输入
+
+| 参数         | Comfy 数据类型 | 描述                                                         |
+| ------------ | -------------- | ------------------------------------------------------------ |
+| `宽度`      | `INT`          | 视频的宽度，默认为 848，最小值为 16，最大值为 `nodes.MAX_RESOLUTION`，步长为 16。 |
+| `高度`     | `INT`          | 视频的高度，默认为 480，最小值为 16，最大值为 `nodes.MAX_RESOLUTION`，步长为 16。 |
+| `长度`     | `INT`          | 视频的长度，默认为 25，最小值为 1，最大值为 `nodes.MAX_RESOLUTION`，步长为 4。 |
+| `批量大小` | `INT`          | 批次大小，默认为 1，最小值为 1，最大值为 4096。           |
+
+## 输出
+
+| 参数         | Comfy 数据类型 | 描述                                                         |
+| ------------ | -------------- | ------------------------------------------------------------ |
+| `samples`    | `LATENT`       | 生成的潜在视频样本，包含全零的张量，适用于后续的处理和生成任务。 |
diff --git a/zh-CN/built-in-nodes/EmptyHunyuanVideo15Latent.mdx b/zh-CN/built-in-nodes/EmptyHunyuanVideo15Latent.mdx
new file mode 100644
index 000000000..99a82b093
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyHunyuanVideo15Latent.mdx
@@ -0,0 +1,27 @@
+---
+title: "EmptyHunyuanVideo15Latent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyHunyuanVideo15Latent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyHunyuanVideo15Latent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyHunyuanVideo15Latent/zh.md)
+
+此节点创建一个专门为 HunyuanVideo 1.5 模型格式化的空潜在张量。它通过为模型潜在空间分配具有正确通道数和空间维度的零张量，为视频生成生成一个空白的起点。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | 是 | - | 视频帧的宽度（像素）。 |
+| `height` | INT | 是 | - | 视频帧的高度（像素）。 |
+| `length` | INT | 是 | - | 视频序列的帧数。 |
+| `batch_size` | INT | 否 | - | 批次中要生成的视频样本数（默认值：1）。 |
+
+**注意：** 生成的潜在张量的空间维度是通过将输入的 `width` 和 `height` 除以 16 来计算的。时间维度（帧数）的计算公式为 `((length - 1) // 4) + 1`。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 一个维度适合 HunyuanVideo 1.5 模型的空潜在张量。该张量的形状为 `[batch_size, 32, frames, height//16, width//16]`。 |
diff --git a/zh-CN/built-in-nodes/EmptyImage.mdx b/zh-CN/built-in-nodes/EmptyImage.mdx
new file mode 100644
index 000000000..095a457fb
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyImage.mdx
@@ -0,0 +1,50 @@
+---
+title: "EmptyImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyImage"
+icon: "circle"
+mode: wide
+---
+`空图像` 节点用于创建指定尺寸和颜色的空白图像。它可以生成纯色背景图像，常用作图像处理工作流的起始点或背景图像。
+
+## 输入
+
+| 参数名称 | 数据类型 | 描述 |
+|----------|----------|------|
+| `宽度` | INT | 设置生成图像的宽度（像素），决定画布的水平尺寸 |
+| `高度` | INT | 设置生成图像的高度（像素），决定画布的垂直尺寸 |
+| `批量大小` | INT | 一次生成的图像数量，用于批量创建相同规格的图像 |
+| `颜色` | INT | 图像的背景颜色，你可以输入十六进制的颜色设置，会被自动转为10进制|
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|----------|------|
+| `image` | IMAGE | 生成的空白图像张量，格式为 [批量大小, 高度, 宽度, 3]，包含RGB三个颜色通道 |
+
+## 常用颜色参考值
+
+由于当前该节点颜色输入并不友好，所有色值输入都会被转为十进制，这里提供一些可以直接使用的常用颜色色值用于直接快速使用
+
+| 颜色名称 | 十六进制值 |
+| -------- | ---------- |
+| 黑色     | 0x000000   |
+| 白色     | 0xFFFFFF   |
+| 红色     | 0xFF0000   |
+| 绿色     | 0x00FF00   |
+| 蓝色     | 0x0000FF   |
+| 黄色     | 0xFFFF00   |
+| 青色     | 0x00FFFF   |
+| 洋红色   | 0xFF00FF   |
+| 橙色     | 0xFF8000   |
+| 紫色     | 0x8000FF   |
+| 粉色     | 0xFF80C0   |
+| 棕色     | 0x8B4513   |
+| 深灰色   | 0x404040   |
+| 浅灰色   | 0xC0C0C0   |
+| 海军蓝   | 0x000080   |
+| 深绿色   | 0x008000   |
+| 深红色   | 0x800000   |
+| 金色     | 0xFFD700   |
+| 银色     | 0xC0C0C0   |
+| 米色     | 0xF5F5DC   |
diff --git a/zh-CN/built-in-nodes/EmptyLTXVLatentVideo.mdx b/zh-CN/built-in-nodes/EmptyLTXVLatentVideo.mdx
new file mode 100644
index 000000000..3addacc9c
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyLTXVLatentVideo.mdx
@@ -0,0 +1,25 @@
+---
+title: "EmptyLTXVLatentVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyLTXVLatentVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyLTXVLatentVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyLTXVLatentVideo/zh.md)
+
+EmptyLTXVLatentVideo 节点用于创建视频处理所需的空潜在张量。它生成具有指定尺寸的空白起始点，可作为视频生成工作流程的输入。该节点会生成一个零填充的潜在表示，其宽度、高度、长度和批次大小均可配置。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `宽度` | INT | 是 | 64 至 MAX_RESOLUTION | 潜在视频张量的宽度（默认值：768，步长：32） |
+| `高度` | INT | 是 | 64 至 MAX_RESOLUTION | 潜在视频张量的高度（默认值：512，步长：32） |
+| `长度` | INT | 是 | 1 至 MAX_RESOLUTION | 潜在视频的帧数（默认值：97，步长：8） |
+| `批量大小` | INT | 否 | 1 至 4096 | 批次中生成的潜在视频数量（默认值：1） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 生成的空潜在张量，在指定维度上均为零值 |
diff --git a/zh-CN/built-in-nodes/EmptyLatentAudio.mdx b/zh-CN/built-in-nodes/EmptyLatentAudio.mdx
new file mode 100644
index 000000000..fe0bf707c
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyLatentAudio.mdx
@@ -0,0 +1,25 @@
+---
+title: "EmptyLatentAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyLatentAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyLatentAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyLatentAudio/zh.md)
+
+## 概述
+
+EmptyLatentAudio 节点为音频处理创建空的潜在张量。它生成具有指定时长和批次大小的空白音频潜在表示，可用作音频生成或处理工作流的输入。该节点根据音频时长和采样率计算适当的潜在维度。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `秒` | FLOAT | 是 | 1.0 - 1000.0 | 音频时长（单位：秒），默认值：47.6 |
+| `批量大小` | INT | 是 | 1 - 4096 | 批次中的潜在图像数量，默认值：1 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 返回具有指定时长和批次大小的空音频潜在张量，用于音频处理 |
diff --git a/zh-CN/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx b/zh-CN/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx
new file mode 100644
index 000000000..993f2722b
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx
@@ -0,0 +1,25 @@
+---
+title: "EmptyLatentHunyuan3Dv2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyLatentHunyuan3Dv2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyLatentHunyuan3Dv2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyLatentHunyuan3Dv2/zh.md)
+
+## 概述
+
+EmptyLatentHunyuan3Dv2 节点创建专门为 Hunyuan3Dv2 3D 生成模型格式化的空白潜空间张量。它生成具有 Hunyuan3Dv2 架构所需正确维度和结构的空潜空间，允许您从头开始 3D 生成工作流程。该节点生成填充零值的潜空间张量，作为后续 3D 生成过程的基础。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `分辨率` | INT | 是 | 1 - 8192 | 潜空间的分辨率维度（默认值：3072） |
+| `批量大小` | INT | 是 | 1 - 4096 | 批次中的潜空间图像数量（默认值：1） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 返回包含为 Hunyuan3Dv2 3D 生成格式化的空样本的潜空间张量 |
diff --git a/zh-CN/built-in-nodes/EmptyLatentImage.mdx b/zh-CN/built-in-nodes/EmptyLatentImage.mdx
new file mode 100644
index 000000000..9775bacee
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyLatentImage.mdx
@@ -0,0 +1,22 @@
+---
+title: "EmptyLatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyLatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyLatentImage"
+icon: "circle"
+mode: wide
+---
+空白的潜空间图像，你可以把它理解成为画布，此节点设计用于生成具有指定维度和批量大小的空白潜在空间表示。该节点是生成或操作潜在空间中图像的基础步骤，为进一步的图像合成或修改过程提供了起点。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `宽度` | `INT` | 指定要生成的潜在图像的宽度。此参数直接影响生成的潜在表示的空间维度。 |
+| `高度` | `INT` | 确定要生成的潜在图像的高度。此参数对定义潜在空间表示的空间维度至关重要。 |
+| `批量大小` | `INT` | 控制单次批量中生成的潜在图像数量。这允许同时生成多个潜在表示，便于批量处理。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `潜在表示` | `LATENT` | 输出是一个张量，代表一批空白潜在图像，作为潜在空间中进一步图像生成或操作的基础。 |
diff --git a/zh-CN/built-in-nodes/EmptyMochiLatentVideo.mdx b/zh-CN/built-in-nodes/EmptyMochiLatentVideo.mdx
new file mode 100644
index 000000000..4d352ccea
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyMochiLatentVideo.mdx
@@ -0,0 +1,27 @@
+---
+title: "EmptyMochiLatentVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyMochiLatentVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyMochiLatentVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyMochiLatentVideo/zh.md)
+
+EmptyMochiLatentVideo 节点可创建具有指定尺寸的空潜视频张量。它生成一个填充零的潜在表示，可用作视频生成工作流程的起点。该节点允许您定义潜视频张量的宽度、高度、长度和批次大小。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `宽度` | INT | 是 | 16 至 MAX_RESOLUTION | 潜视频的宽度（单位：像素，默认值：848，必须能被 16 整除） |
+| `高度` | INT | 是 | 16 至 MAX_RESOLUTION | 潜视频的高度（单位：像素，默认值：480，必须能被 16 整除） |
+| `长度` | INT | 是 | 7 至 MAX_RESOLUTION | 潜视频的帧数（默认值：25） |
+| `批量大小` | INT | 否 | 1 至 4096 | 批次中生成的潜视频数量（默认值：1） |
+
+**注意：** 实际潜在维度计算为 width/8 和 height/8，时间维度计算为 ((length - 1) // 6) + 1。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 具有指定尺寸的空潜视频张量，包含全零值 |
diff --git a/zh-CN/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx b/zh-CN/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx
new file mode 100644
index 000000000..65dbf398b
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx
@@ -0,0 +1,27 @@
+---
+title: "EmptyQwenImageLayeredLatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptyQwenImageLayeredLatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptyQwenImageLayeredLatentImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyQwenImageLayeredLatentImage/zh.md)
+
+Empty Qwen Image Layered Latent 节点创建一个空白的多层潜在表示，用于 Qwen 图像模型。它生成一个填充零值的张量，结构包含指定的层数、批次大小和空间维度。此空潜在表示可作为后续图像生成或处理工作流的起点。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | 是 | 16 至 MAX_RESOLUTION | 要创建的潜在图像的宽度。该值必须能被 16 整除。（默认值：640） |
+| `height` | INT | 是 | 16 至 MAX_RESOLUTION | 要创建的潜在图像的高度。该值必须能被 16 整除。（默认值：640） |
+| `layers` | INT | 是 | 0 至 MAX_RESOLUTION | 要添加到潜在结构中的额外层数。这定义了潜在表示的深度。（默认值：3） |
+| `batch_size` | INT | 否 | 1 至 4096 | 批次中要生成的潜在样本数量。（默认值：1） |
+
+**注意：** `width` 和 `height` 参数在内部会除以 8，以确定输出潜在张量的空间维度。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 一个填充零值的潜在张量。其形状为 `[batch_size, 16, layers + 1, height // 8, width // 8]`。 |
diff --git a/zh-CN/built-in-nodes/EmptySD3LatentImage.mdx b/zh-CN/built-in-nodes/EmptySD3LatentImage.mdx
new file mode 100644
index 000000000..6eece5b6a
--- /dev/null
+++ b/zh-CN/built-in-nodes/EmptySD3LatentImage.mdx
@@ -0,0 +1,24 @@
+---
+title: "EmptySD3LatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EmptySD3LatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EmptySD3LatentImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptySD3LatentImage/zh.md)
+
+EmptySD3LatentImage 节点可创建专为 Stable Diffusion 3 模型格式化的空白潜空间图像张量。它会生成一个填充零值的张量，该张量具有 SD3 流程所需的正确维度和结构。这通常用作图像生成流程的起点。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `宽度` | INT | 是 | 16 至 MAX_RESOLUTION（步长：16） | 输出潜空间图像的宽度（单位：像素，默认值：1024） |
+| `高度` | INT | 是 | 16 至 MAX_RESOLUTION（步长：16） | 输出潜空间图像的高度（单位：像素，默认值：1024） |
+| `批量大小` | INT | 是 | 1 至 4096 | 单批次生成的潜空间图像数量（默认值：1） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 包含具有 SD3 兼容维度的空白样本的潜空间张量 |
diff --git a/zh-CN/built-in-nodes/Epsilon Scaling.mdx b/zh-CN/built-in-nodes/Epsilon Scaling.mdx
new file mode 100644
index 000000000..f4b173e68
--- /dev/null
+++ b/zh-CN/built-in-nodes/Epsilon Scaling.mdx	
@@ -0,0 +1,23 @@
+---
+title: "Epsilon Scaling - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Epsilon Scaling node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Epsilon Scaling"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon%20Scaling/zh.md)
+
+此节点实现了研究论文《阐明扩散模型中的曝光偏差》中提出的 Epsilon Scaling 方法。它通过在采样过程中缩放预测噪声来帮助减少曝光偏差，从而提升生成图像的质量。此实现采用了论文推荐的“均匀调度”方案。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 将应用 epsilon 缩放补丁的模型。 |
+| `scaling_factor` | FLOAT | 否 | 0.5 - 1.5 | 预测噪声的缩放因子。大于 1.0 的值会减少噪声，小于 1.0 的值则会增加噪声（默认值：1.005）。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 输入模型的修补版本，其采样过程已应用 epsilon 缩放功能。 |
diff --git a/zh-CN/built-in-nodes/EpsilonScaling.mdx b/zh-CN/built-in-nodes/EpsilonScaling.mdx
new file mode 100644
index 000000000..0ccee5beb
--- /dev/null
+++ b/zh-CN/built-in-nodes/EpsilonScaling.mdx
@@ -0,0 +1,23 @@
+---
+title: "EpsilonScaling - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the EpsilonScaling node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "EpsilonScaling"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EpsilonScaling/zh.md)
+
+实现了研究论文《阐明扩散模型中的曝光偏差》中的 Epsilon Scaling 方法。该方法通过在采样过程中缩放预测噪声来改善样本质量。它使用统一的调度策略来减轻扩散模型中的曝光偏差。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要应用 epsilon scaling 的模型 |
+| `scaling_factor` | FLOAT | 否 | 0.5 - 1.5 | 用于缩放预测噪声的因子（默认值：1.005） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 应用了 epsilon scaling 的模型 |
diff --git a/zh-CN/built-in-nodes/ExponentialScheduler.mdx b/zh-CN/built-in-nodes/ExponentialScheduler.mdx
new file mode 100644
index 000000000..7d4cfc9da
--- /dev/null
+++ b/zh-CN/built-in-nodes/ExponentialScheduler.mdx
@@ -0,0 +1,24 @@
+---
+title: "ExponentialScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ExponentialScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ExponentialScheduler"
+icon: "circle"
+mode: wide
+---
+`ExponentialScheduler`节点旨在为扩散采样过程生成一系列按照指数时间表的sigma值。它提供了一种可定制的方法来控制扩散过程中每一步应用的噪声水平，从而可以微调采样行为。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `步数` | `INT` | 指定扩散过程中的步数。它影响生成的sigma序列的长度，从而影响噪声应用的粒度。 |
+| `最大Sigma` | `FLOAT` | 定义最大sigma值，设置扩散过程中噪声强度的上限。它在确定应用的噪声水平范围中起着关键作用。 |
+| `最新Sigma` | `FLOAT` | 设置最小sigma值，建立噪声强度的下限边界。此参数有助于微调噪声应用的起始点。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `sigmas` | `SIGMAS` | 根据指数时间表生成的一系列sigma值。这些值用于控制扩散过程中每一步的噪声水平。 |
+
+---
diff --git a/zh-CN/built-in-nodes/ExtendIntermediateSigmas.mdx b/zh-CN/built-in-nodes/ExtendIntermediateSigmas.mdx
new file mode 100644
index 000000000..79f9cb997
--- /dev/null
+++ b/zh-CN/built-in-nodes/ExtendIntermediateSigmas.mdx
@@ -0,0 +1,28 @@
+---
+title: "ExtendIntermediateSigmas - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ExtendIntermediateSigmas node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ExtendIntermediateSigmas"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ExtendIntermediateSigmas/zh.md)
+
+ExtendIntermediateSigmas 节点接收现有的 sigma 值序列，并在它们之间插入额外的中间 sigma 值。它允许您指定要添加的额外步数、用于插值的间距方法，以及可选的起始和结束 sigma 边界，以控制在 sigma 序列中进行扩展的位置。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `sigmas` | SIGMAS | 是 | - | 要插入中间值的输入 sigma 序列 |
+| `步数` | INT | 是 | 1-100 | 在现有 sigma 值之间插入的中间步数（默认值：2） |
+| `起始 sigma` | FLOAT | 是 | -1.0 到 20000.0 | 扩展的上限 sigma 边界 - 仅扩展低于此值的 sigma（默认值：-1.0，表示无穷大） |
+| `结束 sigma` | FLOAT | 是 | 0.0 到 20000.0 | 扩展的下限 sigma 边界 - 仅扩展高于此值的 sigma（默认值：12.0） |
+| `间距` | COMBO | 是 | "linear"<br />"cosine"<br />"sine" | 用于中间 sigma 值间距的插值方法 |
+
+**注意：** 该节点仅在满足当前 sigma 小于等于 `start_at_sigma` 且大于等于 `end_at_sigma` 条件的现有 sigma 对之间插入中间 sigma 值。当 `start_at_sigma` 设置为 -1.0 时，它被视为无穷大，这意味着仅应用 `end_at_sigma` 下限边界。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | 插入了额外中间值的扩展 sigma 序列 |
diff --git a/zh-CN/built-in-nodes/FeatherMask.mdx b/zh-CN/built-in-nodes/FeatherMask.mdx
new file mode 100644
index 000000000..b1f750e51
--- /dev/null
+++ b/zh-CN/built-in-nodes/FeatherMask.mdx
@@ -0,0 +1,24 @@
+---
+title: "FeatherMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FeatherMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FeatherMask"
+icon: "circle"
+mode: wide
+---
+羽化遮罩节点对给定遮罩的边缘应用羽化效果，通过调整每个边缘指定距离内的不透明度，平滑过渡遮罩的边缘。这创造了一个更柔和、更混合的边缘效果。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `遮罩` | MASK | 应用羽化效果的遮罩。它决定了图像中将受羽化影响的区域。 |
+| `左` | INT | 指定从左侧边缘开始应用羽化效果的距离。 |
+| `顶` | INT | 指定从顶部边缘开始应用羽化效果的距离。 |
+| `右` | INT | 指定从右侧边缘开始应用羽化效果的距离。 |
+| `底` | INT | 指定从底部边缘开始应用羽化效果的距离。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `遮罩` | MASK | 输出是应用了羽化效果的输入遮罩的修改版本，其边缘经过羽化处理。 |
diff --git a/zh-CN/built-in-nodes/FlipSigmas.mdx b/zh-CN/built-in-nodes/FlipSigmas.mdx
new file mode 100644
index 000000000..f669f6067
--- /dev/null
+++ b/zh-CN/built-in-nodes/FlipSigmas.mdx
@@ -0,0 +1,20 @@
+---
+title: "FlipSigmas - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FlipSigmas node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FlipSigmas"
+icon: "circle"
+mode: wide
+---
+`FlipSigmas` 节点旨在通过反转顺序并确保原始第一个值为非零（如果原本为零）来操作扩散模型中使用的 sigma 值序列。这一操作对于以相反顺序调整噪声水平至关重要，有助于在通过逐步减少数据中的噪声来操作的模型中促进生成过程。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `sigmas` | `SIGMAS`| 'sigmas' 参数表示要翻转的 sigma 值序列。此序列对于控制扩散过程中应用的噪声水平至关重要，翻转它对于反向生成过程是必不可少的。 |
+
+### 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `sigmas` | `SIGMAS`| 输出是修改后的 sigma 值序列，已翻转并调整以确保原始第一个值为非零（如果原本为零），准备好用于后续的扩散模型操作。 |
diff --git a/zh-CN/built-in-nodes/Flux2Scheduler.mdx b/zh-CN/built-in-nodes/Flux2Scheduler.mdx
new file mode 100644
index 000000000..41898acb9
--- /dev/null
+++ b/zh-CN/built-in-nodes/Flux2Scheduler.mdx
@@ -0,0 +1,24 @@
+---
+title: "Flux2Scheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Flux2Scheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Flux2Scheduler"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Flux2Scheduler/zh.md)
+
+Flux2Scheduler 节点为去噪过程生成一系列噪声水平值（sigmas），专为 Flux 模型定制。它根据去噪步骤的数量和目标图像的尺寸计算一个调度表，该调度表会影响图像生成过程中噪声去除的进程。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `steps` | INT | 是 | 1 到 4096 | 要执行的去噪步骤数。数值越高通常会产生更详细的结果，但处理时间更长（默认值：20）。 |
+| `width` | INT | 是 | 16 到 16384 | 要生成的图像的宽度，以像素为单位。此值会影响噪声调度表的计算（默认值：1024）。 |
+| `height` | INT | 是 | 16 到 16384 | 要生成的图像的高度，以像素为单位。此值会影响噪声调度表的计算（默认值：1024）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | 一系列噪声水平值（sigmas），定义了采样器的去噪调度表。 |
diff --git a/zh-CN/built-in-nodes/FluxDisableGuidance.mdx b/zh-CN/built-in-nodes/FluxDisableGuidance.mdx
new file mode 100644
index 000000000..423d52dd8
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxDisableGuidance.mdx
@@ -0,0 +1,24 @@
+---
+title: "FluxDisableGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxDisableGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxDisableGuidance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxDisableGuidance/zh.md)
+
+## 概述
+
+此节点通过将 CLIP 模型的引导嵌入功能完全禁用，适用于 Flux 及类似模型。它接收条件数据作为输入，并通过将引导组件设置为 None 来移除该功能，从而在生成过程中有效关闭基于引导的条件控制。
+
+## 输入
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | 是 | - | 需要处理并移除引导功能的条件数据 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | 已禁用引导功能的修改后条件数据 |
diff --git a/zh-CN/built-in-nodes/FluxGuidance.mdx b/zh-CN/built-in-nodes/FluxGuidance.mdx
new file mode 100644
index 000000000..2b991dc31
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxGuidance.mdx
@@ -0,0 +1,19 @@
+---
+title: "FluxGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxGuidance"
+icon: "circle"
+mode: wide
+---
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+|---------|--------|------|
+| `条件` | CONDITIONING | 输入的条件控制数据，通常来自之前的编码或处理步骤 |
+| `引导` | FLOAT | 控制文本提示对图像生成的影响程度，可调节范围为 0.0 到 100.0 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+|---------|--------|------|
+| CONDITIONING | CONDITIONING | 更新后的条件控制数据，包含新的 guidance 值 |
diff --git a/zh-CN/built-in-nodes/FluxKontextImageScale.mdx b/zh-CN/built-in-nodes/FluxKontextImageScale.mdx
new file mode 100644
index 000000000..6bb61a6bd
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxKontextImageScale.mdx
@@ -0,0 +1,44 @@
+---
+title: "FluxKontextImageScale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxKontextImageScale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxKontextImageScale"
+icon: "circle"
+mode: wide
+---
+这个节点会根据输入图像的宽高比，使用 Lanczos 算法进行图像缩放将输入图像调整为 Flux Kontext 模型训练时使用的最优尺寸。因为输入过大尺寸的图像可能导致模型输出效果变差，或者出现类似多主体等情况，所以此节点在这些情况下特别有用。
+
+## 输入参数说明
+
+| 参数名称 | 数据类型 | 输入方式 | 默认值 | 取值范围 | 功能说明 |
+|----------|----------|----------|---------|----------|----------|
+| `image` | IMAGE | 必需 | - | - | 需要调整尺寸的输入图像 |
+
+## 输出结果说明
+
+| 输出名称 | 数据类型 | 说明 |
+|----------|----------|------|
+| `image` | IMAGE | 调整尺寸后的图像 |
+
+## 预设尺寸列表
+
+以下是模型训练时使用的标准尺寸列表，节点会根据输入图像的宽高比选择最接近的尺寸：
+
+| 宽度 | 高度 | 宽高比 |
+|------|------|--------|
+| 672  | 1568 | 0.429  |
+| 688  | 1504 | 0.457  |
+| 720  | 1456 | 0.494  |
+| 752  | 1392 | 0.540  |
+| 800  | 1328 | 0.603  |
+| 832  | 1248 | 0.667  |
+| 880  | 1184 | 0.743  |
+| 944  | 1104 | 0.855  |
+| 1024 | 1024 | 1.000  |
+| 1104 | 944  | 1.170  |
+| 1184 | 880  | 1.345  |
+| 1248 | 832  | 1.500  |
+| 1328 | 800  | 1.660  |
+| 1392 | 752  | 1.851  |
+| 1456 | 720  | 2.022  |
+| 1504 | 688  | 2.186  |
+| 1568 | 672  | 2.333  |
diff --git a/zh-CN/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx b/zh-CN/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx
new file mode 100644
index 000000000..19404a795
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx
@@ -0,0 +1,25 @@
+---
+title: "FluxKontextMultiReferenceLatentMethod - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxKontextMultiReferenceLatentMethod node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxKontextMultiReferenceLatentMethod"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxKontextMultiReferenceLatentMethod/zh.md)
+
+## 概述
+
+FluxKontextMultiReferenceLatentMethod 节点通过设置特定的参考潜空间方法来修改条件数据。它会将选定的方法附加到条件输入中，从而影响后续生成步骤中参考潜空间的处理方式。该节点标记为实验性功能，属于 Flux 条件系统的一部分。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | 是 | - | 需要应用参考潜空间方法进行修改的条件数据 |
+| `reference_latents_method` | STRING | 是 | `"offset"`<br />`"index"`<br />`"uxo/uno"` | 用于参考潜空间处理的方法。如果选择 "uxo" 或 "uso"，将被转换为 "uxo" |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | 已应用参考潜空间方法的修改后条件数据 |
diff --git a/zh-CN/built-in-nodes/FluxProCannyNode.mdx b/zh-CN/built-in-nodes/FluxProCannyNode.mdx
new file mode 100644
index 000000000..396f5633e
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxProCannyNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "FluxProCannyNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProCannyNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProCannyNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProCannyNode/zh.md)
+
+使用控制图像（canny）生成图像。该节点接收控制图像，根据提供的提示词生成新图像，同时遵循在控制图像中检测到的边缘结构。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `control_image` | IMAGE | 是 | - | 用于 canny 边缘检测控制的输入图像 |
+| `prompt` | STRING | 否 | - | 图像生成的提示词（默认：空字符串） |
+| `prompt_upsampling` | BOOLEAN | 否 | - | 是否对提示词进行上采样处理。如果启用，会自动修改提示词以实现更具创意的生成，但结果具有不确定性（相同的种子不会产生完全相同的结果）（默认：False） |
+| `canny_low_threshold` | FLOAT | 否 | 0.01 - 0.99 | Canny 边缘检测的低阈值；如果 skip_processing 为 True 则忽略此参数（默认：0.1） |
+| `canny_high_threshold` | FLOAT | 否 | 0.01 - 0.99 | Canny 边缘检测的高阈值；如果 skip_processing 为 True 则忽略此参数（默认：0.4） |
+| `skip_preprocessing` | BOOLEAN | 否 | - | 是否跳过预处理；如果 control_image 已经是 canny 处理后的图像则设为 True，如果是原始图像则设为 False（默认：False） |
+| `guidance` | FLOAT | 否 | 1 - 100 | 图像生成过程的引导强度（默认：30） |
+| `steps` | INT | 否 | 15 - 50 | 图像生成过程的步数（默认：50） |
+| `seed` | INT | 否 | 0 - 18446744073709551615 | 用于创建噪声的随机种子（默认：0） |
+
+**注意：** 当 `skip_preprocessing` 设置为 True 时，`canny_low_threshold` 和 `canny_high_threshold` 参数将被忽略，因为此时假定控制图像已经是经过 canny 边缘处理的图像。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | 基于控制图像和提示词生成的图像 |
diff --git a/zh-CN/built-in-nodes/FluxProDepthNode.mdx b/zh-CN/built-in-nodes/FluxProDepthNode.mdx
new file mode 100644
index 000000000..f533208e9
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxProDepthNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "FluxProDepthNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProDepthNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProDepthNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProDepthNode/zh.md)
+
+## 概述
+
+此节点使用深度控制图像作为引导来生成图像。它接收一个控制图像和文本提示，然后创建一个既遵循控制图像深度信息又符合提示描述的新图像。该节点连接到外部 API 来执行图像生成过程。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `control_image` | IMAGE | 是 | - | 用于引导图像生成的深度控制图像 |
+| `prompt` | STRING | 否 | - | 图像生成的提示词（默认：空字符串） |
+| `prompt_upsampling` | BOOLEAN | 否 | - | 是否对提示词执行上采样。如果启用，会自动修改提示词以实现更具创意的生成，但结果具有不确定性（相同的种子不会产生完全相同的结果）。（默认：False） |
+| `skip_preprocessing` | BOOLEAN | 否 | - | 是否跳过预处理；如果 control_image 已经是深度化图像则设为 True，如果是原始图像则设为 False。（默认：False） |
+| `guidance` | FLOAT | 否 | 1-100 | 图像生成过程的引导强度（默认：15） |
+| `steps` | INT | 否 | 15-50 | 图像生成过程的步数（默认：50） |
+| `seed` | INT | 否 | 0-18446744073709551615 | 用于创建噪声的随机种子。（默认：0） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | 基于深度控制图像和提示词生成的图像 |
diff --git a/zh-CN/built-in-nodes/FluxProExpandNode.mdx b/zh-CN/built-in-nodes/FluxProExpandNode.mdx
new file mode 100644
index 000000000..f5947015c
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxProExpandNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "FluxProExpandNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProExpandNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProExpandNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProExpandNode/zh.md)
+
+## 概述
+
+根据提示进行图像外绘。此节点通过在图像的上、下、左、右各边添加像素来扩展图像，同时生成与提供的文本描述相匹配的新内容。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 要扩展的输入图像 |
+| `提示词` | STRING | 否 | - | 用于图像生成的提示词（默认：""） |
+| `提示词上采样` | BOOLEAN | 否 | - | 是否对提示词执行上采样。如果启用，会自动修改提示词以进行更具创造性的生成，但结果具有不确定性（相同的种子不会产生完全相同的结果）。（默认：False） |
+| `上方扩展` | INT | 否 | 0-2048 | 在图像顶部扩展的像素数量（默认：0） |
+| `下方扩展` | INT | 否 | 0-2048 | 在图像底部扩展的像素数量（默认：0） |
+| `左侧扩展` | INT | 否 | 0-2048 | 在图像左侧扩展的像素数量（默认：0） |
+| `右侧扩展` | INT | 否 | 0-2048 | 在图像右侧扩展的像素数量（默认：0） |
+| `引导强度` | FLOAT | 否 | 1.5-100 | 图像生成过程的引导强度（默认：60） |
+| `步数` | INT | 否 | 15-50 | 图像生成过程的步数（默认：50） |
+| `种子` | INT | 否 | 0-18446744073709551615 | 用于创建噪声的随机种子。（默认：0） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `图像` | IMAGE | 扩展后的输出图像 |
diff --git a/zh-CN/built-in-nodes/FluxProFillNode.mdx b/zh-CN/built-in-nodes/FluxProFillNode.mdx
new file mode 100644
index 000000000..77a5cbd12
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxProFillNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "FluxProFillNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProFillNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProFillNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProFillNode/zh.md)
+
+## 概述
+
+基于遮罩和提示对图像进行修复。此节点使用 Flux.1 模型，根据提供的文本描述填充图像的遮罩区域，生成与周围图像内容相匹配的新内容。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 需要进行修复的输入图像 |
+| `mask` | MASK | 是 | - | 定义图像中哪些区域需要填充的遮罩 |
+| `提示词` | STRING | 否 | - | 图像生成的提示词（默认：空字符串） |
+| `提示词上采样` | BOOLEAN | 否 | - | 是否对提示词进行上采样处理。如果启用，会自动修改提示词以实现更具创造性的生成，但结果具有不确定性（相同种子不会产生完全一致的结果）。（默认：false） |
+| `引导强度` | FLOAT | 否 | 1.5-100 | 图像生成过程的引导强度（默认：60） |
+| `步数` | INT | 否 | 15-50 | 图像生成过程的步数（默认：50） |
+| `种子` | INT | 否 | 0-18446744073709551615 | 用于创建噪声的随机种子（默认：0） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | 根据提示词填充遮罩区域后生成的图像 |
diff --git a/zh-CN/built-in-nodes/FluxProImageNode.mdx b/zh-CN/built-in-nodes/FluxProImageNode.mdx
new file mode 100644
index 000000000..2f5437b62
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxProImageNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "FluxProImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProImageNode/zh.md)
+
+基于提示词和分辨率同步生成图像。该节点通过向 API 端点发送请求并等待完整响应后返回生成的图像，使用 Flux 1.1 Pro 模型创建图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 图像生成的提示词（默认：空字符串） |
+| `prompt_upsampling` | BOOLEAN | 是 | - | 是否对提示词执行上采样。如果启用，会自动修改提示词以实现更具创造性的生成，但结果具有不确定性（相同种子不会产生完全相同的结果）。（默认：False） |
+| `width` | INT | 是 | 256-1440 | 图像宽度（像素）（默认：1024，步长：32） |
+| `height` | INT | 是 | 256-1440 | 图像高度（像素）（默认：768，步长：32） |
+| `seed` | INT | 是 | 0-18446744073709551615 | 用于创建噪声的随机种子（默认：0） |
+| `image_prompt` | IMAGE | 否 | - | 可选参考图像，用于指导生成过程 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 从 API 返回的生成图像 |
diff --git a/zh-CN/built-in-nodes/FluxProUltraImageNode.mdx b/zh-CN/built-in-nodes/FluxProUltraImageNode.mdx
new file mode 100644
index 000000000..01b922d08
--- /dev/null
+++ b/zh-CN/built-in-nodes/FluxProUltraImageNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "FluxProUltraImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FluxProUltraImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FluxProUltraImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProUltraImageNode/zh.md)
+
+使用 Flux Pro 1.1 Ultra 通过 API 根据提示词和分辨率生成图像。此节点连接到外部服务，根据您的文本描述和指定尺寸创建图像。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 参数说明 |
+|-----------|-----------|----------|-------|-------------|
+| `提示词` | STRING | 是 | - | 图像生成的提示词（默认：空字符串） |
+| `提示词上采样` | BOOLEAN | 否 | - | 是否对提示词进行上采样处理。启用时，会自动修改提示词以获得更具创意的生成结果，但结果具有不确定性（相同种子不会产生完全相同的结果）。（默认：False） |
+| `种子` | INT | 否 | 0 到 18446744073709551615 | 用于创建噪声的随机种子。（默认：0） |
+| `宽高比` | STRING | 否 | - | 图像宽高比；必须在 1:4 到 4:1 之间。（默认："16:9"） |
+| `原始` | BOOLEAN | 否 | - | 为 True 时，生成较少处理、更自然外观的图像。（默认：False） |
+| `图像提示词` | IMAGE | 否 | - | 可选参考图像，用于引导生成过程 |
+| `图像提示词强度` | FLOAT | 否 | 0.0 到 1.0 | 在提示词和图像提示之间的混合强度。（默认：0.1） |
+
+**注意：** `aspect_ratio` 参数必须在 1:4 到 4:1 之间。当提供 `image_prompt` 时，`image_prompt_strength` 将变为活动状态，控制参考图像对最终输出的影响程度。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 输出说明 |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | 由 Flux Pro 1.1 Ultra 生成的图像 |
diff --git a/zh-CN/built-in-nodes/FreSca.mdx b/zh-CN/built-in-nodes/FreSca.mdx
new file mode 100644
index 000000000..a458a5009
--- /dev/null
+++ b/zh-CN/built-in-nodes/FreSca.mdx
@@ -0,0 +1,27 @@
+---
+title: "FreSca - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FreSca node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FreSca"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FreSca/zh.md)
+
+## 概述
+
+FreSca 节点在采样过程中对引导信号应用频率相关缩放。它通过傅里叶滤波将引导信号分离为低频和高频分量，然后对每个频率范围应用不同的缩放因子，最后重新组合它们。这能够实现对引导信号如何影响生成输出不同方面的更精细控制。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要应用频率缩放的模型 |
+| `scale_low` | FLOAT | 否 | 0-10 | 低频分量的缩放因子（默认值：1.0） |
+| `scale_high` | FLOAT | 否 | 0-10 | 高频分量的缩放因子（默认值：1.25） |
+| `freq_cutoff` | INT | 否 | 1-10000 | 围绕中心被视为低频的频率索引数量（默认值：20） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 已修改的模型，其引导函数应用了频率相关缩放 |
diff --git a/zh-CN/built-in-nodes/FreeU.mdx b/zh-CN/built-in-nodes/FreeU.mdx
new file mode 100644
index 000000000..feb576403
--- /dev/null
+++ b/zh-CN/built-in-nodes/FreeU.mdx
@@ -0,0 +1,26 @@
+---
+title: "FreeU - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FreeU node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FreeU"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FreeU/zh.md)
+
+FreeU 节点对模型的输出块进行频域修改，以提升图像生成质量。它通过缩放不同通道组并对特定特征图应用傅里叶滤波来实现这一效果，从而在生成过程中对模型行为进行精细调控。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型` | MODEL | 是 | - | 要应用 FreeU 修改的模型 |
+| `b1` | FLOAT | 是 | 0.0 - 10.0 | 模型通道数×4特征的主干缩放因子（默认：1.1） |
+| `b2` | FLOAT | 是 | 0.0 - 10.0 | 模型通道数×2特征的主干缩放因子（默认：1.2） |
+| `s1` | FLOAT | 是 | 0.0 - 10.0 | 模型通道数×4特征的跳跃连接缩放因子（默认：0.9） |
+| `s2` | FLOAT | 是 | 0.0 - 10.0 | 模型通道数×2特征的跳跃连接缩放因子（默认：0.2） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `模型` | MODEL | 应用了 FreeU 补丁的修改后模型 |
diff --git a/zh-CN/built-in-nodes/FreeU_V2.mdx b/zh-CN/built-in-nodes/FreeU_V2.mdx
new file mode 100644
index 000000000..8622a1b9f
--- /dev/null
+++ b/zh-CN/built-in-nodes/FreeU_V2.mdx
@@ -0,0 +1,26 @@
+---
+title: "FreeU_V2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the FreeU_V2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "FreeU_V2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FreeU_V2/zh.md)
+
+FreeU_V2 节点通过修改 U-Net 架构对扩散模型进行基于频率的增强。它使用可配置参数对不同特征通道进行缩放，从而在不需额外训练的情况下提升图像生成质量。该节点通过修补模型的输出块，将缩放因子应用于特定通道维度。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型` | MODEL | 是 | - | 要应用 FreeU 增强的扩散模型 |
+| `b1` | FLOAT | 是 | 0.0 - 10.0 | 第一区块的主干特征缩放因子（默认：1.3） |
+| `b2` | FLOAT | 是 | 0.0 - 10.0 | 第二区块的主干特征缩放因子（默认：1.4） |
+| `s1` | FLOAT | 是 | 0.0 - 10.0 | 第一区块的跳跃特征缩放因子（默认：0.9） |
+| `s2` | FLOAT | 是 | 0.0 - 10.0 | 第二区块的跳跃特征缩放因子（默认：0.2） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `模型` | MODEL | 应用了 FreeU 修改的增强版扩散模型 |
diff --git a/zh-CN/built-in-nodes/GITSScheduler.mdx b/zh-CN/built-in-nodes/GITSScheduler.mdx
new file mode 100644
index 000000000..fd4efa66d
--- /dev/null
+++ b/zh-CN/built-in-nodes/GITSScheduler.mdx
@@ -0,0 +1,26 @@
+---
+title: "GITSScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GITSScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GITSScheduler"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GITSScheduler/zh.md)
+
+GITSScheduler 节点为 GITS（生成式迭代时间步长）采样方法生成噪声调度 sigma 值。该节点基于系数参数和步长数量计算 sigma 值，并包含一个可选的降噪因子，可用于减少实际使用的总步数。该节点使用预定义的噪声级别和插值方法来创建最终的 sigma 调度表。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `系数` | FLOAT | 是 | 0.80 - 1.50 | 控制噪声调度曲线的系数值（默认：1.20） |
+| `步数` | INT | 是 | 2 - 1000 | 生成 sigma 值所需的总采样步数（默认：10） |
+| `降噪` | FLOAT | 是 | 0.0 - 1.0 | 降噪因子，可减少实际使用的步数（默认：1.0） |
+
+**注意：** 当 `denoise` 设置为 0.0 时，节点将返回空张量。当 `denoise` 小于 1.0 时，实际使用的步数按 `round(steps * denoise)` 计算。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | 为噪声调度生成的 sigma 值 |
diff --git a/zh-CN/built-in-nodes/GLIGENLoader.mdx b/zh-CN/built-in-nodes/GLIGENLoader.mdx
new file mode 100644
index 000000000..2e84d0ed3
--- /dev/null
+++ b/zh-CN/built-in-nodes/GLIGENLoader.mdx
@@ -0,0 +1,23 @@
+---
+title: "GLIGENLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GLIGENLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GLIGENLoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/gligen` 文件夹下的模型，
+同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，
+有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+GLIGEN模型加载节点旨在加载GLIGEN模型，这些是专门的生成模型。它简化了从指定路径检索和初始化这些模型的过程，使它们准备好用于进一步的生成任务。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `gligen名称` | COMBO[STRING] | 要加载的GLIGEN模型的名称。此参数指定要检索和加载的模型文件，在初始化GLIGEN模型以供使用时起着关键作用。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `gligen` | GLIGEN | 加载的GLIGEN模型，准备用于生成任务。此输出表示已从指定路径加载的完全初始化的模型。 |
diff --git a/zh-CN/built-in-nodes/GLIGENTextBoxApply.mdx b/zh-CN/built-in-nodes/GLIGENTextBoxApply.mdx
new file mode 100644
index 000000000..bc9bfafe1
--- /dev/null
+++ b/zh-CN/built-in-nodes/GLIGENTextBoxApply.mdx
@@ -0,0 +1,29 @@
+---
+title: "GLIGENTextBoxApply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GLIGENTextBoxApply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GLIGENTextBoxApply"
+icon: "circle"
+mode: wide
+---
+
+`GLIGENTextBoxApply` 节点旨在将基于文本的条件信息整合到生成模型的输入中，具体做法是应用文本框参数并使用 CLIP 模型对其进行编码。这个过程通过空间和文本信息丰富了条件信息，从而促进了更精确和上下文感知的生成。
+
+## 输入
+
+| 参数名称             | 数据类型           | 作用                                                         |
+|----------------------|------------------|------------------------------------------------------------|
+| `条件到`    | `CONDITIONING`   | 指定初始条件输入，文本框参数和编码后的文本信息将附加于此。它通过整合新的条件数据，在确定最终输出中起着关键作用。 |
+| `CLIPCLIP`               | `CLIP`            | 用于将提供的文本编码为生成模型可以使用的格式的 CLIP 模型。它对于将文本信息转换为兼容的条件格式至关重要。 |
+| `GLIGEN文本框模型` | `GLIGEN`        | 表示要用于生成文本框的特定 GLIGEN 模型配置。它对于确保根据所需的规格生成文本框至关重要。 |
+| `文本`               | `STRING`          | 要编码并整合到条件中的文本内容。它提供了指导生成模型的语义信息。 |
+| `宽度`              | `INT`             | 文本框的宽度，以像素为单位。它定义了文本框在生成图像中的空间尺寸。 |
+| `高度`             | `INT`             | 文本框的高度，以像素为单位。与宽度类似，它定义了文本框在生成图像中的空间尺寸。 |
+| `x`                  | `INT`             | 文本框在生成图像内左上角的 x 坐标。它指定了文本框的水平位置。 |
+| `y`                  | `INT`             | 文本框在生成图像内左上角的 y 坐标。它指定了文本框的垂直位置。 |
+
+## 输出
+
+| 参数名称             | 数据类型           | 作用                                                         |
+|----------------------|------------------|------------------------------------------------------------|
+| `conditioning`       | `CONDITIONING`   | 丰富的条件输出，包括原始条件数据以及新附加的文本框参数和编码后的文本信息。它用于指导生成模型产生上下文感知的输出。 |
+S
diff --git a/zh-CN/built-in-nodes/GLSLShader.mdx b/zh-CN/built-in-nodes/GLSLShader.mdx
new file mode 100644
index 000000000..8aa0812a2
--- /dev/null
+++ b/zh-CN/built-in-nodes/GLSLShader.mdx
@@ -0,0 +1,38 @@
+---
+title: "GLSLShader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GLSLShader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GLSLShader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GLSLShader/zh.md)
+
+GLSL Shader 节点将自定义的 GLSL ES 片段着色器代码应用于输入图像。它允许您编写可以处理多个图像并接受统一参数（浮点数和整数）以创建复杂视觉效果的着色器程序。输出尺寸可以由第一个输入图像决定，也可以手动设置。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `fragment_shader` | STRING | 是 | 不适用 | GLSL 片段着色器源代码（兼容 GLSL ES 3.00 / WebGL 2.0）。默认值：一个输出第一个输入图像的基本着色器。 |
+| `size_mode` | COMBO | 是 | `"from_input"`<br />`"custom"` | 输出尺寸模式：'from_input' 使用第一个输入图像的尺寸，'custom' 允许手动设置尺寸。 |
+| `width` | INT | 否 | 1 到 16384 | 当 `size_mode` 设置为 `"custom"` 时，输出图像的宽度。默认值：512。 |
+| `height` | INT | 否 | 1 到 16384 | 当 `size_mode` 设置为 `"custom"` 时，输出图像的高度。默认值：512。 |
+| `images` | IMAGE | 是 | 1 到 8 张图像 | 由着色器处理的输入图像。在着色器代码中，图像以 `u_image0` 到 `u_image7`（sampler2D）的形式提供。 |
+| `floats` | FLOAT | 否 | 0 到 8 个浮点数 | 着色器使用的浮点型统一值。在着色器代码中，浮点数以 `u_float0` 到 `u_float7` 的形式提供。默认值：0.0。 |
+| `ints` | INT | 否 | 0 到 8 个整数 | 着色器使用的整型统一值。在着色器代码中，整数以 `u_int0` 到 `u_int7` 的形式提供。默认值：0。 |
+
+**注意：**
+
+* 仅当 `size_mode` 设置为 `"custom"` 时，`width` 和 `height` 参数才是必需的且可见。
+* 至少需要一个输入图像。
+* 着色器代码始终可以访问一个包含输出尺寸的 `u_resolution`（vec2）统一变量。
+* 最多可以提供 8 个输入图像、8 个浮点型统一变量和 8 个整型统一变量。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE0` | IMAGE | 着色器输出的第一个图像。在着色器代码中通过 `layout(location = 0) out vec4 fragColor0` 提供。 |
+| `IMAGE1` | IMAGE | 着色器输出的第二个图像。在着色器代码中通过 `layout(location = 1) out vec4 fragColor1` 提供。 |
+| `IMAGE2` | IMAGE | 着色器输出的第三个图像。在着色器代码中通过 `layout(location = 2) out vec4 fragColor2` 提供。 |
+| `IMAGE3` | IMAGE | 着色器输出的第四个图像。在着色器代码中通过 `layout(location = 3) out vec4 fragColor3` 提供。 |
diff --git a/zh-CN/built-in-nodes/GeminiImage.mdx b/zh-CN/built-in-nodes/GeminiImage.mdx
new file mode 100644
index 000000000..537c97311
--- /dev/null
+++ b/zh-CN/built-in-nodes/GeminiImage.mdx
@@ -0,0 +1,29 @@
+---
+title: "GeminiImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImage/zh.md)
+
+GeminiImage 节点通过谷歌的 Gemini AI 模型生成文本和图像响应。它允许您提供包括文本提示、图像和文件在内的多模态输入，以创建连贯的文本和图像输出。该节点负责与最新 Gemini 模型的所有 API 通信和响应解析。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `prompt` | STRING | 必填 | "" | - | 用于生成的文本提示 |
+| `model` | COMBO | 必填 | gemini_2_5_flash_image_preview | 可用的 Gemini 模型<br />选项从 GeminiImageModel 枚举中提取 | 用于生成响应的 Gemini 模型 |
+| `seed` | INT | 必填 | 42 | 0 到 18446744073709551615 | 当种子固定为特定值时，模型会尽力为重复请求提供相同的响应。不保证输出具有确定性。此外，即使使用相同的种子值，更改模型或参数设置（如温度）也可能导致响应发生变化。默认情况下使用随机种子值 |
+| `images` | IMAGE | 可选 | 无 | - | 用作模型上下文的可选图像。要包含多个图像，可以使用 Batch Images 节点 |
+| `files` | GEMINI_INPUT_FILES | 可选 | 无 | - | 用作模型上下文的可选文件。接受来自 Gemini Generate Content Input Files 节点的输入 |
+
+**注意：** 该节点包含由系统自动处理的隐藏参数（`auth_token`、`comfy_api_key`、`unique_id`），无需用户输入。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 从 Gemini 模型生成的图像响应 |
+| `STRING` | STRING | 从 Gemini 模型生成的文本响应 |
diff --git a/zh-CN/built-in-nodes/GeminiImage2Node.mdx b/zh-CN/built-in-nodes/GeminiImage2Node.mdx
new file mode 100644
index 000000000..72add2f7c
--- /dev/null
+++ b/zh-CN/built-in-nodes/GeminiImage2Node.mdx
@@ -0,0 +1,36 @@
+---
+title: "GeminiImage2Node - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiImage2Node node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiImage2Node"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImage2Node/zh.md)
+
+GeminiImage2Node 使用 Google 的 Vertex AI Gemini 模型生成或编辑图像。它将文本提示词和可选的参考图像或文件发送到 API，并返回生成的图像和/或文本描述。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | 不适用 | 描述要生成图像或应用编辑的文本提示词。包含模型应遵循的任何约束、风格或细节。 |
+| `model` | COMBO | 是 | `"gemini-3-pro-image-preview"` | 用于生成图像的特定 Gemini 模型。 |
+| `seed` | INT | 是 | 0 至 18446744073709551615 | 当固定为特定值时，模型会尽力为重复请求提供相同的响应。不保证输出具有确定性。更改模型或其他设置可能导致即使使用相同种子也会产生变化。默认值：42。 |
+| `aspect_ratio` | COMBO | 是 | `"auto"`<br />`"1:1"`<br />`"2:3"`<br />`"3:2"`<br />`"3:4"`<br />`"4:3"`<br />`"4:5"`<br />`"5:4"`<br />`"9:16"`<br />`"16:9"`<br />`"21:9"` | 输出图像的期望宽高比。如果设置为 'auto'，则匹配输入图像的宽高比；如果未提供图像，则通常生成 16:9 的正方形。默认值："auto"。 |
+| `resolution` | COMBO | 是 | `"1K"`<br />`"2K"`<br />`"4K"` | 目标输出分辨率。对于 2K/4K，使用 Gemini 原生超分功能。 |
+| `response_modalities` | COMBO | 是 | `"IMAGE+TEXT"`<br />`"IMAGE"` | 选择 'IMAGE' 仅输出图像，或选择 'IMAGE+TEXT' 同时返回生成的图像和文本响应。 |
+| `images` | IMAGE | 否 | 不适用 | 可选的参考图像。要包含多张图像，请使用 Batch Images 节点（最多 14 张）。 |
+| `files` | CUSTOM | 否 | 不适用 | 可选文件，用作模型的上下文。接受来自 Gemini Generate Content Input Files 节点的输入。 |
+| `system_prompt` | STRING | 否 | 不适用 | 规定 AI 行为的基础指令。默认值：预定义的图像生成系统提示词。 |
+
+**约束条件：**
+
+* `images` 输入最多支持 14 张图像。如果提供更多，将引发错误。
+* `files` 输入必须连接到输出 `GEMINI_INPUT_FILES` 数据类型的节点。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 由 Gemini 模型生成或编辑的图像。 |
+| `string` | STRING | 来自模型的文本响应。如果 `response_modalities` 设置为 "IMAGE"，此输出将为空。 |
diff --git a/zh-CN/built-in-nodes/GeminiImageNode.mdx b/zh-CN/built-in-nodes/GeminiImageNode.mdx
new file mode 100644
index 000000000..b4367a9f0
--- /dev/null
+++ b/zh-CN/built-in-nodes/GeminiImageNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "GeminiImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImageNode/zh.md)
+
+GeminiImage 节点通过谷歌的 Gemini AI 模型生成文本和图像响应。它允许您提供包括文本提示、图像和文件在内的多模态输入，以创建连贯的文本和图像输出。该节点负责与最新 Gemini 模型的所有 API 通信和响应解析。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 取值范围 | 描述 |
+|------|-----------|------------|---------|-------|-------------|
+| `prompt` | STRING | 必填 | "" | - | 用于生成的文本提示 |
+| `model` | COMBO | 必填 | gemini_2_5_flash_image_preview | 可用的 Gemini 模型<br />选项从 GeminiImageModel 枚举中提取 | 用于生成响应的 Gemini 模型 |
+| `seed` | INT | 必填 | 42 | 0 到 18446744073709551615 | 当种子固定为特定值时，模型会尽力为重复请求提供相同的响应。不保证确定性输出。此外，即使使用相同的种子值，更改模型或参数设置（如温度）也可能导致响应变化。默认使用随机种子值 |
+| `images` | IMAGE | 可选 | 无 | - | 用作模型上下文的可选图像。要包含多个图像，可以使用 Batch Images 节点 |
+| `files` | GEMINI_INPUT_FILES | 可选 | 无 | - | 用作模型上下文的可选文件。接受来自 Gemini Generate Content Input Files 节点的输入 |
+
+*注意：该节点包含由系统自动处理的隐藏参数（`auth_token`、`comfy_api_key`、`unique_id`），无需用户输入。*
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 从 Gemini 模型生成的图像响应 |
+| `STRING` | STRING | 从 Gemini 模型生成的文本响应 |
diff --git a/zh-CN/built-in-nodes/GeminiInputFiles.mdx b/zh-CN/built-in-nodes/GeminiInputFiles.mdx
new file mode 100644
index 000000000..e1667e5a9
--- /dev/null
+++ b/zh-CN/built-in-nodes/GeminiInputFiles.mdx
@@ -0,0 +1,25 @@
+---
+title: "GeminiInputFiles - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiInputFiles node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiInputFiles"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiInputFiles/zh.md)
+
+为 Gemini API 加载并格式化输入文件。此节点允许用户将文本文件 (.txt) 和 PDF 文件 (.pdf) 作为输入上下文包含在 Gemini 模型中。文件会被转换为 API 所需的适当格式，并且可以链接在一起，以便在单个请求中包含多个文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `file` | COMBO | 是 | 提供多个选项 | 要作为模型上下文包含的输入文件。目前仅接受文本文件 (.txt) 和 PDF 文件 (.pdf)。文件必须小于最大输入文件大小限制。 |
+| `GEMINI_INPUT_FILES` | GEMINI_INPUT_FILES | 否 | 不适用 | 一个可选的附加文件，用于与此节点加载的文件批量组合。允许链接输入文件，以便单个消息可以包含多个输入文件。 |
+
+**注意：** `file` 参数仅显示小于最大输入文件大小限制的文本文件 (.txt) 和 PDF 文件 (.pdf)。文件会自动按名称过滤和排序。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `GEMINI_INPUT_FILES` | GEMINI_INPUT_FILES | 格式化后的文件数据，已准备好供 Gemini LLM 节点使用，包含已加载文件内容，格式符合 API 要求。 |
diff --git a/zh-CN/built-in-nodes/GeminiNode.mdx b/zh-CN/built-in-nodes/GeminiNode.mdx
new file mode 100644
index 000000000..a6b8cbb5c
--- /dev/null
+++ b/zh-CN/built-in-nodes/GeminiNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "GeminiNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GeminiNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GeminiNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiNode/zh.md)
+
+此节点允许用户与 Google 的 Gemini AI 模型交互以生成文本响应。您可以提供多种类型的输入，包括文本、图像、音频、视频和文件，作为模型的上下文，以生成更相关和更有意义的响应。该节点会自动处理所有 API 通信和响应解析。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 提供给模型的文本输入，用于生成响应。您可以包含详细的指令、问题或上下文信息。默认值：空字符串。 |
+| `model` | COMBO | 是 | `gemini-2.0-flash-exp`<br />`gemini-2.0-flash-thinking-exp`<br />`gemini-2.5-pro-exp`<br />`gemini-2.0-flash`<br />`gemini-2.0-flash-thinking`<br />`gemini-2.5-pro`<br />`gemini-2.0-flash-lite`<br />`gemini-1.5-flash`<br />`gemini-1.5-flash-8b`<br />`gemini-1.5-pro`<br />`gemini-1.0-pro` | 用于生成响应的 Gemini 模型。默认值：gemini-2.5-pro。 |
+| `seed` | INT | 是 | 0 到 18446744073709551615 | 当种子固定为特定值时，模型会尽力为重复的请求提供相同的响应。不保证输出是确定性的。此外，即使使用相同的种子值，更改模型或参数设置（例如温度）也可能导致响应发生变化。默认情况下，使用随机种子值。默认值：42。 |
+| `images` | IMAGE | 否 | - | 用作模型上下文的可选图像。要包含多个图像，您可以使用批处理图像节点。默认值：无。 |
+| `audio` | AUDIO | 否 | - | 用作模型上下文的可选音频。默认值：无。 |
+| `video` | VIDEO | 否 | - | 用作模型上下文的可选视频。默认值：无。 |
+| `files` | GEMINI_INPUT_FILES | 否 | - | 用作模型上下文的可选文件。接受来自 Gemini 生成内容输入文件节点的输入。默认值：无。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `STRING` | STRING | 由 Gemini 模型生成的文本响应。 |
diff --git a/zh-CN/built-in-nodes/GenerateTracks.mdx b/zh-CN/built-in-nodes/GenerateTracks.mdx
new file mode 100644
index 000000000..5a60d0bbd
--- /dev/null
+++ b/zh-CN/built-in-nodes/GenerateTracks.mdx
@@ -0,0 +1,38 @@
+---
+title: "GenerateTracks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GenerateTracks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GenerateTracks"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GenerateTracks/zh.md)
+
+`GenerateTracks` 节点为视频生成创建多条平行的运动轨迹。它定义了一条从起点到终点的主路径，然后生成一组与此路径平行、均匀间隔的轨迹。您可以控制路径的形状（直线或贝塞尔曲线）、沿路径移动的速度以及轨迹在哪些帧中可见。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `width` | INT | 是 | 16 - 4096 | 视频帧的宽度（像素）。默认值为 832。 |
+| `height` | INT | 是 | 16 - 4096 | 视频帧的高度（像素）。默认值为 480。 |
+| `start_x` | FLOAT | 是 | 0.0 - 1.0 | 起点位置的归一化 X 坐标 (0-1)。默认值为 0.0。 |
+| `start_y` | FLOAT | 是 | 0.0 - 1.0 | 起点位置的归一化 Y 坐标 (0-1)。默认值为 0.0。 |
+| `end_x` | FLOAT | 是 | 0.0 - 1.0 | 终点位置的归一化 X 坐标 (0-1)。默认值为 1.0。 |
+| `end_y` | FLOAT | 是 | 0.0 - 1.0 | 终点位置的归一化 Y 坐标 (0-1)。默认值为 1.0。 |
+| `num_frames` | INT | 是 | 1 - 1024 | 要为其生成轨迹位置的总帧数。默认值为 81。 |
+| `num_tracks` | INT | 是 | 1 - 100 | 要生成的平行轨迹数量。默认值为 5。 |
+| `track_spread` | FLOAT | 是 | 0.0 - 1.0 | 轨迹之间的归一化距离。轨迹沿垂直于运动方向的方向展开。默认值为 0.025。 |
+| `bezier` | BOOLEAN | 是 | True / False | 启用使用中点作为控制点的贝塞尔曲线路径。默认值为 False。 |
+| `mid_x` | FLOAT | 是 | 0.0 - 1.0 | 贝塞尔曲线的归一化 X 控制点。仅在启用 `bezier` 时使用。默认值为 0.5。 |
+| `mid_y` | FLOAT | 是 | 0.0 - 1.0 | 贝塞尔曲线的归一化 Y 控制点。仅在启用 `bezier` 时使用。默认值为 0.5。 |
+| `interpolation` | COMBO | 是 | `"linear"`<br />`"ease_in"`<br />`"ease_out"`<br />`"ease_in_out"`<br />`"constant"` | 控制沿路径移动的时序/速度。默认值为 "linear"。 |
+| `track_mask` | MASK | 否 | - | 指示可见帧的可选遮罩。 |
+
+**注意：** `mid_x` 和 `mid_y` 参数仅在 `bezier` 参数设置为 `True` 时使用。当 `bezier` 为 `False` 时，路径是从起点到终点的直线。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `TRACKS` | TRACKS | 一个轨迹对象，包含所有帧中所有轨迹的生成路径坐标和可见性信息。 |
+| `track_length` | INT | 生成轨迹的帧数，与输入的 `num_frames` 匹配。 |
diff --git a/zh-CN/built-in-nodes/GetImageSize.mdx b/zh-CN/built-in-nodes/GetImageSize.mdx
new file mode 100644
index 000000000..46b8561f7
--- /dev/null
+++ b/zh-CN/built-in-nodes/GetImageSize.mdx
@@ -0,0 +1,25 @@
+---
+title: "GetImageSize - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GetImageSize node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GetImageSize"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetImageSize/zh.md)
+
+GetImageSize 节点从输入图像中提取尺寸和批次信息。它会返回图像的宽度、高度和批次大小，同时将这些信息作为进度文本显示在节点界面上。原始图像数据保持不变。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 用于提取尺寸信息的输入图像 |
+| `unique_id` | UNIQUE_ID | 否 | - | 用于显示进度信息的内部标识符 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `width` | INT | 输入图像的宽度（像素） |
+| `height` | INT | 输入图像的高度（像素） |
+| `batch_size` | INT | 批次中的图像数量 |
diff --git a/zh-CN/built-in-nodes/GetVideoComponents.mdx b/zh-CN/built-in-nodes/GetVideoComponents.mdx
new file mode 100644
index 000000000..0cd7057a0
--- /dev/null
+++ b/zh-CN/built-in-nodes/GetVideoComponents.mdx
@@ -0,0 +1,26 @@
+---
+title: "GetVideoComponents - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GetVideoComponents node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GetVideoComponents"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetVideoComponents/zh.md)
+
+## 概述
+
+Get Video Components 节点可从视频文件中提取所有主要元素。它将视频分离为独立帧，提取音轨，并提供视频的帧率信息。这使您能够独立处理每个组件以进行后续处理或分析。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `视频` | VIDEO | 是 | - | 要从中提取组件的视频。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `音频` | IMAGE | 从视频中提取的独立帧，以单独图像形式呈现。 |
+| `帧率` | AUDIO | 从视频中提取的音轨。 |
+| `fps` | FLOAT | 视频的帧率，以每秒帧数为单位。 |
diff --git a/zh-CN/built-in-nodes/GrokImageEditNode.mdx b/zh-CN/built-in-nodes/GrokImageEditNode.mdx
new file mode 100644
index 000000000..4a7e2b11c
--- /dev/null
+++ b/zh-CN/built-in-nodes/GrokImageEditNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "GrokImageEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrokImageEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrokImageEditNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokImageEditNode/zh.md)
+
+Grok Image Edit 节点根据文本提示修改现有图像。它使用 Grok API 生成一张或多张新图像，这些图像是在您的描述引导下对输入图像的变体。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"grok-imagine-image-beta"` | 用于图像编辑的特定 AI 模型。 |
+| `image` | IMAGE | 是 | | 待编辑的输入图像。仅支持单张图像。 |
+| `prompt` | STRING | 是 | | 用于生成编辑后图像的文本提示。 |
+| `resolution` | COMBO | 是 | `"1K"` | 输出图像的分辨率。 |
+| `number_of_images` | INT | 否 | 1 到 10 | 要生成的编辑图像数量（默认值：1）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于确定节点是否应重新运行的种子；无论种子值如何，实际结果都是非确定性的（默认值：0）。 |
+
+**注意：** `image` 输入必须恰好包含一张图像。提供多张图像将导致错误。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 由节点生成的编辑后图像。如果 `number_of_images` 大于 1，输出将拼接成一个批次。 |
diff --git a/zh-CN/built-in-nodes/GrokImageNode.mdx b/zh-CN/built-in-nodes/GrokImageNode.mdx
new file mode 100644
index 000000000..fcef7fe42
--- /dev/null
+++ b/zh-CN/built-in-nodes/GrokImageNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "GrokImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrokImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrokImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokImageNode/zh.md)
+
+Grok Image 节点使用 Grok AI 模型，基于文本描述生成一张或多张图像。它会将您的提示词发送至外部服务，并将生成的图像作为可在工作流中使用的张量返回。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"grok-imagine-image-beta"` | 用于图像生成的具体 Grok 模型。 |
+| `prompt` | STRING | 是 | N/A | 用于生成图像的文本提示词。此描述指导 AI 创建内容。 |
+| `aspect_ratio` | COMBO | 是 | `"1:1"`<br />`"2:3"`<br />`"3:2"`<br />`"3:4"`<br />`"4:3"`<br />`"9:16"`<br />`"16:9"`<br />`"9:19.5"`<br />`"19.5:9"`<br />`"9:20"`<br />`"20:9"`<br />`"1:2"`<br />`"2:1"` | 生成图像所需的宽高比。 |
+| `number_of_images` | INT | 否 | 1 到 10 | 要生成的图像数量（默认值：1）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于确定节点是否应重新运行的种子值。实际的图像结果具有不确定性，即使使用相同的种子，结果也会有所不同（默认值：0）。 |
+
+**注意：** `seed` 参数主要用于控制节点在工作流中何时重新执行。由于外部 AI 服务的特性，生成的图像无法重现，即使使用完全相同的种子，多次运行的结果也不会完全相同。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 生成的图像或图像批次。如果 `number_of_images` 为 1，则返回单个图像张量。如果大于 1，则返回一个图像张量批次。 |
diff --git a/zh-CN/built-in-nodes/GrokVideoEditNode.mdx b/zh-CN/built-in-nodes/GrokVideoEditNode.mdx
new file mode 100644
index 000000000..f761ccc9a
--- /dev/null
+++ b/zh-CN/built-in-nodes/GrokVideoEditNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "GrokVideoEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrokVideoEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrokVideoEditNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoEditNode/zh.md)
+
+此节点使用 Grok API 根据文本提示编辑现有视频。它会将您的视频上传，向 AI 模型发送请求以根据您的描述进行修改，并返回新生成的视频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"grok-imagine-video-beta"` | 用于视频编辑的 AI 模型。 |
+| `prompt` | STRING | 是 | N/A | 期望视频的文本描述。 |
+| `video` | VIDEO | 是 | N/A | 待编辑的输入视频。最大支持时长为 8.7 秒，文件大小不超过 50MB。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于确定节点是否应重新运行的种子值。无论种子值如何，实际结果都是非确定性的（默认值：0）。 |
+
+**限制条件：**
+
+* 输入 `video` 的时长必须在 1 到 8.7 秒之间。
+* 输入 `video` 的文件大小不得超过 50MB。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 由 AI 模型生成的编辑后的视频。 |
diff --git a/zh-CN/built-in-nodes/GrokVideoNode.mdx b/zh-CN/built-in-nodes/GrokVideoNode.mdx
new file mode 100644
index 000000000..09ebacdc4
--- /dev/null
+++ b/zh-CN/built-in-nodes/GrokVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "GrokVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrokVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrokVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoNode/zh.md)
+
+Grok Video 节点能够根据文本描述生成短视频。它既可以通过提示词从头创建视频，也可以基于提示词对单张输入图像进行动画化处理。该节点会向外部 API 发送请求并返回生成的视频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"grok-imagine-video-beta"` | 用于视频生成的模型。 |
+| `prompt` | STRING | 是 | - | 期望视频的文本描述。 |
+| `resolution` | COMBO | 是 | `"480p"`<br />`"720p"` | 输出视频的分辨率。 |
+| `aspect_ratio` | COMBO | 是 | `"auto"`<br />`"16:9"`<br />`"4:3"`<br />`"3:2"`<br />`"1:1"`<br />`"2:3"`<br />`"3:4"`<br />`"9:16"` | 输出视频的宽高比。 |
+| `duration` | INT | 是 | 1 到 15 | 输出视频的时长（单位：秒，默认值：6）。 |
+| `seed` | INT | 是 | 0 到 2147483647 | 用于判断节点是否应重新运行的种子值；无论种子值如何，实际结果都是非确定性的（默认值：0）。 |
+| `image` | IMAGE | 否 | - | 用于动画化的可选输入图像。 |
+
+**注意：** 如果提供了 `image`，则仅支持单张图像。提供多张图像将导致错误。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频。 |
diff --git a/zh-CN/built-in-nodes/GrowMask.mdx b/zh-CN/built-in-nodes/GrowMask.mdx
new file mode 100644
index 000000000..dc2a9d85d
--- /dev/null
+++ b/zh-CN/built-in-nodes/GrowMask.mdx
@@ -0,0 +1,22 @@
+---
+title: "GrowMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the GrowMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "GrowMask"
+icon: "circle"
+mode: wide
+---
+扩展遮罩节点旨在修改给定遮罩的大小，可以是扩展或收缩，同时可以选择性地对角落应用渐缩效果。这个功能对于动态调整图像处理任务中的遮罩边界至关重要，允许对感兴趣区域进行更灵活和精确的控制。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `遮罩` | MASK | 要修改的输入遮罩。这个参数是节点操作的核心，作为遮罩扩展或收缩的基础。 |
+| `扩展` | INT | 确定遮罩修改的大小和方向。正值导致遮罩扩展，而负值导致收缩。这个参数直接影响遮罩的最终大小。 |
+| `倒角` | BOOLEAN | 一个布尔标志，设置为 True 时，在修改过程中对遮罩的角落应用渐缩效果。这个选项允许更平滑的过渡和视觉上更吸引人的结果。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `遮罩` | MASK | 应用了指定的扩展/收缩和可选的渐缩角落效果后的修改遮罩。 |
diff --git a/zh-CN/built-in-nodes/HitPawGeneralImageEnhance.mdx b/zh-CN/built-in-nodes/HitPawGeneralImageEnhance.mdx
new file mode 100644
index 000000000..300f0a13d
--- /dev/null
+++ b/zh-CN/built-in-nodes/HitPawGeneralImageEnhance.mdx
@@ -0,0 +1,27 @@
+---
+title: "HitPawGeneralImageEnhance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HitPawGeneralImageEnhance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HitPawGeneralImageEnhance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HitPawGeneralImageEnhance/zh.md)
+
+此节点通过将低分辨率图像放大至超分辨率来增强图像质量，同时去除伪影和噪声。它使用外部 API 处理图像，并能自动调整输入尺寸以确保不超过处理限制。最大允许输出尺寸为 400 万像素。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | STRING | 是 | `"generative_portrait"`<br />`"generative"` | 要使用的图像增强模型。 |
+| `image` | IMAGE | 是 | - | 待增强的输入图像。 |
+| `upscale_factor` | INT | 是 | `1`<br />`2`<br />`4` | 图像尺寸的放大倍数。 |
+| `auto_downscale` | BOOLEAN | 否 | - | 如果输出尺寸将超过限制，则自动缩小输入图像。(默认值: `False`) |
+
+**注意：** 如果计算出的输出尺寸（输入高度 × upscale_factor × 输入宽度 × upscale_factor）超过 4,000,000 像素（4MP）且 `auto_downscale` 被禁用，节点将引发错误。当启用 `auto_downscale` 时，节点将尝试在应用请求的放大倍数之前，先缩小输入图像以使其符合尺寸限制。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 经过增强和放大的输出图像。 |
diff --git a/zh-CN/built-in-nodes/HitPawVideoEnhance.mdx b/zh-CN/built-in-nodes/HitPawVideoEnhance.mdx
new file mode 100644
index 000000000..341385c38
--- /dev/null
+++ b/zh-CN/built-in-nodes/HitPawVideoEnhance.mdx
@@ -0,0 +1,31 @@
+---
+title: "HitPawVideoEnhance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HitPawVideoEnhance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HitPawVideoEnhance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HitPawVideoEnhance/zh.md)
+
+## 概述
+
+HitPaw Video Enhance 节点通过外部 API 提升视频质量。它可以将低分辨率视频放大到更高分辨率，去除视觉伪影并降低噪点。处理费用根据输入视频的时长（每秒）计算。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | DYNAMIC COMBO | 是 | 提供多个选项 | 用于视频增强的 AI 模型。选择一个模型会显示嵌套的 `resolution` 参数。 |
+| `model.resolution` | COMBO | 是 | `"original"`<br />`"720p"`<br />`"1080p"`<br />`"2k/qhd"`<br />`"4k/uhd"`<br />`"8k"` | 增强视频的目标分辨率。某些选项可能根据所选的 `model` 而不可用。 |
+| `video` | VIDEO | 是 | N/A | 待增强的输入视频文件。 |
+
+**约束条件：**
+
+* 输入 `video` 的时长必须在 0.5 秒到 60 分钟（3600 秒）之间。
+* 所选的 `resolution` 必须大于输入视频的尺寸。如果视频是正方形，所选分辨率必须大于其宽度/高度。对于非正方形视频，所选分辨率必须大于视频的较短边尺寸。如果目标分辨率更小，将会引发错误。选择 `"original"` 可保持输入视频的分辨率。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 增强后的视频文件。 |
diff --git a/zh-CN/built-in-nodes/Hunyuan3Dv2Conditioning.mdx b/zh-CN/built-in-nodes/Hunyuan3Dv2Conditioning.mdx
new file mode 100644
index 000000000..c4109b1d6
--- /dev/null
+++ b/zh-CN/built-in-nodes/Hunyuan3Dv2Conditioning.mdx
@@ -0,0 +1,25 @@
+---
+title: "Hunyuan3Dv2Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Hunyuan3Dv2Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Hunyuan3Dv2Conditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2Conditioning/zh.md)
+
+## 概述
+
+Hunyuan3Dv2Conditioning 节点处理 CLIP 视觉输出，为视频模型生成条件数据。它从视觉输出中提取最后隐藏状态的嵌入表示，并创建正负条件对。正条件使用实际的嵌入表示，而负条件则使用相同形状的零值嵌入表示。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip视觉输出` | CLIP_VISION_OUTPUT | 是 | - | 来自 CLIP 视觉模型的输出，包含视觉嵌入表示 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `反向` | CONDITIONING | 包含 CLIP 视觉嵌入表示的正条件数据 |
+| `negative` | CONDITIONING | 包含与正条件嵌入形状匹配的零值嵌入表示的负条件数据 |
diff --git a/zh-CN/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx b/zh-CN/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx
new file mode 100644
index 000000000..edd48c0fe
--- /dev/null
+++ b/zh-CN/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx
@@ -0,0 +1,28 @@
+---
+title: "Hunyuan3Dv2ConditioningMultiView - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Hunyuan3Dv2ConditioningMultiView node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Hunyuan3Dv2ConditioningMultiView"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2ConditioningMultiView/zh.md)
+
+Hunyuan3Dv2ConditioningMultiView 节点处理多视角 CLIP 视觉嵌入以用于 3D 视频生成。它接收可选的前、左、后、右视角嵌入，并将它们与位置编码结合，为视频模型创建条件数据。该节点输出来自组合嵌入的正向条件数据，以及具有零值的负向条件数据。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `前` | CLIP_VISION_OUTPUT | 否 | - | 前视角的 CLIP 视觉输出 |
+| `左` | CLIP_VISION_OUTPUT | 否 | - | 左视角的 CLIP 视觉输出 |
+| `后` | CLIP_VISION_OUTPUT | 否 | - | 后视角的 CLIP 视觉输出 |
+| `右` | CLIP_VISION_OUTPUT | 否 | - | 右视角的 CLIP 视觉输出 |
+
+**注意：** 节点需要至少提供一个视角输入才能正常工作。节点只会处理包含有效 CLIP 视觉输出数据的视角。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `反向` | CONDITIONING | 包含带位置编码的组合多视角嵌入的正向条件数据 |
+| `negative` | CONDITIONING | 用于对比学习的零值负向条件数据 |
diff --git a/zh-CN/built-in-nodes/HunyuanImageToVideo.mdx b/zh-CN/built-in-nodes/HunyuanImageToVideo.mdx
new file mode 100644
index 000000000..1b6e6f31c
--- /dev/null
+++ b/zh-CN/built-in-nodes/HunyuanImageToVideo.mdx
@@ -0,0 +1,36 @@
+---
+title: "HunyuanImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanImageToVideo/zh.md)
+
+HunyuanImageToVideo 节点使用混元视频模型将图像转换为视频潜在表示。该节点接收条件输入和可选的起始图像，生成可供视频生成模型进一步处理的视频潜在表示。该节点支持不同的引导类型，用于控制起始图像对视频生成过程的影响方式。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正向` | CONDITIONING | 是 | - | 用于引导视频生成的正向条件输入 |
+| `vae` | VAE | 是 | - | 用于将图像编码到潜在空间的 VAE 模型 |
+| `宽度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的宽度（单位：像素，默认值：848，步长：16） |
+| `高度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的高度（单位：像素，默认值：480，步长：16） |
+| `长度` | INT | 是 | 1 至 MAX_RESOLUTION | 输出视频的帧数（默认值：53，步长：4） |
+| `批量大小` | INT | 是 | 1 至 4096 | 同时生成的视频数量（默认值：1） |
+| `指导类型` | COMBO | 是 | "v1 (concat)"<br />"v2 (replace)"<br />"custom" | 将起始图像融入视频生成的方法 |
+| `起始图像` | IMAGE | 否 | - | 用于初始化视频生成的可选起始图像 |
+
+**注意：** 当提供 `start_image` 时，节点会根据选择的 `guidance_type` 使用不同的引导方法：
+
+- "v1 (concat)"：将图像潜在表示与视频潜在表示进行拼接
+- "v2 (replace)"：用图像潜在表示替换初始视频帧
+- "custom"：使用图像作为参考潜在表示进行引导
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `潜在空间` | CONDITIONING | 应用了图像引导的修改后正向条件（当提供 start_image 时） |
+| `latent` | LATENT | 准备供视频生成模型进一步处理的视频潜在表示 |
diff --git a/zh-CN/built-in-nodes/HunyuanRefinerLatent.mdx b/zh-CN/built-in-nodes/HunyuanRefinerLatent.mdx
new file mode 100644
index 000000000..140caee53
--- /dev/null
+++ b/zh-CN/built-in-nodes/HunyuanRefinerLatent.mdx
@@ -0,0 +1,27 @@
+---
+title: "HunyuanRefinerLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanRefinerLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanRefinerLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanRefinerLatent/zh.md)
+
+HunyuanRefinerLatent 节点用于处理精炼操作中的条件输入和潜空间输入。该节点对正负条件输入同时应用噪声增强，并结合潜空间图像数据，生成具有特定维度的新潜空间输出以供后续处理。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 待处理的正向条件输入 |
+| `negative` | CONDITIONING | 是 | - | 待处理的负向条件输入 |
+| `latent` | LATENT | 是 | - | 潜空间表示输入 |
+| `noise_augmentation` | FLOAT | 是 | 0.0 - 1.0 | 应用的噪声增强量（默认值：0.10） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 经过噪声增强和潜空间图像拼接处理后的正向条件 |
+| `negative` | CONDITIONING | 经过噪声增强和潜空间图像拼接处理后的负向条件 |
+| `latent` | LATENT | 具有 [batch_size, 32, height, width, channels] 维度的新潜空间输出 |
diff --git a/zh-CN/built-in-nodes/HunyuanVideo15ImageToVideo.mdx b/zh-CN/built-in-nodes/HunyuanVideo15ImageToVideo.mdx
new file mode 100644
index 000000000..7a3b88e85
--- /dev/null
+++ b/zh-CN/built-in-nodes/HunyuanVideo15ImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "HunyuanVideo15ImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanVideo15ImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanVideo15ImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15ImageToVideo/zh.md)
+
+HunyuanVideo15ImageToVideo 节点基于混元视频 1.5 模型，为视频生成准备条件输入和潜在空间数据。它创建视频序列的初始潜在表示，并可选择性地集成起始图像或 CLIP 视觉输出来引导生成过程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 描述视频应包含内容的正面条件提示。 |
+| `negative` | CONDITIONING | 是 | - | 描述视频应避免内容的负面条件提示。 |
+| `vae` | VAE | 是 | - | 用于将起始图像编码到潜在空间的 VAE（变分自编码器）模型。 |
+| `width` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频帧的宽度（以像素为单位）。必须能被 16 整除。（默认值：848） |
+| `height` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频帧的高度（以像素为单位）。必须能被 16 整除。（默认值：480） |
+| `length` | INT | 否 | 1 至 MAX_RESOLUTION | 视频序列的总帧数。（默认值：33） |
+| `batch_size` | INT | 否 | 1 至 4096 | 单批次中生成的视频序列数量。（默认值：1） |
+| `start_image` | IMAGE | 否 | - | 用于初始化视频生成的可选起始图像。如果提供，它将被编码并用于条件化起始帧。 |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | 否 | - | 可选的 CLIP 视觉嵌入，为生成提供额外的视觉条件输入。 |
+
+**注意：** 当提供 `start_image` 时，它会自动使用双线性插值调整大小以匹配指定的 `width` 和 `height`。将使用图像批次的前 `length` 帧。编码后的图像随后会作为 `concat_latent_image` 连同相应的 `concat_mask` 一起添加到 `positive` 和 `negative` 条件输入中。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 修改后的正面条件输入，现在可能包含编码后的起始图像或 CLIP 视觉输出。 |
+| `negative` | CONDITIONING | 修改后的负面条件输入，现在可能包含编码后的起始图像或 CLIP 视觉输出。 |
+| `latent` | LATENT | 一个空的潜在张量，其维度根据指定的批次大小、视频长度、宽度和高度进行配置。 |
diff --git a/zh-CN/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx b/zh-CN/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx
new file mode 100644
index 000000000..93c5d6cc6
--- /dev/null
+++ b/zh-CN/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx
@@ -0,0 +1,29 @@
+---
+title: "HunyuanVideo15LatentUpscaleWithModel - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanVideo15LatentUpscaleWithModel node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanVideo15LatentUpscaleWithModel"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15LatentUpscaleWithModel/zh.md)
+
+Hunyuan Video 15 Latent Upscale With Model 节点用于提升潜在图像表示的分辨率。它首先使用选定的插值方法将潜在样本放大到指定尺寸，然后使用专门的 Hunyuan Video 1.5 放大模型对放大后的结果进行细化，以提高质量。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | LATENT_UPSCALE_MODEL | 是 | N/A | 用于细化放大后样本的 Hunyuan Video 1.5 潜在放大模型。 |
+| `samples` | LATENT | 是 | N/A | 待放大的潜在图像表示。 |
+| `upscale_method` | COMBO | 否 | `"nearest-exact"`<br />`"bilinear"`<br />`"area"`<br />`"bicubic"`<br />`"bislerp"` | 初始放大步骤使用的插值算法（默认：`"bilinear"`）。 |
+| `width` | INT | 否 | 0 至 16384 | 放大后潜在图像的宽度目标值，单位为像素。值为 0 时，将根据目标高度和原始宽高比自动计算宽度。最终输出宽度将是 16 的倍数（默认：1280）。 |
+| `height` | INT | 否 | 0 至 16384 | 放大后潜在图像的高度目标值，单位为像素。值为 0 时，将根据目标宽度和原始宽高比自动计算高度。最终输出高度将是 16 的倍数（默认：720）。 |
+| `crop` | COMBO | 否 | `"disabled"`<br />`"center"` | 确定如何裁剪放大后的潜在图像以适应目标尺寸。 |
+
+**关于尺寸的说明：** 如果 `width` 和 `height` 都设置为 0，节点将返回未经更改的输入 `samples`。如果只有一个维度设置为 0，另一个维度将被计算以保持原始宽高比。最终尺寸总是会被调整为至少 64 像素，并且是 16 的倍数。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 经过放大和模型细化后的潜在图像表示。 |
diff --git a/zh-CN/built-in-nodes/HunyuanVideo15SuperResolution.mdx b/zh-CN/built-in-nodes/HunyuanVideo15SuperResolution.mdx
new file mode 100644
index 000000000..31a1dd63b
--- /dev/null
+++ b/zh-CN/built-in-nodes/HunyuanVideo15SuperResolution.mdx
@@ -0,0 +1,32 @@
+---
+title: "HunyuanVideo15SuperResolution - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HunyuanVideo15SuperResolution node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HunyuanVideo15SuperResolution"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15SuperResolution/zh.md)
+
+HunyuanVideo15SuperResolution 节点为视频超分辨率处理准备条件数据。它接收视频的潜在表示，并可选择性地接收起始图像，然后将它们与噪声增强和 CLIP 视觉数据一起打包成可供模型用于生成更高分辨率输出的格式。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | N/A | 需要用潜在数据和增强数据进行修改的正向条件输入。 |
+| `negative` | CONDITIONING | 是 | N/A | 需要用潜在数据和增强数据进行修改的负向条件输入。 |
+| `vae` | VAE | 否 | N/A | 用于编码可选的 `start_image` 的 VAE。如果提供了 `start_image`，则必须连接此参数。 |
+| `start_image` | IMAGE | 否 | N/A | 用于引导超分辨率的可选起始图像。如果提供，它将被放大并编码到条件潜在空间中。 |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | 否 | N/A | 可选的 CLIP 视觉嵌入，用于添加到条件数据中。 |
+| `latent` | LATENT | 是 | N/A | 将被整合到条件数据中的输入潜在视频表示。 |
+| `noise_augmentation` | FLOAT | 否 | 0.0 - 1.0 | 应用于条件数据的噪声增强强度（默认值：0.70）。 |
+
+**注意：** 如果提供了 `start_image`，则必须同时连接一个 `vae` 来对其进行编码。`start_image` 将自动放大以匹配输入 `latent` 所隐含的尺寸。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 修改后的正向条件数据，现在包含了拼接的潜在数据、噪声增强以及可选的 CLIP 视觉数据。 |
+| `negative` | CONDITIONING | 修改后的负向条件数据，现在包含了拼接的潜在数据、噪声增强以及可选的 CLIP 视觉数据。 |
+| `latent` | LATENT | 输入的潜在数据，原样传递，未作更改。 |
diff --git a/zh-CN/built-in-nodes/HyperTile.mdx b/zh-CN/built-in-nodes/HyperTile.mdx
new file mode 100644
index 000000000..b5268108f
--- /dev/null
+++ b/zh-CN/built-in-nodes/HyperTile.mdx
@@ -0,0 +1,26 @@
+---
+title: "HyperTile - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HyperTile node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HyperTile"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HyperTile/zh.md)
+
+HyperTile 节点对扩散模型中的注意力机制应用分块技术，以优化图像生成过程中的内存使用。它将潜在空间分割成较小的图块并分别处理，然后重新组装结果。这样可以在不耗尽内存的情况下处理更大尺寸的图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用 HyperTile 优化的扩散模型 |
+| `分块尺寸` | INT | 否 | 1-2048 | 处理时的目标图块尺寸（默认值：256） |
+| `分割尺寸` | INT | 否 | 1-128 | 控制处理过程中图块的重新排列方式（默认值：2） |
+| `最大深度` | INT | 否 | 0-10 | 应用分块的最大深度级别（默认值：0） |
+| `规模深度` | BOOLEAN | 否 | - | 是否根据深度级别缩放图块尺寸（默认值：False） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了 HyperTile 优化后的修改模型 |
diff --git a/zh-CN/built-in-nodes/HypernetworkLoader.mdx b/zh-CN/built-in-nodes/HypernetworkLoader.mdx
new file mode 100644
index 000000000..b382e2333
--- /dev/null
+++ b/zh-CN/built-in-nodes/HypernetworkLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "HypernetworkLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the HypernetworkLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "HypernetworkLoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/hypernetworks` 文件夹下的模型，同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+超网络加载节点旨在通过应用超网络来增强或修改给定模型的能力。它加载一个指定的超网络并将其应用于模型，根据强度参数可能改变模型的行为或性能。这个过程允许对模型的架构或参数进行动态调整，从而实现更灵活和适应性的人工智能系统。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型` | MODEL | 应用超网络的模型。此参数至关重要，因为它决定了将被超网络增强或修改的基础架构。 |
+| `HyperNetwork名称` | COMBO[STRING] | 要加载并应用于模型的超网络的名称。此参数指定使用哪个超网络，影响模型的修改后的行为或性能。 |
+| `强度` | FLOAT | 一个标量，用于调整超网络对模型效果的强度。它允许微调超网络如何显著地改变模型的行为或性能。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型` | MODEL | 应用超网络后的修改模型。此输出反映了对原始模型所做的更改，展示了超网络的影响。 |
+
+---
diff --git a/zh-CN/built-in-nodes/IdeogramV1.mdx b/zh-CN/built-in-nodes/IdeogramV1.mdx
new file mode 100644
index 000000000..486ece66c
--- /dev/null
+++ b/zh-CN/built-in-nodes/IdeogramV1.mdx
@@ -0,0 +1,32 @@
+---
+title: "IdeogramV1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the IdeogramV1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "IdeogramV1"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV1/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV1/en.md)
+
+IdeogramV1 节点通过 API 使用 Ideogram V1 模型生成图像。它接收文本提示词和各种生成设置，根据您的输入创建一个或多个图像。该节点支持不同的宽高比和生成模式以自定义输出。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 图像生成的提示词（默认：空） |
+| `turbo` | BOOLEAN | 是 | - | 是否使用极速模式（生成速度更快，可能降低质量）（默认：False） |
+| `aspect_ratio` | COMBO | 否 | "1:1"<br />"16:9"<br />"9:16"<br />"4:3"<br />"3:4"<br />"3:2"<br />"2:3" | 图像生成的宽高比（默认："1:1"） |
+| `magic_prompt_option` | COMBO | 否 | "AUTO"<br />"ON"<br />"OFF" | 确定是否在生成中使用 MagicPrompt（默认："AUTO"） |
+| `seed` | INT | 否 | 0-2147483647 | 生成使用的随机种子值（默认：0） |
+| `negative_prompt` | STRING | 否 | - | 要从图像中排除的内容描述（默认：空） |
+| `num_images` | INT | 否 | 1-8 | 要生成的图像数量（默认：1） |
+
+**注意：** `num_images` 参数每次生成请求最多限制为 8 张图像。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 来自 Ideogram V1 模型生成的图像 |
diff --git a/zh-CN/built-in-nodes/IdeogramV2.mdx b/zh-CN/built-in-nodes/IdeogramV2.mdx
new file mode 100644
index 000000000..025cb8e75
--- /dev/null
+++ b/zh-CN/built-in-nodes/IdeogramV2.mdx
@@ -0,0 +1,34 @@
+---
+title: "IdeogramV2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the IdeogramV2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "IdeogramV2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV2/zh.md)
+
+# Ideogram V2 节点
+
+Ideogram V2 节点使用 Ideogram V2 AI 模型生成图像。它接收文本提示和多种生成设置，通过 API 服务创建图像。该节点支持不同的宽高比、分辨率和风格选项，以自定义输出图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 图像生成的提示词（默认：空字符串） |
+| `turbo` | BOOLEAN | 否 | - | 是否使用极速模式（生成速度更快，可能降低质量）（默认：False） |
+| `aspect_ratio` | COMBO | 否 | "1:1"<br />"16:9"<br />"9:16"<br />"4:3"<br />"3:4"<br />"3:2"<br />"2:3" | 图像生成的宽高比。当分辨率未设置为 AUTO 时忽略此设置。（默认："1:1"） |
+| `resolution` | COMBO | 否 | "Auto"<br />"1024x1024"<br />"1152x896"<br />"896x1152"<br />"1216x832"<br />"832x1216"<br />"1344x768"<br />"768x1344"<br />"1536x640"<br />"640x1536" | 图像生成的分辨率。如果未设置为 AUTO，将覆盖 aspect_ratio 设置。（默认："Auto"） |
+| `magic_prompt_option` | COMBO | 否 | "AUTO"<br />"ON"<br />"OFF" | 确定生成过程中是否使用 MagicPrompt（默认："AUTO"） |
+| `seed` | INT | 否 | 0-2147483647 | 生成随机种子（默认：0） |
+| `style_type` | COMBO | 否 | "AUTO"<br />"GENERAL"<br />"REALISTIC"<br />"DESIGN"<br />"RENDER_3D"<br />"ANIME" | 生成风格类型（仅限 V2 版本）（默认："NONE"） |
+| `negative_prompt` | STRING | 否 | - | 图像中需要排除的内容描述（默认：空字符串） |
+| `num_images` | INT | 否 | 1-8 | 生成的图像数量（默认：1） |
+
+**注意：** 当 `resolution` 未设置为 "Auto" 时，它将覆盖 `aspect_ratio` 设置。`num_images` 参数每次生成最多限制为 8 张图像。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 来自 Ideogram V2 模型生成的图像 |
diff --git a/zh-CN/built-in-nodes/IdeogramV3.mdx b/zh-CN/built-in-nodes/IdeogramV3.mdx
new file mode 100644
index 000000000..6207bf0ba
--- /dev/null
+++ b/zh-CN/built-in-nodes/IdeogramV3.mdx
@@ -0,0 +1,43 @@
+---
+title: "IdeogramV3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the IdeogramV3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "IdeogramV3"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV3/zh.md)
+
+# Ideogram V3 节点
+
+Ideogram V3 节点使用 Ideogram V3 模型生成图像。它支持基于文本提示的常规图像生成，以及在提供图像和遮罩时的图像编辑功能。该节点提供多种控制选项，包括宽高比、分辨率、生成速度以及可选的字符参考图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 用于图像生成或编辑的提示词（默认：空） |
+| `image` | IMAGE | 否 | - | 用于图像编辑的可选参考图像 |
+| `mask` | MASK | 否 | - | 用于局部重绘的可选遮罩（白色区域将被替换） |
+| `aspect_ratio` | COMBO | 否 | "1:1"<br />"16:9"<br />"9:16"<br />"4:3"<br />"3:4"<br />"3:2"<br />"2:3" | 图像生成的宽高比。如果分辨率未设置为自动，则忽略此参数（默认："1:1"） |
+| `resolution` | COMBO | 否 | "Auto"<br />"1024x1024"<br />"1152x896"<br />"896x1152"<br />"1216x832"<br />"832x1216"<br />"1344x768"<br />"768x1344"<br />"1536x640"<br />"640x1536" | 图像生成的分辨率。如果未设置为自动，将覆盖 aspect_ratio 设置（默认："Auto"） |
+| `magic_prompt_option` | COMBO | 否 | "AUTO"<br />"ON"<br />"OFF" | 确定生成过程中是否使用 MagicPrompt（默认："AUTO"） |
+| `seed` | INT | 否 | 0-2147483647 | 生成图像的随机种子（默认：0） |
+| `num_images` | INT | 否 | 1-8 | 要生成的图像数量（默认：1） |
+| `rendering_speed` | COMBO | 否 | "DEFAULT"<br />"TURBO"<br />"QUALITY" | 控制生成速度与质量之间的权衡（默认："DEFAULT"） |
+| `character_image` | IMAGE | 否 | - | 用作字符参考的图像 |
+| `character_mask` | MASK | 否 | - | 字符参考图像的可选遮罩 |
+
+**参数约束：**
+
+- 当同时提供 `image` 和 `mask` 时，节点将切换到编辑模式
+- 如果只提供 `image` 或 `mask` 中的一个，将发生错误
+- `character_mask` 需要与 `character_image` 同时存在
+- 当 `resolution` 未设置为 "Auto" 时，`aspect_ratio` 参数将被忽略
+- 局部重绘过程中，遮罩中的白色区域将被替换
+- 字符遮罩和字符图像必须具有相同尺寸
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 生成或编辑后的图像 |
diff --git a/zh-CN/built-in-nodes/ImageAddNoise.mdx b/zh-CN/built-in-nodes/ImageAddNoise.mdx
new file mode 100644
index 000000000..ebfe1cb63
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageAddNoise.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageAddNoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageAddNoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageAddNoise"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageAddNoise/zh.md)
+
+ImageAddNoise 节点用于向输入图像添加随机噪声。它使用指定的随机种子生成一致的噪声模式，并允许控制噪声效果的强度。输出图像保持与输入相同的尺寸，但增加了视觉纹理。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 需要添加噪声的输入图像 |
+| `seed` | INT | 是 | 0 到 18446744073709551615 | 用于创建噪声的随机种子（默认值：0） |
+| `strength` | FLOAT | 是 | 0.0 到 1.0 | 控制噪声效果的强度（默认值：0.5） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 应用了噪声效果的输出图像 |
diff --git a/zh-CN/built-in-nodes/ImageBatch.mdx b/zh-CN/built-in-nodes/ImageBatch.mdx
new file mode 100644
index 000000000..a277b97d6
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageBatch.mdx
@@ -0,0 +1,21 @@
+---
+title: "ImageBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageBatch"
+icon: "circle"
+mode: wide
+---
+此节点设计用于将两张图像组合成单个批量。如果图像的尺寸不匹配，它会自动重新调整第二张图像的尺寸以匹配第一张图像的尺寸，然后再将它们组合。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像1` | `IMAGE` | 第一张要组合进批量的图像。如果需要，它作为第二张图像将被调整到的尺寸的参考。 |
+| `图像2` | `IMAGE` | 第二张要组合进批量的图像。如果它们不同，它会被自动重新调整尺寸以匹配第一张图像的尺寸。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `image` | `IMAGE` | 组合后的图像批量，必要时第二张图像已重新调整尺寸以匹配第一张图像的尺寸。 |
diff --git a/zh-CN/built-in-nodes/ImageBlend.mdx b/zh-CN/built-in-nodes/ImageBlend.mdx
new file mode 100644
index 000000000..f2ad7b0e7
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageBlend.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageBlend - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageBlend node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageBlend"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于根据指定的混合模式和混合因子将两张图像混合在一起。它支持各种混合模式，如正常、乘法、屏幕、叠加、柔光和差异，允许进行多功能的图像操作和组合技术。此节点对于通过调整两个图像层之间的视觉交互来创建复合图像至关重要。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像1` | `IMAGE` | 第一张要混合的图像。它作为混合操作的基础层。 |
+| `图像2` | `IMAGE` | 第二张要混合的图像。根据混合模式，它修改第一张图像的外观。 |
+| `系数` | `FLOAT` | 确定第二张图像在混合中的权重。更高的混合因子会使第二张图像在结果混合中更加突出。 |
+| `混合模式` | COMBO[STRING] | 指定两种图像混合的方法。支持正常、乘法、屏幕、叠加、柔光和差异等模式，每种模式都产生独特的视觉效果。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `image` | `IMAGE` | 根据指定的混合模式和因子混合两张输入图像后得到的图像。 |
diff --git a/zh-CN/built-in-nodes/ImageBlur.mdx b/zh-CN/built-in-nodes/ImageBlur.mdx
new file mode 100644
index 000000000..cd0ff8831
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageBlur.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageBlur - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageBlur node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageBlur"
+icon: "circle"
+mode: wide
+---
+此节点对图像应用高斯模糊，允许软化边缘并减少细节和噪声。它通过参数提供对模糊强度和扩散的控制。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 要模糊的输入图像。这是模糊效果的主要目标。 |
+| `模糊半径` | `INT` | 确定模糊效果的半径。更大的半径会导致更明显的模糊。 |
+| `西格玛` | `FLOAT` | 控制模糊的扩散。更高的sigma值意味着模糊将影响每个像素周围的更广泛区域。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 输出是输入图像的模糊版本，模糊程度由输入参数决定。 |
diff --git a/zh-CN/built-in-nodes/ImageColorToMask.mdx b/zh-CN/built-in-nodes/ImageColorToMask.mdx
new file mode 100644
index 000000000..bc087bb3f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageColorToMask.mdx
@@ -0,0 +1,21 @@
+---
+title: "ImageColorToMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageColorToMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageColorToMask"
+icon: "circle"
+mode: wide
+---
+图像颜色转遮罩节点用于将图像中的指定颜色转换为遮罩。它处理一张图像和一个目标颜色，生成一个遮罩，其中指定的颜色被突出显示，这有助于进行基于颜色的分割或对象隔离等操作。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | IMAGE | 输入图像，用于确定图像中与指定颜色匹配的区域，这些区域将被转换为遮罩。 |
+| `颜色` | INT | 指定图像中要转换为遮罩的目标颜色，它在识别结果遮罩中要突出显示的特定颜色区域中起着关键作用。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `mask` | MASK | 输出是一个遮罩，它突出显示输入图像中与指定颜色匹配的区域。这个遮罩可以用于进一步的图像处理任务，如分割或对象隔离。 |
diff --git a/zh-CN/built-in-nodes/ImageCompare.mdx b/zh-CN/built-in-nodes/ImageCompare.mdx
new file mode 100644
index 000000000..057ce1c48
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageCompare.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageCompare - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageCompare node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageCompare"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageCompare/zh.md)
+
+Image Compare 节点提供了一个可视化界面，通过可拖动的滑块并排比较两张图像。它被设计为输出节点，这意味着它不会将数据传递给其他节点，而是直接在用户界面中显示图像以供检查。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image_a` | IMAGE | 否 | - | 要比较的第一张图像。 |
+| `image_b` | IMAGE | 否 | - | 要比较的第二张图像。 |
+| `compare_view` | IMAGECOMPARE | 是 | - | 在用户界面中启用滑块比较视图的控件。 |
+
+**注意：** 此节点是一个输出节点。虽然 `image_a` 和 `image_b` 是可选的，但必须至少提供一张图像，节点才能产生可见效果。对于任何未连接的图像输入，节点将显示一个空白区域。
+
+## 输出参数
+
+此节点是一个输出节点，不产生任何可供其他节点使用的数据输出。其功能是在 ComfyUI 界面中显示提供的图像。
diff --git a/zh-CN/built-in-nodes/ImageCompositeMasked.mdx b/zh-CN/built-in-nodes/ImageCompositeMasked.mdx
new file mode 100644
index 000000000..4e8efed7c
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageCompositeMasked.mdx
@@ -0,0 +1,25 @@
+---
+title: "ImageCompositeMasked - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageCompositeMasked node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageCompositeMasked"
+icon: "circle"
+mode: wide
+---
+此节点设计用于组合图像，允许将源图像覆盖在目标图像上，在指定坐标处进行叠加，可选择调整大小和使用遮罩。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `目标图像` | `IMAGE` | 目标图像，源图像将组合在此图像上。它作为组合操作的背景。 |
+| `来源图像` | `IMAGE` | 要组合到目标图像上的源图像。此图像可以选择性地调整大小以适应目标图像的尺寸。 |
+| `x` | `INT` | 在目标图像中，源图像左上角放置的x坐标。 |
+| `y` | `INT` | 在目标图像中，源图像左上角放置的y坐标。 |
+| `缩放来源图像` | `BOOLEAN` | 一个布尔标志，指示是否应调整源图像的尺寸以匹配目标图像的尺寸。 |
+| `遮罩` | `MASK` | 一个可选的遮罩，指定应将源图像的哪些部分组合到目标图像上。这允许进行更复杂的组合操作，如混合或部分叠加。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `image` | `IMAGE` | 图像组合操作后的结果图像，根据指定参数结合了源图像和目标图像的元素。 |
diff --git a/zh-CN/built-in-nodes/ImageCrop.mdx b/zh-CN/built-in-nodes/ImageCrop.mdx
new file mode 100644
index 000000000..704558b5b
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageCrop.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageCrop - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageCrop node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageCrop"
+icon: "circle"
+mode: wide
+---
+此节点设计用于根据指定的宽度和高度以及给定的 x 和 y 坐标对图像进行裁剪。这一功能对于聚焦于图像的特定区域或调整图像大小以满足某些要求至关重要。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 要裁剪的输入图像。此参数至关重要，因为它定义了将根据指定的尺寸和坐标提取区域的源图像。 |
+| `宽度` | `INT` | 指定裁剪图像的宽度。此参数决定了结果裁剪图像的宽度。 |
+| `高度` | `INT` | 指定裁剪图像的高度。此参数决定了结果裁剪图像的高度。 |
+| `x` | `INT` | 裁剪区域左上角的 x 坐标。此参数为裁剪的宽度维度设置了起始点。 |
+| `y` | `INT` | 裁剪区域左上角的 y 坐标。此参数为裁剪的高度维度设置了起始点。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 裁剪操作的结果图像。此输出对于进一步处理或分析指定的图像区域非常重要。 |
diff --git a/zh-CN/built-in-nodes/ImageCropV2.mdx b/zh-CN/built-in-nodes/ImageCropV2.mdx
new file mode 100644
index 000000000..d40864d7f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageCropV2.mdx
@@ -0,0 +1,25 @@
+---
+title: "ImageCropV2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageCropV2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageCropV2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageCropV2/zh.md)
+
+图像裁剪节点从输入图像中提取一个矩形区域。您可以通过指定其左上角坐标以及宽度和高度来定义要保留的区域。该节点随后会返回原始图像的裁剪部分。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | 不适用 | 待裁剪的输入图像。 |
+| `crop_region` | BOUNDINGBOX | 是 | 不适用 | 定义要从图像中提取的矩形区域。它由 `x`（水平起始位置）、`y`（垂直起始位置）、`width`（宽度）和 `height`（高度）指定。如果定义的区域超出了图像的边界，它将自动调整以适应图像的尺寸。 |
+
+**关于区域约束的说明：** 裁剪区域会自动被约束在输入图像的边界内。如果指定的 `x` 或 `y` 坐标大于图像的宽度或高度，它将被设置为最大有效位置。最终的裁剪宽度和高度将被调整，以确保区域不超过图像的边缘。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 原始输入图像的裁剪部分。 |
diff --git a/zh-CN/built-in-nodes/ImageDeduplication.mdx b/zh-CN/built-in-nodes/ImageDeduplication.mdx
new file mode 100644
index 000000000..12d657727
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageDeduplication.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageDeduplication - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageDeduplication node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageDeduplication"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageDeduplication/zh.md)
+
+此节点从一批图像中移除重复或高度相似的图像。其工作原理是为每张图像创建感知哈希——一种基于视觉内容的简单数字指纹——然后进行比较。哈希相似度超过设定阈值的图像将被视为重复项并被过滤掉。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | - | 需要进行去重处理的图像批次。 |
+| `similarity_threshold` | FLOAT | 否 | 0.0 - 1.0 | 相似度阈值（0-1）。值越高表示相似度要求越严格。超过此阈值的图像被视为重复项。（默认值：0.95） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `images` | IMAGE | 已移除重复项后的过滤图像列表。 |
diff --git a/zh-CN/built-in-nodes/ImageFlip.mdx b/zh-CN/built-in-nodes/ImageFlip.mdx
new file mode 100644
index 000000000..3fc71233f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageFlip.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageFlip - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageFlip node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageFlip"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageFlip/zh.md)
+
+ImageFlip 节点可沿不同轴向翻转图像。它能够沿 x 轴垂直翻转或沿 y 轴水平翻转图像。该节点基于选定方法使用 torch.flip 操作执行翻转。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 功能说明 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待翻转的输入图像 |
+| `flip_method` | STRING | 是 | "x-axis: vertically"<br />"y-axis: horizontally" | 需要应用的翻转方向 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 功能说明 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 翻转后的输出图像 |
diff --git a/zh-CN/built-in-nodes/ImageFromBatch.mdx b/zh-CN/built-in-nodes/ImageFromBatch.mdx
new file mode 100644
index 000000000..42b837a5c
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageFromBatch.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageFromBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageFromBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageFromBatch"
+icon: "circle"
+mode: wide
+---
+`ImageFromBatch`节点设计用于根据提供的索引和长度从一批图像中提取特定段。它允许对批处理图像进行更细粒度的控制，使得可以对较大批次中的单个或子集图像执行操作。
+
+## 输入
+
+| 参数名称     | 数据类型 | 作用描述                                   |
+| ------------ | -------- | ------------------------------------------ |
+| `图像`      | IMAGE    | 需要从中提取段的图像批次。此参数对于指定源批次至关重要。 |
+| `批次索引`| INT      | 从批次中开始提取的起始索引。它决定了从批次中提取段的初始位置。 |
+| `长度`     | INT      | 从`批次索引`开始从批次中提取的图像数量。此参数定义了要提取的段的大小。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用描述                                     |
+| -------- | -------- | -------------------------------------------- |
+| `图像`  | IMAGE    | 从指定批次中提取的图像段。此输出表示原始批次的一个子集，由`批次索引`和`长度`参数确定。 |
diff --git a/zh-CN/built-in-nodes/ImageGrid.mdx b/zh-CN/built-in-nodes/ImageGrid.mdx
new file mode 100644
index 000000000..8010e2564
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageGrid.mdx
@@ -0,0 +1,26 @@
+---
+title: "ImageGrid - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageGrid node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageGrid"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageGrid/zh.md)
+
+图像网格节点将多张图像组合成一个有序的网格或拼贴画。它接收一个图像列表，并将它们排列到指定数量的列中，调整每张图像的大小以适配定义的单元格尺寸，并可在图像之间添加可选的内边距。最终输出是一张包含所有输入图像、按网格布局排列的新图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | - | 要排列到网格中的图像列表。节点至少需要一张图像才能工作。 |
+| `columns` | INT | 否 | 1 - 20 | 网格中的列数（默认值：4）。 |
+| `cell_width` | INT | 否 | 32 - 2048 | 网格中每个单元格的宽度，单位为像素（默认值：256）。 |
+| `cell_height` | INT | 否 | 32 - 2048 | 网格中每个单元格的高度，单位为像素（默认值：256）。 |
+| `padding` | INT | 否 | 0 - 50 | 网格中图像之间的内边距大小，单位为像素（默认值：4）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 包含所有输入图像并按网格排列的单一输出图像。 |
diff --git a/zh-CN/built-in-nodes/ImageInvert.mdx b/zh-CN/built-in-nodes/ImageInvert.mdx
new file mode 100644
index 000000000..769414b86
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageInvert.mdx
@@ -0,0 +1,20 @@
+---
+title: "ImageInvert - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageInvert node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageInvert"
+icon: "circle"
+mode: wide
+---
+此节点设计用于反色图像的颜色，有效地将每个像素的颜色值转换为其在色轮上的互补色。此操作适用于创建负片图像或需要颜色反色的视觉效果。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | `图像`参数代表要反色的输入图像。它对于指定要反色的目标图像至关重要，影响节点的执行和反色过程的视觉结果。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 输出是输入图像的反色版本，每个像素的颜色值被转换为其互补色。 |
diff --git a/zh-CN/built-in-nodes/ImageOnlyCheckpointLoader.mdx b/zh-CN/built-in-nodes/ImageOnlyCheckpointLoader.mdx
new file mode 100644
index 000000000..f44deba60
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageOnlyCheckpointLoader.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageOnlyCheckpointLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageOnlyCheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageOnlyCheckpointLoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/checkpoints` 文件夹下的模型，同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+此节点专门用于加载视频生成工作流中基于图像的模型的检查点。它有效地检索和配置来自给定检查点的所需组件，专注于模型的图像相关方面。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Checkpoint名称` | COMBO[STRING] | 指定要加载的检查点的名称。此参数对于从预定义的可用检查点列表中识别和检索正确的检查点文件至关重要。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `model` | MODEL | 返回从检查点加载的并配置用于视频生成上下文中的图像处理的主要模型。 |
+| `clip_vision` | CLIP_VISION | 提供从检查点提取的CLIP视觉组件，专为图像理解和特征提取而设计。 |
+| `vae` | VAE | 提供变分自编码器（VAE）组件，对图像操作和生成任务至关重要。 |
diff --git a/zh-CN/built-in-nodes/ImageOnlyCheckpointSave.mdx b/zh-CN/built-in-nodes/ImageOnlyCheckpointSave.mdx
new file mode 100644
index 000000000..48721d924
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageOnlyCheckpointSave.mdx
@@ -0,0 +1,27 @@
+---
+title: "ImageOnlyCheckpointSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageOnlyCheckpointSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageOnlyCheckpointSave"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageOnlyCheckpointSave/zh.md)
+
+ImageOnlyCheckpointSave 节点用于保存包含模型、CLIP 视觉编码器和 VAE 的检查点文件。它会创建具有指定文件名前缀的 safetensors 文件，并将其存储在输出目录中。该节点专门设计用于将图像相关的模型组件一起保存在单个检查点文件中。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|--------|-----------|------|----------|------|
+| `模型` | MODEL | 是 | - | 要保存到检查点中的模型 |
+| `clip视觉` | CLIP_VISION | 是 | - | 要保存到检查点中的 CLIP 视觉编码器 |
+| `vae` | VAE | 是 | - | 要保存到检查点中的 VAE（变分自编码器） |
+| `文件名前缀` | STRING | 是 | - | 输出文件名的前缀（默认："checkpoints/ComfyUI"） |
+| `prompt` | PROMPT | 否 | - | 用于工作流提示数据的隐藏参数 |
+| `extra_pnginfo` | EXTRA_PNGINFO | 否 | - | 用于额外 PNG 元数据的隐藏参数 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| - | - | 此节点不返回任何输出 |
diff --git a/zh-CN/built-in-nodes/ImagePadForOutpaint.mdx b/zh-CN/built-in-nodes/ImagePadForOutpaint.mdx
new file mode 100644
index 000000000..d887565dc
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImagePadForOutpaint.mdx
@@ -0,0 +1,26 @@
+---
+title: "ImagePadForOutpaint - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImagePadForOutpaint node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImagePadForOutpaint"
+icon: "circle"
+mode: wide
+---
+此节点设计用于通过在图像周围添加填充来准备图像进行外延处理。它调整图像尺寸以确保与外延算法兼容，从而方便生成超出原始边界的扩展图像区域。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | `图像`输入是要准备进行外延处理的主图像，作为填充操作的基础。 |
+| `左` | `INT` | 指定要在图像左侧添加的填充量，影响外延的扩展区域。 |
+| `上` | `INT` | 确定要在图像顶部添加的填充量，影响外延的垂直扩展。 |
+| `右` | `INT` | 定义要在图像右侧添加的填充量，影响外延的水平扩展。 |
+| `下` | `INT` | 指示要在图像底部添加的填充量，有助于外延的垂直扩展。 |
+| `羽化` | `INT` | 控制原始图像与添加的填充之间的过渡平滑度，增强外延的视觉融合。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 输出`图像`代表已填充的图像，准备好进行外延处理。 |
+| `mask` | `MASK` | 输出`mask`指示原始图像和添加的填充区域，有助于指导外延算法。 |
diff --git a/zh-CN/built-in-nodes/ImageQuantize.mdx b/zh-CN/built-in-nodes/ImageQuantize.mdx
new file mode 100644
index 000000000..ed850a8df
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageQuantize.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageQuantize - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageQuantize node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageQuantize"
+icon: "circle"
+mode: wide
+---
+此节点设计用于将图像的颜色数量减少到指定数量，可选择应用抖动技术以维持视觉质量。此过程适用于创建基于调色板的图像或为了某些应用减少颜色复杂性。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 要量化的输入图像张量。它作为颜色减少执行的主要数据。 |
+| `颜色` | `INT` | 指定要将图像减少到的颜色数量。它通过确定调色板大小直接影响量化过程。 |
+| `抖动` | COMBO[STRING] | 确定量化过程中应用的抖动技术，影响输出图像的视觉质量和外观。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 输入图像的量化版本，颜色复杂性减少，并可选择性地应用抖动以维持视觉质量。 |
+
+---
diff --git a/zh-CN/built-in-nodes/ImageRGBToYUV.mdx b/zh-CN/built-in-nodes/ImageRGBToYUV.mdx
new file mode 100644
index 000000000..da15ac605
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageRGBToYUV.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageRGBToYUV - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageRGBToYUV node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageRGBToYUV"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageRGBToYUV/zh.md)
+
+ImageRGBToYUV 节点可将 RGB 彩色图像转换为 YUV 色彩空间。该节点接收 RGB 图像作为输入，并将其分离为三个独立通道：Y（亮度）、U（蓝色投影）和 V（红色投影）。每个输出通道均以独立的灰度图像形式返回，分别对应相应的 YUV 分量。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 需要转换为 YUV 色彩空间的输入 RGB 图像 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `U` | IMAGE | YUV 色彩空间中的亮度分量 |
+| `V` | IMAGE | YUV 色彩空间中的蓝色投影分量 |
+| `V` | IMAGE | YUV 色彩空间中的红色投影分量 |
diff --git a/zh-CN/built-in-nodes/ImageRotate.mdx b/zh-CN/built-in-nodes/ImageRotate.mdx
new file mode 100644
index 000000000..f334c8cb5
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageRotate.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageRotate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageRotate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageRotate"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageRotate/zh.md)
+
+ImageRotate 节点可将输入图像按指定角度进行旋转。它支持四种旋转选项：不旋转、顺时针90度、180度以及顺时针270度。该节点采用高效的张量运算来执行旋转操作，能够完整保持图像数据完整性。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 需要旋转的输入图像 |
+| `rotation` | STRING | 是 | "none"<br />"90 degrees"<br />"180 degrees"<br />"270 degrees" | 要应用于图像的旋转角度 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 旋转后的输出图像 |
diff --git a/zh-CN/built-in-nodes/ImageScale.mdx b/zh-CN/built-in-nodes/ImageScale.mdx
new file mode 100644
index 000000000..a39e8842e
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageScale.mdx
@@ -0,0 +1,26 @@
+---
+title: "ImageScale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageScale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageScale"
+icon: "circle"
+mode: wide
+---
+此节点设计用于将图像调整到特定的尺寸，提供了一系列放大方法以及裁剪调整大小后的图像的能力。它抽象了图像放大和裁剪的复杂性，提供了一个简单的接口，用于根据用户定义的参数修改图像尺寸。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 要放大的输入图像。此参数是节点操作的核心，作为应用尺寸转换的主要数据。输出图像的质量和尺寸直接受原始图像属性的影响。 |
+| `缩放方法` | COMBO[STRING] | 指定用于放大图像的方法。方法的选择可以影响放大图像的质量和特性，影响调整大小后的输出的视觉保真度和潜在的伪影。 |
+| `宽度` | `INT` | 放大图像的目标宽度。此参数直接影响输出图像的尺寸，决定了调整大小操作的水平缩放。 |
+| `高度` | `INT` | 放大图像的目标高度。此参数直接影响输出图像的尺寸，决定了调整大小操作的垂直缩放。 |
+| `裁剪` | COMBO[STRING] | 确定是否以及如何裁剪放大后的图像，提供禁用裁剪或中心裁剪的选项。通过潜在地去除边缘以适应指定的尺寸，这影响图像的最终构图。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 放大（和可选裁剪）的图像，准备好进行进一步处理或可视化。 |
+
+---
diff --git a/zh-CN/built-in-nodes/ImageScaleBy.mdx b/zh-CN/built-in-nodes/ImageScaleBy.mdx
new file mode 100644
index 000000000..99393b01a
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageScaleBy.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageScaleBy - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageScaleBy node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageScaleBy"
+icon: "circle"
+mode: wide
+---
+此节点设计用于使用各种插值方法通过指定的缩放因子放大图像。它允许以灵活的方式调整图像大小，以满足不同的放大需求。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 要放大的输入图像。此参数至关重要，因为它提供了将经历放大过程的基础图像。 |
+| `缩放算法` | COMBO[STRING] | 指定用于放大的插值方法。方法的选择可以影响放大图像的质量和特性。 |
+| `缩放系数` | `FLOAT` | 图像将被放大的因子。这决定了输出图像相对于输入图像的尺寸增加。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 放大后的图像，根据指定的缩放因子和插值方法，比输入图像更大。 |
diff --git a/zh-CN/built-in-nodes/ImageScaleToMaxDimension.mdx b/zh-CN/built-in-nodes/ImageScaleToMaxDimension.mdx
new file mode 100644
index 000000000..c66ced483
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageScaleToMaxDimension.mdx
@@ -0,0 +1,24 @@
+---
+title: "ImageScaleToMaxDimension - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageScaleToMaxDimension node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageScaleToMaxDimension"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageScaleToMaxDimension/zh.md)
+
+ImageScaleToMaxDimension 节点可将图像调整至指定最大尺寸范围内，同时保持原始宽高比。该节点会计算图像是纵向还是横向取向，然后将较大尺寸缩放至目标大小，同时按比例调整较小尺寸。该节点支持多种放大方法，以满足不同的质量和性能需求。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `image` | IMAGE | 是 | - | 需要缩放的输入图像 |
+| `upscale_method` | STRING | 是 | "area"<br />"lanczos"<br />"bilinear"<br />"nearest-exact"<br />"bicubic" | 用于图像缩放的插值方法 |
+| `largest_size` | INT | 是 | 0 到 16384 | 缩放后图像的最大尺寸（默认值：512） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `image` | IMAGE | 最大尺寸与指定大小匹配的缩放后图像 |
diff --git a/zh-CN/built-in-nodes/ImageScaleToTotalPixels.mdx b/zh-CN/built-in-nodes/ImageScaleToTotalPixels.mdx
new file mode 100644
index 000000000..526223359
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageScaleToTotalPixels.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageScaleToTotalPixels - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageScaleToTotalPixels node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageScaleToTotalPixels"
+icon: "circle"
+mode: wide
+---
+此节点设计用于将图像调整到指定的总像素数，同时保持纵横比。它提供多种方法来放大图像以实现所需的像素计数。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 要放大到指定总像素数的输入图像。 |
+| `缩放算法` | COMBO[STRING] | 用于放大图像的方法。它影响放大图像的质量和特性。 |
+| `像素数量` | `FLOAT` | 图像的目标大小，以百万像素为单位。这决定了放大图像的总像素数。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 具有指定总像素数的放大图像，保持原始纵横比。 |
diff --git a/zh-CN/built-in-nodes/ImageSharpen.mdx b/zh-CN/built-in-nodes/ImageSharpen.mdx
new file mode 100644
index 000000000..291e48d4f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageSharpen.mdx
@@ -0,0 +1,23 @@
+---
+title: "ImageSharpen - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageSharpen node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageSharpen"
+icon: "circle"
+mode: wide
+---
+此节点通过强调图像的边缘和细节来增强图像的清晰度。它对图像应用锐化滤镜，可以调整强度和半径，使图像看起来更清晰和鲜明。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 要锐化的输入图像。此参数至关重要，因为它决定了将应用锐化效果的基础图像。 |
+| `锐化半径` | `INT` | 定义锐化效果的半径。较大的半径意味着边缘周围更多的像素将受到影响，导致更明显的锐化效果。 |
+| `Sigma` | `FLOAT` | 控制锐化效果的扩散。较高的sigma值会在边缘产生更平滑的过渡，而较低的sigma使锐化更局部化。 |
+| `alpha` | `FLOAT` | 调整锐化效果的强度。较高的alpha值会导致更强的锐化效果。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 锐化的图像，边缘和细节得到增强，准备好进行进一步处理或显示。 |
diff --git a/zh-CN/built-in-nodes/ImageStitch.mdx b/zh-CN/built-in-nodes/ImageStitch.mdx
new file mode 100644
index 000000000..be4eaab14
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageStitch.mdx
@@ -0,0 +1,59 @@
+---
+title: "ImageStitch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageStitch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageStitch"
+icon: "circle"
+mode: wide
+---
+这个节点可以将两张图片按指定方向（上、下、左、右）拼接在一起，支持调整图片大小匹配和添加间隔。
+
+## 输入
+
+| 参数名称 | 数据类型 | 输入方式 | 默认值 | 取值范围 | 功能说明 |
+|----------|----------|----------|---------|----------|----------|
+| `image1` | IMAGE | 必填 | - | - | 第一张要拼接的图片 |
+| `image2` | IMAGE | 选填 | None | - | 第二张要拼接的图片，如果不提供则只返回第一张图片 |
+| `direction` | STRING | 必填 | right | right/down/left/up | 第二张图片的拼接方向：right(右)、down(下)、left(左)、up(上) |
+| `match_image_size` | BOOLEAN | 必填 | True | True/False | 是否调整第二张图片的大小以匹配第一张图片的尺寸 |
+| `spacing_width` | INT | 必填 | 0 | 0-1024 | 两张图片之间的间隔宽度，必须是偶数 |
+| `spacing_color` | STRING | 必填 | white | white/black/red/green/blue | 拼接图片之间间隔的颜色 |
+
+> 对于 `spacing_color` 除了 "white/black" 之外，如果 `match_image_size` 设置为 `false` 那么空白部分将使用黑色作为填充色
+
+## 输出
+
+| 输出名称 | 数据类型 | 说明 |
+|----------|----------|------|
+| `IMAGE` | IMAGE | 拼接后的图片 |
+
+## 工作流示例
+
+在下面的工作流中，我们使用了3 张不同尺寸的输入图片作为示例
+
+- image1: 500x300
+- image2: 400x250
+- image3: 300x300
+
+![workflow](/images/built-in-nodes/ImageStitch/workflow.webp)
+
+**第一个 Image Stitch 节点**
+
+- `match_image_size`: false, 两张图像将会已原有尺寸拼接
+- `direction`: up, `image2` 将会在 `image1` 上方
+- `spacing_width`: 20
+- `spacing_color` : black
+
+输出图片1:
+
+![output1](/images/built-in-nodes/ImageStitch/output-1.webp)
+
+**第二个 Image Stitch 节点**
+
+- `match_image_size`: true, 第二张图像将会缩放到与第一张图像相同的高度或者宽度
+- `direction`:right, `image3` 将会出现在右侧
+- `spacing_width`: 20
+- `spacing_color` : white
+
+输出图片2:
+
+![output2](/images/built-in-nodes/ImageStitch/output-2.webp)
diff --git a/zh-CN/built-in-nodes/ImageToMask.mdx b/zh-CN/built-in-nodes/ImageToMask.mdx
new file mode 100644
index 000000000..2ad925bbc
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageToMask.mdx
@@ -0,0 +1,21 @@
+---
+title: "ImageToMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageToMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageToMask"
+icon: "circle"
+mode: wide
+---
+ImageToMask 节点旨在根据指定的颜色通道将图像转换为遮罩。它允许提取与图像的红色、绿色、蓝色或 alpha 通道相对应的遮罩层，从而便于进行需要特定通道遮罩或处理的操作。
+
+## 输入
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| `图像`    | `IMAGE`  | 'image' 参数代表将根据指定颜色通道生成遮罩的输入图像。它在确定生成的遮罩的内容和特性方面起着关键作用。 |
+| `通道`  | COMBO[STRING] | 'channel' 参数指定应该使用输入图像的哪种颜色通道（红色、绿色、蓝色或 alpha）来生成遮罩。这个选择直接影响遮罩的外观以及图像的哪些部分被突出显示或遮蔽。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `mask`   | `MASK`   | 输出的 'mask' 是输入图像中指定颜色通道的二进制或灰度表示，适用于进一步的图像处理或遮罩操作。 |
diff --git a/zh-CN/built-in-nodes/ImageUpscaleWithModel.mdx b/zh-CN/built-in-nodes/ImageUpscaleWithModel.mdx
new file mode 100644
index 000000000..97b0ad9c9
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageUpscaleWithModel.mdx
@@ -0,0 +1,22 @@
+---
+title: "ImageUpscaleWithModel - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageUpscaleWithModel node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageUpscaleWithModel"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于使用指定的放大模型放大图像。它通过将图像调整到适当的设备、有效管理内存，并以平铺方式应用放大模型来处理放大过程，以适应潜在的内存不足错误。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `放大模型` | `UPSCALE_MODEL` | 用于放大图像的放大模型。它对于定义放大算法及其参数至关重要。 |
+| `图像` | `IMAGE` | 要放大的图像。此输入对于确定将经历放大过程的源内容至关重要。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 放大后的图像，由放大模型处理。此输出是放大操作的结果，展示了增强的分辨率或质量。 |
diff --git a/zh-CN/built-in-nodes/ImageYUVToRGB.mdx b/zh-CN/built-in-nodes/ImageYUVToRGB.mdx
new file mode 100644
index 000000000..15d3b8b68
--- /dev/null
+++ b/zh-CN/built-in-nodes/ImageYUVToRGB.mdx
@@ -0,0 +1,26 @@
+---
+title: "ImageYUVToRGB - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ImageYUVToRGB node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ImageYUVToRGB"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageYUVToRGB/zh.md)
+
+ImageYUVToRGB 节点将 YUV 色彩空间图像转换为 RGB 色彩空间。该节点接收分别代表 Y（亮度）、U（蓝色投影）和 V（红色投影）通道的三个独立输入图像，并通过色彩空间转换将它们合并为单个 RGB 图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Y` | IMAGE | 是 | - | Y（亮度）通道输入图像 |
+| `U` | IMAGE | 是 | - | U（蓝色投影）通道输入图像 |
+| `V` | IMAGE | 是 | - | V（红色投影）通道输入图像 |
+
+**注意：** 必须同时提供所有三个输入图像（Y、U 和 V），且它们应具有兼容的尺寸以确保正确转换。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 转换后的 RGB 图像 |
diff --git a/zh-CN/built-in-nodes/InpaintModelConditioning.mdx b/zh-CN/built-in-nodes/InpaintModelConditioning.mdx
new file mode 100644
index 000000000..283715eb6
--- /dev/null
+++ b/zh-CN/built-in-nodes/InpaintModelConditioning.mdx
@@ -0,0 +1,27 @@
+---
+title: "InpaintModelConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the InpaintModelConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "InpaintModelConditioning"
+icon: "circle"
+mode: wide
+---
+
+修复模型条件节点旨在简化修复模型的条件处理过程，允许集成和操作各种条件输入以定制修复输出。它包含了一系列功能，从加载特定的模型检查点和应用风格或控制网络模型，到对条件元素进行编码和组合，因此作为定制修复任务的全面工具。
+
+## 输入
+
+| 参数名称  | 数据类型 | 作用 |
+|-----------|----------|------|
+| `正面条件`| `CONDITIONING` | 表示应用于修复模型的正面条件信息或参数。此输入对于定义修复操作应执行的上下文或约束至关重要，对最终输出有显著影响。 |
+| `负面条件`| `CONDITIONING` | 表示应用于修复模型的负面条件信息或参数。此输入对于指定修复过程中要避免的条件或上下文至关重要，因此影响最终输出。 |
+| `vae`     | VAE       | 指定在条件处理过程中使用的VAE模型。此输入对于确定将使用的VAE模型的具体架构和参数至关重要。 |
+| `像素`  | `IMAGE`    | 表示要进行修复的图像的像素数据。此输入对于提供修复任务所需的视觉上下文至关重要。 |
+| `遮罩`    | `MASK`     | 指定要应用于图像的遮罩，指示需要进行修复的区域。此输入对于定义图像中需要修复的特定区域至关重要。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+|-----------|----------|------|
+| `负面条件`| `CONDITIONING` | 处理后的修改正面条件信息，准备应用于修复模型。此输出对于根据指定的正面条件指导修复过程至关重要。 |
+| `Latent`| `CONDITIONING` | 处理后的修改负面条件信息，准备应用于修复模型。此输出对于根据指定的负面条件指导修复过程至关重要。 |
+| `latent`  | `LATENT`   | 从条件处理过程派生的潜在表示。此输出对于理解正在修复的图像的底层特征和特性至关重要。 |
diff --git a/zh-CN/built-in-nodes/InstructPixToPixConditioning.mdx b/zh-CN/built-in-nodes/InstructPixToPixConditioning.mdx
new file mode 100644
index 000000000..aca024b5e
--- /dev/null
+++ b/zh-CN/built-in-nodes/InstructPixToPixConditioning.mdx
@@ -0,0 +1,29 @@
+---
+title: "InstructPixToPixConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the InstructPixToPixConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "InstructPixToPixConditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InstructPixToPixConditioning/zh.md)
+
+InstructPixToPixConditioning 节点通过将正向和负向文本提示与图像数据相结合，为 InstructPix2Pix 图像编辑准备条件数据。该节点通过 VAE 编码器处理输入图像以创建潜在表示，并将这些潜在表示附加到正向和负向条件数据中。该节点通过将图像裁剪为 8 像素的倍数来自动处理图像尺寸，以确保与 VAE 编码过程的兼容性。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正面条件` | CONDITIONING | 是 | - | 包含期望图像特征的文本提示和设置的正向条件数据 |
+| `负面条件` | CONDITIONING | 是 | - | 包含不期望图像特征的文本提示和设置的负向条件数据 |
+| `vae` | VAE | 是 | - | 用于将输入图像编码为潜在表示的 VAE 模型 |
+| `像素` | IMAGE | 是 | - | 待处理并编码到潜在空间的输入图像 |
+
+**注意：** 输入图像的尺寸会自动调整，通过将宽度和高度裁剪到最接近的 8 像素倍数，以确保与 VAE 编码过程的兼容性。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 附带潜在图像表示的正向条件数据 |
+| `Latent` | CONDITIONING | 附带潜在图像表示的负向条件数据 |
+| `latent` | LATENT | 与编码图像尺寸相同的空潜在张量 |
diff --git a/zh-CN/built-in-nodes/InvertBooleanNode.mdx b/zh-CN/built-in-nodes/InvertBooleanNode.mdx
new file mode 100644
index 000000000..32fbee740
--- /dev/null
+++ b/zh-CN/built-in-nodes/InvertBooleanNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "InvertBooleanNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the InvertBooleanNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "InvertBooleanNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InvertBooleanNode/zh.md)
+
+此节点接收一个布尔值（真/假）输入并输出相反值。它执行逻辑非运算，将 `true` 转换为 `false`，将 `false` 转换为 `true`。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `boolean` | BOOLEAN | 是 | `true`<br />`false` | 待取反的输入布尔值。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | BOOLEAN | 取反后的布尔值。 |
diff --git a/zh-CN/built-in-nodes/InvertMask.mdx b/zh-CN/built-in-nodes/InvertMask.mdx
new file mode 100644
index 000000000..528432518
--- /dev/null
+++ b/zh-CN/built-in-nodes/InvertMask.mdx
@@ -0,0 +1,23 @@
+---
+title: "InvertMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the InvertMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "InvertMask"
+icon: "circle"
+mode: wide
+---
+
+反转遮罩节点旨在反转给定遮罩的值，有效地翻转遮罩和未遮罩区域。这个操作在图像处理任务中是基础性的，当需要在前景和背景之间切换兴趣焦点时。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `遮罩` | MASK | 输入遮罩，用于反转。它对于确定在反转过程中要翻转的区域至关重要。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `遮罩` | MASK | 输出是输入遮罩的反转版本，先前的遮罩区域变为未遮罩，反之亦然。 |
+
+---
diff --git a/zh-CN/built-in-nodes/JoinAudioChannels.mdx b/zh-CN/built-in-nodes/JoinAudioChannels.mdx
new file mode 100644
index 000000000..1a1deb761
--- /dev/null
+++ b/zh-CN/built-in-nodes/JoinAudioChannels.mdx
@@ -0,0 +1,27 @@
+---
+title: "JoinAudioChannels - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the JoinAudioChannels node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "JoinAudioChannels"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/JoinAudioChannels/zh.md)
+
+该文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/JoinAudioChannels/en.md)
+
+Join Audio Channels 节点将两个独立的单声道音频输入合并为一个立体声音频输出。它接收一个左声道和一个右声道，确保它们具有兼容的采样率和长度，然后将它们合并成一个双声道音频波形。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio_left` | AUDIO | 是 | | 用作最终立体声音频左声道的单声道音频数据。 |
+| `audio_right` | AUDIO | 是 | | 用作最终立体声音频右声道的单声道音频数据。 |
+
+**注意：** 两个输入音频流都必须是单声道（单通道）。如果它们具有不同的采样率，采样率较低的声道将自动重新采样以匹配较高的采样率。如果音频流的长度不同，它们将被修剪为较短音频流的长度。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 生成的立体声音频，包含合并后的左声道和右声道。 |
diff --git a/zh-CN/built-in-nodes/JoinImageWithAlpha.mdx b/zh-CN/built-in-nodes/JoinImageWithAlpha.mdx
new file mode 100644
index 000000000..f142f7a9b
--- /dev/null
+++ b/zh-CN/built-in-nodes/JoinImageWithAlpha.mdx
@@ -0,0 +1,21 @@
+---
+title: "JoinImageWithAlpha - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the JoinImageWithAlpha node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "JoinImageWithAlpha"
+icon: "circle"
+mode: wide
+---
+此节点专为合成操作设计，特别是用于将图像与其对应的 Alpha 遮罩结合，产生单个输出图像。它有效地将视觉内容与透明度信息结合起来，使得可以创建某些区域是透明或半透明的图像。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `图像`  | `IMAGE`  | 要与 Alpha 遮罩结合的主要视觉内容。它代表没有透明度信息的图像。 |
+| `阿尔法`  | `MASK`   | 定义相应图像透明度的 Alpha 遮罩。它用于确定图像的哪些部分应该是透明的或半透明的。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `图像`  | `IMAGE`  | 输出是将输入图像与 Alpha 遮罩结合的单个图像，将透明度信息整合到视觉内容中。 |
diff --git a/zh-CN/built-in-nodes/KSampler.mdx b/zh-CN/built-in-nodes/KSampler.mdx
new file mode 100644
index 000000000..c9eb01d03
--- /dev/null
+++ b/zh-CN/built-in-nodes/KSampler.mdx
@@ -0,0 +1,31 @@
+---
+title: "KSampler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KSampler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KSampler"
+icon: "circle"
+mode: wide
+---
+KSampler这个采样器，是这样工作的：它会根据提供的特定的模型和正、负两种条件，来改造提供的原始潜在图像信息。
+首先，它会根据设定好的**seed随机种子**和**denoise降噪强度**，给原始图像数据加入一些噪声，然后输入预设的**Model模型**结合**positive正向**和**negative负向**的引导条件，去生成图像
+
+## Input 输入
+
+| 参数名称               | 数据类型         | 必填 | 默认值 | 取值范围/选项            | 说明                                                                         |
+| ---------------------- | ---------------- | ---- | ------ | ------------------------ | ---------------------------------------------------------------------------- |
+| Model模型              | checkpoint模型   | 是   | 无     | -                        | 输入用于降噪过程的模型                                                       |
+| seed随机种子           | Int整数          | 是   | 0      | 0 ~ 18446744073709551615 | 用于生成随机噪声，使用同样的“种子”可以生成相同的画面                         |
+| steps步数              | Int整数          | 是   | 20     | 1 ~ 10000                | 去噪过程中要使用的步骤数，步数越多，结果越准确                               |
+| cfg                    | float浮点数      | 是   | 8.0    | 0.0 ~ 100.0              | 控制生成的图像与输入条件的贴合程度，通常建议6-8                              |
+| sampler_name采样器     | 界面选项         | 是   | 无     | 多种采样算法             | 选择用来降噪的采样器，不同采样器影响生成速度和风格                           |
+| scheduler调度器        | 界面选项         | 是   | 无     | 多种调度器               | 控制噪声去除的方式，不同调度器会影响生成过程                                 |
+| Positive正向条件       | conditioning条件 | 是   | 无     | -                        | 用于引导降噪的正向条件，可理解为想要在画面中出现的内容                       |
+| Negative负向条件       | conditioning条件 | 是   | 无     | -                        | 用于引导降噪的负向条件，可理解为不想要在画面中出现的内容                     |
+| Latent_Image           | Latent           | 是   | 无     | -                        | 用于降噪的潜像                                                               |
+| denoise降噪            | float浮点数      | 否   | 1.0    | 0.0 ~ 1.0                | 决定去除多少比例的噪声，值越小生成图像与输入图像关联越小，值越大越像输入图像 |
+| control_after_generate | 界面选项         | 否   | 无     | 随机/增量/减量/保持      | 提供在每次提示后更改种子数的能力，节点可以随机、增量、减量或保持种子数不变   |
+
+## Output 输出
+
+| 参数名称 | 作用                       |
+| -------- | -------------------------- |
+| Latent   | 输出经过采样器降噪后的潜像 |
diff --git a/zh-CN/built-in-nodes/KSamplerAdvanced.mdx b/zh-CN/built-in-nodes/KSamplerAdvanced.mdx
new file mode 100644
index 000000000..814906f51
--- /dev/null
+++ b/zh-CN/built-in-nodes/KSamplerAdvanced.mdx
@@ -0,0 +1,33 @@
+---
+title: "KSamplerAdvanced - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KSamplerAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KSamplerAdvanced"
+icon: "circle"
+mode: wide
+---
+
+`KSampler AdvancedK采样器（高级）`节点是`KSampler`节点的高级版本。`KSampler`在使用中总会向潜像中添加噪声，然后完全去除加噪后的潜像中的罩上，但`KSampler AdvancedK采样器（高级）`节点可以更细致地控制这个过程。可以通过**add_noise添加噪波**设置告诉`KSampler AdvancedK采样器（高级）`节点要不要向潜像中添加噪声。它还可以通过**return_with_leftover_noise返回噪波**设置返回部分去噪后的潜像。与`KSampler`节点不同，此节点没有**denoise降噪**设置，但这个过程是由**start_at_step开始降噪步数**和**end_at_step结束降噪步数**设置控制的。所以通过这个节点你可以将部分去除噪声的潜像输入到下一个`KSampler AdvancedK采样器（高级）`，从而在不同降噪过程中采用不同的方法。
+
+## 输入
+
+| 参数名称             | 数据类型 | 作用                                                         |
+|---------------------|----------|--------------------------------------------------------------|
+| `模型`             | MODEL    | 指定用于生成样本的模型，对采样过程至关重要。               |
+| `添加噪波`         | COMBO[STRING] | 确定是否向采样过程添加噪声，影响生成样本的多样性和质量。   |
+| `随机种`        | INT      | 设置噪声生成的种子，确保采样过程的可重复性。               |
+| `步数`             | INT      | 定义采样过程中要执行的步骤数，影响输出的细节和质量。       |
+| `cfg`               | FLOAT    | 控制条件因子，影响采样过程的方向和空间。                   |
+| `采样器名称`      | COMBO[STRING] | 选择要使用的特定采样器，允许定制采样技术。               |
+| `调度器`         | COMBO[STRING] | 选择调度器以控制采样过程，影响样本的进展和质量。       |
+| `正面条件`          | CONDITIONING | 指定正向条件以引导采样朝向期望的属性。                 |
+| `负面条件`          | CONDITIONING | 指定负向条件以使采样远离某些属性。                       |
+| `Latent图像`      | LATENT   | 提供采样过程中使用的初始潜在图像，作为起点。               |
+| `开始步数`     | INT      | 确定采样过程的起始步骤，允许控制采样进展。               |
+| `结束步数`       | INT      | 设置采样过程的结束步骤，定义采样的范围。                   |
+| `返回剩余噪波` | COMBO[STRING] | 指示是否返回带有剩余噪声的样本，影响最终输出的外观。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `latent` | LATENT   | 输出代表从模型生成的潜在图像，反映了应用的配置和技术。   |
diff --git a/zh-CN/built-in-nodes/KSamplerSelect.mdx b/zh-CN/built-in-nodes/KSamplerSelect.mdx
new file mode 100644
index 000000000..819f25453
--- /dev/null
+++ b/zh-CN/built-in-nodes/KSamplerSelect.mdx
@@ -0,0 +1,21 @@
+---
+title: "KSamplerSelect - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KSamplerSelect node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KSamplerSelect"
+icon: "circle"
+mode: wide
+---
+
+`KSamplerSelect` 类用于根据提供的采样器名称选择特定的采样器。它简化了采样器选择的复杂性，允许用户轻松地在不同采样策略之间切换，以适应他们的任务需求。
+
+## 输入
+
+| 参数名称       | 数据类型 | 作用描述                                     |
+| -------------- | -------- | -------------------------------------------- |
+| `采样器名称` | COMBO[STRING] | 指定要被选择的采样器名称。此参数决定了将使用哪种采样策略，影响整体采样行为和结果。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用描述                                     |
+| -------- | -------- | -------------------------------------------- |
+| `sampler` | `SAMPLER` | 返回被选择的采样器对象，准备用于采样任务。 |
diff --git a/zh-CN/built-in-nodes/Kandinsky5ImageToVideo.mdx b/zh-CN/built-in-nodes/Kandinsky5ImageToVideo.mdx
new file mode 100644
index 000000000..fc166eb2a
--- /dev/null
+++ b/zh-CN/built-in-nodes/Kandinsky5ImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "Kandinsky5ImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Kandinsky5ImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Kandinsky5ImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Kandinsky5ImageToVideo/zh.md)
+
+Kandinsky5ImageToVideo 节点为使用 Kandinsky 模型生成视频准备条件数据和潜在空间数据。它会创建一个空的视频潜在张量，并可选择性地编码起始图像以引导生成视频的初始帧，同时相应地修改正向和负向条件数据。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | N/A | 用于引导视频生成的正向条件提示。 |
+| `negative` | CONDITIONING | 是 | N/A | 用于使视频生成避开某些概念的负向条件提示。 |
+| `vae` | VAE | 是 | N/A | 用于将可选的起始图像编码到潜在空间的 VAE 模型。 |
+| `width` | INT | 否 | 16 至 8192（步长 16） | 输出视频的宽度（像素）（默认：768）。 |
+| `height` | INT | 否 | 16 至 8192（步长 16） | 输出视频的高度（像素）（默认：512）。 |
+| `length` | INT | 否 | 1 至 8192（步长 4） | 视频的帧数（默认：121）。 |
+| `batch_size` | INT | 否 | 1 至 4096 | 同时生成的视频序列数量（默认：1）。 |
+| `start_image` | IMAGE | 否 | N/A | 可选的起始图像。如果提供，它将被编码并用于替换模型输出潜在张量的噪声起始部分。 |
+
+**注意：** 当提供 `start_image` 时，它会自动使用双线性插值调整大小以匹配指定的 `width` 和 `height`。图像批次的前 `length` 帧将用于编码。编码后的潜在表示随后会被注入到 `positive` 和 `negative` 条件数据中，以引导视频的初始外观。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 修改后的正向条件数据，可能已更新为编码后的起始图像数据。 |
+| `negative` | CONDITIONING | 修改后的负向条件数据，可能已更新为编码后的起始图像数据。 |
+| `latent` | LATENT | 一个由零填充的空视频潜在张量，其形状符合指定的维度。 |
+| `cond_latent` | LATENT | 所提供起始图像的干净、编码后的潜在表示。这在内部用于替换生成的视频潜在张量的噪声起始部分。 |
diff --git a/zh-CN/built-in-nodes/KarrasScheduler.mdx b/zh-CN/built-in-nodes/KarrasScheduler.mdx
new file mode 100644
index 000000000..7d99e034a
--- /dev/null
+++ b/zh-CN/built-in-nodes/KarrasScheduler.mdx
@@ -0,0 +1,25 @@
+---
+title: "KarrasScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KarrasScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KarrasScheduler"
+icon: "circle"
+mode: wide
+---
+`KarrasScheduler` 节点旨在根据 Karras 等人（2022 年）的噪声时间表生成一系列噪声水平（sigmas）。这个调度器对于控制生成模型中的扩散过程非常有用，允许对生成过程中每一步应用的噪声水平进行微调。
+
+## 输入
+
+| 参数名称     | 数据类型       | 作用                                                         |
+|--------------|----------------|--------------------------------------------------------------|
+| `步数`      | INT            | 指定噪声时间表中的步骤数，影响生成的 sigmas 序列的粒度。   |
+| `sigma_max`  | FLOAT          | 噪声时间表中的最大 sigma 值，设置噪声水平的上限。         |
+| `sigma_min`  | FLOAT          | 噪声时间表中的最小 sigma 值，设置噪声水平的下限。         |
+| `rho`        | FLOAT          | 控制噪声时间表曲线形状的参数，影响噪声水平从 sigma_min 到 sigma_max 的变化过程。 |
+
+## 输出
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| `sigmas`   | SIGMAS   | 根据 Karras 等人（2022 年）噪声时间表生成的噪声水平（sigmas）序列。 |
+
+---
diff --git a/zh-CN/built-in-nodes/KlingCameraControlI2VNode.mdx b/zh-CN/built-in-nodes/KlingCameraControlI2VNode.mdx
new file mode 100644
index 000000000..42bd5a9b8
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingCameraControlI2VNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "KlingCameraControlI2VNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingCameraControlI2VNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingCameraControlI2VNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlI2VNode/zh.md)
+
+# Kling 图像转视频相机控制节点
+
+Kling 图像转视频相机控制节点能够将静态图像转换为具有专业相机运镜效果的电影级视频。这个专业的图像转视频节点允许您控制虚拟相机动作，包括缩放、旋转、平移、倾斜和第一人称视角，同时保持对原始图像的聚焦。相机控制目前仅在专业模式下支持，使用 kling-v1-5 模型，时长为 5 秒。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `start_frame` | IMAGE | 是 | - | 参考图像 - URL 或 Base64 编码字符串，不能超过 10MB，分辨率不低于 300*300px，宽高比在 1:2.5 ~ 2.5:1 之间。Base64 不应包含 data:image 前缀。 |
+| `prompt` | STRING | 是 | - | 正向文本提示词 |
+| `negative_prompt` | STRING | 是 | - | 负向文本提示词 |
+| `cfg_scale` | FLOAT | 否 | 0.0-1.0 | 控制文本引导的强度（默认：0.75） |
+| `aspect_ratio` | COMBO | 否 | 多个选项可用 | 视频宽高比选择（默认：16:9） |
+| `camera_control` | CAMERA_CONTROL | 是 | - | 可使用 Kling 相机控制节点创建。控制视频生成过程中的相机移动和运动。 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video_id` | VIDEO | 生成的视频输出 |
+| `duration` | STRING | 生成视频的唯一标识符 |
+| `duration` | STRING | 生成视频的时长 |
diff --git a/zh-CN/built-in-nodes/KlingCameraControlT2VNode.mdx b/zh-CN/built-in-nodes/KlingCameraControlT2VNode.mdx
new file mode 100644
index 000000000..ed41eb2ac
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingCameraControlT2VNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "KlingCameraControlT2VNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingCameraControlT2VNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingCameraControlT2VNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlT2VNode/zh.md)
+
+# ## 概述
+
+Kling 文生视频相机控制节点可将文本转换为具有专业相机运动的电影级视频，模拟真实世界的电影摄影效果。此节点支持控制虚拟相机动作，包括缩放、旋转、平移、倾斜和第一人称视角，同时保持对原始文本的关注。由于相机控制仅在专业模式下支持，使用 kling-v1-5 模型且时长为 5 秒，因此持续时间、模式和模型名称已硬编码。
+
+# ## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `prompt` | STRING | 是 | - | 正向文本提示词 |
+| `negative_prompt` | STRING | 是 | - | 负向文本提示词 |
+| `cfg_scale` | FLOAT | 否 | 0.0-1.0 | 控制输出与提示词的贴合程度（默认值：0.75） |
+| `aspect_ratio` | COMBO | 否 | "16:9"<br />"9:16"<br />"1:1"<br />"21:9"<br />"3:4"<br />"4:3" | 生成视频的宽高比（默认值："16:9"） |
+| `camera_control` | CAMERA_CONTROL | 否 | - | 可使用 Kling 相机控制节点创建。控制视频生成过程中的相机移动和运动效果。 |
+
+# ## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `output` | VIDEO | 带有相机控制效果的生成视频 |
+| `video_id` | STRING | 生成视频的唯一标识符 |
+| `duration` | STRING | 生成视频的时长 |
diff --git a/zh-CN/built-in-nodes/KlingCameraControls.mdx b/zh-CN/built-in-nodes/KlingCameraControls.mdx
new file mode 100644
index 000000000..6df9b4b87
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingCameraControls.mdx
@@ -0,0 +1,30 @@
+---
+title: "KlingCameraControls - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingCameraControls node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingCameraControls"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControls/zh.md)
+
+Kling Camera Controls 节点允许您配置各种摄像机移动和旋转参数，用于在视频生成中创建运动控制效果。它提供摄像机定位、旋转和缩放控制，以模拟不同的摄像机运动。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `camera_control_type` | COMBO | 是 | 多个选项可用 | 指定要使用的摄像机控制配置类型 |
+| `horizontal_movement` | FLOAT | 否 | -10.0 到 10.0 | 控制摄像机沿水平轴（x轴）的移动。负值表示向左，正值表示向右（默认：0.0） |
+| `vertical_movement` | FLOAT | 否 | -10.0 到 10.0 | 控制摄像机沿垂直轴（y轴）的移动。负值表示向下，正值表示向上（默认：0.0） |
+| `pan` | FLOAT | 否 | -10.0 到 10.0 | 控制摄像机在垂直平面（x轴）上的旋转。负值表示向下旋转，正值表示向上旋转（默认：0.5） |
+| `tilt` | FLOAT | 否 | -10.0 到 10.0 | 控制摄像机在水平平面（y轴）上的旋转。负值表示向左旋转，正值表示向右旋转（默认：0.0） |
+| `roll` | FLOAT | 否 | -10.0 到 10.0 | 控制摄像机的滚动量（z轴）。负值表示逆时针，正值表示顺时针（默认：0.0） |
+| `zoom` | FLOAT | 否 | -10.0 到 10.0 | 控制摄像机焦距的变化。负值表示视野变窄，正值表示视野变宽（默认：0.0） |
+
+**注意：** 至少有一个摄像机控制参数（`horizontal_movement`、`vertical_movement`、`pan`、`tilt`、`roll` 或 `zoom`）必须具有非零值，配置才有效。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `camera_control` | CAMERA_CONTROL | 返回配置好的摄像机控制设置，用于视频生成 |
diff --git a/zh-CN/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx b/zh-CN/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx
new file mode 100644
index 000000000..d4a14366f
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "KlingDualCharacterVideoEffectNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingDualCharacterVideoEffectNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingDualCharacterVideoEffectNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingDualCharacterVideoEffectNode/zh.md)
+
+Kling 双角色视频特效节点可根据所选场景创建带有特效的视频。该节点接收两张图像，并将第一张图像定位在合成视频的左侧，第二张图像定位在右侧。根据选择的不同特效场景，会应用不同的视觉效果。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 参数说明 |
+|-----------|-----------|----------|-------|-------------|
+| `image_left` | IMAGE | 是 | - | 左侧图像 |
+| `image_right` | IMAGE | 是 | - | 右侧图像 |
+| `effect_scene` | COMBO | 是 | 多个选项可选 | 应用于视频生成的特效场景类型 |
+| `model_name` | COMBO | 否 | 多个选项可选 | 用于角色特效的模型（默认："kling-v1"） |
+| `mode` | COMBO | 否 | 多个选项可选 | 视频生成模式（默认："std"） |
+| `duration` | COMBO | 是 | 多个选项可选 | 生成视频的时长 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 输出说明 |
+|-------------|-----------|-------------|
+| `duration` | VIDEO | 生成的双角色特效视频 |
+| `duration` | STRING | 生成视频的时长信息 |
diff --git a/zh-CN/built-in-nodes/KlingFirstLastFrameNode.mdx b/zh-CN/built-in-nodes/KlingFirstLastFrameNode.mdx
new file mode 100644
index 000000000..be3e30c9e
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingFirstLastFrameNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "KlingFirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingFirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingFirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingFirstLastFrameNode/zh.md)
+
+此节点使用 Kling 3.0 模型生成视频。它基于文本提示、指定时长以及提供的起始帧和结束帧两张图像来创建视频。该节点还可以为视频生成伴随音频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | N/A | 指导视频生成的文本描述。长度必须在 1 到 2500 个字符之间。 |
+| `duration` | INT | 否 | 3 到 15 | 视频的时长，单位为秒（默认值：5）。 |
+| `first_frame` | IMAGE | 是 | N/A | 视频的起始图像。必须至少为 300x300 像素，且宽高比在 1:2.5 到 2.5:1 之间。 |
+| `end_frame` | IMAGE | 是 | N/A | 视频的结束图像。必须至少为 300x300 像素，且宽高比在 1:2.5 到 2.5:1 之间。 |
+| `generate_audio` | BOOLEAN | 否 | N/A | 控制是否为视频生成音频（默认值：True）。 |
+| `model` | COMBO | 否 | `"kling-v3"` | 模型和生成设置。选择此选项会显示一个嵌套的 `resolution` 参数。 |
+| `model.resolution` | COMBO | 否 | `"1080p"`<br />`"720p"` | 生成视频的分辨率。此参数仅在 `model` 设置为 `"kling-v3"` 时可用。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于控制节点是否应重新运行的数字。无论种子值如何，结果都是非确定性的（默认值：0）。 |
+
+**注意：** `first_frame` 和 `end_frame` 图像必须满足指定的最小尺寸和宽高比要求，节点才能正常工作。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/KlingImage2VideoNode.mdx b/zh-CN/built-in-nodes/KlingImage2VideoNode.mdx
new file mode 100644
index 000000000..1330a426a
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingImage2VideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "KlingImage2VideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingImage2VideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingImage2VideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImage2VideoNode/zh.md)
+
+Kling Image to Video 节点能够基于起始图像，通过文本提示生成视频内容。该节点接收参考图像，并根据提供的正向和负向文本描述创建视频序列，同时提供多种配置选项用于模型选择、时长和宽高比。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 是否必填 | 取值范围 | 参数说明 |
+|----------|----------|----------|----------|----------|
+| `start_frame` | IMAGE | 是 | - | 用于生成视频的参考图像。 |
+| `prompt` | STRING | 是 | - | 正向文本提示。 |
+| `negative_prompt` | STRING | 是 | - | 负向文本提示。 |
+| `model_name` | COMBO | 是 | 提供多个选项 | 视频生成模型选择（默认："kling-v2-master"）。 |
+| `cfg_scale` | FLOAT | 是 | 0.0-1.0 | 配置缩放参数（默认：0.8）。 |
+| `mode` | COMBO | 是 | 提供多个选项 | 视频生成模式选择（默认：std）。 |
+| `aspect_ratio` | COMBO | 是 | 提供多个选项 | 生成视频的宽高比（默认：field_16_9）。 |
+| `duration` | COMBO | 是 | 提供多个选项 | 生成视频的时长（默认：field_5）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 输出说明 |
+|----------|----------|----------|
+| `video_id` | VIDEO | 生成的视频输出。 |
+| `duration` | STRING | 生成视频的唯一标识符。 |
+| `duration` | STRING | 生成视频的时长信息。 |
diff --git a/zh-CN/built-in-nodes/KlingImageGenerationNode.mdx b/zh-CN/built-in-nodes/KlingImageGenerationNode.mdx
new file mode 100644
index 000000000..948ef94be
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingImageGenerationNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "KlingImageGenerationNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingImageGenerationNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingImageGenerationNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImageGenerationNode/zh.md)
+
+Kling 图像生成节点能够根据文本提示生成图像，并可选使用参考图像进行引导。该节点基于您的文本描述和参考设置创建一张或多张图像，然后将生成的图像作为输出返回。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 正向文本提示 |
+| `negative_prompt` | STRING | 是 | - | 负向文本提示 |
+| `image_type` | COMBO | 是 | KlingImageGenImageReferenceType 中的选项<br />（从源代码提取） | 图像参考类型选择 |
+| `image_fidelity` | FLOAT | 是 | 0.0 - 1.0 | 用户上传图像的参考强度（默认值：0.5） |
+| `human_fidelity` | FLOAT | 是 | 0.0 - 1.0 | 主体参考相似度（默认值：0.45） |
+| `model_name` | COMBO | 是 | "kling-v1"<br />（及 KlingImageGenModelName 中的其他选项） | 图像生成的模型选择（默认值："kling-v1"） |
+| `aspect_ratio` | COMBO | 是 | "16:9"<br />（及 KlingImageGenAspectRatio 中的其他选项） | 生成图像的宽高比（默认值："16:9"） |
+| `n` | INT | 是 | 1 - 9 | 生成图像的数量（默认值：1） |
+| `image` | IMAGE | 否 | - | 可选的参考图像 |
+
+**参数约束：**
+
+- `image` 参数是可选的，但当提供参考图像时，kling-v1 模型不支持参考图像功能
+- 正向提示和负向提示有最大长度限制（MAX_PROMPT_LENGTH_IMAGE_GEN）
+- 当未提供参考图像时，`image_type` 参数会自动设置为 None
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 基于输入参数生成的图像 |
diff --git a/zh-CN/built-in-nodes/KlingImageToVideoWithAudio.mdx b/zh-CN/built-in-nodes/KlingImageToVideoWithAudio.mdx
new file mode 100644
index 000000000..8d21fa37b
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingImageToVideoWithAudio.mdx
@@ -0,0 +1,27 @@
+---
+title: "KlingImageToVideoWithAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingImageToVideoWithAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingImageToVideoWithAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImageToVideoWithAudio/zh.md)
+
+Kling Image(First Frame) to Video with Audio 节点使用 Kling AI 模型，从单张起始图像和文本提示生成短视频。它会创建一个以提供的图像为起始帧的视频序列，并可选择性地包含 AI 生成的音频来配合视觉效果。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | 是 | `"kling-v2-6"` | 用于视频生成的 Kling AI 模型的具体版本。 |
+| `start_frame` | IMAGE | 是 | - | 将作为生成视频第一帧的图像。图像必须至少为 300x300 像素，且宽高比在 1:2.5 到 2.5:1 之间。 |
+| `prompt` | STRING | 是 | - | 正向文本提示。用于描述您想要生成的视频内容。提示长度必须在 1 到 2500 个字符之间。 |
+| `mode` | COMBO | 是 | `"pro"` | 视频生成的操作模式。 |
+| `duration` | COMBO | 是 | `5`<br />`10` | 要生成的视频长度，单位为秒。 |
+| `generate_audio` | BOOLEAN | 否 | - | 启用时，节点将生成伴随视频的音频。禁用时，视频将没有声音。（默认值：True） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 生成的视频文件，根据 `generate_audio` 输入参数，可能包含音频。 |
diff --git a/zh-CN/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx b/zh-CN/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx
new file mode 100644
index 000000000..9b8513933
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx
@@ -0,0 +1,35 @@
+---
+title: "KlingLipSyncAudioToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingLipSyncAudioToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingLipSyncAudioToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncAudioToVideoNode/zh.md)
+
+Kling Lip Sync Audio to Video 节点能够将视频文件中的口型动作与音频文件的内容进行同步。该节点通过分析音频中的人声模式，并调整视频中的面部动作，从而生成逼真的口型同步效果。此处理过程要求视频必须包含清晰可辨的人脸，且音频文件需包含明显可区分的人声。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `视频` | VIDEO | 是 | - | 包含待同步口型人脸的视频文件 |
+| `音频` | AUDIO | 是 | - | 包含需要与视频同步人声的音频文件 |
+| `语音语言` | COMBO | 否 | `"en"`<br />`"zh"`<br />`"es"`<br />`"fr"`<br />`"de"`<br />`"it"`<br />`"pt"`<br />`"pl"`<br />`"tr"`<br />`"ru"`<br />`"nl"`<br />`"cs"`<br />`"ar"`<br />`"ja"`<br />`"hu"`<br />`"ko"` | 音频文件中人声的语言（默认值："en"） |
+
+**重要限制条件：**
+
+- 音频文件大小不得超过 5MB
+- 视频文件大小不得超过 100MB
+- 视频尺寸的高/宽应在 720px 至 1920px 之间
+- 视频时长应在 2 秒至 10 秒之间
+- 音频必须包含清晰可辨的人声
+- 视频必须包含清晰可辨的人脸
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `视频ID` | VIDEO | 经过口型同步处理后的视频 |
+| `时长` | STRING | 已处理视频的唯一标识符 |
+| `duration` | STRING | 已处理视频的时长 |
diff --git a/zh-CN/built-in-nodes/KlingLipSyncTextToVideoNode.mdx b/zh-CN/built-in-nodes/KlingLipSyncTextToVideoNode.mdx
new file mode 100644
index 000000000..9e06b6c92
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingLipSyncTextToVideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "KlingLipSyncTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingLipSyncTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingLipSyncTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncTextToVideoNode/zh.md)
+
+Kling 唇形同步文本转视频节点可将视频文件中的嘴部运动与文本提示进行同步。该节点接收输入视频并生成一个新视频，其中角色的唇部运动与提供的文本内容保持一致。该节点利用语音合成技术创建自然逼真的语音同步效果。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `视频` | VIDEO | 是 | - | 用于唇形同步的输入视频文件 |
+| `文本` | STRING | 是 | - | 唇形同步视频生成的文本内容。在模式为 text2video 时必需。最大长度为 120 个字符。 |
+| `语音` | COMBO | 否 | "Melody"<br />"Bella"<br />"Aria"<br />"Ethan"<br />"Ryan"<br />"Dorothy"<br />"Nathan"<br />"Lily"<br />"Aaron"<br />"Emma"<br />"Grace"<br />"Henry"<br />"Isabella"<br />"James"<br />"Katherine"<br />"Liam"<br />"Mia"<br />"Noah"<br />"Olivia"<br />"Sophia" | 唇形同步音频的语音选择（默认："Melody"） |
+| `语速` | FLOAT | 否 | 0.8-2.0 | 语速。有效范围：0.8~2.0，精确到小数点后一位（默认：1） |
+
+**视频要求：**
+
+- 视频文件大小不应超过 100MB
+- 高度/宽度应在 720px 至 1920px 之间
+- 时长应在 2 秒至 10 秒之间
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `视频ID` | VIDEO | 生成的带唇形同步音频的视频 |
+| `时长` | STRING | 生成视频的唯一标识符 |
+| `duration` | STRING | 生成视频的时长信息 |
diff --git a/zh-CN/built-in-nodes/KlingMotionControl.mdx b/zh-CN/built-in-nodes/KlingMotionControl.mdx
new file mode 100644
index 000000000..7e55c377e
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingMotionControl.mdx
@@ -0,0 +1,32 @@
+---
+title: "KlingMotionControl - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingMotionControl node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingMotionControl"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingMotionControl/zh.md)
+
+Kling Motion Control 节点通过将参考视频中的动作、表情和摄像机运动应用到由参考图像和文本提示定义的角色上，从而生成视频。它允许您控制角色的最终朝向是来自参考视频还是参考图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | N/A | 对期望视频的文本描述。最大长度为 2500 个字符。 |
+| `reference_image` | IMAGE | 是 | N/A | 要动画化的角色图像。最小尺寸为 340x340 像素。宽高比必须在 1:2.5 到 2.5:1 之间。 |
+| `reference_video` | VIDEO | 是 | N/A | 用于驱动角色运动和表情的运动参考视频。最小尺寸为 340x340 像素，最大尺寸为 3850x3850 像素。时长限制取决于 `character_orientation` 设置。 |
+| `keep_original_sound` | BOOLEAN | 否 | N/A | 决定是否在输出中保留参考视频的原始音频。默认值为 `True`。 |
+| `character_orientation` | COMBO | 否 | `"video"`<br />`"image"` | 控制角色的朝向/方向来源。`"video"`：运动、表情、摄像机移动和朝向均遵循运动参考视频。`"image"`：运动和表情遵循运动参考视频，但角色朝向与参考图像匹配。 |
+| `mode` | COMBO | 否 | `"pro"`<br />`"std"` | 要使用的生成模式。 |
+
+**约束条件：**
+
+* 当 `character_orientation` 设置为 `"video"` 时，`reference_video` 的时长必须在 3 到 30 秒之间。
+* 当 `character_orientation` 设置为 `"image"` 时，`reference_video` 的时长必须在 3 到 10 秒之间。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频，其中角色执行参考视频中的动作。 |
diff --git a/zh-CN/built-in-nodes/KlingOmniProEditVideoNode.mdx b/zh-CN/built-in-nodes/KlingOmniProEditVideoNode.mdx
new file mode 100644
index 000000000..0db57298e
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingOmniProEditVideoNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "KlingOmniProEditVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProEditVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProEditVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProEditVideoNode/zh.md)
+
+Kling Omni 编辑视频（专业版）节点使用 AI 模型，根据文本描述编辑现有视频。您提供源视频和提示词，节点将生成一个时长相同、包含所请求更改的新视频。它可以选择性地使用参考图像来引导风格，并保留源视频的原始音频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | 是 | `"kling-video-o1"` | 用于视频编辑的 AI 模型。 |
+| `prompt` | STRING | 是 | | 描述视频内容的文本提示词。可以包含正向和负向描述。 |
+| `video` | VIDEO | 是 | | 待编辑的视频。输出视频的时长将与此相同。 |
+| `keep_original_sound` | BOOLEAN | 是 | | 决定是否在输出视频中保留输入视频的原始音频（默认值：True）。 |
+| `reference_images` | IMAGE | 否 | | 最多 4 张额外的参考图像。 |
+| `resolution` | COMBO | 否 | `"1080p"`<br />`"720p"` | 输出视频的分辨率（默认值："1080p"）。 |
+
+**约束与限制：**
+
+* `prompt` 的长度必须在 1 到 2500 个字符之间。
+* 输入 `video` 的时长必须在 3.0 到 10.05 秒之间。
+* 输入 `video` 的尺寸必须在 720x720 到 2160x2160 像素之间。
+* 使用视频时，最多可提供 4 张 `reference_images`。
+* 每张 `reference_image` 的尺寸必须至少为 300x300 像素。
+* 每张 `reference_image` 的宽高比必须在 1:2.5 到 2.5:1 之间。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 由 AI 模型生成的编辑后的视频。 |
diff --git a/zh-CN/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx b/zh-CN/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx
new file mode 100644
index 000000000..1432a4d3a
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx
@@ -0,0 +1,37 @@
+---
+title: "KlingOmniProFirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProFirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProFirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProFirstLastFrameNode/zh.md)
+
+此节点使用 Kling AI 模型生成视频。它需要一个起始图像和文本提示。您可以选择性地提供一个结束图像或最多六个参考图像，以引导视频的内容和风格。该节点处理这些输入，以创建指定时长和分辨率的视频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | 是 | `"kling-video-o1"` | 用于视频生成的具体 Kling AI 模型。 |
+| `prompt` | STRING | 是 | - | 描述视频内容的文本提示。可以包含正面和负面的描述。 |
+| `duration` | INT | 是 | 3 到 10 | 生成视频的期望时长，单位为秒（默认：5）。 |
+| `first_frame` | IMAGE | 是 | - | 视频序列的起始图像。 |
+| `end_frame` | IMAGE | 否 | - | 视频的可选结束帧。此参数不能与 `reference_images` 同时使用。 |
+| `reference_images` | IMAGE | 否 | - | 最多 6 个额外的参考图像。 |
+| `resolution` | COMBO | 否 | `"1080p"`<br />`"720p"` | 生成视频的输出分辨率（默认："1080p"）。 |
+
+**重要限制：**
+
+* `end_frame` 输入不能与 `reference_images` 输入同时使用。
+* 如果您不提供 `end_frame` 或任何 `reference_images`，则 `duration` 只能设置为 5 或 10 秒。
+* 所有输入图像（`first_frame`、`end_frame` 以及任何 `reference_images`）的宽度和高度都必须至少为 300 像素。
+* 所有输入图像的宽高比必须在 1:2.5 到 2.5:1 之间。
+* 通过 `reference_images` 输入最多可提供 6 张图像。
+* `prompt` 文本的长度必须在 1 到 2500 个字符之间。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/KlingOmniProImageNode.mdx b/zh-CN/built-in-nodes/KlingOmniProImageNode.mdx
new file mode 100644
index 000000000..9a27e1bd9
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingOmniProImageNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "KlingOmniProImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProImageNode/zh.md)
+
+Kling Omni 图像（专业版）节点使用 Kling AI 模型生成或编辑图像。它基于文本描述创建图像，并允许您提供参考图像来引导风格或内容。该节点会向外部 API 发送请求，由 API 处理任务并返回最终图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+| :--- | :--- | :--- | :--- | :--- |
+| `model_name` | COMBO | 是 | `"kling-image-o1"` | 用于图像生成的具体 Kling AI 模型。 |
+| `prompt` | STRING | 是 | - | 描述图像内容的文本提示。可以包含正向和负向描述。文本长度必须在 1 到 2500 个字符之间。 |
+| `resolution` | COMBO | 是 | `"1K"`<br />`"2K"` | 生成图像的目标分辨率。 |
+| `aspect_ratio` | COMBO | 是 | `"16:9"`<br />`"9:16"`<br />`"1:1"`<br />`"4:3"`<br />`"3:4"`<br />`"3:2"`<br />`"2:3"`<br />`"21:9"` | 生成图像所需的宽高比。 |
+| `reference_images` | IMAGE | 否 | - | 最多 10 张额外的参考图像。每张图像的宽度和高度必须至少为 300 像素，且宽高比必须在 1:2.5 到 2.5:1 之间。 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+| :--- | :--- | :--- |
+| `image` | IMAGE | 由 Kling AI 模型生成或编辑的最终图像。 |
diff --git a/zh-CN/built-in-nodes/KlingOmniProImageToVideoNode.mdx b/zh-CN/built-in-nodes/KlingOmniProImageToVideoNode.mdx
new file mode 100644
index 000000000..5398bac2c
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingOmniProImageToVideoNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "KlingOmniProImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProImageToVideoNode/zh.md)
+
+此节点使用 Kling AI 模型，基于文本提示词和最多七张参考图像生成视频。它允许您控制视频的宽高比、时长和分辨率。该节点将请求发送至外部 API 并返回生成的视频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | 是 | `"kling-video-o1"` | 用于视频生成的具体 Kling 模型。 |
+| `prompt` | STRING | 是 | - | 描述视频内容的文本提示词。可以包含正向和负向描述。文本会自动进行规范化处理，长度必须在 1 到 2500 个字符之间。 |
+| `aspect_ratio` | COMBO | 是 | `"16:9"`<br />`"9:16"`<br />`"1:1"` | 生成视频的期望宽高比。 |
+| `duration` | INT | 是 | 3 到 10 | 视频的时长，单位为秒。可通过滑块调整该值（默认值：3）。 |
+| `reference_images` | IMAGE | 是 | - | 最多 7 张参考图像。每张图像必须至少为 300x300 像素，且宽高比在 1:2.5 到 2.5:1 之间。 |
+| `resolution` | COMBO | 否 | `"1080p"`<br />`"720p"` | 视频的输出分辨率。此参数为可选参数（默认值："1080p"）。 |
+
+**注意：** `reference_images` 输入最多接受 7 张图像。如果提供了更多图像，节点将报错。每张图像都会进行最小尺寸和宽高比的验证。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/KlingOmniProTextToVideoNode.mdx b/zh-CN/built-in-nodes/KlingOmniProTextToVideoNode.mdx
new file mode 100644
index 000000000..c870bcd8b
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingOmniProTextToVideoNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "KlingOmniProTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProTextToVideoNode/zh.md)
+
+此节点使用 Kling AI 模型，根据文本描述生成视频。它会将您的提示词发送至远程 API，并返回生成的视频。该节点允许您控制视频的时长、画面比例和质量。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | 是 | `"kling-video-o1"` | 用于视频生成的具体 Kling 模型。 |
+| `prompt` | STRING | 是 | 1 到 2500 个字符 | 描述视频内容的文本提示词。可以包含正向和负向描述。 |
+| `aspect_ratio` | COMBO | 是 | `"16:9"`<br />`"9:16"`<br />`"1:1"` | 要生成的视频的画面比例或尺寸。 |
+| `duration` | COMBO | 是 | `5`<br />`10` | 视频的时长，单位为秒。 |
+| `resolution` | COMBO | 否 | `"1080p"`<br />`"720p"` | 视频的质量或像素分辨率（默认值：`"1080p"`）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 根据提供的文本提示词生成的视频。 |
diff --git a/zh-CN/built-in-nodes/KlingOmniProVideoToVideoNode.mdx b/zh-CN/built-in-nodes/KlingOmniProVideoToVideoNode.mdx
new file mode 100644
index 000000000..c208926c5
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingOmniProVideoToVideoNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "KlingOmniProVideoToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingOmniProVideoToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingOmniProVideoToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProVideoToVideoNode/zh.md)
+
+此节点使用 Kling AI 模型，基于输入视频和可选的参考图像生成新视频。您提供描述所需内容的文本提示，节点将相应地转换参考视频。它还可以整合最多四张额外的参考图像，以指导输出的风格和内容。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | 是 | `"kling-video-o1"` | 用于视频生成的具体 Kling 模型。 |
+| `prompt` | STRING | 是 | N/A | 描述视频内容的文本提示。可以包含正面和负面的描述。 |
+| `aspect_ratio` | COMBO | 是 | `"16:9"`<br />`"9:16"`<br />`"1:1"` | 生成视频的期望宽高比。 |
+| `duration` | INT | 是 | 3 到 10 | 生成视频的长度（单位：秒，默认值：3）。 |
+| `reference_video` | VIDEO | 是 | N/A | 用作参考的视频。 |
+| `keep_original_sound` | BOOLEAN | 是 | N/A | 决定输出中是否保留参考视频的音频（默认值：True）。 |
+| `reference_images` | IMAGE | 否 | N/A | 最多 4 张额外的参考图像。 |
+| `resolution` | COMBO | 否 | `"1080p"`<br />`"720p"` | 生成视频的分辨率（默认值："1080p"）。 |
+
+**参数约束：**
+
+* `prompt` 的长度必须在 1 到 2500 个字符之间。
+* `reference_video` 的时长必须在 3.0 到 10.05 秒之间。
+* `reference_video` 的尺寸必须在 720x720 到 2160x2160 像素之间。
+* 最多可提供 4 张 `reference_images`。每张图像的尺寸必须至少为 300x300 像素，且宽高比在 1:2.5 到 2.5:1 之间。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 新生成的视频。 |
diff --git a/zh-CN/built-in-nodes/KlingSingleImageVideoEffectNode.mdx b/zh-CN/built-in-nodes/KlingSingleImageVideoEffectNode.mdx
new file mode 100644
index 000000000..a921c2c06
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingSingleImageVideoEffectNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "KlingSingleImageVideoEffectNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingSingleImageVideoEffectNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingSingleImageVideoEffectNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingSingleImageVideoEffectNode/zh.md)
+
+## 概述
+
+Kling 单图视频特效节点基于单张参考图像创建具有不同特殊效果的视频。它应用各种视觉效果和场景，将静态图像转换为动态视频内容。该节点支持不同的特效场景、模型选项和视频时长，以实现所需的视觉效果。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 参考图像。URL 或 Base64 编码字符串（不带 data:image 前缀）。文件大小不能超过 10MB，分辨率不低于 300*300px，宽高比在 1:2.5 ~ 2.5:1 之间 |
+| `effect_scene` | COMBO | 是 | KlingSingleImageEffectsScene 中的选项 | 应用于视频生成的特效场景类型 |
+| `model_name` | COMBO | 是 | KlingSingleImageEffectModelName 中的选项 | 用于生成视频特效的具体模型 |
+| `duration` | COMBO | 是 | KlingVideoGenDuration 中的选项 | 生成视频的长度 |
+
+**注意：** `effect_scene`、`model_name` 和 `duration` 的具体选项由其各自枚举类（KlingSingleImageEffectsScene、KlingSingleImageEffectModelName 和 KlingVideoGenDuration）中的可用值决定。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video_id` | VIDEO | 应用了特效的生成视频 |
+| `duration` | STRING | 生成视频的唯一标识符 |
+| `duration` | STRING | 生成视频的时长 |
diff --git a/zh-CN/built-in-nodes/KlingStartEndFrameNode.mdx b/zh-CN/built-in-nodes/KlingStartEndFrameNode.mdx
new file mode 100644
index 000000000..a683882e5
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingStartEndFrameNode.mdx
@@ -0,0 +1,39 @@
+---
+title: "KlingStartEndFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingStartEndFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingStartEndFrameNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingStartEndFrameNode/zh.md)
+
+# ## 概述
+
+Kling 首尾帧转视频节点可创建一个在提供的起始图像和结束图像之间过渡的视频序列。它会生成中间所有帧，从而产生从第一帧到最后一帧的平滑转换。此节点调用图像转视频 API，但仅支持与 `image_tail` 请求字段配合使用的输入选项。
+
+## ## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `start_frame` | IMAGE | 是 | - | 参考图像 - URL 或 Base64 编码字符串，不能超过 10MB，分辨率不低于 300*300 像素，宽高比在 1:2.5 ~ 2.5:1 之间。Base64 不应包含 data:image 前缀。 |
+| `end_frame` | IMAGE | 是 | - | 参考图像 - 结束帧控制。URL 或 Base64 编码字符串，不能超过 10MB，分辨率不低于 300*300 像素。Base64 不应包含 data:image 前缀。 |
+| `prompt` | STRING | 是 | - | 正向文本提示词 |
+| `negative_prompt` | STRING | 是 | - | 负向文本提示词 |
+| `cfg_scale` | FLOAT | 否 | 0.0-1.0 | 控制提示词引导的强度（默认值：0.5） |
+| `aspect_ratio` | COMBO | 否 | "16:9"<br />"9:16"<br />"1:1"<br />"21:9"<br />"9:21"<br />"3:4"<br />"4:3" | 生成视频的宽高比（默认值："16:9"） |
+| `mode` | COMBO | 否 | 提供多个选项 | 用于视频生成的配置，遵循格式：模式 / 时长 / 模型名称。（默认值：可用模式中的第三个选项） |
+
+**图像约束条件：**
+
+- 必须同时提供 `start_frame` 和 `end_frame`，且文件大小不能超过 10MB
+- 最小分辨率：两张图像均为 300×300 像素
+- `start_frame` 的宽高比必须在 1:2.5 和 2.5:1 之间
+- Base64 编码的图像不应包含 "data:image" 前缀
+
+## ## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `output` | VIDEO | 生成的视频序列 |
+| `video_id` | STRING | 生成视频的唯一标识符 |
+| `duration` | STRING | 生成视频的时长 |
diff --git a/zh-CN/built-in-nodes/KlingTextToVideoNode.mdx b/zh-CN/built-in-nodes/KlingTextToVideoNode.mdx
new file mode 100644
index 000000000..314dc9b33
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingTextToVideoNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "KlingTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoNode/zh.md)
+
+Kling 文本转视频节点可将文本描述转换为视频内容。它接收文本提示并根据指定的配置设置生成相应的视频序列。该节点支持不同的宽高比和生成模式，可生成不同时长和质量的视频。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 正向文本提示（默认：无） |
+| `negative_prompt` | STRING | 是 | - | 负向文本提示（默认：无） |
+| `cfg_scale` | FLOAT | 否 | 0.0-1.0 | 配置缩放值（默认：1.0） |
+| `aspect_ratio` | COMBO | 否 | KlingVideoGenAspectRatio 中的选项 | 视频宽高比设置（默认："16:9"） |
+| `mode` | COMBO | 否 | 提供多个选项 | 用于视频生成的配置，格式为：模式/时长/模型名称（默认：modes[4]） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video_id` | VIDEO | 生成的视频输出 |
+| `duration` | STRING | 生成视频的唯一标识符 |
+| `duration` | STRING | 生成视频的时长信息 |
diff --git a/zh-CN/built-in-nodes/KlingTextToVideoWithAudio.mdx b/zh-CN/built-in-nodes/KlingTextToVideoWithAudio.mdx
new file mode 100644
index 000000000..91d4bc114
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingTextToVideoWithAudio.mdx
@@ -0,0 +1,27 @@
+---
+title: "KlingTextToVideoWithAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingTextToVideoWithAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingTextToVideoWithAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoWithAudio/zh.md)
+
+Kling Text to Video with Audio 节点可根据文本描述生成短视频。它会向 Kling AI 服务发送请求，该服务处理提示词并返回视频文件。该节点还可根据文本为视频生成伴随音频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | COMBO | 是 | `"kling-v2-6"` | 用于视频生成的特定 AI 模型。 |
+| `prompt` | STRING | 是 | - | 正向文本提示词。用于生成视频的描述。长度必须在 1 到 2500 个字符之间。 |
+| `mode` | COMBO | 是 | `"pro"` | 视频生成的操作模式。 |
+| `aspect_ratio` | COMBO | 是 | `"16:9"`<br />`"9:16"`<br />`"1:1"` | 生成视频所需的宽高比。 |
+| `duration` | COMBO | 是 | `5`<br />`10` | 视频长度，单位为秒。 |
+| `generate_audio` | BOOLEAN | 否 | - | 控制是否为视频生成音频。启用后，AI 将根据提示词创建声音。（默认值：`True`） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/KlingVideoExtendNode.mdx b/zh-CN/built-in-nodes/KlingVideoExtendNode.mdx
new file mode 100644
index 000000000..36a80d1cb
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingVideoExtendNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "KlingVideoExtendNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingVideoExtendNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingVideoExtendNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoExtendNode/zh.md)
+
+Kling 视频扩展节点允许您扩展由其他 Kling 节点创建的视频。该节点通过视频 ID 识别现有视频，并根据您的文本提示生成额外内容。该节点的工作原理是将您的扩展请求发送到 Kling API，并返回扩展后的视频及其新的 ID 和时长。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 否 | - | 用于指导视频扩展的正面文本提示 |
+| `negative_prompt` | STRING | 否 | - | 用于避免在扩展视频中出现某些元素的负面文本提示 |
+| `cfg_scale` | FLOAT | 否 | 0.0 - 1.0 | 控制提示引导的强度（默认值：0.5） |
+| `video_id` | STRING | 是 | - | 要扩展的视频 ID。支持由文生视频、图生视频和先前视频扩展操作生成的视频。扩展后总时长不能超过 3 分钟。 |
+
+**注意：** `video_id` 必须引用由其他 Kling 节点创建的视频，且扩展后的总时长不能超过 3 分钟。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video_id` | VIDEO | 由 Kling API 生成的扩展视频 |
+| `duration` | STRING | 扩展视频的唯一标识符 |
+| `duration` | STRING | 扩展视频的时长 |
diff --git a/zh-CN/built-in-nodes/KlingVideoNode.mdx b/zh-CN/built-in-nodes/KlingVideoNode.mdx
new file mode 100644
index 000000000..0268987fc
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingVideoNode.mdx
@@ -0,0 +1,42 @@
+---
+title: "KlingVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoNode/zh.md)
+
+此节点使用 Kling V3 模型生成视频。它支持两种主要模式：文本到视频（根据文本描述创建视频）和图像到视频（对现有图像进行动画处理）。它还提供高级功能，例如创建具有不同片段提示和时长的多段视频（故事板），并可选择生成伴随音频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `multi_shot` | COMBO | 是 | `"disabled"`<br />`"1 storyboard"`<br />`"2 storyboards"`<br />`"3 storyboards"`<br />`"4 storyboards"`<br />`"5 storyboards"`<br />`"6 storyboards"` | 控制是生成单个视频，还是生成一系列具有独立提示和时长的片段。当不为 "disabled" 时，会显示每个故事板的提示和时长输入项。 |
+| `generate_audio` | BOOLEAN | 是 | `True` / `False` | 启用后，节点将为视频生成音频。默认值为 `True`。 |
+| `model` | COMBO | 是 | `"kling-v3"` | 模型及其相关设置。选择此选项会显示 `resolution` 和 `aspect_ratio` 子参数。 |
+| `model.resolution` | COMBO | 是 | `"1080p"`<br />`"720p"` | 生成视频的分辨率。当 `model` 设置为 "kling-v3" 时，此设置可用。 |
+| `model.aspect_ratio` | COMBO | 是 | `"16:9"`<br />`"9:16"`<br />`"1:1"` | 生成视频的宽高比。当为 `start_frame` 提供了图像（图像到视频模式）时，此设置将被忽略。在 `model` 设置为 "kling-v3" 时可用。 |
+| `seed` | INT | 是 | 0 到 2147483647 | 生成的种子值。更改此值将导致节点重新运行，但结果是非确定性的。默认值为 `0`。 |
+| `start_frame` | IMAGE | 否 | - | 可选的起始图像。当连接此输入时，节点将从文本到视频模式切换到图像到视频模式，对提供的图像进行动画处理。 |
+
+**`multi_shot` 模式下的输入：**
+
+* 当 `multi_shot` 设置为 **"disabled"** 时，会出现以下输入：
+  * `prompt` (STRING): 视频的主要文本描述。必填。长度必须在 1 到 2500 个字符之间。
+  * `negative_prompt` (STRING): 描述视频中不应出现内容的文本。可选。
+  * `duration` (INT): 视频时长（秒）。必须在 3 到 15 秒之间。默认值为 `5`。
+* 当 `multi_shot` 设置为故事板选项（例如 `"3 storyboards"`）时，会出现每个故事板片段的输入（例如 `storyboard_1_prompt`、`storyboard_1_duration`）。每个提示的长度必须在 1 到 512 个字符之间。**所有故事板时长的总和**必须在 3 到 15 秒之间。
+
+**约束条件：**
+
+* 当 `start_frame` 未连接时，节点在**文本到视频**模式下运行。在此模式下，它使用 `model.aspect_ratio` 设置。
+* 当 `start_frame` 连接时，节点在**图像到视频**模式下运行。`model.aspect_ratio` 设置将被忽略。输入图像必须至少为 300x300 像素，且宽高比在 1:2.5 到 2.5:1 之间。
+* 在故事板模式下（`multi_shot` 不为 "disabled"），主 `prompt` 和 `negative_prompt` 输入将被隐藏且不被使用。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/KlingVirtualTryOnNode.mdx b/zh-CN/built-in-nodes/KlingVirtualTryOnNode.mdx
new file mode 100644
index 000000000..6e75e7fe2
--- /dev/null
+++ b/zh-CN/built-in-nodes/KlingVirtualTryOnNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "KlingVirtualTryOnNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the KlingVirtualTryOnNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "KlingVirtualTryOnNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVirtualTryOnNode/zh.md)
+
+# ## 概述
+
+Kling 虚拟试穿节点。输入人物图像和服装图像，在人物身上试穿服装。您可以将多个服装物品图片合并为一张白色背景的图像。
+
+# ## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `human_image` | IMAGE | 是 | - | 用于试穿服装的人物图像 |
+| `cloth_image` | IMAGE | 是 | - | 要在人物身上试穿的服装图像 |
+| `model_name` | STRING | 是 | `"kolors-virtual-try-on-v1"` | 使用的虚拟试穿模型（默认："kolors-virtual-try-on-v1"） |
+
+# ## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 生成的显示人物试穿服装后的图像 |
diff --git a/zh-CN/built-in-nodes/LTXAVTextEncoderLoader.mdx b/zh-CN/built-in-nodes/LTXAVTextEncoderLoader.mdx
new file mode 100644
index 000000000..113526a31
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXAVTextEncoderLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "LTXAVTextEncoderLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXAVTextEncoderLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXAVTextEncoderLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXAVTextEncoderLoader/zh.md)
+
+此节点为 LTXV 音频模型加载专用的文本编码器。它将特定的文本编码器文件与检查点文件结合，创建一个可用于音频相关文本条件任务的 CLIP 模型。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text_encoder` | STRING | 是 | 提供多个选项 | 要加载的 LTXV 文本编码器模型的文件名。可用选项从 `text_encoders` 文件夹加载。 |
+| `ckpt_name` | STRING | 是 | 提供多个选项 | 要加载的检查点文件名。可用选项从 `checkpoints` 文件夹加载。 |
+| `device` | STRING | 否 | `"default"`<br />`"cpu"` | 指定加载模型的目标设备。使用 `"cpu"` 强制加载到 CPU。默认行为 (`"default"`) 使用系统的自动设备分配。 |
+
+**注意：** `text_encoder` 和 `ckpt_name` 参数需配合使用。节点会加载指定的两个文件以创建一个完整可用的 CLIP 模型。这些文件必须与 LTXV 架构兼容。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `clip` | CLIP | 已加载的 LTXV CLIP 模型，可用于为音频生成任务编码文本提示。 |
diff --git a/zh-CN/built-in-nodes/LTXVAddGuide.mdx b/zh-CN/built-in-nodes/LTXVAddGuide.mdx
new file mode 100644
index 000000000..e13f1e298
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVAddGuide.mdx
@@ -0,0 +1,34 @@
+---
+title: "LTXVAddGuide - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVAddGuide node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVAddGuide"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAddGuide/zh.md)
+
+## 概述
+
+LTXVAddGuide 节点通过编码输入图像或视频并将其作为关键帧融入条件数据，为潜在序列添加视频条件引导。该节点通过 VAE 编码器处理输入，并将生成的潜在表示策略性地放置在指定帧位置，同时使用关键帧信息更新正向和负向条件数据。该节点处理帧对齐约束，并允许控制条件影响的强度。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `正向` | CONDITIONING | 是 | - | 待使用关键帧引导修改的正向条件输入 |
+| `负向` | CONDITIONING | 是 | - | 待使用关键帧引导修改的负向条件输入 |
+| `vae` | VAE | 是 | - | 用于编码输入图像/视频帧的 VAE 模型 |
+| `潜在空间` | LATENT | 是 | - | 将接收条件帧的输入潜在序列 |
+| `图像` | IMAGE | 是 | - | 用于为潜在视频添加条件的图像或视频。必须为 8*n + 1 帧。如果视频不是 8*n + 1 帧，将被裁剪至最接近的 8*n + 1 帧。 |
+| `帧索引` | INT | 否 | -9999 到 9999 | 开始添加条件引导的帧索引。对于单帧图像或 1-8 帧的视频，任何 frame_idx 值均可接受。对于 9+ 帧的视频，frame_idx 必须能被 8 整除，否则将向下取整至最接近的 8 的倍数。负值表示从视频末尾开始计数。（默认值：0） |
+| `强度` | FLOAT | 否 | 0.0 到 1.0 | 条件影响的强度，1.0 表示应用完整条件，0.0 表示不应用条件（默认值：1.0） |
+
+**注意：** 输入图像/视频的帧数必须符合 8*n + 1 模式（例如 1、9、17、25 帧）。如果输入超出此模式，将自动裁剪至最接近的有效帧数。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `负向` | CONDITIONING | 使用关键帧引导信息更新后的正向条件数据 |
+| `潜在空间` | CONDITIONING | 使用关键帧引导信息更新后的负向条件数据 |
+| `潜在空间` | LATENT | 包含条件帧并更新了噪声掩码的潜在序列 |
diff --git a/zh-CN/built-in-nodes/LTXVAudioVAEDecode.mdx b/zh-CN/built-in-nodes/LTXVAudioVAEDecode.mdx
new file mode 100644
index 000000000..5dae7adbd
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVAudioVAEDecode.mdx
@@ -0,0 +1,25 @@
+---
+title: "LTXVAudioVAEDecode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVAudioVAEDecode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVAudioVAEDecode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAEDecode/zh.md)
+
+LTXV Audio VAE Decode 节点将音频的潜在表示转换回音频波形。它使用专门的 Audio VAE 模型来执行此解码过程，生成具有特定采样率的音频输出。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | 是 | N/A | 待解码的潜在表示。 |
+| `audio_vae` | VAE | 是 | N/A | 用于解码潜在表示的 Audio VAE 模型。 |
+
+**注意：** 如果提供的潜在表示是嵌套的（包含多个潜在表示），节点将自动使用序列中的最后一个潜在表示进行解码。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `Audio` | AUDIO | 解码后的音频波形及其关联的采样率。 |
diff --git a/zh-CN/built-in-nodes/LTXVAudioVAEEncode.mdx b/zh-CN/built-in-nodes/LTXVAudioVAEEncode.mdx
new file mode 100644
index 000000000..816d61b32
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVAudioVAEEncode.mdx
@@ -0,0 +1,23 @@
+---
+title: "LTXVAudioVAEEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVAudioVAEEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVAudioVAEEncode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAEEncode/zh.md)
+
+LTXV Audio VAE Encode 节点接收音频输入，并使用指定的 Audio VAE 模型将其压缩为更小的潜在表示。此过程对于在潜在空间工作流中生成或操作音频至关重要，因为它将原始音频数据转换为流程中其他节点能够理解和处理的格式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | 是 | - | 待编码的音频。 |
+| `audio_vae` | VAE | 是 | - | 用于编码的 Audio VAE 模型。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `Audio Latent` | LATENT | 输入音频的压缩潜在表示。输出包含潜在样本、VAE 模型的采样率以及一个类型标识符。 |
diff --git a/zh-CN/built-in-nodes/LTXVAudioVAELoader.mdx b/zh-CN/built-in-nodes/LTXVAudioVAELoader.mdx
new file mode 100644
index 000000000..8cadfd335
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVAudioVAELoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "LTXVAudioVAELoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVAudioVAELoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVAudioVAELoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAELoader/zh.md)
+
+该节点从检查点文件加载预训练的音频变分自编码器（VAE）模型。它会读取指定的检查点，加载其权重和元数据，并准备该模型以在 ComfyUI 内的音频生成或处理工作流中使用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `ckpt_name` | STRING | 是 | `checkpoints` 文件夹中的所有文件。<br />*示例：`"audio_vae.safetensors"`* | 要加载的音频 VAE 检查点。这是一个下拉列表，其中填充了在 ComfyUI `checkpoints` 目录中找到的所有文件。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `Audio VAE` | VAE | 已加载的音频变分自编码器模型，可连接到其他音频处理节点。 |
diff --git a/zh-CN/built-in-nodes/LTXVConcatAVLatent.mdx b/zh-CN/built-in-nodes/LTXVConcatAVLatent.mdx
new file mode 100644
index 000000000..17fcdc4b7
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVConcatAVLatent.mdx
@@ -0,0 +1,25 @@
+---
+title: "LTXVConcatAVLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVConcatAVLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVConcatAVLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVConcatAVLatent/zh.md)
+
+LTXVConcatAVLatent 节点将视频潜在表示和音频潜在表示合并为一个单一的、拼接后的潜在输出。它会合并两个输入中的 `samples` 张量，如果存在的话，也会合并它们的 `noise_mask` 张量，为视频生成流程中的后续处理做好准备。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `video_latent` | LATENT | 是 | | 视频数据的潜在表示。 |
+| `audio_latent` | LATENT | 是 | | 音频数据的潜在表示。 |
+
+**注意：** `video_latent` 和 `audio_latent` 输入中的 `samples` 张量会被拼接。如果任一输入包含 `noise_mask`，则会使用它；如果某个输入缺少 `noise_mask`，则会为其创建一个全为 1 的掩码（形状与对应的 `samples` 相同）。然后，生成的掩码也会被拼接。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `latent` | LATENT | 一个单一的潜在字典，包含拼接后的 `samples`，以及（如果适用）来自视频和音频输入的拼接后的 `noise_mask`。 |
diff --git a/zh-CN/built-in-nodes/LTXVConditioning.mdx b/zh-CN/built-in-nodes/LTXVConditioning.mdx
new file mode 100644
index 000000000..12a66ba4b
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVConditioning.mdx
@@ -0,0 +1,27 @@
+---
+title: "LTXVConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVConditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVConditioning/zh.md)
+
+## 概述
+
+LTXVConditioning 节点用于为视频生成模型的正负条件输入添加帧率信息。该节点接收现有的条件数据，并将指定的帧率值应用于两组条件数据，使其适用于视频模型处理。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正面条件` | CONDITIONING | 是 | - | 将接收帧率信息的正条件输入 |
+| `负面条件` | CONDITIONING | 是 | - | 将接收帧率信息的负条件输入 |
+| `帧率` | FLOAT | 否 | 0.0 - 1000.0 | 要应用于两组条件数据的帧率值（默认值：25.0） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 已应用帧率信息的正条件数据 |
+| `负面条件` | CONDITIONING | 已应用帧率信息的负条件数据 |
diff --git a/zh-CN/built-in-nodes/LTXVCropGuides.mdx b/zh-CN/built-in-nodes/LTXVCropGuides.mdx
new file mode 100644
index 000000000..8927890d6
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVCropGuides.mdx
@@ -0,0 +1,28 @@
+---
+title: "LTXVCropGuides - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVCropGuides node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVCropGuides"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVCropGuides/zh.md)
+
+## 概述
+
+LTXVCropGuides 节点通过移除关键帧信息并调整潜在维度，为视频生成处理条件输入和潜在输入。该节点会裁剪潜在图像和噪声掩码以排除关键帧部分，同时清除正负条件输入中的关键帧索引。这为不需要关键帧引导的视频生成工作流程准备了数据。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正向` | CONDITIONING | 是 | - | 包含生成引导信息的正条件输入 |
+| `负向` | CONDITIONING | 是 | - | 包含生成过程中需要避免内容的引导信息的负条件输入 |
+| `潜在空间` | LATENT | 是 | - | 包含图像样本和噪声掩码数据的潜在表示 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负向` | CONDITIONING | 已清除关键帧索引的处理后正条件输入 |
+| `潜在空间` | CONDITIONING | 已清除关键帧索引的处理后负条件输入 |
+| `潜在空间` | LATENT | 包含调整后样本和噪声掩码的裁剪后潜在表示 |
diff --git a/zh-CN/built-in-nodes/LTXVEmptyLatentAudio.mdx b/zh-CN/built-in-nodes/LTXVEmptyLatentAudio.mdx
new file mode 100644
index 000000000..d232bf2c8
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVEmptyLatentAudio.mdx
@@ -0,0 +1,27 @@
+---
+title: "LTXVEmptyLatentAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVEmptyLatentAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVEmptyLatentAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVEmptyLatentAudio/zh.md)
+
+LTXV Empty Latent Audio 节点创建一批空（零填充）的潜在音频张量。它使用提供的 Audio VAE 模型的配置来确定潜在空间的正确维度，例如通道数和频率仓的数量。这个空的潜在张量可作为 ComfyUI 内音频生成或处理工作流的起点。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `frames_number` | INT | 是 | 1 到 1000 | 帧数。默认值为 97。 |
+| `frame_rate` | INT | 是 | 1 到 1000 | 每秒帧数。默认值为 25。 |
+| `batch_size` | INT | 是 | 1 到 4096 | 批次中潜在音频样本的数量。默认值为 1。 |
+| `audio_vae` | VAE | 是 | N/A | 用于获取配置的 Audio VAE 模型。此参数为必需项。 |
+
+**注意：** `audio_vae` 输入是强制性的。如果未提供，节点将引发错误。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `Latent` | LATENT | 一个空的潜在音频张量，其结构（样本数，采样率，类型）被配置为与输入的 Audio VAE 相匹配。 |
diff --git a/zh-CN/built-in-nodes/LTXVImgToVideo.mdx b/zh-CN/built-in-nodes/LTXVImgToVideo.mdx
new file mode 100644
index 000000000..0a5f854b5
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVImgToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "LTXVImgToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVImgToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVImgToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVImgToVideo/zh.md)
+
+> 本文档由 AI 生成，如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVImgToVideo/en.md)
+
+LTXVImgToVideo 节点将输入图像转换为视频生成模型所需的视频潜在表示。它接收单张图像，使用 VAE 编码器将其扩展为帧序列，然后应用带强度控制的调节，以确定在视频生成过程中保留原始图像内容与修改内容的比例。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-------|-----------|----------|-------|-------------|
+| `正面条件` | CONDITIONING | 是 | - | 用于引导视频生成的正向调节提示 |
+| `负面条件` | CONDITIONING | 是 | - | 用于避免视频中出现特定元素的负向调节提示 |
+| `vae` | VAE | 是 | - | 用于将输入图像编码到潜在空间的 VAE 模型 |
+| `图像` | IMAGE | 是 | - | 待转换为视频帧的输入图像 |
+| `宽度` | INT | 否 | 64 至 MAX_RESOLUTION | 输出视频宽度（像素）（默认：768，步长：32） |
+| `高度` | INT | 否 | 64 至 MAX_RESOLUTION | 输出视频高度（像素）（默认：512，步长：32） |
+| `长度` | INT | 否 | 9 至 MAX_RESOLUTION | 生成视频的帧数（默认：97，步长：8） |
+| `批量大小` | INT | 否 | 1 至 4096 | 同时生成的视频数量（默认：1） |
+| `强度` | FLOAT | 否 | 0.0 至 1.0 | 控制视频生成过程中对原始图像的修改程度，1.0 保留最多原始内容，0.0 允许最大程度修改（默认：1.0） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 应用视频帧掩码处理后的正向调节 |
+| `Latent` | CONDITIONING | 应用视频帧掩码处理后的负向调节 |
+| `latent` | LATENT | 包含编码帧和噪声掩码的视频潜在表示，用于视频生成 |
diff --git a/zh-CN/built-in-nodes/LTXVImgToVideoInplace.mdx b/zh-CN/built-in-nodes/LTXVImgToVideoInplace.mdx
new file mode 100644
index 000000000..7e7a66553
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVImgToVideoInplace.mdx
@@ -0,0 +1,28 @@
+---
+title: "LTXVImgToVideoInplace - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVImgToVideoInplace node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVImgToVideoInplace"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVImgToVideoInplace/zh.md)
+
+LTXVImgToVideoInplace 节点通过将输入图像编码到其初始帧中，来对视频潜在表示进行条件化处理。其工作原理是使用 VAE 将图像编码到潜在空间，然后根据指定的强度将其与现有的潜在样本进行混合。这使得图像可以作为视频生成的起点或条件信号。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `vae` | VAE | 是 | - | 用于将输入图像编码到潜在空间的 VAE 模型。 |
+| `image` | IMAGE | 是 | - | 待编码并用于对视频潜在表示进行条件化的输入图像。 |
+| `latent` | LATENT | 是 | - | 待修改的目标潜在视频表示。 |
+| `strength` | FLOAT | 否 | 0.0 - 1.0 | 控制编码图像混合到潜在表示中的强度。值为 1.0 时完全替换初始帧，较低的值则进行混合。(默认值: 1.0) |
+| `bypass` | BOOLEAN | 否 | - | 绕过条件化处理。启用时，节点返回未经修改的输入潜在表示。(默认值: False) |
+
+**注意：** `image` 将根据 `latent` 输入的宽度和高度，自动调整大小以匹配 `vae` 编码所需的空间维度。
+
+## 输出参数
+
+| 输出名 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `latent` | LATENT | 修改后的潜在视频表示。它包含更新后的样本以及一个将条件化强度应用于初始帧的 `noise_mask`。 |
diff --git a/zh-CN/built-in-nodes/LTXVLatentUpsampler.mdx b/zh-CN/built-in-nodes/LTXVLatentUpsampler.mdx
new file mode 100644
index 000000000..564860453
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVLatentUpsampler.mdx
@@ -0,0 +1,26 @@
+---
+title: "LTXVLatentUpsampler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVLatentUpsampler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVLatentUpsampler"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVLatentUpsampler/zh.md)
+
+该文档由AI生成。如果您发现任何错误或有改进建议，欢迎贡献！[在GitHub上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVLatentUpsampler/en.md)
+
+LTXVLatentUpsampler 节点将视频潜在表示的空间分辨率提升两倍。它使用一个专门的放大模型来处理潜在数据，该数据首先会进行反归一化，然后使用提供的VAE的通道统计量重新归一化。此节点专为潜在空间内的视频工作流设计。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | 是 | | 待放大的视频输入潜在表示。 |
+| `upscale_model` | LATENT_UPSCALE_MODEL | 是 | | 用于对潜在数据执行2倍放大的已加载模型。 |
+| `vae` | VAE | 是 | | 用于在放大前对输入潜在表示进行反归一化，并在放大后对输出潜在表示进行归一化的VAE模型。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 放大后的潜在表示，其空间维度相比输入扩大了一倍。 |
diff --git a/zh-CN/built-in-nodes/LTXVPreprocess.mdx b/zh-CN/built-in-nodes/LTXVPreprocess.mdx
new file mode 100644
index 000000000..ee77d6c66
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVPreprocess.mdx
@@ -0,0 +1,23 @@
+---
+title: "LTXVPreprocess - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVPreprocess node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVPreprocess"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVPreprocess/zh.md)
+
+LTXVPreprocess 节点对图像应用压缩预处理。它接收输入图像并使用指定的压缩级别进行处理，输出应用了压缩设置的处理后图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 待处理的输入图像 |
+| `图像压缩` | INT | 否 | 0-100 | 应用于图像的压缩量（默认值：35） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output_image` | IMAGE | 应用压缩处理后的输出图像 |
diff --git a/zh-CN/built-in-nodes/LTXVScheduler.mdx b/zh-CN/built-in-nodes/LTXVScheduler.mdx
new file mode 100644
index 000000000..e2dff0388
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVScheduler.mdx
@@ -0,0 +1,29 @@
+---
+title: "LTXVScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVScheduler"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVScheduler/zh.md)
+
+LTXVScheduler 节点为自定义采样过程生成 sigma 值。它根据输入潜在表示中的令牌数量计算噪声调度参数，并应用 sigmoid 变换来创建采样调度。该节点可以选择性地拉伸生成的 sigma 值以匹配指定的终止值。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `步数` | INT | 是 | 1-10000 | 采样步数（默认值：20） |
+| `最大移位` | FLOAT | 是 | 0.0-100.0 | sigma 计算的最大偏移值（默认值：2.05） |
+| `基础移位` | FLOAT | 是 | 0.0-100.0 | sigma 计算的基础偏移值（默认值：0.95） |
+| `拉伸` | BOOLEAN | 是 | True/False | 将 sigma 拉伸到 [terminal, 1] 范围内（默认值：True） |
+| `终值` | FLOAT | 是 | 0.0-0.99 | 拉伸后 sigma 的终止值（默认值：0.1） |
+| `Latent` | LATENT | 否 | - | 用于计算令牌数量以进行 sigma 调整的可选潜在表示输入 |
+
+**注意：** `latent` 参数是可选的。当未提供时，节点将使用默认令牌数量 4096 进行计算。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | 为采样过程生成的 sigma 值 |
diff --git a/zh-CN/built-in-nodes/LTXVSeparateAVLatent.mdx b/zh-CN/built-in-nodes/LTXVSeparateAVLatent.mdx
new file mode 100644
index 000000000..433b39b8b
--- /dev/null
+++ b/zh-CN/built-in-nodes/LTXVSeparateAVLatent.mdx
@@ -0,0 +1,25 @@
+---
+title: "LTXVSeparateAVLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LTXVSeparateAVLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LTXVSeparateAVLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVSeparateAVLatent/zh.md)
+
+LTXVSeparateAVLatent 节点接收一个组合的视听潜在表示，并将其拆分为两个独立的部分：一部分用于视频，另一部分用于音频。它会从输入的潜在表示中分离出样本，如果存在噪声掩码，也会一并分离，从而创建两个新的潜在对象。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `av_latent` | LATENT | 是 | N/A | 待分离的组合视听潜在表示。 |
+
+**注意：** 输入潜在表示的 `samples` 张量在其第一个维度（批次维度）上应至少包含两个元素。第一个元素用于视频潜在表示，第二个元素用于音频潜在表示。如果存在 `noise_mask`，也会以相同方式进行分离。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video_latent` | LATENT | 包含已分离视频数据的潜在表示。 |
+| `audio_latent` | LATENT | 包含已分离音频数据的潜在表示。 |
diff --git a/zh-CN/built-in-nodes/LaplaceScheduler.mdx b/zh-CN/built-in-nodes/LaplaceScheduler.mdx
new file mode 100644
index 000000000..a0457f429
--- /dev/null
+++ b/zh-CN/built-in-nodes/LaplaceScheduler.mdx
@@ -0,0 +1,26 @@
+---
+title: "LaplaceScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LaplaceScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LaplaceScheduler"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LaplaceScheduler/zh.md)
+
+LaplaceScheduler 节点遵循拉普拉斯分布生成一系列 sigma 值，用于扩散采样过程。它创建了一个从最大值逐渐递减至最小值的噪声级别调度表，通过拉普拉斯分布参数来控制衰减进程。该调度器常用于自定义采样工作流中，为扩散模型定义噪声调度方案。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `步数` | INT | 是 | 1 至 10000 | 调度表中的采样步数（默认值：20） |
+| `sigma_max` | FLOAT | 是 | 0.0 至 5000.0 | 调度起始时的最大 sigma 值（默认值：14.614642） |
+| `sigma_min` | FLOAT | 是 | 0.0 至 5000.0 | 调度结束时的最小 sigma 值（默认值：0.0291675） |
+| `mu` | FLOAT | 是 | -10.0 至 10.0 | 拉普拉斯分布的均值参数（默认值：0.0） |
+| `beta` | FLOAT | 是 | 0.0 至 10.0 | 拉普拉斯分布的尺度参数（默认值：0.5） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `SIGMAS` | SIGMAS | 遵循拉普拉斯分布调度的一系列 sigma 值 |
diff --git a/zh-CN/built-in-nodes/LatentAdd.mdx b/zh-CN/built-in-nodes/LatentAdd.mdx
new file mode 100644
index 000000000..c67e5487e
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentAdd.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentAdd - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentAdd node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentAdd"
+icon: "circle"
+mode: wide
+---
+
+LatentAdd节点旨在对两个潜在表示进行加法运算。它通过执行逐元素加法，促进了这些表示中编码的特征或特性的组合。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent1` | `LATENT` | 要相加的第一组潜在样本。它代表了要与另一组潜在样本结合的特征的输入之一。 |
+| `Latent2` | `LATENT` | 要相加的第二组潜在样本。它作为另一个输入，其特征通过逐元素相加与第一组潜在样本结合。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 两个潜在样本逐元素相加的结果，代表结合了两个输入特征的新的潜在样本集。 |
+
+---
diff --git a/zh-CN/built-in-nodes/LatentApplyOperation.mdx b/zh-CN/built-in-nodes/LatentApplyOperation.mdx
new file mode 100644
index 000000000..f357bfbc3
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentApplyOperation.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentApplyOperation - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentApplyOperation node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentApplyOperation"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentApplyOperation/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentApplyOperation/en.md)
+
+LatentApplyOperation 节点对潜在样本应用指定操作。它接收潜在数据和操作作为输入，使用提供的操作处理潜在样本，并返回修改后的潜在数据。该节点允许您在工作流中转换或操作潜在表示。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Latent` | LATENT | 是 | - | 需要通过操作处理的潜在样本 |
+| `操作` | LATENT_OPERATION | 是 | - | 要应用于潜在样本的操作 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | LATENT | 应用操作后修改的潜在样本 |
diff --git a/zh-CN/built-in-nodes/LatentApplyOperationCFG.mdx b/zh-CN/built-in-nodes/LatentApplyOperationCFG.mdx
new file mode 100644
index 000000000..4f304487e
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentApplyOperationCFG.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentApplyOperationCFG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentApplyOperationCFG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentApplyOperationCFG"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentApplyOperationCFG/zh.md)
+
+## 概述
+
+LatentApplyOperationCFG 节点通过应用潜在操作来修改模型中的条件引导过程。该节点的工作原理是在无分类器引导（CFG）采样过程中拦截条件输出，并在潜在表示被用于生成之前对其应用指定操作。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 将应用 CFG 操作的模型 |
+| `操作` | LATENT_OPERATION | 是 | - | 在 CFG 采样过程中要应用的潜在操作 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 已在其采样过程中应用 CFG 操作的修改后模型 |
diff --git a/zh-CN/built-in-nodes/LatentBatch.mdx b/zh-CN/built-in-nodes/LatentBatch.mdx
new file mode 100644
index 000000000..611c5caef
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentBatch.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentBatch"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于将两组潜在样本合并为一个单一的批量，可能在拼接前调整其中一组的大小以匹配另一组的尺寸。这个操作便于将不同的潜在表示组合起来进行进一步的处理或生成任务。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent1` | `LATENT` | 要合并的第一组潜在样本。它在确定合并后的批量的最终形状中起着关键作用。 |
+| `Latent2` | `LATENT` | 要合并的第二组潜在样本。如果其尺寸与第一组不同，在合并前会调整其大小以确保兼容。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 合并后的潜在样本集，现在组合成一个单一的批量以供进一步处理。 |
diff --git a/zh-CN/built-in-nodes/LatentBatchSeedBehavior.mdx b/zh-CN/built-in-nodes/LatentBatchSeedBehavior.mdx
new file mode 100644
index 000000000..b4fbd7062
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentBatchSeedBehavior.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentBatchSeedBehavior - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentBatchSeedBehavior node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentBatchSeedBehavior"
+icon: "circle"
+mode: wide
+---
+
+潜在批量种子行为节点旨在修改一批潜在样本的种子行为。它允许对种子进行随机化或固定，从而通过引入变化性或保持生成输出的一致性来影响生成过程。
+
+## 输入
+
+| 参数名称         | 数据类型     | 作用                                                         |
+|------------------|--------------|--------------------------------------------------------------|
+| `Latent`        | `LATENT`     | `Latent` 参数代表要处理的潜在样本批次。其修改取决于所选择的种子行为，影响生成输出的一致性或变化性。 |
+| `随机种行为`  | COMBO[STRING] | `随机种行为` 参数决定一批潜在样本的种子应该是随机化的还是固定的。这个选择通过引入变化性或确保批次的一致性，显著影响生成过程。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                       |
+|----------|----------|--------------------------------------------|
+| `latent` | `LATENT` | 输出是基于指定的种子行为调整后的输入潜在样本的修改版本。它保持或改变批次索引以反映所选择的种子行为。 |
diff --git a/zh-CN/built-in-nodes/LatentBlend.mdx b/zh-CN/built-in-nodes/LatentBlend.mdx
new file mode 100644
index 000000000..890ba2103
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentBlend.mdx
@@ -0,0 +1,26 @@
+---
+title: "LatentBlend - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentBlend node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentBlend"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentBlend/zh.md)
+
+LatentBlend 节点通过使用指定的混合因子将两个潜在样本进行混合。该节点接收两个潜在输入，并创建一个新的输出，其中第一个样本按混合因子加权，第二个样本按反向权重加权。如果输入样本具有不同的形状，第二个样本会自动调整大小以匹配第一个样本的维度。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Latent1` | LATENT | 是 | - | 要混合的第一个潜在样本 |
+| `Latent2` | LATENT | 是 | - | 要混合的第二个潜在样本 |
+| `系数` | FLOAT | 是 | 0 到 1 | 控制两个样本之间的混合比例（默认值：0.5） |
+
+**注意：** 如果 `samples1` 和 `samples2` 具有不同的形状，`samples2` 将使用双三次插值和中心裁剪自动调整尺寸以匹配 `samples1` 的维度。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `latent` | LATENT | 混合两个输入样本后得到的潜在样本 |
diff --git a/zh-CN/built-in-nodes/LatentComposite.mdx b/zh-CN/built-in-nodes/LatentComposite.mdx
new file mode 100644
index 000000000..75303182a
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentComposite.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentComposite - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentComposite node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentComposite"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于将两个潜在表示混合或合并为单个输出。这一过程对于通过控制方式结合输入潜在特征来创建组合图像或特征至关重要。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent到` | `LATENT` | 'samples_to'的潜在表示，是'samples_from'组合的基础。 |
+| `Latent从` | `LATENT` | 要组合到'samples_to'上的'samples_from'潜在表示。它为最终组合输出贡献其特征或特性。 |
+| `x` | `INT` | 'samples_from'潜在将放置在'samples_to'上的x坐标（水平位置）。它决定了组合的水平对齐方式。 |
+| `y` | `INT` | 'samples_from'潜在将放置在'samples_to'上的y坐标（垂直位置）。它决定了组合的垂直对齐方式。 |
+| `羽化` | `INT` | 一个布尔值，指示在组合之前是否应将'samples_from'潜在调整大小以匹配'samples_to'。这可能影响组合结果的规模和比例。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 输出是一个组合的潜在表示，根据指定的坐标和调整大小选项，混合了'samples_to'和'samples_from'潜在的特征。 |
diff --git a/zh-CN/built-in-nodes/LatentCompositeMasked.mdx b/zh-CN/built-in-nodes/LatentCompositeMasked.mdx
new file mode 100644
index 000000000..64e014d57
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentCompositeMasked.mdx
@@ -0,0 +1,26 @@
+---
+title: "LatentCompositeMasked - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentCompositeMasked node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentCompositeMasked"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于在指定坐标处将两个潜在表示混合在一起，可选择使用遮罩进行更受控的组合。该节点允许通过将一个图像的部分覆盖在另一个图像上来创建复杂的潜在图像，并能够调整源图像的大小以实现完美贴合。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `目标Latent` | `LATENT` | 另一个潜在表示将被组合到其上的潜在表示。作为组合操作的基础层。 |
+| `来源Latent` | `LATENT` | 要组合到目标上的潜在表示。这个源层可以根据指定的参数调整大小和位置。 |
+| `x` | `INT` | 在目标潜在表示中放置源的x坐标。允许精确定位源层。 |
+| `y` | `INT` | 在目标潜在表示中放置源的y坐标，实现准确的叠加定位。 |
+| `调整来源大小` | `BOOLEAN` | 一个布尔标志，指示在组合之前是否应将源潜在表示调整大小以匹配目标的尺寸。 |
+| `遮罩` | `MASK` | 一个可选的遮罩，用于控制源与目标的混合。遮罩定义了源的哪些部分将在最终组合中可见。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 在将源组合到目标上后得到的潜在表示，可能使用遮罩进行选择性混合。 |
diff --git a/zh-CN/built-in-nodes/LatentConcat.mdx b/zh-CN/built-in-nodes/LatentConcat.mdx
new file mode 100644
index 000000000..9fe441f29
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentConcat.mdx
@@ -0,0 +1,26 @@
+---
+title: "LatentConcat - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentConcat node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentConcat"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentConcat/zh.md)
+
+LatentConcat 节点沿着指定维度合并两个潜在样本。它接收两个潜在输入，并沿着选定的轴（x、y 或 t 维度）将它们连接在一起。在执行连接操作之前，该节点会自动调整第二个输入的批次大小以匹配第一个输入。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `samples1` | LATENT | 是 | - | 要连接的第一个潜在样本 |
+| `samples2` | LATENT | 是 | - | 要连接的第二个潜在样本 |
+| `dim` | COMBO | 是 | `"x"`<br />`"-x"`<br />`"y"`<br />`"-y"`<br />`"t"`<br />`"-t"` | 连接潜在样本所沿的维度。正值表示将 samples1 连接在 samples2 之前，负值表示将 samples2 连接在 samples1 之前 |
+
+**注意：** 在连接操作之前，第二个潜在样本 (`samples2`) 会自动调整以匹配第一个潜在样本 (`samples1`) 的批次大小。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | LATENT | 沿着指定维度合并两个输入样本后得到的连接潜在样本 |
diff --git a/zh-CN/built-in-nodes/LatentCrop.mdx b/zh-CN/built-in-nodes/LatentCrop.mdx
new file mode 100644
index 000000000..0159be55b
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentCrop.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentCrop - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentCrop node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentCrop"
+icon: "circle"
+mode: wide
+---
+
+LatentCrop节点旨在对图像的潜在表示执行裁剪操作。它允许指定裁剪尺寸和位置，从而实现对潜在空间的针对性修改。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `Latent` | LATENT   | `Latent` 参数代表要裁剪的潜在表示。它对于定义裁剪操作将执行的数据至关重要。 |
+| `宽度`   | INT      | 指定裁剪区域的宽度。它直接影响输出潜在表示的维度。           |
+| `高度`  | INT      | 指定裁剪区域的高度，影响裁剪后潜在表示的大小。             |
+| `x`       | INT      | 确定裁剪区域起始的x坐标，影响裁剪在原始潜在表示内的位置。   |
+| `y`       | INT      | 确定裁剪区域起始的y坐标，设定裁剪在原始潜在表示内的位置。   |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `latent` | LATENT   | 输出是应用了指定裁剪的修改后的潜在表示。                     |
diff --git a/zh-CN/built-in-nodes/LatentCut.mdx b/zh-CN/built-in-nodes/LatentCut.mdx
new file mode 100644
index 000000000..c482e5498
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentCut.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentCut - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentCut node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentCut"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentCut/zh.md)
+
+LatentCut 节点沿着选定维度从潜在样本中提取特定部分。它允许您通过指定维度（x、y 或 t）、起始位置和提取数量来截取潜在表示的一部分。该节点支持正向和负向索引，并会自动调整提取数量以确保在可用范围内操作。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | 是 | - | 用于提取的输入潜在样本 |
+| `dim` | COMBO | 是 | "x"<br />"y"<br />"t" | 截取潜在样本所沿的维度 |
+| `index` | INT | 否 | -16384 到 16384 | 截取的起始位置（默认：0）。正值从起始处计数，负值从末尾计数 |
+| `amount` | INT | 否 | 1 到 16384 | 沿指定维度提取的元素数量（默认：1） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | LATENT | 提取的潜在样本部分 |
diff --git a/zh-CN/built-in-nodes/LatentCutToBatch.mdx b/zh-CN/built-in-nodes/LatentCutToBatch.mdx
new file mode 100644
index 000000000..d595f3e3d
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentCutToBatch.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentCutToBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentCutToBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentCutToBatch"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentCutToBatch/zh.md)
+
+LatentCutToBatch 节点接收一个潜在表示，并沿着指定维度将其分割成多个切片。这些切片随后被堆叠到一个新的批次维度中，从而有效地将单个潜在样本转换为一批较小的潜在样本。这对于独立处理潜在空间的不同部分非常有用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | 是 | - | 待分割和批处理的潜在表示。 |
+| `dim` | COMBO | 是 | `"t"`<br />`"x"`<br />`"y"` | 切割潜在样本所沿的维度。`"t"` 指时间维度，`"x"` 指宽度，`"y"` 指高度。 |
+| `slice_size` | INT | 是 | 1 到 16384 | 从指定维度切割的每个切片的大小。如果维度的大小不能被此值整除，余数将被丢弃。(默认值: 1) |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 处理后的潜在批次，包含切片并堆叠后的样本。 |
diff --git a/zh-CN/built-in-nodes/LatentFlip.mdx b/zh-CN/built-in-nodes/LatentFlip.mdx
new file mode 100644
index 000000000..ed602d03e
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentFlip.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentFlip - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentFlip node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentFlip"
+icon: "circle"
+mode: wide
+---
+
+LatentFlip节点旨在通过垂直或水平翻转来操作潜在表示。此操作允许转换潜在空间，可能揭示数据中的新变化或视角。
+
+## 输入
+
+| 参数名称      | 数据类型 | 作用                                                         |
+|---------------|----------|--------------------------------------------------------------|
+| `Latent`     | LATENT   | `Latent` 参数代表要翻转的潜在表示。翻转操作会根据`翻转方法`参数，沿垂直或水平方向改变这些表示，从而转换潜在空间中的数据。 |
+| `翻转方法` | COMBO[STRING] | `翻转方法` 参数指定了潜在样本将沿哪个轴翻转。它可以是 'x-axis: 垂直' 或 'y-axis: 水平'，决定了翻转的方向，因此也决定了应用于潜在表示的转换性质。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `latent` | LATENT   | 输出是输入潜在表示的修改版本，已根据指定的方法翻转。这种转换可以在潜在空间中引入新的变体。 |
diff --git a/zh-CN/built-in-nodes/LatentFromBatch.mdx b/zh-CN/built-in-nodes/LatentFromBatch.mdx
new file mode 100644
index 000000000..4bfc4e53e
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentFromBatch.mdx
@@ -0,0 +1,23 @@
+---
+title: "LatentFromBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentFromBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentFromBatch"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于根据指定的批量索引和长度从给定的批量中提取特定子集的潜在样本。它允许对潜在样本进行选择性处理，便于对批量的较小段进行高效操作或针对性操作。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent` | `LATENT` | 将从中提取子集的潜在样本集合。此参数对于确定要处理的源批量样本至关重要。 |
+| `批次索引` | `INT` | 指定批量中子集样本开始的起始索引。此参数使从批量中的特定位置提取样本成为可能。 |
+| `长度` | `INT` | 定义从指定起始索引提取的样本数量。此参数控制要处理的子集的大小，允许灵活地操作批量段。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 提取的潜在样本子集，现在可供进一步处理或分析。 |
diff --git a/zh-CN/built-in-nodes/LatentInterpolate.mdx b/zh-CN/built-in-nodes/LatentInterpolate.mdx
new file mode 100644
index 000000000..3c321a92b
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentInterpolate.mdx
@@ -0,0 +1,25 @@
+---
+title: "LatentInterpolate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentInterpolate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentInterpolate"
+icon: "circle"
+mode: wide
+---
+
+Latent插值节点旨在基于指定的比率对两组潜在样本执行插值，混合这两组的特性以产生一组新的、中间的潜在样本。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent1` | `LATENT` | 要进行插值的第一组潜在样本。它作为插值过程的起始点。 |
+| `Latent2` | `LATENT` | 要进行插值的第二组潜在样本。它作为插值过程的终点。 |
+| `比率` | `FLOAT` | 一个浮点值，用于确定插值输出中每组样本的权重。比率为0时产生第一组的副本，比率为1时产生第二组的副本。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 输出是一个新的潜在样本集，代表两个输入集之间的插值状态，基于指定的比率。 |
+
+---
diff --git a/zh-CN/built-in-nodes/LatentMultiply.mdx b/zh-CN/built-in-nodes/LatentMultiply.mdx
new file mode 100644
index 000000000..95afdd74e
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentMultiply.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentMultiply"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于通过指定的乘数来缩放样本的潜在表示。此操作允许调整潜在空间内特征的强度或大小，从而实现对生成内容的微调或探索给定潜在方向内的变体。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent` | `LATENT` | `Latent`参数代表要缩放的潜在表示。它对于定义乘法操作将执行的输入数据至关重要。 |
+| `乘数` | `FLOAT` | `乘数`参数指定要应用于潜在样本的缩放因子。它在调整潜在特征的大小方面起着关键作用，允许对生成的输出进行精细控制。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 输出是输入潜在样本的修改版本，已按指定的乘数进行了缩放。这允许通过调整其特征的强度来探索潜在空间内的变体。 |
+
+---
diff --git a/zh-CN/built-in-nodes/LatentOperationSharpen.mdx b/zh-CN/built-in-nodes/LatentOperationSharpen.mdx
new file mode 100644
index 000000000..8028b7dc9
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentOperationSharpen.mdx
@@ -0,0 +1,26 @@
+---
+title: "LatentOperationSharpen - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentOperationSharpen node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentOperationSharpen"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentOperationSharpen/zh.md)
+
+## 概述
+
+LatentOperationSharpen 节点使用高斯核对潜空间表示应用锐化效果。其工作原理包括对潜空间数据进行归一化处理，应用自定义锐化核进行卷积运算，然后恢复原始亮度。这样可以增强潜空间表示中的细节和边缘。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `锐化半径` | INT | 否 | 1-31 | 锐化核的半径（默认值：9） |
+| `西格玛` | FLOAT | 否 | 0.1-10.0 | 高斯核的标准差（默认值：1.0） |
+| `阿尔法` | FLOAT | 否 | 0.0-5.0 | 锐化强度因子（默认值：0.1） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `operation` | LATENT_OPERATION | 返回一个可应用于潜空间数据的锐化操作 |
diff --git a/zh-CN/built-in-nodes/LatentOperationTonemapReinhard.mdx b/zh-CN/built-in-nodes/LatentOperationTonemapReinhard.mdx
new file mode 100644
index 000000000..df8c0d5c2
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentOperationTonemapReinhard.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentOperationTonemapReinhard - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentOperationTonemapReinhard node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentOperationTonemapReinhard"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentOperationTonemapReinhard/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentOperationTonemapReinhard/en.md)
+
+LatentOperationTonemapReinhard 节点对潜在向量应用 Reinhard 色调映射技术。该方法通过基于均值和标准差的统计方法对潜在向量进行归一化处理，并调整其幅度，处理强度由乘数参数控制。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `乘数` | FLOAT | 否 | 0.0 至 100.0 | 控制色调映射效果的强度（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `operation` | LATENT_OPERATION | 返回可应用于潜在向量的色调映射操作 |
diff --git a/zh-CN/built-in-nodes/LatentRotate.mdx b/zh-CN/built-in-nodes/LatentRotate.mdx
new file mode 100644
index 000000000..59f0d5d39
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentRotate.mdx
@@ -0,0 +1,21 @@
+---
+title: "LatentRotate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentRotate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentRotate"
+icon: "circle"
+mode: wide
+---
+LatentRotate节点旨在通过指定角度旋转图像的潜在表示。它抽象了操作潜在空间以实现旋转效果的复杂性，使用户能够在生成模型的潜在空间中轻松变换图像。
+
+## 输入
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| `Latent`  | LATENT   | `Latent` 参数代表要旋转的图像的潜在表示。它对于确定旋转操作的起始点至关重要。 |
+| `旋转` | COMBO[STRING] | `旋转` 参数指定了潜在图像应旋转的角度。它直接影响生成图像的方向。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `latent` | LATENT   | 输出是输入潜在表示的修改版本，已按指定角度旋转。          |
diff --git a/zh-CN/built-in-nodes/LatentSubtract.mdx b/zh-CN/built-in-nodes/LatentSubtract.mdx
new file mode 100644
index 000000000..13f13d5ef
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentSubtract.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentSubtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentSubtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentSubtract"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于从一个潜在表示中减去另一个潜在表示。此操作可用于通过从一个潜在空间中有效地移除特征或属性来操纵或修改生成模型的输出。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent1` | `LATENT` | 要被减去的第一个潜在样本集。它作为减法操作的基础。 |
+| `Latent2` | `LATENT` | 将从第一个潜在样本集中减去的第二个潜在样本集。此操作可以通过移除属性或特征来改变生成模型的输出。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 从第一个潜在样本集中减去第二个潜在样本集的结果。这个修改后的潜在表示可用于进一步的生成任务。 |
+
+---
diff --git a/zh-CN/built-in-nodes/LatentUpscale.mdx b/zh-CN/built-in-nodes/LatentUpscale.mdx
new file mode 100644
index 000000000..93b9a90c0
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentUpscale.mdx
@@ -0,0 +1,24 @@
+---
+title: "LatentUpscale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentUpscale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentUpscale"
+icon: "circle"
+mode: wide
+---
+此节点设计用于放大图像的潜在表示。它允许调整输出图像的尺寸和放大方法，提供在提高潜在图像分辨率方面的灵活性。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent` | `LATENT` | 要放大的图像的潜在表示，它是确定放大过程起点的关键参数。 |
+| `缩放算法` | COMBO[STRING] | 指定用于放大潜在图像的方法。不同的方法会影响放大图像的质量和特性。 |
+| `宽度` | `INT` | 期望放大图像的宽度。如果设置为0，将根据高度计算以保持纵横比。 |
+| `高度` | `INT` | 期望放大图像的高度。如果设置为0，将根据宽度计算以保持纵横比。 |
+| `裁剪` | COMBO[STRING] | 确定如何裁剪放大后的图像，影响输出的最终外观和尺寸。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 图像的放大潜在表示，准备好进行进一步处理或生成。 |
diff --git a/zh-CN/built-in-nodes/LatentUpscaleBy.mdx b/zh-CN/built-in-nodes/LatentUpscaleBy.mdx
new file mode 100644
index 000000000..c131011f0
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentUpscaleBy.mdx
@@ -0,0 +1,34 @@
+---
+title: "LatentUpscaleBy - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentUpscaleBy node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentUpscaleBy"
+icon: "circle"
+mode: wide
+---
+这一节点将使用特定算法对潜空间图像进行缩放，它允许调整放大比例和放大方法，提供在提高潜在样本分辨率方面的灵活性。
+
+### 关于upscale_method中几个方法的说明介绍
+
+| 算法名称 | 描述 |
+| --- | --- |
+| Nearest-Exact (最近邻) | 最简单的插值方法，选取离目标像素最近的已知像素点的颜色作为该点颜色。在放大时会导致锯齿和块状效果，但计算速度快。 |
+| Bilinear Interpolation（双线性插值） | 对于每个目标像素，基于其周围4个相邻像素的灰度值进行线性内插。能够提供更平滑的结果，特别是在图像缩放时改善了视觉质量，但可能仍保留轻微的块效应。 |
+| Area Interpolation（区域插值） | 基于像素面积关系重采样（抗锯齿），计算目标像素值时考虑贡献源像素的面积。减少aliasing失真，适合保留精细细节|
+| Bicubic Interpolation（双三次插值） | 双三次插值，使用三次多项式根据16个最近源像素计算像素值，提供更平滑的过渡和更好的细节保留，适用于高质量图像缩放。 |
+| Bislerp | 结合了双线性插值的简洁性和 sinc 函数插值的优点，实现了高质量的图像缩放，同时减少了失真与伪影。它在图像质量和计算成本之间取得了平衡。|
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent` | `LATENT` | 要放大的图像的潜在表示，此参数是确定将经历放大过程的输入数据的关键。 |
+| `缩放算法` | COMBO[STRING] | 指定用于放大潜在样本的方法。方法的选择可以显著影响放大输出的质量和特性。 |
+| `缩放比例` | `FLOAT` | 确定潜在样本放大的比例。此参数直接影响输出的分辨率，允许对放大过程进行精确控制。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 放大后的潜在表示，准备好进行进一步的处理或生成任务。此输出对于提高生成图像的分辨率或后续模型操作至关重要。 |
+
+---
diff --git a/zh-CN/built-in-nodes/LatentUpscaleModelLoader.mdx b/zh-CN/built-in-nodes/LatentUpscaleModelLoader.mdx
new file mode 100644
index 000000000..b90f2027c
--- /dev/null
+++ b/zh-CN/built-in-nodes/LatentUpscaleModelLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "LatentUpscaleModelLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LatentUpscaleModelLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LatentUpscaleModelLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentUpscaleModelLoader/zh.md)
+
+该节点加载专为放大潜空间表示而设计的模型。它从系统的指定文件夹中读取模型文件，并自动检测其类型（720p、1080p 或其他），以实例化并配置正确的内部模型架构。加载后的模型即可供其他节点用于潜空间超分辨率任务。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_name` | STRING | 是 | *`latent_upscale_models` 文件夹中的所有文件* | 要加载的潜空间放大模型文件名。可用选项根据 ComfyUI `latent_upscale_models` 目录中的文件动态生成。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | LATENT_UPSCALE_MODEL | 已加载并配置好、可供使用的潜空间放大模型。 |
diff --git a/zh-CN/built-in-nodes/LazyCache.mdx b/zh-CN/built-in-nodes/LazyCache.mdx
new file mode 100644
index 000000000..c39d8b370
--- /dev/null
+++ b/zh-CN/built-in-nodes/LazyCache.mdx
@@ -0,0 +1,26 @@
+---
+title: "LazyCache - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LazyCache node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LazyCache"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LazyCache/zh.md)
+
+LazyCache 是 EasyCache 的自制版本，提供了更简易的实现方式。它兼容 ComfyUI 中的任何模型，并通过添加缓存功能来减少采样过程中的计算量。虽然其性能通常不如 EasyCache，但在某些罕见情况下可能更有效，且具有通用兼容性。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要添加 LazyCache 功能的模型 |
+| `reuse_threshold` | FLOAT | 否 | 0.0 - 3.0 | 重用缓存步骤的阈值（默认值：0.2） |
+| `start_percent` | FLOAT | 否 | 0.0 - 1.0 | 开始使用 LazyCache 的相对采样步数（默认值：0.15） |
+| `end_percent` | FLOAT | 否 | 0.0 - 1.0 | 停止使用 LazyCache 的相对采样步数（默认值：0.95） |
+| `verbose` | BOOLEAN | 否 | - | 是否输出详细日志信息（默认值：False） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 已添加 LazyCache 功能的模型 |
diff --git a/zh-CN/built-in-nodes/Load3D.mdx b/zh-CN/built-in-nodes/Load3D.mdx
index d2faf6ae2..ecc32fb32 100644
--- a/zh-CN/built-in-nodes/Load3D.mdx
+++ b/zh-CN/built-in-nodes/Load3D.mdx
@@ -1,18 +1,18 @@
 ---
-title: "加载3D - ComfyUI内置节点文档"
-description: "Load3D 节点是 ComfyUI 中用于加载和预览多种 3D 模型文件的核心节点，支持多格式导入与丰富的三维视图操作。"
-sidebarTitle: "加载3D"
+title: "Load3D - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Load3D node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Load3D"
 icon: "circle"
+mode: wide
 ---
-
-Load3D 节点用于加载和处理 3D 模型文件的核心节点，在加载节点时会自动获取  ` ComfyUI/input/3d/`  可用的 3D 资源，你也可以通过上传功能将受支持的 3D 文件上传然后进行预览。
+Load3D 节点用于加载和处理 3D 模型文件的核心节点，在加载节点时会自动获取  `ComfyUI/input/3d/`  可用的 3D 资源，你也可以通过上传功能将受支持的 3D 文件上传然后进行预览。
 
 **支持格式**
 目前该节点支持多种 3D 文件格式，包括 `.gltf`、`.glb`、`.obj`、`.fbx` 和 `.stl`。
 
 **3D 节点预设**
 3D 节点的一些相关偏好设置可以在 ComfyUI 的设置菜单中进行设置，请参考下面的文档了解对应的设置
-[设置菜单 - 3D](/zh-CN/interface/settings/3d)
+[设置菜单](https://docs.comfy.org/zh-CN/interface/settings/3d)
 
 除了常规的节点输出之外， Load3D 有许多相关的 3D 视图相关操作是位于预览区域菜单, 3D 节点
 
@@ -20,7 +20,7 @@ Load3D 节点用于加载和处理 3D 模型文件的核心节点，在加载节
 
 | 参数名        | 类型        | 描述                     | 默认值 | 范围         |
 |--------------|------------|--------------------------|--------|--------------|
-| 模型文件   | 文件选择    | 3D 模型文件路径，支持上传，默认读取 ` ComfyUI/input/3d/` 下的模型文件 | -      | 受支持格式文件 |
+| 模型文件   | 文件选择    | 3D 模型文件路径，支持上传，默认读取 `ComfyUI/input/3d/` 下的模型文件 | -      | 受支持格式文件 |
 | 宽度        | INT        | 画布渲染宽度                 | 1024   | 1-4096       |
 | 高度       | INT        | 画布渲染高度                 | 1024   | 1-4096       |
 
@@ -37,19 +37,20 @@ Load3D 节点用于加载和处理 3D 模型文件的核心节点，在加载节
 | recording_video | VIDEO         | 录制视频（仅当有录制视频存在时）     |
 
 对应所有的输出预览如下：
-![视图操作演示](/images/comfy_core/load3d/load3d_outputs.jpg)
+![视图操作演示](/images/built-in-nodes/Load3D/load3d_outputs.webp)
 
 ## 模型画布(Canvas)区说明
 
 Load 3D 节点的 Canvas 区域包含了诸多的视图操作，包括：
+
 - 预览视图设置（网格、背景色、预览视图）
 - 相机控制: 控制FOV、相机类型
 - 全局光照强度: 调节光照强度
 - 视频录制: 录制视频并导出视频
-- 模型导出: 支持`GLB`、`OBJ`、`STL` 格式 
+- 模型导出: 支持`GLB`、`OBJ`、`STL` 格式
 - 等
 
-![Load 3D 节点UI](/images/comfy_core/load3d/load3d_ui.jpg)
+![Load 3D 节点UI](/images/built-in-nodes/Load3D/load3d_ui.jpg)
 
 1. 包含了 Load 3D 节点的多个菜单以及隐藏菜单
 2. 重新`缩放预览窗口大小`以及进行`画布视频录制`菜单
@@ -57,19 +58,15 @@ Load 3D 节点的 Canvas 区域包含了诸多的视图操作，包括：
 4. 预览缩略图
 5. 预览尺寸设置，通过设置尺寸然后再缩放窗口大小来缩放预览视图显示
 
-
 ### 1. 视图操作
 
-<video
-  controls
-  muted
-  loop
-  playsInline
-  className="w-full aspect-video rounded-xl"
-  src="/images/comfy_core/load3d/view_operations.mp4"
-></video>
+<video controls width="640" height="360">
+  <source src="/images/built-in-nodes/Load3D/view_operations.mp4" type="video/mp4" />
+  您的浏览器不支持视频播放。
+</video>
 
 视图控制操作：
+
 - 鼠标左键点击 + 拖拽： 视图旋转控制
 - 鼠标右键 + 拖拽： 平移视图
 - 鼠标中键： 缩放控制
@@ -77,9 +74,10 @@ Load 3D 节点的 Canvas 区域包含了诸多的视图操作，包括：
 
 ### 2. 左侧菜单功能
 
-![Menu](/images/comfy_core/load3d/menu.jpg)
+![Menu](/images/built-in-nodes/Load3D/menu.webp)
 
 在预览区域，有些视图操作相关的菜单被隐藏在了菜单里，点击菜单按钮可以展开对应不同的菜单
+
 - 1. 场景（Scene）: 包含预览窗口网格、背景色、缩略图设置
 - 2. 模型（Model）: 模型渲染模式、纹理材质、上方向设置
 - 3. 摄像机（Camera）: 轴测视图和透视视图切换、透视视角大小设置
@@ -88,53 +86,53 @@ Load 3D 节点的 Canvas 区域包含了诸多的视图操作，包括：
 
 #### 场景（Scene）
 
-![scene menu](/images/comfy_core/load3d/menu_scene.jpg)
+![scene menu](/images/built-in-nodes/Load3D/menu_scene.webp)
 
 场景菜单提供了对场景的一些基础设置功能
+
 1. 显示 / 隐藏网格
 2. 设置背景色
 3. 点击上传设置背景图片
-4. 隐藏预览图
+4. 隐藏缩略预览图
 
 #### 模型(Model)
 
-![Menu_Scene](/images/comfy_core/load3d/menu_model.jpg)
+![Menu_Scene](/images/built-in-nodes/Load3D/menu_model.webp)
 
 模型菜单提供了一些模型的相关功能
+
 1. **上方向(Up direction)**: 确定模型的哪个轴为上方向
 2. **渲染模式（Material mode）**: 模型渲染模式切换 原始（Original）、法线(Normal)、线框(Wireframe)、线稿(Lineart)
 
 #### 摄像机（Camera）
 
-![menu_modelmenu_camera](/images/comfy_core/load3d/menu_camera.jpg)
+![menu_modelmenu_camera](/images/built-in-nodes/Load3D/menu_camera.webp)
 
 该菜单提供了轴测视图和透视视图切换、透视视角大小设置
+
 1. **相机（Camera）**: 在轴测视图和正交视图之间快速切换
 2. **视场角(FOV)**: 调整 FOV 视角角度
 
 #### 灯光（Light）
 
-![menu_modelmenu_camera](/images/comfy_core/load3d/menu_light.jpg)
+![menu_modelmenu_camera](/images/built-in-nodes/Load3D/menu_light.webp)
 
 通过该菜单可以快速调节模型场景的全局光照强度
 
 #### 导出（Export）
 
-![menu_export](/images/comfy_core/load3d/menu_export.jpg)
+![menu_export](/images/built-in-nodes/Load3D/menu_export.webp)
 
 该菜单提供了一个快速转换模型格式并导出的能力
 
 ### 3. 右侧菜单功能
 
-<video
-  controls
-  muted
-  loop
-  playsInline
-  className="w-full aspect-video rounded-xl"
-  src="/images/comfy_core/load3d/recording.mp4"
-></video>
+<video controls width="640" height="360">
+  <source src="https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/view_operations.mp4" type="video/mp4" />
+  您的浏览器不支持视频播放。
+</video>
 
 右侧菜单的两个主要功能为：
+
 1. **重设视图比例**： 点击按钮后视图将根据设定好的宽高按比例调整画布渲染区域比例
 2. **视频录制**： 允许你将当前的 3D 视图操作录制为视频，允许导入，并可以作为 `recording_video` 输出给后续节点
diff --git a/zh-CN/built-in-nodes/Load3DAnimation.mdx b/zh-CN/built-in-nodes/Load3DAnimation.mdx
new file mode 100644
index 000000000..0eccc329b
--- /dev/null
+++ b/zh-CN/built-in-nodes/Load3DAnimation.mdx
@@ -0,0 +1,141 @@
+---
+title: "Load3DAnimation - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Load3DAnimation node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Load3DAnimation"
+icon: "circle"
+mode: wide
+---
+Load3DAnimation 节点用于加载和处理 3D 模型文件的核心节点，在加载节点时会自动获取  `ComfyUI/input/3d/`  可用的 3D 资源，你也可以通过上传功能将受支持的 3D 文件上传然后进行预览。
+
+> - 该节点功能大部分与 Load 3D 节点相同，但这个节点支持加载带有动画的模型加载，可以在节点中预览对应的动画
+> - 本篇文档内容与 Load3D 节点相同，因为除了动画预览播放外他们的能力都是相同的。
+
+**支持格式**
+目前该节点支持多种 3D 文件格式，包括 `.gltf`、`.glb`、`.obj`、`.fbx` 和 `.stl`。
+
+**3D 节点预设**
+3D 节点的一些相关偏好设置可以在 ComfyUI 的设置菜单中进行设置，请参考下面的文档了解对应的设置
+[设置菜单](https://docs.comfy.org/zh-CN/interface/settings/3d)
+
+除了常规的节点输出之外， Load3D 有许多相关的 3D 视图相关操作是位于预览区域菜单, 3D 节点
+
+## 输入
+
+| 参数名        | 类型        | 描述                     | 默认值 | 范围         |
+|--------------|------------|--------------------------|--------|--------------|
+| 模型文件   | 文件选择    | 3D 模型文件路径，支持上传，默认读取 `ComfyUI/input/3d/` 下的模型文件 | -      | 受支持格式文件 |
+| 宽度        | INT        | 画布渲染宽度                 | 1024   | 1-4096       |
+| 高度       | INT        | 画布渲染高度                 | 1024   | 1-4096       |
+
+## 输出
+
+| 参数名称         | 数据类型        | 说明                             |
+| --------------- | ------------- | -------------------------------- |
+| image           | IMAGE         | 画布渲染渲染图像                    |
+| mask            | MASK          | 包含当前模型位置的遮罩               |
+| mesh_path       | STRING        | 模型文件路径在`ComfyUI/input` 文件夹下的路径               |
+| normal          | IMAGE         | 法线贴图                          |
+| lineart         | IMAGE         | 线稿图像输出，对应的 `edge_threshold` 可在画布的模型菜单中进行调节                      |
+| camera_info     | LOAD3D_CAMERA | 相机信息                         |
+| recording_video | VIDEO         | 录制视频（仅当有录制视频存在时）     |
+
+对应所有的输出预览如下：
+![视图操作演示](/images/built-in-nodes/Load3DAnimation/load3d_outputs.webp)
+
+## 模型画布(Canvas)区说明
+
+Load 3D 节点的 Canvas 区域包含了诸多的视图操作，包括：
+
+- 预览视图设置（网格、背景色、预览视图）
+- 相机控制: 控制FOV、相机类型
+- 全局光照强度: 调节光照强度
+- 视频录制: 录制视频并导出视频
+- 模型导出: 支持`GLB`、`OBJ`、`STL` 格式
+- 等
+
+![Load 3D 节点UI](/images/built-in-nodes/Load3DAnimation/load3d_ui.jpg)
+
+1. 包含了 Load 3D 节点的多个菜单以及隐藏菜单
+2. 重新`缩放预览窗口大小`以及进行`画布视频录制`菜单
+3. 3D 视图操作轴
+4. 预览缩略图
+5. 预览尺寸设置，通过设置尺寸然后再缩放窗口大小来缩放预览视图显示
+
+### 1. 视图操作
+
+<video controls width="640" height="360">
+  <source src="https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/view_operations.mp4" type="video/mp4" />
+  您的浏览器不支持视频播放。
+</video>
+
+视图控制操作：
+
+- 鼠标左键点击 + 拖拽： 视图旋转控制
+- 鼠标右键 + 拖拽： 平移视图
+- 鼠标中键： 缩放控制
+- 坐标轴： 切换视图
+
+### 2. 左侧菜单功能
+
+![Menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu.webp)
+
+在预览区域，有些视图操作相关的菜单被隐藏在了菜单里，点击菜单按钮可以展开对应不同的菜单
+
+- 1. 场景（Scene）: 包含预览窗口网格、背景色、缩略图设置
+- 2. 模型（Model）: 模型渲染模式、纹理材质、上方向设置
+- 3. 摄像机（Camera）: 轴测视图和透视视图切换、透视视角大小设置
+- 4. 灯光（Light）: 场景全局光照强度
+- 5. 导出（Export）: 导出模型为其它格式（GLB、OBJ、STL）
+
+#### 场景（Scene）
+
+![scene menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_scene.webp)
+
+场景菜单提供了对场景的一些基础设置功能
+
+1. 显示 / 隐藏网格
+2. 设置背景色
+3. 点击上传设置背景图片
+4. 隐藏缩略预览图
+
+#### 模型(Model)
+
+![Menu_Scene](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_model.webp)
+
+模型菜单提供了一些模型的相关功能
+
+1. **上方向(Up direction)**: 确定模型的哪个轴为上方向
+2. **渲染模式（Material mode）**: 模型渲染模式切换 原始（Original）、法线(Normal)、线框(Wireframe)、线稿(Lineart)
+
+#### 摄像机（Camera）
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_camera.webp)
+
+该菜单提供了轴测视图和透视视图切换、透视视角大小设置
+
+1. **相机（Camera）**: 在轴测视图和正交视图之间快速切换
+2. **视场角(FOV)**: 调整 FOV 视角角度
+
+#### 灯光（Light）
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_light.webp)
+
+通过该菜单可以快速调节模型场景的全局光照强度
+
+#### 导出（Export）
+
+![menu_export](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_export.webp)
+
+该菜单提供了一个快速转换模型格式并导出的能力
+
+### 3. 右侧菜单功能
+
+<video controls width="640" height="360">
+  <source src="/images/built-in-nodes/Load3DAnimation/recording.mp4" type="video/mp4" />
+  您的浏览器不支持视频播放。
+</video>
+
+右侧菜单的两个主要功能为：
+
+1. **重设视图比例**： 点击按钮后视图将根据设定好的宽高按比例调整画布渲染区域比例
+2. **视频录制**： 允许你将当前的 3D 视图操作录制为视频，允许导入，并可以作为 `recording_video` 输出给后续节点
diff --git a/zh-CN/built-in-nodes/LoadAudio.mdx b/zh-CN/built-in-nodes/LoadAudio.mdx
new file mode 100644
index 000000000..ced6347d1
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadAudio.mdx
@@ -0,0 +1,26 @@
+---
+title: "LoadAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadAudio/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadAudio/en.md)
+
+LoadAudio 节点从输入目录加载音频文件，并将其转换为可供 ComfyUI 中其他音频节点处理的格式。该节点读取音频文件并提取波形数据和采样率，使其可用于下游音频处理任务。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `音频` | AUDIO | 是 | 输入目录中所有支持的音频/视频文件 | 要从输入目录加载的音频文件 |
+
+**注意：** 该节点仅接受 ComfyUI 输入目录中存在的音频和视频文件。文件必须存在且可访问才能成功加载。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `AUDIO` | AUDIO | 包含波形和采样率信息的音频数据 |
diff --git a/zh-CN/built-in-nodes/LoadImage.mdx b/zh-CN/built-in-nodes/LoadImage.mdx
new file mode 100644
index 000000000..76168e647
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadImage.mdx
@@ -0,0 +1,26 @@
+---
+title: "LoadImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImage"
+icon: "circle"
+mode: wide
+---
+
+在节点上右键,在菜单中选择**Open in MaskEditor-在遮罩编辑器中打开**，可以打开已载入图像的遮罩编辑器
+
+>上传后的图像会默认上传至*ComfyUI/input*文件夹，默认加载图像为 **input**文件夹内图像
+
+加载图像节点旨在从指定路径加载和预处理图像。它处理具有多帧的图像格式，应用必要的变换，如根据EXIF数据旋转，归一化像素值，并可选择为具有alpha通道的图像生成遮罩。此节点对于准备图像以在管道内进行进一步处理或分析至关重要。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `图像`  | COMBO[STRING] | `图像` 参数指定要加载和处理的图像的标识符。它对于确定图像文件的路径，随后加载图像以进行转换和归一化至关重要。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `图像`  | `IMAGE`  | 已处理的图像，像素值已归一化，并根据需要应用了变换。它准备好进行进一步的处理或分析。 |
+| `mask`   | `MASK`   | （可选）为图像提供的遮罩输出，在图像包含用于透明度的alpha通道的场景中非常有用。 |
diff --git a/zh-CN/built-in-nodes/LoadImageDataSetFromFolder.mdx b/zh-CN/built-in-nodes/LoadImageDataSetFromFolder.mdx
new file mode 100644
index 000000000..34067380b
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadImageDataSetFromFolder.mdx
@@ -0,0 +1,22 @@
+---
+title: "LoadImageDataSetFromFolder - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageDataSetFromFolder node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageDataSetFromFolder"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageDataSetFromFolder/zh.md)
+
+此节点从 ComfyUI 输入目录内的指定子文件夹加载多张图像。它会扫描所选文件夹以查找常见的图像文件类型，并将其作为列表返回，这对于批处理或数据集准备非常有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `folder` | STRING | 是 | *提供多个选项* | 要从中加载图像的文件夹。选项是 ComfyUI 主输入目录中存在的子文件夹。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `images` | IMAGE | 已加载图像的列表。该节点会加载在所选文件夹中找到的所有有效图像文件（PNG、JPG、JPEG、WEBP）。 |
diff --git a/zh-CN/built-in-nodes/LoadImageMask.mdx b/zh-CN/built-in-nodes/LoadImageMask.mdx
new file mode 100644
index 000000000..62fb09ae5
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadImageMask.mdx
@@ -0,0 +1,21 @@
+---
+title: "LoadImageMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageMask"
+icon: "circle"
+mode: wide
+---
+LoadImageMask 节点旨在从指定路径加载图像及其相关遮罩，处理它们以确保与进一步的图像操作或分析任务兼容。它专注于处理各种图像格式和条件，例如遮罩的 alpha 通道的存在，并通过对它们进行标准化格式转换，为下游处理准备图像和遮罩。
+
+## 输入
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| `图像`    | COMBO[STRING] | 'image' 参数指定要加载和处理的图像文件。它通过提供源图像用于遮罩提取和格式转换，在确定输出方面起着关键作用。 |
+| `通道`  | COMBO[STRING] | 'channel' 参数指定用于生成遮罩的图像颜色通道。这允许根据不同的颜色通道灵活创建遮罩，增强节点在各种图像处理场景中的实用性。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `mask`   | `MASK`   | 此节点输出从指定图像和通道生成的遮罩，以标准化格式准备，适用于图像操作任务中的进一步处理。 |
diff --git a/zh-CN/built-in-nodes/LoadImageOutput.mdx b/zh-CN/built-in-nodes/LoadImageOutput.mdx
new file mode 100644
index 000000000..c1646b3bf
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadImageOutput.mdx
@@ -0,0 +1,25 @@
+---
+title: "LoadImageOutput - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageOutput node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageOutput"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageOutput/zh.md)
+
+## 概述
+
+LoadImageOutput 节点从输出文件夹加载图像。当您点击刷新按钮时，它会更新可用图像列表并自动选择第一个图像，便于您浏览生成的图像。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | COMBO | 是 | 提供多个选项 | 从输出文件夹加载图像。包含上传选项和刷新按钮，用于更新图像列表。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `图像` | IMAGE | 从输出文件夹加载的图像 |
+| `mask` | MASK | 与加载图像关联的蒙版 |
diff --git a/zh-CN/built-in-nodes/LoadImageSetFromFolderNode.mdx b/zh-CN/built-in-nodes/LoadImageSetFromFolderNode.mdx
new file mode 100644
index 000000000..6b08bc6eb
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadImageSetFromFolderNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "LoadImageSetFromFolderNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageSetFromFolderNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageSetFromFolderNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageSetFromFolderNode/zh.md)
+
+## 概述
+
+LoadImageSetFromFolderNode 从指定文件夹目录加载多张图像用于训练目的。它能自动检测常见图像格式，并可选择在使用不同方法调整图像尺寸后，将图像作为批次返回。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `folder` | STRING | 是 | 多种选项可用 | 要从中加载图像的文件夹。 |
+| `resize_method` | STRING | 否 | "None"<br />"Stretch"<br />"Crop"<br />"Pad" | 用于调整图像尺寸的方法（默认值："None"）。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 作为单个张量加载的图像批次。 |
diff --git a/zh-CN/built-in-nodes/LoadImageSetNode.mdx b/zh-CN/built-in-nodes/LoadImageSetNode.mdx
new file mode 100644
index 000000000..777f4ef95
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadImageSetNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "LoadImageSetNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageSetNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageSetNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageSetNode/zh.md)
+
+## 概述
+
+LoadImageSetNode 从输入目录加载多张图像，用于批处理和训练目的。它支持多种图像格式，并可选使用不同方法调整图像尺寸。该节点将所有选中的图像作为批次处理，并以单个张量形式返回。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | 多个图像文件 | 从输入目录选择多张图像。支持 PNG、JPG、JPEG、WEBP、BMP、GIF、JPE、APNG、TIF 和 TIFF 格式。允许批量选择图像。 |
+| `resize_method` | STRING | 否 | "None"<br />"Stretch"<br />"Crop"<br />"Pad" | 调整加载图像尺寸的可选方法（默认："None"）。选择 "None" 保持原始尺寸，"Stretch" 强制调整尺寸，"Crop" 通过裁剪保持宽高比，或 "Pad" 通过添加填充保持宽高比。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 包含所有加载图像作为批次的张量，用于进一步处理。 |
diff --git a/zh-CN/built-in-nodes/LoadImageTextDataSetFromFolder.mdx b/zh-CN/built-in-nodes/LoadImageTextDataSetFromFolder.mdx
new file mode 100644
index 000000000..19fecea93
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadImageTextDataSetFromFolder.mdx
@@ -0,0 +1,25 @@
+---
+title: "LoadImageTextDataSetFromFolder - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageTextDataSetFromFolder node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageTextDataSetFromFolder"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextDataSetFromFolder/zh.md)
+
+此节点从指定文件夹加载图像及其对应文本描述的数据集。它会搜索图像文件，并自动查找具有相同基础名称的匹配 `.txt` 文件作为描述。该节点还支持特定的文件夹结构，其中子文件夹可以用数字前缀命名（例如 `10_folder_name`），以指示其中的图像应在输出中重复多次。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `folder` | COMBO | 是 | *动态从 `folder_paths.get_input_subfolders()` 加载* | 要从中加载图像的文件夹。可用选项是 ComfyUI 输入目录内的子目录。 |
+
+**注意：** 此节点期望特定的文件结构。对于每个图像文件（`.png`、`.jpg`、`.jpeg`、`.webp`），它将查找具有相同名称的 `.txt` 文件作为描述。如果未找到描述文件，则使用空字符串。该节点还支持一种特殊结构，即子文件夹的名称以数字和下划线开头（例如 `5_cats`），这将导致该子文件夹内的所有图像在最终输出列表中重复该次数。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `images` | IMAGE | 已加载的图像张量列表。 |
+| `texts` | STRING | 与每个已加载图像对应的文本描述列表。 |
diff --git a/zh-CN/built-in-nodes/LoadImageTextSetFromFolderNode.mdx b/zh-CN/built-in-nodes/LoadImageTextSetFromFolderNode.mdx
new file mode 100644
index 000000000..bdaa14782
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadImageTextSetFromFolderNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "LoadImageTextSetFromFolderNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadImageTextSetFromFolderNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadImageTextSetFromFolderNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextSetFromFolderNode/zh.md)
+
+从指定目录加载一批图像及其对应的文本描述，用于训练目的。该节点会自动搜索图像文件及其关联的文本描述文件，根据指定的调整尺寸设置处理图像，并使用提供的 CLIP 模型对描述文本进行编码。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `folder` | STRING | 是 | - | 要从中加载图像的文件夹路径。 |
+| `clip` | CLIP | 是 | - | 用于编码文本的 CLIP 模型。 |
+| `resize_method` | COMBO | 否 | "None"<br />"Stretch"<br />"Crop"<br />"Pad" | 用于调整图像尺寸的方法（默认："None"）。 |
+| `width` | INT | 否 | -1 到 10000 | 调整图像后的宽度。-1 表示使用原始宽度（默认：-1）。 |
+| `height` | INT | 否 | -1 到 10000 | 调整图像后的高度。-1 表示使用原始高度（默认：-1）。 |
+
+**注意：** CLIP 输入必须有效且不能为 None。如果 CLIP 模型来自检查点加载器节点，请确保检查点包含有效的 CLIP 或文本编码器模型。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 加载并处理后的图像批次。 |
+| `CONDITIONING` | CONDITIONING | 从文本描述编码得到的条件数据。 |
diff --git a/zh-CN/built-in-nodes/LoadLatent.mdx b/zh-CN/built-in-nodes/LoadLatent.mdx
new file mode 100644
index 000000000..a18ed3e80
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadLatent.mdx
@@ -0,0 +1,22 @@
+---
+title: "LoadLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadLatent/zh.md)
+
+LoadLatent 节点从输入目录中的 .latent 文件加载先前保存的潜在表示。该节点会从文件中读取潜在张量数据，并在返回潜在数据供其他节点使用之前应用必要的缩放调整。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Latent` | STRING | 是 | 输入目录中的所有 .latent 文件 | 从输入目录中的可用文件中选择要加载的 .latent 文件 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 返回从选定文件加载的潜在表示数据 |
diff --git a/zh-CN/built-in-nodes/LoadTrainingDataset.mdx b/zh-CN/built-in-nodes/LoadTrainingDataset.mdx
new file mode 100644
index 000000000..b993ff729
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadTrainingDataset.mdx
@@ -0,0 +1,23 @@
+---
+title: "LoadTrainingDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadTrainingDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadTrainingDataset"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadTrainingDataset/zh.md)
+
+此节点加载先前已保存到磁盘的编码训练数据集。它会在 ComfyUI 输出目录的指定文件夹中搜索并读取所有数据分片文件，然后返回合并的潜在向量和条件数据，以供训练工作流使用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `folder_name` | STRING | 否 | N/A | 包含已保存数据集的文件夹名称，位于 ComfyUI 输出目录内（默认值："training_dataset"）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `latents` | LATENT | 一个潜在字典列表，其中每个字典包含一个带有张量的 `"samples"` 键。 |
+| `conditioning` | CONDITIONING | 一个条件列表的列表，其中每个内部列表包含对应样本的条件数据。 |
diff --git a/zh-CN/built-in-nodes/LoadVideo.mdx b/zh-CN/built-in-nodes/LoadVideo.mdx
new file mode 100644
index 000000000..53676a747
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoadVideo.mdx
@@ -0,0 +1,26 @@
+---
+title: "LoadVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoadVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoadVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadVideo/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadVideo/en.md)
+
+Load Video 节点从输入目录加载视频文件，使其可在工作流中进行处理。它从指定的输入文件夹读取视频文件，并将其输出为可连接到其他视频处理节点的视频数据。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `文件` | STRING | 是 | 提供多个选项 | 要从输入目录加载的视频文件 |
+
+**注意：** `file` 参数的可用选项会根据输入目录中存在的视频文件动态生成。仅显示支持内容类型的视频文件。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `video` | VIDEO | 已加载的视频数据，可传递给其他视频处理节点 |
diff --git a/zh-CN/built-in-nodes/LoraLoader.mdx b/zh-CN/built-in-nodes/LoraLoader.mdx
new file mode 100644
index 000000000..c9b84fbf7
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoraLoader.mdx
@@ -0,0 +1,34 @@
+---
+title: "LoraLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraLoader"
+icon: "circle"
+mode: wide
+---
+这个节点会自动检测位于 LoRA 文件夹下的模型(包括子文件夹)对应模型路径为 `ComfyUI\models\loras`
+
+LoRA加载器节点主要用于加载LoRA模型，你可以简单把 LoRA 模型理解为滤镜，它可以让你的图片具有特定的风格、内容、细节等。
+
+- 使画面具有特定的画风（如水墨画）
+- 使人物具有某类人物的特征（如某些游戏角色）
+- 使画面具有特定的细节
+以上这些都可以通过LoRA来实现。
+
+如果需要加载 多个LoRA 模型，你可以直接将多个节点进行一个串联, 如下图所示
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型` | MODEL | 通常用于连接基础模型 |
+| `CLIPCLIP` | CLIP | 通常用于连接CLIP模型 |
+| `LoRA名称` | COMBO[STRING] | 选择要使用的LoRA模型名称 |
+| `模型强度` | FLOAT |  取值范围 -100.0 到 100.0 ,日常使用用于图片生成时我们通常使用0~1之间, 取值越大, 应用的这个模型调整的效果越明显 |
+| `CLIP强度` | FLOAT | 取值范围 -100.0 到 100.0 ,日常使用用于图片生成时我们通常使用0~1之间, 取值越大, 应用的这个模型调整的效果越明显 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型` | MODEL | 应用了LoRA调整的模型 |
+| `CLIPCLIP` | CLIP | 应用了LoRA调整的CLIP实例 |
diff --git a/zh-CN/built-in-nodes/LoraLoaderBypass.mdx b/zh-CN/built-in-nodes/LoraLoaderBypass.mdx
new file mode 100644
index 000000000..7c92d4a11
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoraLoaderBypass.mdx
@@ -0,0 +1,29 @@
+---
+title: "LoraLoaderBypass - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraLoaderBypass node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraLoaderBypass"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraLoaderBypass/zh.md)
+
+LoraLoaderBypass 节点以一种特殊的“旁路”模式将 LoRA（低秩适应）应用于扩散模型和 CLIP 模型。与标准的 LoRA 加载器不同，此方法不会永久修改基础模型的权重。相反，它通过将 LoRA 的效果添加到模型的正常前向传递中来计算输出，这在训练或处理权重已卸载的模型时非常有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 将应用 LoRA 的扩散模型。 |
+| `clip` | CLIP | 是 | - | 将应用 LoRA 的 CLIP 模型。 |
+| `lora_name` | COMBO | 是 | *可用 LoRA 文件列表* | 要应用的 LoRA 文件的名称。选项从 `loras` 文件夹加载。 |
+| `strength_model` | FLOAT | 是 | -100.0 到 100.0 | 修改扩散模型的强度。此值可以为负数（默认值：1.0）。 |
+| `strength_clip` | FLOAT | 是 | -100.0 到 100.0 | 修改 CLIP 模型的强度。此值可以为负数（默认值：1.0）。 |
+
+**注意：** 如果 `strength_model` 和 `strength_clip` 都设置为 0，节点将返回未经处理的原始 `model` 和 `clip` 输入。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | 以旁路模式应用了 LoRA 的扩散模型。 |
+| `CLIP` | CLIP | 以旁路模式应用了 LoRA 的 CLIP 模型。 |
diff --git a/zh-CN/built-in-nodes/LoraLoaderBypassModelOnly.mdx b/zh-CN/built-in-nodes/LoraLoaderBypassModelOnly.mdx
new file mode 100644
index 000000000..f86135d57
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoraLoaderBypassModelOnly.mdx
@@ -0,0 +1,24 @@
+---
+title: "LoraLoaderBypassModelOnly - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraLoaderBypassModelOnly node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraLoaderBypassModelOnly"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraLoaderBypassModelOnly/zh.md)
+
+此节点将 LoRA（低秩适应）应用于模型以修改其行为，但仅影响模型组件本身。它会加载指定的 LoRA 文件，并按给定的强度调整模型的权重，同时保持 CLIP 文本编码器等其他组件不变。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 将应用 LoRA 调整的基础模型。 |
+| `lora_name` | STRING | 是 | （可用 LoRA 文件列表） | 要加载并应用的 LoRA 文件名。选项从 `loras` 目录中的文件填充。 |
+| `strength_model` | FLOAT | 是 | -100.0 到 100.0 | LoRA 对模型权重的影响强度。正值应用 LoRA，负值应用其逆效果，值为 0 则无效果（默认值：1.0）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 已将 LoRA 调整应用于其权重的修改后模型。 |
diff --git a/zh-CN/built-in-nodes/LoraLoaderModelOnly.mdx b/zh-CN/built-in-nodes/LoraLoaderModelOnly.mdx
new file mode 100644
index 000000000..f1ea8a298
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoraLoaderModelOnly.mdx
@@ -0,0 +1,26 @@
+---
+title: "LoraLoaderModelOnly - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraLoaderModelOnly node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraLoaderModelOnly"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/loras` 文件夹下的模型，
+同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，
+有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+此节点专门用于加载LoRA模型，而无需CLIP模型，专注于根据LoRA参数增强或修改给定模型。它允许通过LoRA参数动态调整模型的强度，从而对模型的行为进行微调控制。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型` | MODEL | 应用LoRA调整的模型。它作为修改的基础。 |
+| `LoRA名称` | COMBO[STRING] | 要加载的LoRA文件的名称。这指定了要应用于模型的LoRA调整。 |
+| `模型强度` | FLOAT | 确定应用于模型的 LoRA 的强度。较高的值表示更显著的修改。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型` | MODEL | 应用了LoRA调整的修改后的模型，反映了模型行为或能力的变化。 |
diff --git a/zh-CN/built-in-nodes/LoraModelLoader.mdx b/zh-CN/built-in-nodes/LoraModelLoader.mdx
new file mode 100644
index 000000000..18999d455
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoraModelLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "LoraModelLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraModelLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraModelLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraModelLoader/zh.md)
+
+LoraModelLoader 节点将训练好的 LoRA（低秩自适应）权重应用于扩散模型。它通过从训练好的 LoRA 模型加载权重并调整其影响强度来修改基础模型。这使您能够定制扩散模型的行为，而无需从头开始重新训练。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要应用 LoRA 的扩散模型。 |
+| `lora` | LORA_MODEL | 是 | - | 要应用于扩散模型的 LoRA 模型。 |
+| `strength_model` | FLOAT | 是 | -100.0 到 100.0 | 修改扩散模型的强度。该值可以为负数（默认值：1.0）。 |
+
+**注意：** 当 `strength_model` 设置为 0 时，节点将返回原始模型，不应用任何 LoRA 修改。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 应用了 LoRA 权重后的修改版扩散模型。 |
diff --git a/zh-CN/built-in-nodes/LoraSave.mdx b/zh-CN/built-in-nodes/LoraSave.mdx
new file mode 100644
index 000000000..72337f62e
--- /dev/null
+++ b/zh-CN/built-in-nodes/LoraSave.mdx
@@ -0,0 +1,29 @@
+---
+title: "LoraSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LoraSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LoraSave"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraSave/zh.md)
+
+LoraSave 节点从模型差异中提取并保存 LoRA（低秩自适应）文件。它可以处理扩散模型差异、文本编码器差异或两者，将它们转换为具有指定秩和类型的 LoRA 格式。生成的 LoRA 文件将保存到输出目录中，供后续使用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `文件名前缀` | STRING | 是 | - | 输出文件名的前缀（默认："loras/ComfyUI_extracted_lora"） |
+| `排名` | INT | 是 | 1-4096 | LoRA 的秩值，控制大小和复杂度（默认：8） |
+| `lora类型` | COMBO | 是 | 多个可用选项 | 要创建的 LoRA 类型，提供多种可用选项 |
+| `偏差差异` | BOOLEAN | 是 | - | 是否在 LoRA 计算中包含偏置差异（默认：True） |
+| `模型差异` | MODEL | 否 | - | 要转换为 lora 的 ModelSubtract 输出 |
+| `文本编码器差异` | CLIP | 否 | - | 要转换为 lora 的 CLIPSubtract 输出 |
+
+**注意：** 要使节点正常工作，必须至少提供 `model_diff` 或 `text_encoder_diff` 中的一个参数。如果两者都未提供，节点将不会产生任何输出。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| - | - | 此节点将 LoRA 文件保存到输出目录，但不会通过工作流返回任何数据 |
diff --git a/zh-CN/built-in-nodes/LossGraphNode.mdx b/zh-CN/built-in-nodes/LossGraphNode.mdx
new file mode 100644
index 000000000..2e3ad963a
--- /dev/null
+++ b/zh-CN/built-in-nodes/LossGraphNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "LossGraphNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LossGraphNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LossGraphNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LossGraphNode/zh.md)
+
+LossGraphNode 可创建训练损失值随时间变化的可视化图表，并将其保存为图像文件。该节点从训练过程中获取损失数据，并生成显示损失在训练步骤中变化情况的折线图。生成的图表包含坐标轴标签、最小/最大损失值，并会自动保存到临时输出目录并附带时间戳。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `loss` | LOSS | 是 | 支持多种选项 | 包含要绘制的损失值的损失数据（默认值：空字典） |
+| `filename_prefix` | STRING | 是 | - | 输出图像文件名的前缀（默认值："loss_graph"） |
+
+**注意：** `loss` 参数需要包含带有损失值的 "loss" 键的有效损失字典。该节点会自动缩放损失值以适应图表尺寸，并生成显示训练步骤中损失变化情况的折线图。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `ui.images` | IMAGE | 已保存到临时目录的生成损失图表图像 |
diff --git a/zh-CN/built-in-nodes/LotusConditioning.mdx b/zh-CN/built-in-nodes/LotusConditioning.mdx
new file mode 100644
index 000000000..169154156
--- /dev/null
+++ b/zh-CN/built-in-nodes/LotusConditioning.mdx
@@ -0,0 +1,24 @@
+---
+title: "LotusConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LotusConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LotusConditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LotusConditioning/zh.md)
+
+## 概述
+
+LotusConditioning 节点为 Lotus 模型提供预计算的条件嵌入。它使用带有空条件的冻结编码器，并返回硬编码的提示嵌入，以实现与参考实现的等效性，无需进行推理或加载大型张量文件。该节点输出一个固定的条件张量，可直接用于生成流程。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| *无输入* | - | - | - | 此节点不接受任何输入参数。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | 为 Lotus 模型预计算的条件嵌入，包含固定的提示嵌入和一个空字典。 |
diff --git a/zh-CN/built-in-nodes/LtxvApiImageToVideo.mdx b/zh-CN/built-in-nodes/LtxvApiImageToVideo.mdx
new file mode 100644
index 000000000..1711ff2a6
--- /dev/null
+++ b/zh-CN/built-in-nodes/LtxvApiImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "LtxvApiImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LtxvApiImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LtxvApiImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LtxvApiImageToVideo/zh.md)
+
+LTXV 图像转视频节点能够从单张起始图像生成专业质量的视频。它通过外部 API 根据您的文本提示创建视频序列，允许您自定义时长、分辨率和帧率。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 用于生成视频的首帧图像。 |
+| `model` | COMBO | 是 | `"LTX-2 (Fast)"`<br />`"LTX-2 (Quality)"` | 用于视频生成的 AI 模型。"Fast" 模型针对速度进行了优化，而 "Quality" 模型则优先考虑视觉保真度。 |
+| `prompt` | STRING | 是 | - | 用于引导生成视频内容和运动的文本描述。 |
+| `duration` | COMBO | 是 | `6`<br />`8`<br />`10`<br />`12`<br />`14`<br />`16`<br />`18`<br />`20` | 视频的时长（单位：秒，默认值：8）。 |
+| `resolution` | COMBO | 是 | `"1920x1080"`<br />`"2560x1440"`<br />`"3840x2160"` | 生成视频的输出分辨率。 |
+| `fps` | COMBO | 是 | `25`<br />`50` | 视频的帧率（单位：帧/秒，默认值：25）。 |
+| `generate_audio` | BOOLEAN | 否 | - | 为 True 时，生成的视频将包含与场景匹配的 AI 生成音频（默认值：False）。 |
+
+**重要限制：**
+
+* `image` 输入必须恰好包含一张图像。
+* `prompt` 的长度必须在 1 到 10,000 个字符之间。
+* 如果您选择的 `duration` 超过 10 秒，则必须使用 **"LTX-2 (Fast)"** 模型、**"1920x1080"** 分辨率和 **25** FPS。此组合是生成长视频的必要条件。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/LtxvApiTextToVideo.mdx b/zh-CN/built-in-nodes/LtxvApiTextToVideo.mdx
new file mode 100644
index 000000000..9d3c564a1
--- /dev/null
+++ b/zh-CN/built-in-nodes/LtxvApiTextToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "LtxvApiTextToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LtxvApiTextToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LtxvApiTextToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LtxvApiTextToVideo/zh.md)
+
+## 概述
+
+LTXV Text To Video 节点能够根据文本描述生成专业质量的视频。它通过连接外部 API 来创建可自定义时长、分辨率和帧率的视频。您还可以选择为视频添加 AI 生成的音频。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"LTX-2 (Fast)"`<br />`"LTX-2 (Quality)"`<br />`"LTX-2 (Turbo)"` | 用于视频生成的 AI 模型。可用模型映射自源代码中的 `MODELS_MAP`。 |
+| `prompt` | STRING | 是 | - | AI 将用于生成视频的文本描述。此字段支持多行文本。 |
+| `duration` | COMBO | 是 | `6`<br />`8`<br />`10`<br />`12`<br />`14`<br />`16`<br />`18`<br />`20` | 生成视频的时长，单位为秒（默认：8）。 |
+| `resolution` | COMBO | 是 | `"1920x1080"`<br />`"2560x1440"`<br />`"3840x2160"` | 输出视频的像素尺寸（宽 x 高）。 |
+| `fps` | COMBO | 是 | `25`<br />`50` | 视频的帧率，单位为每秒帧数（默认：25）。 |
+| `generate_audio` | BOOLEAN | 否 | - | 启用后，生成的视频将包含与场景匹配的 AI 生成音频（默认：False）。 |
+
+**重要限制：**
+
+* `prompt` 的长度必须在 1 到 10,000 个字符之间。
+* 如果您选择的 `duration` 大于 10 秒，则必须同时使用 `"LTX-2 (Fast)"` 模型、`"1920x1080"` 分辨率和 `25` 的 `fps`。此组合是生成长视频的必要条件。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/LumaConceptsNode.mdx b/zh-CN/built-in-nodes/LumaConceptsNode.mdx
new file mode 100644
index 000000000..573d26548
--- /dev/null
+++ b/zh-CN/built-in-nodes/LumaConceptsNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "LumaConceptsNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaConceptsNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaConceptsNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaConceptsNode/zh.md)
+
+## 概述
+
+持有一个或多个相机概念，用于 Luma 文生视频和 Luma 图生视频节点。此节点允许您选择最多四个相机概念，并可选择将它们与现有概念链组合使用。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `concept1` | STRING | 是 | 提供多个选项<br />包含"None"选项 | 从可用的 Luma 概念中选择第一个相机概念 |
+| `concept2` | STRING | 是 | 提供多个选项<br />包含"None"选项 | 从可用的 Luma 概念中选择第二个相机概念 |
+| `concept3` | STRING | 是 | 提供多个选项<br />包含"None"选项 | 从可用的 Luma 概念中选择第三个相机概念 |
+| `concept4` | STRING | 是 | 提供多个选项<br />包含"None"选项 | 从可用的 Luma 概念中选择第四个相机概念 |
+| `luma_concepts` | LUMA_CONCEPTS | 否 | 不适用 | 可选的相机概念，用于添加到此处选择的概念中 |
+
+**注意：** 如果您不想使用全部四个概念插槽，所有概念参数（`concept1` 到 `concept4`）都可以设置为"None"。该节点会将任何提供的 `luma_concepts` 与选定的概念合并，以创建组合的概念链。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `luma_concepts` | LUMA_CONCEPTS | 包含所有选定概念的组合相机概念链 |
diff --git a/zh-CN/built-in-nodes/LumaImageModifyNode.mdx b/zh-CN/built-in-nodes/LumaImageModifyNode.mdx
new file mode 100644
index 000000000..3f84d3c29
--- /dev/null
+++ b/zh-CN/built-in-nodes/LumaImageModifyNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "LumaImageModifyNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaImageModifyNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaImageModifyNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageModifyNode/zh.md)
+
+基于提示词和宽高比同步修改图像。此节点接收输入图像，并根据提供的文本提示词进行转换，同时保持原始图像的宽高比。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待修改的输入图像 |
+| `prompt` | STRING | 是 | - | 图像生成的提示词（默认：""） |
+| `image_weight` | FLOAT | 否 | 0.0-0.98 | 图像权重；越接近1.0，图像修改程度越小（默认：0.1） |
+| `model` | MODEL | 是 | 提供多个选项 | 用于图像修改的Luma模型 |
+| `seed` | INT | 否 | 0-18446744073709551615 | 决定节点是否重新运行的种子；无论种子如何，实际结果都是非确定性的（默认：0） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 由Luma模型生成的修改后图像 |
diff --git a/zh-CN/built-in-nodes/LumaImageNode.mdx b/zh-CN/built-in-nodes/LumaImageNode.mdx
new file mode 100644
index 000000000..6815d7f28
--- /dev/null
+++ b/zh-CN/built-in-nodes/LumaImageNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "LumaImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageNode/zh.md)
+
+基于提示词和宽高比同步生成图像。此节点使用文本描述创建图像，并允许通过各种参考输入来控制图像尺寸和风格。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `提示词` | STRING | 是 | - | 图像生成的提示词（默认：空字符串） |
+| `模型` | COMBO | 是 | 多个可用选项 | 用于图像生成的模型选择 |
+| `宽高比` | COMBO | 是 | 多个可用选项 | 生成图像的宽高比（默认：16:9比例） |
+| `种子` | INT | 是 | 0 到 18446744073709551615 | 确定节点是否应重新运行的种子；无论种子如何，实际结果都是非确定性的（默认：0） |
+| `风格图权重` | FLOAT | 否 | 0.0 到 1.0 | 风格图像的权重。如果未提供style_image则忽略（默认：1.0） |
+| `Luma 参考图` | LUMA_REF | 否 | - | Luma参考节点连接，通过输入图像影响生成；最多可考虑4张图像 |
+| `风格参考图` | IMAGE | 否 | - | 风格参考图像；仅使用1张图像 |
+| `角色参考图` | IMAGE | 否 | - | 角色参考图像；可以是多张图像的批次，最多可考虑4张图像 |
+
+**参数约束：**
+
+- `image_luma_ref` 参数最多可接受4张参考图像
+- `character_image` 参数最多可接受4张角色参考图像
+- `style_image` 参数仅接受1张风格参考图像
+- `style_image_weight` 参数仅在提供 `style_image` 时使用
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 基于输入参数生成的图像 |
diff --git a/zh-CN/built-in-nodes/LumaImageToVideoNode.mdx b/zh-CN/built-in-nodes/LumaImageToVideoNode.mdx
new file mode 100644
index 000000000..df54c4922
--- /dev/null
+++ b/zh-CN/built-in-nodes/LumaImageToVideoNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "LumaImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageToVideoNode/zh.md)
+
+基于提示词、输入图像和输出尺寸同步生成视频。此节点通过提供文本提示词和可选的起始/结束图像来定义视频内容和结构，使用 Luma API 创建视频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `提示词` | STRING | 是 | - | 视频生成的提示词（默认：""） |
+| `模型` | COMBO | 是 | 多个可用选项 | 从可用的 Luma 模型中选择视频生成模型 |
+| `分辨率` | COMBO | 是 | 多个可用选项 | 生成视频的输出分辨率（默认：540p） |
+| `时长` | COMBO | 是 | 多个可用选项 | 生成视频的时长 |
+| `循环` | BOOLEAN | 是 | - | 生成的视频是否应循环播放（默认：False） |
+| `种子` | INT | 是 | 0 到 18446744073709551615 | 用于确定节点是否应重新运行的种子值；无论种子值如何，实际结果都是非确定性的（默认：0） |
+| `首帧图像` | IMAGE | 否 | - | 生成视频的首帧图像（可选） |
+| `末帧图像` | IMAGE | 否 | - | 生成视频的末帧图像（可选） |
+| `luma_concepts` | CUSTOM | 否 | - | 通过 Luma Concepts 节点控制摄像机运动的自定义摄像机概念（可选） |
+
+**注意：** 必须提供 `first_image` 或 `last_image` 中的至少一个。如果两者都缺失，节点将引发异常。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/LumaReferenceNode.mdx b/zh-CN/built-in-nodes/LumaReferenceNode.mdx
new file mode 100644
index 000000000..43ab40b92
--- /dev/null
+++ b/zh-CN/built-in-nodes/LumaReferenceNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "LumaReferenceNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaReferenceNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaReferenceNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaReferenceNode/zh.md)
+
+此节点保存图像和权重值，用于 Luma 生成图像节点。它创建一个参考链，可传递给其他 Luma 节点以影响图像生成。该节点可以启动新的参考链，也可以添加到现有参考链中。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图片` | IMAGE | 是 | - | 用作参考的图像。 |
+| `权重` | FLOAT | 是 | 0.0 - 1.0 | 图像参考的权重（默认值：1.0）。 |
+| `luma_ref` | LUMA_REF | 否 | - | 可选的现有 Luma 参考链，用于添加到此链中。 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `luma_ref` | LUMA_REF | 包含图像和权重的 Luma 参考链。 |
diff --git a/zh-CN/built-in-nodes/LumaVideoNode.mdx b/zh-CN/built-in-nodes/LumaVideoNode.mdx
new file mode 100644
index 000000000..ffad1f6b0
--- /dev/null
+++ b/zh-CN/built-in-nodes/LumaVideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "LumaVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the LumaVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "LumaVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaVideoNode/zh.md)
+
+## 概述
+
+根据提示词和输出设置同步生成视频。此节点使用文本描述和各种生成参数来创建视频内容，在生成过程完成后输出最终视频。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `提示词` | STRING | 是 | - | 视频生成的提示词（默认：空字符串） |
+| `模型` | COMBO | 是 | 多个可用选项 | 要使用的视频生成模型 |
+| `宽高比` | COMBO | 是 | 多个可用选项 | 生成视频的宽高比（默认：16:9） |
+| `分辨率` | COMBO | 是 | 多个可用选项 | 视频的输出分辨率（默认：540p） |
+| `时长` | COMBO | 是 | 多个可用选项 | 生成视频的时长 |
+| `循环` | BOOLEAN | 是 | - | 视频是否应循环播放（默认：False） |
+| `种子` | INT | 是 | 0 到 18446744073709551615 | 用于确定节点是否应重新运行的种子值；无论种子值如何，实际结果都是非确定性的（默认：0） |
+| `luma_concepts` | CUSTOM | 否 | - | 通过 Luma Concepts 节点控制摄像机运动的可选摄像机概念 |
+
+**注意：** 使用 `ray_1_6` 模型时，`duration` 和 `resolution` 参数会自动设置为 None 且不会影响生成过程。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/MagnificImageRelightNode.mdx b/zh-CN/built-in-nodes/MagnificImageRelightNode.mdx
new file mode 100644
index 000000000..2c6352360
--- /dev/null
+++ b/zh-CN/built-in-nodes/MagnificImageRelightNode.mdx
@@ -0,0 +1,42 @@
+---
+title: "MagnificImageRelightNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageRelightNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageRelightNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageRelightNode/zh.md)
+
+Magnific Image Relight 节点用于调整输入图像的照明效果。它可以根据文本提示应用风格化照明，或从可选的参考图像中转移照明特性。该节点提供多种控制选项，用于微调最终输出的亮度、对比度和整体氛围。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | N/A | 需要重新照明的图像。必须且仅能输入一张图像。最小尺寸为 160x160 像素。宽高比必须在 1:3 到 3:1 之间。 |
+| `prompt` | STRING | 否 | N/A | 用于照明的描述性引导。支持强调符号 (1-1.4)。默认为空字符串。 |
+| `light_transfer_strength` | INT | 是 | 0 到 100 | 应用光线转移的强度。默认值：100。 |
+| `style` | COMBO | 是 | `"standard"`<br />`"darker_but_realistic"`<br />`"clean"`<br />`"smooth"`<br />`"brighter"`<br />`"contrasted_n_hdr"`<br />`"just_composition"` | 风格化输出偏好。 |
+| `interpolate_from_original` | BOOLEAN | 是 | N/A | 限制生成自由度，使其更接近原始图像。默认值：False。 |
+| `change_background` | BOOLEAN | 是 | N/A | 根据提示或参考图像修改背景。默认值：True。 |
+| `preserve_details` | BOOLEAN | 是 | N/A | 保留原始图像的纹理和精细细节。默认值：True。 |
+| `advanced_settings` | DYNAMICCOMBO | 是 | `"disabled"`<br />`"enabled"` | 用于高级照明控制的微调选项。设置为 `"enabled"` 时，将启用额外参数。 |
+| `reference_image` | IMAGE | 否 | N/A | 用于转移照明效果的可选参考图像。如果提供，必须且仅能输入一张图像。最小尺寸为 160x160 像素。宽高比必须在 1:3 到 3:1 之间。 |
+
+**关于高级设置的说明：** 当 `advanced_settings` 设置为 `"enabled"` 时，以下嵌套参数将被激活：
+
+* `whites`：调整图像中最亮的色调。范围：0 到 100。默认值：50。
+* `blacks`：调整图像中最暗的色调。范围：0 到 100。默认值：50。
+* `brightness`：整体亮度调整。范围：0 到 100。默认值：50。
+* `contrast`：对比度调整。范围：0 到 100。默认值：50。
+* `saturation`：色彩饱和度调整。范围：0 到 100。默认值：50。
+* `engine`：处理引擎选择。选项：`"automatic"`, `"balanced"`, `"cool"`, `"real"`, `"illusio"`, `"fairy"`, `"colorful_anime"`, `"hard_transform"`, `"softy"`。
+* `transfer_light_a`：光线转移的强度。选项：`"automatic"`, `"low"`, `"medium"`, `"normal"`, `"high"`, `"high_on_faces"`。
+* `transfer_light_b`：同样修改光线转移强度。可与前一个控制项结合以产生不同效果。选项：`"automatic"`, `"composition"`, `"straight"`, `"smooth_in"`, `"smooth_out"`, `"smooth_both"`, `"reverse_both"`, `"soft_in"`, `"soft_out"`, `"soft_mid"`, `"style_shift"`, `"strong_shift"`。
+* `fixed_generation`：确保使用相同设置时输出结果一致。默认值：True。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 重新照明后的图像。 |
diff --git a/zh-CN/built-in-nodes/MagnificImageSkinEnhancerNode.mdx b/zh-CN/built-in-nodes/MagnificImageSkinEnhancerNode.mdx
new file mode 100644
index 000000000..eb4e8e8b6
--- /dev/null
+++ b/zh-CN/built-in-nodes/MagnificImageSkinEnhancerNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "MagnificImageSkinEnhancerNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageSkinEnhancerNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageSkinEnhancerNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageSkinEnhancerNode/zh.md)
+
+Magnific Image Skin Enhancer 节点对肖像图像应用专门的 AI 处理，以改善皮肤外观。它提供三种不同的模式以满足不同的增强目标：创意模式用于艺术效果，忠实模式用于保留原始外观，灵活模式用于针对性的改进，如光照或真实感。该节点将图像上传到外部 API 进行处理，并返回增强后的结果。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待增强的肖像图像。 |
+| `sharpen` | INT | 否 | 0 到 100 | 锐化强度级别（默认值：0）。 |
+| `smart_grain` | INT | 否 | 0 到 100 | 智能颗粒感强度级别（默认值：2）。 |
+| `mode` | COMBO | 是 | `"creative"`<br />`"faithful"`<br />`"flexible"` | 使用的处理模式。`"creative"` 用于艺术增强，`"faithful"` 用于保留原始外观，`"flexible"` 用于针对性优化。 |
+| `skin_detail` | INT | 否 | 0 到 100 | 皮肤细节增强级别。此输入仅在 `mode` 设置为 `"faithful"` 时可用且必需（默认值：80）。 |
+| `optimized_for` | COMBO | 否 | `"enhance_skin"`<br />`"improve_lighting"`<br />`"enhance_everything"`<br />`"transform_to_real"`<br />`"no_make_up"` | 增强优化目标。此输入仅在 `mode` 设置为 `"flexible"` 时可用且必需。 |
+
+**约束条件：**
+
+* 该节点仅接受一个输入图像。
+* 输入图像的高度和宽度必须至少为 160 像素。
+* `skin_detail` 参数仅在 `mode` 设置为 `"faithful"` 时生效。
+* `optimized_for` 参数仅在 `mode` 设置为 `"flexible"` 时生效。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 增强后的肖像图像。 |
diff --git a/zh-CN/built-in-nodes/MagnificImageStyleTransferNode.mdx b/zh-CN/built-in-nodes/MagnificImageStyleTransferNode.mdx
new file mode 100644
index 000000000..9a4ce6115
--- /dev/null
+++ b/zh-CN/built-in-nodes/MagnificImageStyleTransferNode.mdx
@@ -0,0 +1,39 @@
+---
+title: "MagnificImageStyleTransferNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageStyleTransferNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageStyleTransferNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageStyleTransferNode/zh.md)
+
+此节点将参考图像的视觉风格应用到您的输入图像上。它使用外部 AI 服务来处理图像，允许您控制风格迁移的强度以及原始图像结构的保留程度。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 要应用风格迁移的图像。 |
+| `reference_image` | IMAGE | 是 | - | 用于提取风格的参考图像。 |
+| `prompt` | STRING | 否 | - | 用于引导风格迁移的可选文本提示。 |
+| `style_strength` | INT | 否 | 0 到 100 | 风格强度百分比（默认值：100）。 |
+| `structure_strength` | INT | 否 | 0 到 100 | 保持原始图像的结构（默认值：50）。 |
+| `flavor` | COMBO | 否 | "faithful"<br />"gen_z"<br />"psychedelia"<br />"detaily"<br />"clear"<br />"donotstyle"<br />"donotstyle_sharp" | 风格迁移类型。 |
+| `engine` | COMBO | 否 | "balanced"<br />"definio"<br />"illusio"<br />"3d_cartoon"<br />"colorful_anime"<br />"caricature"<br />"real"<br />"super_real"<br />"softy" | 处理引擎选择。 |
+| `portrait_mode` | COMBO | 否 | "disabled"<br />"enabled" | 启用人像模式以进行面部增强。 |
+| `portrait_style` | COMBO | 否 | "standard"<br />"pop"<br />"super_pop" | 应用于人像图像的视觉风格。此输入仅在 `portrait_mode` 设置为 "enabled" 时可用。 |
+| `portrait_beautifier` | COMBO | 否 | "none"<br />"beautify_face"<br />"beautify_face_max" | 人像面部美化强度。此输入仅在 `portrait_mode` 设置为 "enabled" 时可用。 |
+| `fixed_generation` | BOOLEAN | 否 | - | 禁用时，每次生成都会引入一定程度的随机性，从而产生更多样化的结果（默认值：True）。 |
+
+**约束条件：**
+
+* 必须恰好提供一个 `image` 和一个 `reference_image`。
+* 两张图像的宽高比必须在 1:3 到 3:1 之间。
+* 两张图像的最小高度和宽度必须为 160 像素。
+* `portrait_style` 和 `portrait_beautifier` 参数仅在 `portrait_mode` 设置为 "enabled" 时生效且为必需。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 应用风格迁移后得到的图像。 |
diff --git a/zh-CN/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx b/zh-CN/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx
new file mode 100644
index 000000000..aa4469d2d
--- /dev/null
+++ b/zh-CN/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx
@@ -0,0 +1,38 @@
+---
+title: "MagnificImageUpscalerCreativeNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageUpscalerCreativeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageUpscalerCreativeNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageUpscalerCreativeNode/zh.md)
+
+此节点使用 Magnific AI 服务对图像进行放大和创意增强。它允许您通过文本提示来引导增强过程，选择特定的优化风格，并控制创意过程的各个方面，如细节、与原图的相似度以及风格化强度。该节点会输出按您选择的倍数（2倍、4倍、8倍或16倍）放大的图像，最大输出尺寸为2530万像素。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待放大和增强的输入图像。 |
+| `prompt` | STRING | 否 | - | 用于引导图像创意增强的文本描述。此为可选参数（默认：空）。 |
+| `scale_factor` | COMBO | 是 | `"2x"`<br />`"4x"`<br />`"8x"`<br />`"16x"` | 图像尺寸的放大倍数。 |
+| `optimized_for` | COMBO | 是 | `"standard"`<br />`"soft_portraits"`<br />`"hard_portraits"`<br />`"art_n_illustration"`<br />`"videogame_assets"`<br />`"nature_n_landscapes"`<br />`"films_n_photography"`<br />`"3d_renders"`<br />`"science_fiction_n_horror"` | 为增强过程优化的风格或内容类型。 |
+| `creativity` | INT | 否 | -10 到 10 | 控制应用于图像的创意解读程度（默认：0）。 |
+| `hdr` | INT | 否 | -10 到 10 | 清晰度和细节水平（默认：0）。 |
+| `resemblance` | INT | 否 | -10 到 10 | 与原图的相似度水平（默认：0）。 |
+| `fractality` | INT | 否 | -10 到 10 | 提示的强度以及每平方像素的复杂精细度（默认：0）。 |
+| `engine` | COMBO | 是 | `"automatic"`<br />`"magnific_illusio"`<br />`"magnific_sharpy"`<br />`"magnific_sparkle"` | 用于处理的特定 AI 引擎。 |
+| `auto_downscale` | BOOLEAN | 否 | - | 启用后，如果请求的放大尺寸将超过允许的最大输出尺寸 2530 万像素，节点将自动缩小输入图像（默认：False）。 |
+
+**约束条件：**
+
+* 输入 `image` 必须恰好是一张图像。
+* 输入图像的高度和宽度必须至少为 160 像素。
+* 输入图像的宽高比必须在 1:3 到 3:1 之间。
+* 最终输出尺寸（输入尺寸乘以 `scale_factor`）不能超过 25,300,000 像素。如果 `auto_downscale` 被禁用且将超过此限制，节点将引发错误。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 经过创意增强和放大的输出图像。 |
diff --git a/zh-CN/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx b/zh-CN/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx
new file mode 100644
index 000000000..85d3f6c09
--- /dev/null
+++ b/zh-CN/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx
@@ -0,0 +1,32 @@
+---
+title: "MagnificImageUpscalerPreciseV2Node - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MagnificImageUpscalerPreciseV2Node node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MagnificImageUpscalerPreciseV2Node"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageUpscalerPreciseV2Node/zh.md)
+
+## 概述
+
+Magnific Image Upscale (Precise V2) 节点执行高保真图像放大，可精确控制锐度、颗粒感和细节增强。它通过外部 API 处理图像，支持最大输出分辨率达 10060×10060 像素。该节点提供不同的处理风格，并且如果请求的输出尺寸超过允许的最大尺寸，可以自动对输入进行降尺度处理。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待放大的输入图像。必须且仅能输入一张图像。最小尺寸为 160x160 像素。宽高比必须在 1:3 到 3:1 之间。 |
+| `scale_factor` | STRING | 是 | `"2x"`<br />`"4x"`<br />`"8x"`<br />`"16x"` | 期望的放大倍数。 |
+| `flavor` | STRING | 是 | `"sublime"`<br />`"photo"`<br />`"photo_denoiser"` | 处理风格。"sublime" 适用于通用场景，"photo" 针对照片优化，"photo_denoiser" 适用于有噪点的照片。 |
+| `sharpen` | INT | 否 | 0 到 100 | 控制图像锐化强度以增强边缘清晰度和整体清晰度。值越高，结果越锐利。默认值：7。 |
+| `smart_grain` | INT | 否 | 0 到 100 | 添加智能颗粒或纹理增强，防止放大后的图像看起来过于平滑或人工化。默认值：7。 |
+| `ultra_detail` | INT | 否 | 0 到 100 | 控制在放大过程中添加的精细细节、纹理和微观细节的数量。默认值：30。 |
+| `auto_downscale` | BOOLEAN | 否 | - | 启用后，如果计算出的输出尺寸超过允许的最大分辨率 10060x10060 像素，节点将自动对输入图像进行降尺度处理。这有助于防止错误，但可能会影响质量。默认值：False。 |
+
+**注意：** 如果 `auto_downscale` 被禁用，且请求的输出尺寸（输入尺寸 × `scale_factor`）超过 10060x10060 像素，节点将引发错误。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 放大后的结果图像。 |
diff --git a/zh-CN/built-in-nodes/Mahiro.mdx b/zh-CN/built-in-nodes/Mahiro.mdx
new file mode 100644
index 000000000..eb3f406fb
--- /dev/null
+++ b/zh-CN/built-in-nodes/Mahiro.mdx
@@ -0,0 +1,22 @@
+---
+title: "Mahiro - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Mahiro node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Mahiro"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Mahiro/zh.md)
+
+Mahiro 节点通过修改引导函数，使其更专注于正向提示词的方向，而非正向与负向提示词之间的差异。该节点会创建一个修补后的模型，该模型采用自定义的引导缩放方法，利用归一化后的条件性与无条件性去噪输出之间的余弦相似度。这个实验性节点有助于更强烈地将生成过程引导至正向提示词的预期方向。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | | 需要应用修改后引导函数进行修补的模型 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | 应用了 Mahiro 引导函数后的修改模型 |
diff --git a/zh-CN/built-in-nodes/MakeTrainingDataset.mdx b/zh-CN/built-in-nodes/MakeTrainingDataset.mdx
new file mode 100644
index 000000000..a3c15ae32
--- /dev/null
+++ b/zh-CN/built-in-nodes/MakeTrainingDataset.mdx
@@ -0,0 +1,30 @@
+---
+title: "MakeTrainingDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MakeTrainingDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MakeTrainingDataset"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MakeTrainingDataset/zh.md)
+
+此节点通过编码图像和文本来准备训练数据。它接收图像列表和对应的文本描述列表，然后使用 VAE 模型将图像转换为潜在表示，并使用 CLIP 模型将文本转换为条件数据。最终输出的配对潜在表示和条件数据以列表形式呈现，可直接用于训练工作流。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | N/A | 待编码的图像列表。 |
+| `vae` | VAE | 是 | N/A | 用于将图像编码为潜在表示的 VAE 模型。 |
+| `clip` | CLIP | 是 | N/A | 用于将文本编码为条件数据的 CLIP 模型。 |
+| `texts` | STRING | 否 | N/A | 文本描述列表。长度可以是 n（与图像数量匹配）、1（为所有图像重复使用）或省略（使用空字符串）。 |
+
+**参数约束：**
+
+* `texts` 列表中的项目数必须为 0、1，或与 `images` 列表中的项目数完全匹配。如果为 0，则所有图像都使用空字符串。如果为 1，则该单一文本会为所有图像重复使用。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `latents` | LATENT | 潜在字典列表。 |
+| `conditioning` | CONDITIONING | 条件列表的列表。 |
diff --git a/zh-CN/built-in-nodes/ManualSigmas.mdx b/zh-CN/built-in-nodes/ManualSigmas.mdx
new file mode 100644
index 000000000..54672942e
--- /dev/null
+++ b/zh-CN/built-in-nodes/ManualSigmas.mdx
@@ -0,0 +1,22 @@
+---
+title: "ManualSigmas - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ManualSigmas node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ManualSigmas"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ManualSigmas/zh.md)
+
+ManualSigmas 节点允许您为采样过程手动定义自定义的噪声级别序列。您输入一个数字列表作为字符串，节点会将其转换为可供其他采样节点使用的张量。这对于测试或创建特定的噪声调度非常有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `sigmas` | STRING | 是 | 任意逗号或空格分隔的数字 | 包含 sigma 值的字符串。节点将从此字符串中提取所有数字。例如："1, 0.5, 0.1" 或 "1 0.5 0.1"。默认值为 "1, 0.5"。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | 包含从输入字符串中提取的 sigma 值序列的张量。 |
diff --git a/zh-CN/built-in-nodes/MarkdownNote.mdx b/zh-CN/built-in-nodes/MarkdownNote.mdx
new file mode 100644
index 000000000..041ecf123
--- /dev/null
+++ b/zh-CN/built-in-nodes/MarkdownNote.mdx
@@ -0,0 +1,14 @@
+---
+title: "MarkdownNote - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MarkdownNote node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MarkdownNote"
+icon: "circle"
+mode: wide
+---
+用于向工作流添加注释的节点。它支持使用 Markdown 语法进行文本格式化。
+
+## 输入
+
+## 输出
+
+该节点没有定义输出类型。
diff --git a/zh-CN/built-in-nodes/MaskComposite.mdx b/zh-CN/built-in-nodes/MaskComposite.mdx
new file mode 100644
index 000000000..0dd842c08
--- /dev/null
+++ b/zh-CN/built-in-nodes/MaskComposite.mdx
@@ -0,0 +1,26 @@
+---
+title: "MaskComposite - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MaskComposite node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MaskComposite"
+icon: "circle"
+mode: wide
+---
+遮罩组合节点专门通过各种操作（如加法、减法和逻辑操作）结合两个遮罩输入，以产生一个新的、修改后的遮罩。它抽象地处理遮罩数据的操纵，以实现复杂的遮罩效果，是遮罩基础的图像编辑和处理工作流程中的关键组件。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `目标` | MASK | 主要遮罩，将根据与源遮罩的操作进行修改。在组合操作中扮演中心角色，作为修改的基础。 |
+| `源` | MASK | 次要遮罩，将与目标遮罩结合使用以执行指定操作，影响最终输出的遮罩。 |
+| `x` | INT | 水平偏移量，用于确定源遮罩应用于目标遮罩的位置，影响合成结果的位置。 |
+| `y` | INT | 垂直偏移量，用于确定源遮罩应用于目标遮罩的位置，影响合成结果的位置。 |
+| `操作` | COMBO[STRING] | 指定要在目标遮罩和源遮罩之间应用的操作类型，如'add'（加法）、'subtract'（减法）或逻辑操作，决定合成效果的性质。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `mask` | MASK | 在目标遮罩和源遮罩之间应用指定操作后得到的遮罩，代表合成的结果。 |
+
+---
diff --git a/zh-CN/built-in-nodes/MaskPreview.mdx b/zh-CN/built-in-nodes/MaskPreview.mdx
new file mode 100644
index 000000000..fafeecbbf
--- /dev/null
+++ b/zh-CN/built-in-nodes/MaskPreview.mdx
@@ -0,0 +1,25 @@
+---
+title: "MaskPreview - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MaskPreview node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MaskPreview"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MaskPreview/zh.md)
+
+MaskPreview 节点通过将遮罩转换为三通道图像格式并保存为临时文件，生成遮罩的可视化预览。它接收遮罩输入并将其重塑为适合图像显示的格式，然后将结果保存到临时目录并附带随机文件名前缀。这使用户能够在工作流执行过程中直观检查遮罩数据。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `mask` | MASK | 是 | - | 需要预览并转换为图像格式的遮罩数据 |
+| `filename_prefix` | STRING | 否 | - | 输出文件名的前缀（默认为"ComfyUI"） |
+| `prompt` | PROMPT | 否 | - | 用于元数据的提示信息（自动提供） |
+| `extra_pnginfo` | EXTRA_PNGINFO | 否 | - | 用于元数据的额外PNG信息（自动提供） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `ui` | DICT | 包含用于显示的预览图像信息和元数据 |
diff --git a/zh-CN/built-in-nodes/MaskToImage.mdx b/zh-CN/built-in-nodes/MaskToImage.mdx
new file mode 100644
index 000000000..01cfe9aa0
--- /dev/null
+++ b/zh-CN/built-in-nodes/MaskToImage.mdx
@@ -0,0 +1,21 @@
+---
+title: "MaskToImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MaskToImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MaskToImage"
+icon: "circle"
+mode: wide
+---
+
+MaskToImage 节点旨在将遮罩转换为图像格式。这种转换允许将遮罩作为图像进行可视化和进一步处理，从而在基于遮罩的操作和基于图像的应用程序之间架起了一座桥梁。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `遮罩`   | `MASK`   | 遮罩输入对于转换过程至关重要，作为将被转换成图像格式的源数据。此输入决定了结果图像的形状和内容。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `image`  | `IMAGE`  | 输出是输入遮罩的图像表示，使视觉检查和进一步的基于图像的操作成为可能。 |
diff --git a/zh-CN/built-in-nodes/MergeImageLists.mdx b/zh-CN/built-in-nodes/MergeImageLists.mdx
new file mode 100644
index 000000000..21162ae22
--- /dev/null
+++ b/zh-CN/built-in-nodes/MergeImageLists.mdx
@@ -0,0 +1,24 @@
+---
+title: "MergeImageLists - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MergeImageLists node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MergeImageLists"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MergeImageLists/zh.md)
+
+此节点将多个独立的图像列表合并为一个连续的列表。其工作原理是接收每个已连接输入中的所有图像，并按照接收顺序将它们拼接在一起。这对于组织或批处理来自不同来源的图像以进行进一步处理非常有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | - | 待合并的图像列表。此输入可接受多个连接，每个已连接的列表将被拼接成最终的输出列表。 |
+
+**注意：** 此节点设计为接收多个输入。您可以将多个图像列表连接到单个 `images` 输入端口。节点将自动把所有已连接列表中的所有图像拼接成一个输出列表。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `images` | IMAGE | 包含所有已连接输入列表中所有图像的单一合并列表。 |
diff --git a/zh-CN/built-in-nodes/MergeTextLists.mdx b/zh-CN/built-in-nodes/MergeTextLists.mdx
new file mode 100644
index 000000000..77273a44f
--- /dev/null
+++ b/zh-CN/built-in-nodes/MergeTextLists.mdx
@@ -0,0 +1,24 @@
+---
+title: "MergeTextLists - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MergeTextLists node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MergeTextLists"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MergeTextLists/zh.md)
+
+此节点将多个文本列表合并为一个统一的列表。它接收文本输入作为列表，并将它们连接在一起。该节点会记录合并后列表中的文本总数。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `texts` | STRING | 是 | 不适用 | 待合并的文本列表。可以将多个列表连接到此输入，它们将被连接成一个列表。 |
+
+**注意：** 此节点被配置为组处理过程 (`is_group_process = True`)，这意味着它会在主处理函数运行之前自动处理多个列表输入，将它们连接起来。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `texts` | STRING | 包含所有输入文本的单一合并列表。 |
diff --git a/zh-CN/built-in-nodes/MeshyAnimateModelNode.mdx b/zh-CN/built-in-nodes/MeshyAnimateModelNode.mdx
new file mode 100644
index 000000000..e23fbb377
--- /dev/null
+++ b/zh-CN/built-in-nodes/MeshyAnimateModelNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "MeshyAnimateModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyAnimateModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyAnimateModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyAnimateModelNode/zh.md)
+
+此节点对已使用 Meshy 服务完成骨骼绑定的 3D 角色模型应用特定动画。它接收先前骨骼绑定操作的任务 ID 和一个动作 ID，用于从动画库中选择所需的动画。随后节点会处理请求，并以 GLB 和 FBX 两种文件格式返回带动画的模型。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `rig_task_id` | STRING | 是 | 无 | 来自先前已完成的 Meshy 角色骨骼绑定操作的唯一任务 ID。 |
+| `action_id` | INT | 是 | 0 至 696 | 要应用的动画动作的 ID 编号。可访问 [https://docs.meshy.ai/en/api/animation-library](https://docs.meshy.ai/en/api/animation-library) 查看可用值列表。（默认值：0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 带动画模型的字符串标识符。此输出仅为向后兼容性而提供。 |
+| `GLB` | FILE3DGLB | GLB 格式的带动画 3D 模型文件。 |
+| `FBX` | FILE3DFBX | FBX 格式的带动画 3D 模型文件。 |
diff --git a/zh-CN/built-in-nodes/MeshyImageToModelNode.mdx b/zh-CN/built-in-nodes/MeshyImageToModelNode.mdx
new file mode 100644
index 000000000..2621a89bb
--- /dev/null
+++ b/zh-CN/built-in-nodes/MeshyImageToModelNode.mdx
@@ -0,0 +1,42 @@
+---
+title: "MeshyImageToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyImageToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyImageToModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyImageToModelNode/zh.md)
+
+Meshy: Image to Model 节点使用 Meshy API 从单张输入图像生成 3D 模型。它会将您的图像上传，提交处理任务，并返回生成的 3D 模型文件（GLB 和 FBX）以及用于参考的任务 ID。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"latest"` | 指定用于生成的 AI 模型版本。 |
+| `image` | IMAGE | 是 | - | 要转换为 3D 模型的输入图像。 |
+| `should_remesh` | DYNAMIC COMBO | 是 | `"true"`<br />`"false"` | 确定是否对生成的网格进行处理。当设置为 `"false"` 时，节点将返回未经处理的三角网格。 |
+| `topology` | COMBO | 否* | `"triangle"`<br />`"quad"` | 重新网格化模型的目标多边形拓扑。此输入仅在 `should_remesh` 设置为 `"true"` 时可用且必需。 |
+| `target_polycount` | INT | 否* | 100 - 300000 | 重新网格化模型的目标多边形数量。此输入仅在 `should_remesh` 设置为 `"true"` 时可用且必需。默认值为 300000。 |
+| `symmetry_mode` | COMBO | 是 | `"auto"`<br />`"on"`<br />`"off"` | 控制应用于生成的 3D 模型的对称性。 |
+| `should_texture` | DYNAMIC COMBO | 是 | `"true"`<br />`"false"` | 确定是否为模型生成纹理。将其设置为 `"false"` 将跳过纹理阶段，并返回一个没有纹理的网格。 |
+| `enable_pbr` | BOOLEAN | 否* | - | 当 `should_texture` 为 `"true"` 时，此选项会生成 PBR 贴图（金属度、粗糙度、法线）以及基础颜色。默认值为 `False`。 |
+| `texture_prompt` | STRING | 否* | - | 用于指导纹理生成过程的文本提示（最多 600 个字符）。此输入仅在 `should_texture` 设置为 `"true"` 时可用。不能与 `texture_image` 同时使用。 |
+| `texture_image` | IMAGE | 否* | - | 用于指导纹理生成过程的图像。此输入仅在 `should_texture` 设置为 `"true"` 时可用。不能与 `texture_prompt` 同时使用。 |
+| `pose_mode` | COMBO | 是 | `""`<br />`"A-pose"`<br />`"T-pose"` | 指定生成模型的姿态模式。 |
+| `seed` | INT | 是 | 0 - 2147483647 | 生成过程的种子值。无论种子值如何，结果都是非确定性的。默认值为 0。 |
+
+**关于参数约束的说明：**
+
+* `topology` 和 `target_polycount` 输入仅在 `should_remesh` 设置为 `"true"` 时必需。
+* `enable_pbr`、`texture_prompt` 和 `texture_image` 输入仅在 `should_texture` 设置为 `"true"` 时可用。
+* 不能同时使用 `texture_prompt` 和 `texture_image`。如果在 `should_texture` 为 `"true"` 时同时提供了两者，节点将引发错误。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的 GLB 模型的文件名。（为向后兼容而保留）。 |
+| `meshy_task_id` | MESHY_TASK_ID | Meshy API 任务的唯一标识符，可用于参考或故障排除。 |
+| `GLB` | FILE3DGLB | 生成的 GLB 文件格式的 3D 模型。 |
+| `FBX` | FILE3DFBX | 生成的 FBX 文件格式的 3D 模型。 |
diff --git a/zh-CN/built-in-nodes/MeshyMultiImageToModelNode.mdx b/zh-CN/built-in-nodes/MeshyMultiImageToModelNode.mdx
new file mode 100644
index 000000000..acd2c13ee
--- /dev/null
+++ b/zh-CN/built-in-nodes/MeshyMultiImageToModelNode.mdx
@@ -0,0 +1,43 @@
+---
+title: "MeshyMultiImageToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyMultiImageToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyMultiImageToModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyMultiImageToModelNode/zh.md)
+
+此节点使用 Meshy API 从多个输入图像生成 3D 模型。它会上传提供的图像，提交处理任务，并返回生成的 3D 模型文件（GLB 和 FBX）以及用于参考的任务 ID。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+| :--- | :--- | :--- | :--- | :--- |
+| `model` | COMBO | 是 | `"latest"` | 指定要使用的 AI 模型版本。 |
+| `images` | IMAGE | 是 | 2 到 4 张图像 | 用于生成 3D 模型的一组图像。必须提供 2 到 4 张图像。 |
+| `should_remesh` | COMBO | 是 | `"true"`<br />`"false"` | 确定是否对生成的网格进行处理。当设置为 `"false"` 时，节点将返回未经处理的三角网格。 |
+| `topology` | COMBO | 否 | `"triangle"`<br />`"quad"` | 重新网格化输出的目标多边形类型。此参数仅在 `should_remesh` 设置为 `"true"` 时可用且必需。 |
+| `target_polycount` | INT | 否 | 100 到 300000 | 重新网格化模型的目标多边形数量（默认值：300000）。此参数仅在 `should_remesh` 设置为 `"true"` 时可用。 |
+| `symmetry_mode` | COMBO | 是 | `"auto"`<br />`"on"`<br />`"off"` | 控制是否对生成的模型应用对称性。 |
+| `should_texture` | COMBO | 是 | `"true"`<br />`"false"` | 确定是否生成纹理。将其设置为 `"false"` 将跳过纹理阶段，并返回一个没有纹理的网格。 |
+| `enable_pbr` | BOOLEAN | 否 | `True` / `False` | 当 `should_texture` 为 `"true"` 时，此选项会生成 PBR 贴图（金属度、粗糙度、法线）以及基础颜色（默认值：`False`）。 |
+| `texture_prompt` | STRING | 否 | - | 用于指导纹理生成过程的文本提示（最多 600 个字符）。不能与 `texture_image` 同时使用。此参数仅在 `should_texture` 设置为 `"true"` 时可用。 |
+| `texture_image` | IMAGE | 否 | - | 用于指导纹理生成过程的图像。`texture_image` 和 `texture_prompt` 只能同时使用其中一个。此参数仅在 `should_texture` 设置为 `"true"` 时可用。 |
+| `pose_mode` | COMBO | 是 | `""`<br />`"A-pose"`<br />`"T-pose"` | 指定生成模型的姿态模式。 |
+| `seed` | INT | 是 | 0 到 2147483647 | 生成过程的种子值（默认值：0）。无论种子值如何，结果都是非确定性的，但更改种子值可以触发节点重新运行。 |
+
+**参数约束：**
+
+* 必须为 `images` 输入提供 2 到 4 张图像。
+* `topology` 和 `target_polycount` 参数仅在 `should_remesh` 设置为 `"true"` 时生效。
+* `enable_pbr`、`texture_prompt` 和 `texture_image` 参数仅在 `should_texture` 设置为 `"true"` 时生效。
+* 不能同时使用 `texture_prompt` 和 `texture_image`；它们是互斥的。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+| :--- | :--- | :--- |
+| `model_file` | STRING | 生成的 GLB 模型的文件名。此输出是为了向后兼容而提供的。 |
+| `meshy_task_id` | MESHY_TASK_ID | Meshy API 任务的唯一标识符。 |
+| `GLB` | FILE3DGLB | 生成的 GLB 格式的 3D 模型。 |
+| `FBX` | FILE3DFBX | 生成的 FBX 格式的 3D 模型。 |
diff --git a/zh-CN/built-in-nodes/MeshyRefineNode.mdx b/zh-CN/built-in-nodes/MeshyRefineNode.mdx
new file mode 100644
index 000000000..80d4372ba
--- /dev/null
+++ b/zh-CN/built-in-nodes/MeshyRefineNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "MeshyRefineNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyRefineNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyRefineNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRefineNode/zh.md)
+
+Meshy: Refine Draft Model 节点接收先前生成的 3D 草稿模型并提升其质量，可选择添加纹理。它会向 Meshy API 提交一个精炼任务，并在处理完成后返回最终的 3D 模型文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"latest"` | 指定用于精炼的 AI 模型。目前仅提供 "latest" 模型。 |
+| `meshy_task_id` | MESHY_TASK_ID | 是 | - | 你想要精炼的草稿模型的唯一任务 ID。 |
+| `enable_pbr` | BOOLEAN | 否 | - | 除了基础颜色外，还生成 PBR 贴图（金属度、粗糙度、法线）。注意：使用雕塑风格时应设置为 false，因为雕塑风格会生成其自己的一套 PBR 贴图。（默认值：`False`） |
+| `texture_prompt` | STRING | 否 | - | 提供文本提示来指导纹理生成过程。最多 600 个字符。不能与 'texture_image' 同时使用。（默认值：空字符串） |
+| `texture_image` | IMAGE | 否 | - | 'texture_image' 和 'texture_prompt' 只能同时使用其中一个。（可选） |
+
+**注意：** `texture_prompt` 和 `texture_image` 输入是互斥的。在同一操作中，你不能同时提供文本提示和图像来进行纹理处理。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的 GLB 模型的文件名。（仅用于向后兼容） |
+| `meshy_task_id` | MESHY_TASK_ID | 已提交的精炼任务的唯一任务 ID。 |
+| `GLB` | FILE3DGLB | 最终精炼后的 3D 模型，格式为 GLB。 |
+| `FBX` | FILE3DFBX | 最终精炼后的 3D 模型，格式为 FBX。 |
diff --git a/zh-CN/built-in-nodes/MeshyRigModelNode.mdx b/zh-CN/built-in-nodes/MeshyRigModelNode.mdx
new file mode 100644
index 000000000..3ab5ffdbc
--- /dev/null
+++ b/zh-CN/built-in-nodes/MeshyRigModelNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "MeshyRigModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyRigModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyRigModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRigModelNode/zh.md)
+
+Meshy: Rig Model 节点接收来自 Meshy 的 3D 模型任务并生成一个已绑定骨骼的角色模型。它会自动为模型创建骨架，使其能够被摆姿势和制作动画。该节点以 GLB 和 FBX 两种文件格式输出已绑定骨骼的模型。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `meshy_task_id` | STRING | 是 | N/A | 来自先前 Meshy 操作（例如，文本转 3D 或图像转 3D）的唯一任务 ID，该操作生成了待绑定骨骼的模型。 |
+| `height_meters` | FLOAT | 是 | 0.1 至 15.0 | 角色模型的近似高度（单位：米）。这有助于提高缩放和骨骼绑定的准确性（默认值：1.7）。 |
+| `texture_image` | IMAGE | 否 | N/A | 模型的 UV 展开后的基础颜色纹理图像。 |
+
+**注意：** 当前的自动骨骼绑定过程不适用于未贴图的网格、非人形资产或肢体和身体结构不清晰的人形资产。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 用于向后兼容的遗留输出，包含 GLB 模型的文件名。 |
+| `rig_task_id` | STRING | 此骨骼绑定操作的唯一任务 ID，可用于引用结果。 |
+| `GLB` | FILE3DGLB | 以 GLB 文件格式保存的已绑定骨骼的 3D 角色模型。 |
+| `FBX` | FILE3DFBX | 以 FBX 文件格式保存的已绑定骨骼的 3D 角色模型。 |
diff --git a/zh-CN/built-in-nodes/MeshyTextToModelNode.mdx b/zh-CN/built-in-nodes/MeshyTextToModelNode.mdx
new file mode 100644
index 000000000..f591368eb
--- /dev/null
+++ b/zh-CN/built-in-nodes/MeshyTextToModelNode.mdx
@@ -0,0 +1,35 @@
+---
+title: "MeshyTextToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyTextToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyTextToModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextToModelNode/zh.md)
+
+Meshy: Text to Model 节点使用 Meshy API，根据文本描述生成 3D 模型。它会将您的提示词和设置发送到 API，然后等待生成完成并下载生成的模型文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"latest"` | 指定要使用的 AI 模型版本。目前仅提供 "latest" 版本。 |
+| `prompt` | STRING | 是 | - | 您想要生成的 3D 模型的文本描述。长度必须在 1 到 600 个字符之间。 |
+| `style` | COMBO | 是 | `"realistic"`<br />`"sculpture"` | 生成 3D 模型的艺术风格。 |
+| `should_remesh` | DYNAMIC COMBO | 是 | `"true"`<br />`"false"` | 控制是否对生成的网格进行处理。设置为 "false" 时，节点将返回未经处理的三角网格。选择 "true" 会显示拓扑结构和多边形数量的额外参数。 |
+| `topology` | COMBO | 否* | `"triangle"`<br />`"quad"` | 重新网格化模型的目标多边形类型。此参数仅在 `should_remesh` 设置为 "true" 时可用且必需。 |
+| `target_polycount` | INT | 否* | 100 - 300000 | 重新网格化模型的目标多边形数量。默认值为 300000。此参数仅在 `should_remesh` 设置为 "true" 时可用且必需。 |
+| `symmetry_mode` | COMBO | 是 | `"auto"`<br />`"on"`<br />`"off"` | 控制生成模型中的对称性。 |
+| `pose_mode` | COMBO | 是 | `""`<br />`"A-pose"`<br />`"T-pose"` | 指定生成模型的姿态模式。空字符串表示不请求特定姿态。 |
+| `seed` | INT | 是 | 0 - 2147483647 | 生成的种子值。设置此值可控制节点是否应重新运行，但无论种子值如何，结果都是非确定性的。默认值为 0。 |
+
+*注意：`topology` 和 `target_polycount` 参数是条件性必需的。它们仅在 `should_remesh` 参数设置为 "true" 时出现且必须设置。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的 GLB 模型的文件名。此输出为向后兼容性而提供。 |
+| `meshy_task_id` | MESHY_TASK_ID | Meshy API 任务的唯一标识符。 |
+| `GLB` | FILE3DGLB | 生成的 GLB 格式的 3D 模型文件。 |
+| `FBX` | FILE3DFBX | 生成的 FBX 格式的 3D 模型文件。 |
diff --git a/zh-CN/built-in-nodes/MeshyTextureNode.mdx b/zh-CN/built-in-nodes/MeshyTextureNode.mdx
new file mode 100644
index 000000000..2a9556889
--- /dev/null
+++ b/zh-CN/built-in-nodes/MeshyTextureNode.mdx
@@ -0,0 +1,35 @@
+---
+title: "MeshyTextureNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MeshyTextureNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MeshyTextureNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextureNode/zh.md)
+
+Meshy: Texture 节点将 AI 生成的纹理应用到 3D 模型上。它接收来自先前 Meshy 3D 生成或转换节点的任务 ID，并使用文本描述或参考图像为模型创建新纹理。该节点以 GLB 和 FBX 文件格式输出带纹理的模型。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"latest"` | 用于纹理生成的 AI 模型版本。目前仅提供 "latest" 版本。 |
+| `meshy_task_id` | MESHY_TASK_ID | 是 | - | 来自先前 Meshy 3D 生成或转换任务的唯一标识符（任务 ID）。这提供了待纹理化的基础 3D 模型。 |
+| `enable_original_uv` | BOOLEAN | 否 | - | 启用时（默认：`True`），节点将使用上传模型的原始 UV 布局，保留任何现有纹理。如果模型没有原始 UV，输出质量可能会降低。 |
+| `pbr` | BOOLEAN | 否 | - | 为带纹理的模型启用基于物理的渲染（PBR）材质输出（默认：`False`）。 |
+| `text_style_prompt` | STRING | 否 | - | 对象所需纹理风格的文本描述。最多 600 个字符。不能与 `image_style` 同时使用。 |
+| `image_style` | IMAGE | 否 | - | 用于指导纹理生成过程的 2D 参考图像。不能与 `text_style_prompt` 同时使用。 |
+
+**参数约束：**
+
+* 必须提供 `text_style_prompt` 或 `image_style` 中的一个，但不能同时提供两者。
+* `text_style_prompt` 最多限制为 600 个字符。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的 GLB 模型的文件名。此输出为向后兼容性而提供。 |
+| `meshy_task_id` | MODEL_TASK_ID | 此纹理生成任务的唯一任务标识符，可用于引用结果。 |
+| `GLB` | FILE3DGLB | 以 GLB 文件格式保存的带纹理 3D 模型。 |
+| `FBX` | FILE3DFBX | 以 FBX 文件格式保存的带纹理 3D 模型。 |
diff --git a/zh-CN/built-in-nodes/MinimaxHailuoVideoNode.mdx b/zh-CN/built-in-nodes/MinimaxHailuoVideoNode.mdx
new file mode 100644
index 000000000..fa08ac89b
--- /dev/null
+++ b/zh-CN/built-in-nodes/MinimaxHailuoVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "MinimaxHailuoVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MinimaxHailuoVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MinimaxHailuoVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxHailuoVideoNode/zh.md)
+
+## 概述
+
+使用 MiniMax Hailuo-02 模型从文本提示生成视频。您可以选择提供起始图像作为第一帧，以创建从该图像继续的视频。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt_text` | STRING | 是 | - | 用于指导视频生成的文本提示。 |
+| `seed` | INT | 否 | 0 到 18446744073709551615 | 用于创建噪声的随机种子（默认值：0）。 |
+| `first_frame_image` | IMAGE | 否 | - | 可选图像，用作生成视频的第一帧。 |
+| `prompt_optimizer` | BOOLEAN | 否 | - | 在需要时优化提示以提高生成质量（默认值：True）。 |
+| `duration` | COMBO | 否 | `6`<br />`10` | 输出视频的长度，单位为秒（默认值：6）。 |
+| `resolution` | COMBO | 否 | `"768P"`<br />`"1080P"` | 视频显示的尺寸。1080p 为 1920x1080，768p 为 1366x768（默认值："768P"）。 |
+
+**注意：** 当使用 MiniMax-Hailuo-02 模型并选择 1080P 分辨率时，视频时长限制为 6 秒。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/MinimaxImageToVideoNode.mdx b/zh-CN/built-in-nodes/MinimaxImageToVideoNode.mdx
new file mode 100644
index 000000000..e83cc1127
--- /dev/null
+++ b/zh-CN/built-in-nodes/MinimaxImageToVideoNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "MinimaxImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MinimaxImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MinimaxImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxImageToVideoNode/zh.md)
+
+基于输入图像和提示文本，以及可选参数，使用 MiniMax 的 API 同步生成视频。该节点接收输入图像和文本描述来创建视频序列，并提供多种模型选项和配置设置。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 用作视频生成首帧的输入图像 |
+| `prompt_text` | STRING | 是 | - | 指导视频生成的文本提示（默认值：空字符串） |
+| `model` | COMBO | 是 | "I2V-01-Director"<br />"I2V-01"<br />"I2V-01-live" | 用于视频生成的模型（默认值："I2V-01"） |
+| `seed` | INT | 否 | 0 到 18446744073709551615 | 用于创建噪声的随机种子（默认值：0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频输出 |
diff --git a/zh-CN/built-in-nodes/MinimaxSubjectToVideoNode.mdx b/zh-CN/built-in-nodes/MinimaxSubjectToVideoNode.mdx
new file mode 100644
index 000000000..29aba3bf3
--- /dev/null
+++ b/zh-CN/built-in-nodes/MinimaxSubjectToVideoNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "MinimaxSubjectToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MinimaxSubjectToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MinimaxSubjectToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxSubjectToVideoNode/zh.md)
+
+基于图像和提示词，以及可选参数，使用 MiniMax 的 API 同步生成视频。该节点通过主体图像和文本描述，利用 MiniMax 的视频生成服务创建视频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `subject` | IMAGE | 是 | - | 用于视频生成参考的主体图像 |
+| `prompt_text` | STRING | 是 | - | 指导视频生成的文本提示词（默认：空字符串） |
+| `model` | COMBO | 否 | "S2V-01"<br /> | 用于视频生成的模型（默认："S2V-01"） |
+| `seed` | INT | 否 | 0 到 18446744073709551615 | 用于创建噪声的随机种子（默认：0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 基于输入主体图像和提示词生成的视频 |
diff --git a/zh-CN/built-in-nodes/MinimaxTextToVideoNode.mdx b/zh-CN/built-in-nodes/MinimaxTextToVideoNode.mdx
new file mode 100644
index 000000000..f71e3dd05
--- /dev/null
+++ b/zh-CN/built-in-nodes/MinimaxTextToVideoNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "MinimaxTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MinimaxTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MinimaxTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxTextToVideoNode/zh.md)
+
+基于提示文本和可选参数，使用 MiniMax 的 API 同步生成视频。该节点通过连接 MiniMax 的文生视频服务，将文本描述转换为视频内容。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt_text` | STRING | 是 | - | 用于指导视频生成的文本提示 |
+| `model` | COMBO | 否 | "T2V-01"<br />"T2V-01-Director" | 用于视频生成的模型（默认："T2V-01"） |
+| `seed` | INT | 否 | 0 到 18446744073709551615 | 用于创建噪声的随机种子（默认：0） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 基于输入提示生成的视频 |
diff --git a/zh-CN/built-in-nodes/ModelComputeDtype.mdx b/zh-CN/built-in-nodes/ModelComputeDtype.mdx
new file mode 100644
index 000000000..b045a442a
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelComputeDtype.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelComputeDtype - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelComputeDtype node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelComputeDtype"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelComputeDtype/zh.md)
+
+ModelComputeDtype 节点允许您在推理过程中更改模型使用的计算数据类型。它会创建输入模型的副本并应用指定的数据类型设置，这有助于根据硬件能力优化内存使用和性能。该节点在调试和测试不同精度设置时特别有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 需要应用新计算数据类型的输入模型 |
+| `dtype` | STRING | 是 | "default"<br />"fp32"<br />"fp16"<br />"bf16" | 要应用于模型的计算数据类型 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 已应用新计算数据类型的修改后模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeAdd.mdx b/zh-CN/built-in-nodes/ModelMergeAdd.mdx
new file mode 100644
index 000000000..7b3633155
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeAdd.mdx
@@ -0,0 +1,22 @@
+---
+title: "ModelMergeAdd - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeAdd node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeAdd"
+icon: "circle"
+mode: wide
+---
+
+`ModelMergeAdd` 节点旨在通过添加一个模型的关键补丁到另一个模型来合并两个模型。这个过程涉及克隆第一个模型，然后应用第二个模型的补丁，从而允许结合两个模型的特征或行为。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型1` | `MODEL` | 这是要被克隆并添加第二个模型补丁的第一个模型。它作为合并过程的基础模型。 |
+| `模型2` | `MODEL` | 这是提取关键补丁并添加到第一个模型的第二个模型。它为合并后的模型贡献了额外的特征或行为。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `model` | `MODEL` | 通过将第二个模型的关键补丁添加到第一个模型来合并两个模型的结果。这个合并后的模型结合了两个模型的特征或行为。 |
diff --git a/zh-CN/built-in-nodes/ModelMergeAuraflow.mdx b/zh-CN/built-in-nodes/ModelMergeAuraflow.mdx
new file mode 100644
index 000000000..2f2812bf6
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeAuraflow.mdx
@@ -0,0 +1,66 @@
+---
+title: "ModelMergeAuraflow - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeAuraflow node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeAuraflow"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeAuraflow/zh.md)
+
+ModelMergeAuraflow 节点允许您通过调整不同模型组件的特定混合权重，将两个不同的模型融合在一起。它提供了对模型从初始层到最终输出的不同部分如何合并的细粒度控制。该节点特别适用于创建自定义模型组合，并精确控制合并过程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型1` | MODEL | 是 | - | 要合并的第一个模型 |
+| `模型2` | MODEL | 是 | - | 要合并的第二个模型 |
+| `init_x_linear.` | FLOAT | 是 | 0.0 - 1.0 | 初始线性变换的混合权重（默认：1.0） |
+| `位置编码` | FLOAT | 是 | 0.0 - 1.0 | 位置编码组件的混合权重（默认：1.0） |
+| `cond_seq_linear.` | FLOAT | 是 | 0.0 - 1.0 | 条件序列线性层的混合权重（默认：1.0） |
+| `注册令牌` | FLOAT | 是 | 0.0 - 1.0 | 令牌注册组件的混合权重（默认：1.0） |
+| `t_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入组件的混合权重（默认：1.0） |
+| `double_layers.0.` | FLOAT | 是 | 0.0 - 1.0 | 双层组0的混合权重（默认：1.0） |
+| `double_layers.1.` | FLOAT | 是 | 0.0 - 1.0 | 双层组1的混合权重（默认：1.0） |
+| `double_layers.2.` | FLOAT | 是 | 0.0 - 1.0 | 双层组2的混合权重（默认：1.0） |
+| `double_layers.3.` | FLOAT | 是 | 0.0 - 1.0 | 双层组3的混合权重（默认：1.0） |
+| `single_layers.0.` | FLOAT | 是 | 0.0 - 1.0 | 单层0的混合权重（默认：1.0） |
+| `single_layers.1.` | FLOAT | 是 | 0.0 - 1.0 | 单层1的混合权重（默认：1.0） |
+| `single_layers.2.` | FLOAT | 是 | 0.0 - 1.0 | 单层2的混合权重（默认：1.0） |
+| `single_layers.3.` | FLOAT | 是 | 0.0 - 1.0 | 单层3的混合权重（默认：1.0） |
+| `single_layers.4.` | FLOAT | 是 | 0.0 - 1.0 | 单层4的混合权重（默认：1.0） |
+| `single_layers.5.` | FLOAT | 是 | 0.0 - 1.0 | 单层5的混合权重（默认：1.0） |
+| `single_layers.6.` | FLOAT | 是 | 0.0 - 1.0 | 单层6的混合权重（默认：1.0） |
+| `single_layers.7.` | FLOAT | 是 | 0.0 - 1.0 | 单层7的混合权重（默认：1.0） |
+| `single_layers.8.` | FLOAT | 是 | 0.0 - 1.0 | 单层8的混合权重（默认：1.0） |
+| `single_layers.9.` | FLOAT | 是 | 0.0 - 1.0 | 单层9的混合权重（默认：1.0） |
+| `single_layers.10.` | FLOAT | 是 | 0.0 - 1.0 | 单层10的混合权重（默认：1.0） |
+| `single_layers.11.` | FLOAT | 是 | 0.0 - 1.0 | 单层11的混合权重（默认：1.0） |
+| `single_layers.12.` | FLOAT | 是 | 0.0 - 1.0 | 单层12的混合权重（默认：1.0） |
+| `single_layers.13.` | FLOAT | 是 | 0.0 - 1.0 | 单层13的混合权重（默认：1.0） |
+| `single_layers.14.` | FLOAT | 是 | 0.0 - 1.0 | 单层14的混合权重（默认：1.0） |
+| `single_layers.15.` | FLOAT | 是 | 0.0 - 1.0 | 单层15的混合权重（默认：1.0） |
+| `single_layers.16.` | FLOAT | 是 | 0.0 - 1.0 | 单层16的混合权重（默认：1.0） |
+| `single_layers.17.` | FLOAT | 是 | 0.0 - 1.0 | 单层17的混合权重（默认：1.0） |
+| `single_layers.18.` | FLOAT | 是 | 0.0 - 1.0 | 单层18的混合权重（默认：1.0） |
+| `single_layers.19.` | FLOAT | 是 | 0.0 - 1.0 | 单层19的混合权重（默认：1.0） |
+| `single_layers.20.` | FLOAT | 是 | 0.0 - 1.0 | 单层20的混合权重（默认：1.0） |
+| `single_layers.21.` | FLOAT | 是 | 0.0 - 1.0 | 单层21的混合权重（默认：1.0） |
+| `single_layers.22.` | FLOAT | 是 | 0.0 - 1.0 | 单层22的混合权重（默认：1.0） |
+| `single_layers.23.` | FLOAT | 是 | 0.0 - 1.0 | 单层23的混合权重（默认：1.0） |
+| `single_layers.24.` | FLOAT | 是 | 0.0 - 1.0 | 单层24的混合权重（默认：1.0） |
+| `single_layers.25.` | FLOAT | 是 | 0.0 - 1.0 | 单层25的混合权重（默认：1.0） |
+| `single_layers.26.` | FLOAT | 是 | 0.0 - 1.0 | 单层26的混合权重（默认：1.0） |
+| `single_layers.27.` | FLOAT | 是 | 0.0 - 1.0 | 单层27的混合权重（默认：1.0） |
+| `single_layers.28.` | FLOAT | 是 | 0.0 - 1.0 | 单层28的混合权重（默认：1.0） |
+| `single_layers.29.` | FLOAT | 是 | 0.0 - 1.0 | 单层29的混合权重（默认：1.0） |
+| `single_layers.30.` | FLOAT | 是 | 0.0 - 1.0 | 单层30的混合权重（默认：1.0） |
+| `single_layers.31.` | FLOAT | 是 | 0.0 - 1.0 | 单层31的混合权重（默认：1.0） |
+| `modF.` | FLOAT | 是 | 0.0 - 1.0 | modF组件的混合权重（默认：1.0） |
+| `final_linear.` | FLOAT | 是 | 0.0 - 1.0 | 最终线性变换的混合权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 根据指定的混合权重合并两个输入模型特征的融合模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeBlocks.mdx b/zh-CN/built-in-nodes/ModelMergeBlocks.mdx
new file mode 100644
index 000000000..8f73620aa
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeBlocks.mdx
@@ -0,0 +1,25 @@
+---
+title: "ModelMergeBlocks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeBlocks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeBlocks"
+icon: "circle"
+mode: wide
+---
+
+融合模型（分层）节点旨在进行高级的模型融合操作，它允许将两个模型通过可定制的混合比例进行整合，以实现不同模型部分的融合。该节点通过基于指定参数选择性地合并两个源模型的组件，从而方便创建混合模型。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型1` | `MODEL` | 要合并的第一个模型。它作为基础模型，在其上应用第二个模型的补丁。 |
+| `模型2` | `MODEL` | 提取补丁并将其应用于第一个模型的第二个模型，基于指定的混合比例。 |
+| `输入` | `FLOAT` | 指定模型输入层的混合比例。它决定了第二个模型输入层融合到第一个模型中的程度。 |
+| `中间` | `FLOAT` | 定义模型中间层的混合比例。此参数控制模型中间层的整合程度。 |
+| `输出` | `FLOAT` | 确定模型输出层的混合比例。它通过调整第二个模型输出层的贡献来影响最终输出。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `model` | `MODEL` | 结果融合的模型，它是两个输入模型的混合体，根据指定的混合比例应用补丁。 |
diff --git a/zh-CN/built-in-nodes/ModelMergeCosmos14B.mdx b/zh-CN/built-in-nodes/ModelMergeCosmos14B.mdx
new file mode 100644
index 000000000..8bd0ffdcb
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeCosmos14B.mdx
@@ -0,0 +1,65 @@
+---
+title: "ModelMergeCosmos14B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeCosmos14B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeCosmos14B"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeCosmos14B/zh.md)
+
+ModelMergeCosmos14B 节点采用基于模块的融合方式，专门针对 Cosmos 14B 模型架构设计，用于合并两个AI模型。通过调整每个模型块和嵌入层的权重值（范围0.0至1.0），您可以混合两个模型的不同组件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型1` | MODEL | 是 | - | 要合并的第一个模型 |
+| `模型2` | MODEL | 是 | - | 要合并的第二个模型 |
+| `pos_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 位置嵌入器权重（默认：1.0） |
+| `extra_pos_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 额外位置嵌入器权重（默认：1.0） |
+| `x_embedder.` | FLOAT | 是 | 0.0 - 1.0 | X嵌入器权重（默认：1.0） |
+| `t_embedder.` | FLOAT | 是 | 0.0 - 1.0 | T嵌入器权重（默认：1.0） |
+| `affline_norm.` | FLOAT | 是 | 0.0 - 1.0 | 仿射归一化权重（默认：1.0） |
+| `blocks.block0.` | FLOAT | 是 | 0.0 - 1.0 | 块0权重（默认：1.0） |
+| `blocks.block1.` | FLOAT | 是 | 0.0 - 1.0 | 块1权重（默认：1.0） |
+| `blocks.block2.` | FLOAT | 是 | 0.0 - 1.0 | 块2权重（默认：1.0） |
+| `blocks.block3.` | FLOAT | 是 | 0.0 - 1.0 | 块3权重（默认：1.0） |
+| `blocks.block4.` | FLOAT | 是 | 0.0 - 1.0 | 块4权重（默认：1.0） |
+| `blocks.block5.` | FLOAT | 是 | 0.0 - 1.0 | 块5权重（默认：1.0） |
+| `blocks.block6.` | FLOAT | 是 | 0.0 - 1.0 | 块6权重（默认：1.0） |
+| `blocks.block7.` | FLOAT | 是 | 0.0 - 1.0 | 块7权重（默认：1.0） |
+| `blocks.block8.` | FLOAT | 是 | 0.0 - 1.0 | 块8权重（默认：1.0） |
+| `blocks.block9.` | FLOAT | 是 | 0.0 - 1.0 | 块9权重（默认：1.0） |
+| `blocks.block10.` | FLOAT | 是 | 0.0 - 1.0 | 块10权重（默认：1.0） |
+| `blocks.block11.` | FLOAT | 是 | 0.0 - 1.0 | 块11权重（默认：1.0） |
+| `blocks.block12.` | FLOAT | 是 | 0.0 - 1.0 | 块12权重（默认：1.0） |
+| `blocks.block13.` | FLOAT | 是 | 0.0 - 1.0 | 块13权重（默认：1.0） |
+| `blocks.block14.` | FLOAT | 是 | 0.0 - 1.0 | 块14权重（默认：1.0） |
+| `blocks.block15.` | FLOAT | 是 | 0.0 - 1.0 | 块15权重（默认：1.0） |
+| `blocks.block16.` | FLOAT | 是 | 0.0 - 1.0 | 块16权重（默认：1.0） |
+| `blocks.block17.` | FLOAT | 是 | 0.0 - 1.0 | 块17权重（默认：1.0） |
+| `blocks.block18.` | FLOAT | 是 | 0.0 - 1.0 | 块18权重（默认：1.0） |
+| `blocks.block19.` | FLOAT | 是 | 0.0 - 1.0 | 块19权重（默认：1.0） |
+| `blocks.block20.` | FLOAT | 是 | 0.0 - 1.0 | 块20权重（默认：1.0） |
+| `blocks.block21.` | FLOAT | 是 | 0.0 - 1.0 | 块21权重（默认：1.0） |
+| `blocks.block22.` | FLOAT | 是 | 0.0 - 1.0 | 块22权重（默认：1.0） |
+| `blocks.block23.` | FLOAT | 是 | 0.0 - 1.0 | 块23权重（默认：1.0） |
+| `blocks.block24.` | FLOAT | 是 | 0.0 - 1.0 | 块24权重（默认：1.0） |
+| `blocks.block25.` | FLOAT | 是 | 0.0 - 1.0 | 块25权重（默认：1.0） |
+| `blocks.block26.` | FLOAT | 是 | 0.0 - 1.0 | 块26权重（默认：1.0） |
+| `blocks.block27.` | FLOAT | 是 | 0.0 - 1.0 | 块27权重（默认：1.0） |
+| `blocks.block28.` | FLOAT | 是 | 0.0 - 1.0 | 块28权重（默认：1.0） |
+| `blocks.block29.` | FLOAT | 是 | 0.0 - 1.0 | 块29权重（默认：1.0） |
+| `blocks.block30.` | FLOAT | 是 | 0.0 - 1.0 | 块30权重（默认：1.0） |
+| `blocks.block31.` | FLOAT | 是 | 0.0 - 1.0 | 块31权重（默认：1.0） |
+| `blocks.block32.` | FLOAT | 是 | 0.0 - 1.0 | 块32权重（默认：1.0） |
+| `blocks.block33.` | FLOAT | 是 | 0.0 - 1.0 | 块33权重（默认：1.0） |
+| `blocks.block34.` | FLOAT | 是 | 0.0 - 1.0 | 块34权重（默认：1.0） |
+| `blocks.block35.` | FLOAT | 是 | 0.0 - 1.0 | 块35权重（默认：1.0） |
+| `final_layer.` | FLOAT | 是 | 0.0 - 1.0 | 最终层权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `model` | MODEL | 融合了两个输入模型特征的合并模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeCosmos7B.mdx b/zh-CN/built-in-nodes/ModelMergeCosmos7B.mdx
new file mode 100644
index 000000000..69a15e48f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeCosmos7B.mdx
@@ -0,0 +1,57 @@
+---
+title: "ModelMergeCosmos7B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeCosmos7B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeCosmos7B"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeCosmos7B/zh.md)
+
+ModelMergeCosmos7B 节点通过特定组件的加权混合将两个 AI 模型合并在一起。它允许通过调整位置嵌入、Transformer 块和最终层的独立权重，来精细控制模型不同部分的融合方式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型1` | MODEL | 是 | - | 要合并的第一个模型 |
+| `模型2` | MODEL | 是 | - | 要合并的第二个模型 |
+| `pos_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 位置嵌入器组件的权重（默认：1.0） |
+| `extra_pos_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 额外位置嵌入器组件的权重（默认：1.0） |
+| `x_embedder.` | FLOAT | 是 | 0.0 - 1.0 | x 嵌入器组件的权重（默认：1.0） |
+| `t_embedder.` | FLOAT | 是 | 0.0 - 1.0 | t 嵌入器组件的权重（默认：1.0） |
+| `affline_norm.` | FLOAT | 是 | 0.0 - 1.0 | 仿射归一化组件的权重（默认：1.0） |
+| `blocks.block0.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 0 的权重（默认：1.0） |
+| `blocks.block1.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 1 的权重（默认：1.0） |
+| `blocks.block2.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 2 的权重（默认：1.0） |
+| `blocks.block3.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 3 的权重（默认：1.0） |
+| `blocks.block4.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 4 的权重（默认：1.0） |
+| `blocks.block5.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 5 的权重（默认：1.0） |
+| `blocks.block6.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 6 的权重（默认：1.0） |
+| `blocks.block7.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 7 的权重（默认：1.0） |
+| `blocks.block8.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 8 的权重（默认：1.0） |
+| `blocks.block9.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 9 的权重（默认：1.0） |
+| `blocks.block10.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 10 的权重（默认：1.0） |
+| `blocks.block11.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 11 的权重（默认：1.0） |
+| `blocks.block12.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 12 的权重（默认：1.0） |
+| `blocks.block13.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 13 的权重（默认：1.0） |
+| `blocks.block14.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 14 的权重（默认：1.0） |
+| `blocks.block15.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 15 的权重（默认：1.0） |
+| `blocks.block16.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 16 的权重（默认：1.0） |
+| `blocks.block17.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 17 的权重（默认：1.0） |
+| `blocks.block18.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 18 的权重（默认：1.0） |
+| `blocks.block19.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 19 的权重（默认：1.0） |
+| `blocks.block20.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 20 的权重（默认：1.0） |
+| `blocks.block21.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 21 的权重（默认：1.0） |
+| `blocks.block22.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 22 的权重（默认：1.0） |
+| `blocks.block23.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 23 的权重（默认：1.0） |
+| `blocks.block24.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 24 的权重（默认：1.0） |
+| `blocks.block25.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 25 的权重（默认：1.0） |
+| `blocks.block26.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 26 的权重（默认：1.0） |
+| `blocks.block27.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 27 的权重（默认：1.0） |
+| `final_layer.` | FLOAT | 是 | 0.0 - 1.0 | 最终层组件的权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `model` | MODEL | 融合了两个输入模型特征的合并模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx b/zh-CN/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx
new file mode 100644
index 000000000..c6e84af56
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx
@@ -0,0 +1,66 @@
+---
+title: "ModelMergeCosmosPredict2_14B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeCosmosPredict2_14B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeCosmosPredict2_14B"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeCosmosPredict2_14B/zh.md)
+
+ModelMergeCosmosPredict2_14B 节点允许您通过调整不同模型组件的影响力来合并两个 AI 模型。它提供了对第二个模型的每个部分在最终合并模型中的贡献程度的细粒度控制，使用特定模型层和组件的混合权重。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | 是 | - | 用于合并的基础模型 |
+| `model2` | MODEL | 是 | - | 要合并到基础模型中的次要模型 |
+| `pos_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 位置嵌入器混合权重（默认：1.0） |
+| `x_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 输入嵌入器混合权重（默认：1.0） |
+| `t_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入器混合权重（默认：1.0） |
+| `t_embedding_norm.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入归一化混合权重（默认：1.0） |
+| `blocks.0.` | FLOAT | 是 | 0.0 - 1.0 | 块 0 混合权重（默认：1.0） |
+| `blocks.1.` | FLOAT | 是 | 0.0 - 1.0 | 块 1 混合权重（默认：1.0） |
+| `blocks.2.` | FLOAT | 是 | 0.0 - 1.0 | 块 2 混合权重（默认：1.0） |
+| `blocks.3.` | FLOAT | 是 | 0.0 - 1.0 | 块 3 混合权重（默认：1.0） |
+| `blocks.4.` | FLOAT | 是 | 0.0 - 1.0 | 块 4 混合权重（默认：1.0） |
+| `blocks.5.` | FLOAT | 是 | 0.0 - 1.0 | 块 5 混合权重（默认：1.0） |
+| `blocks.6.` | FLOAT | 是 | 0.0 - 1.0 | 块 6 混合权重（默认：1.0） |
+| `blocks.7.` | FLOAT | 是 | 0.0 - 1.0 | 块 7 混合权重（默认：1.0） |
+| `blocks.8.` | FLOAT | 是 | 0.0 - 1.0 | 块 8 混合权重（默认：1.0） |
+| `blocks.9.` | FLOAT | 是 | 0.0 - 1.0 | 块 9 混合权重（默认：1.0） |
+| `blocks.10.` | FLOAT | 是 | 0.0 - 1.0 | 块 10 混合权重（默认：1.0） |
+| `blocks.11.` | FLOAT | 是 | 0.0 - 1.0 | 块 11 混合权重（默认：1.0） |
+| `blocks.12.` | FLOAT | 是 | 0.0 - 1.0 | 块 12 混合权重（默认：1.0） |
+| `blocks.13.` | FLOAT | 是 | 0.0 - 1.0 | 块 13 混合权重（默认：1.0） |
+| `blocks.14.` | FLOAT | 是 | 0.0 - 1.0 | 块 14 混合权重（默认：1.0） |
+| `blocks.15.` | FLOAT | 是 | 0.0 - 1.0 | 块 15 混合权重（默认：1.0） |
+| `blocks.16.` | FLOAT | 是 | 0.0 - 1.0 | 块 16 混合权重（默认：1.0） |
+| `blocks.17.` | FLOAT | 是 | 0.0 - 1.0 | 块 17 混合权重（默认：1.0） |
+| `blocks.18.` | FLOAT | 是 | 0.0 - 1.0 | 块 18 混合权重（默认：1.0） |
+| `blocks.19.` | FLOAT | 是 | 0.0 - 1.0 | 块 19 混合权重（默认：1.0） |
+| `blocks.20.` | FLOAT | 是 | 0.0 - 1.0 | 块 20 混合权重（默认：1.0） |
+| `blocks.21.` | FLOAT | 是 | 0.0 - 1.0 | 块 21 混合权重（默认：1.0） |
+| `blocks.22.` | FLOAT | 是 | 0.0 - 1.0 | 块 22 混合权重（默认：1.0） |
+| `blocks.23.` | FLOAT | 是 | 0.0 - 1.0 | 块 23 混合权重（默认：1.0） |
+| `blocks.24.` | FLOAT | 是 | 0.0 - 1.0 | 块 24 混合权重（默认：1.0） |
+| `blocks.25.` | FLOAT | 是 | 0.0 - 1.0 | 块 25 混合权重（默认：1.0） |
+| `blocks.26.` | FLOAT | 是 | 0.0 - 1.0 | 块 26 混合权重（默认：1.0） |
+| `blocks.27.` | FLOAT | 是 | 0.0 - 1.0 | 块 27 混合权重（默认：1.0） |
+| `blocks.28.` | FLOAT | 是 | 0.0 - 1.0 | 块 28 混合权重（默认：1.0） |
+| `blocks.29.` | FLOAT | 是 | 0.0 - 1.0 | 块 29 混合权重（默认：1.0） |
+| `blocks.30.` | FLOAT | 是 | 0.0 - 1.0 | 块 30 混合权重（默认：1.0） |
+| `blocks.31.` | FLOAT | 是 | 0.0 - 1.0 | 块 31 混合权重（默认：1.0） |
+| `blocks.32.` | FLOAT | 是 | 0.0 - 1.0 | 块 32 混合权重（默认：1.0） |
+| `blocks.33.` | FLOAT | 是 | 0.0 - 1.0 | 块 33 混合权重（默认：1.0） |
+| `blocks.34.` | FLOAT | 是 | 0.0 - 1.0 | 块 34 混合权重（默认：1.0） |
+| `blocks.35.` | FLOAT | 是 | 0.0 - 1.0 | 块 35 混合权重（默认：1.0） |
+| `final_layer.` | FLOAT | 是 | 0.0 - 1.0 | 最终层混合权重（默认：1.0） |
+
+**注意：** 所有混合权重参数接受 0.0 到 1.0 之间的值，其中 0.0 表示该特定组件不包含 model2 的贡献，1.0 表示该特定组件完全使用 model2 的贡献。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 合并后的模型，结合了两个输入模型的特征 |
diff --git a/zh-CN/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx b/zh-CN/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx
new file mode 100644
index 000000000..b47b08d39
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx
@@ -0,0 +1,56 @@
+---
+title: "ModelMergeCosmosPredict2_2B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeCosmosPredict2_2B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeCosmosPredict2_2B"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeCosmosPredict2_2B/zh.md)
+
+ModelMergeCosmosPredict2_2B 节点采用基于模块化的方法合并两个扩散模型，可对不同模型组件进行细粒度控制。该节点通过调整位置嵌入器、时间嵌入器、Transformer 模块和最终层的插值权重，允许您混合两个模型的特定部分。这为精确控制每个模型中不同架构组件对最终合并结果的贡献提供了可能。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `model1` | MODEL | 是 | - | 要合并的第一个模型 |
+| `model2` | MODEL | 是 | - | 要合并的第二个模型 |
+| `pos_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 位置嵌入器插值权重（默认：1.0） |
+| `x_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 输入嵌入器插值权重（默认：1.0） |
+| `t_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入器插值权重（默认：1.0） |
+| `t_embedding_norm.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入归一化插值权重（默认：1.0） |
+| `blocks.0.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 0 插值权重（默认：1.0） |
+| `blocks.1.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 1 插值权重（默认：1.0） |
+| `blocks.2.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 2 插值权重（默认：1.0） |
+| `blocks.3.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 3 插值权重（默认：1.0） |
+| `blocks.4.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 4 插值权重（默认：1.0） |
+| `blocks.5.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 5 插值权重（默认：1.0） |
+| `blocks.6.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 6 插值权重（默认：1.0） |
+| `blocks.7.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 7 插值权重（默认：1.0） |
+| `blocks.8.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 8 插值权重（默认：1.0） |
+| `blocks.9.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 9 插值权重（默认：1.0） |
+| `blocks.10.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 10 插值权重（默认：1.0） |
+| `blocks.11.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 11 插值权重（默认：1.0） |
+| `blocks.12.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 12 插值权重（默认：1.0） |
+| `blocks.13.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 13 插值权重（默认：1.0） |
+| `blocks.14.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 14 插值权重（默认：1.0） |
+| `blocks.15.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 15 插值权重（默认：1.0） |
+| `blocks.16.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 16 插值权重（默认：1.0） |
+| `blocks.17.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 17 插值权重（默认：1.0） |
+| `blocks.18.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 18 插值权重（默认：1.0） |
+| `blocks.19.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 19 插值权重（默认：1.0） |
+| `blocks.20.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 20 插值权重（默认：1.0） |
+| `blocks.21.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 21 插值权重（默认：1.0） |
+| `blocks.22.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 22 插值权重（默认：1.0） |
+| `blocks.23.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 23 插值权重（默认：1.0） |
+| `blocks.24.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 24 插值权重（默认：1.0） |
+| `blocks.25.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 25 插值权重（默认：1.0） |
+| `blocks.26.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 26 插值权重（默认：1.0） |
+| `blocks.27.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 模块 27 插值权重（默认：1.0） |
+| `final_layer.` | FLOAT | 是 | 0.0 - 1.0 | 最终层插值权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `model` | MODEL | 融合了两个输入模型特征的合并模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeFlux1.mdx b/zh-CN/built-in-nodes/ModelMergeFlux1.mdx
new file mode 100644
index 000000000..4d319026b
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeFlux1.mdx
@@ -0,0 +1,86 @@
+---
+title: "ModelMergeFlux1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeFlux1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeFlux1"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeFlux1/zh.md)
+
+ModelMergeFlux1 节点通过加权插值的方式融合两个扩散模型的组件，实现模型合并功能。该节点支持对模型不同部分进行细粒度控制，包括图像处理块、时间嵌入层、引导机制、向量输入、文本编码器以及各种变换器块。这使得用户能够基于两个源模型创建具有定制化特征的混合模型。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型1` | MODEL | 是 | - | 要合并的第一个源模型 |
+| `模型2` | MODEL | 是 | - | 要合并的第二个源模型 |
+| `img_in.` | FLOAT | 是 | 0.0 到 1.0 | 图像输入插值权重（默认：1.0） |
+| `time_in.` | FLOAT | 是 | 0.0 到 1.0 | 时间嵌入插值权重（默认：1.0） |
+| `输入引导` | FLOAT | 是 | 0.0 到 1.0 | 引导机制插值权重（默认：1.0） |
+| `vector_in.` | FLOAT | 是 | 0.0 到 1.0 | 向量输入插值权重（默认：1.0） |
+| `txt_in.` | FLOAT | 是 | 0.0 到 1.0 | 文本编码器插值权重（默认：1.0） |
+| `double_blocks.0.` | FLOAT | 是 | 0.0 到 1.0 | 双块0插值权重（默认：1.0） |
+| `double_blocks.1.` | FLOAT | 是 | 0.0 到 1.0 | 双块1插值权重（默认：1.0） |
+| `double_blocks.2.` | FLOAT | 是 | 0.0 到 1.0 | 双块2插值权重（默认：1.0） |
+| `double_blocks.3.` | FLOAT | 是 | 0.0 到 1.0 | 双块3插值权重（默认：1.0） |
+| `double_blocks.4.` | FLOAT | 是 | 0.0 到 1.0 | 双块4插值权重（默认：1.0） |
+| `double_blocks.5.` | FLOAT | 是 | 0.0 到 1.0 | 双块5插值权重（默认：1.0） |
+| `double_blocks.6.` | FLOAT | 是 | 0.0 到 1.0 | 双块6插值权重（默认：1.0） |
+| `double_blocks.7.` | FLOAT | 是 | 0.0 到 1.0 | 双块7插值权重（默认：1.0） |
+| `double_blocks.8.` | FLOAT | 是 | 0.0 到 1.0 | 双块8插值权重（默认：1.0） |
+| `double_blocks.9.` | FLOAT | 是 | 0.0 到 1.0 | 双块9插值权重（默认：1.0） |
+| `double_blocks.10.` | FLOAT | 是 | 0.0 到 1.0 | 双块10插值权重（默认：1.0） |
+| `double_blocks.11.` | FLOAT | 是 | 0.0 到 1.0 | 双块11插值权重（默认：1.0） |
+| `double_blocks.12.` | FLOAT | 是 | 0.0 到 1.0 | 双块12插值权重（默认：1.0） |
+| `double_blocks.13.` | FLOAT | 是 | 0.0 到 1.0 | 双块13插值权重（默认：1.0） |
+| `double_blocks.14.` | FLOAT | 是 | 0.0 到 1.0 | 双块14插值权重（默认：1.0） |
+| `double_blocks.15.` | FLOAT | 是 | 0.0 到 1.0 | 双块15插值权重（默认：1.0） |
+| `double_blocks.16.` | FLOAT | 是 | 0.0 到 1.0 | 双块16插值权重（默认：1.0） |
+| `double_blocks.17.` | FLOAT | 是 | 0.0 到 1.0 | 双块17插值权重（默认：1.0） |
+| `double_blocks.18.` | FLOAT | 是 | 0.0 到 1.0 | 双块18插值权重（默认：1.0） |
+| `single_blocks.0.` | FLOAT | 是 | 0.0 到 1.0 | 单块0插值权重（默认：1.0） |
+| `single_blocks.1.` | FLOAT | 是 | 0.0 到 1.0 | 单块1插值权重（默认：1.0） |
+| `single_blocks.2.` | FLOAT | 是 | 0.0 到 1.0 | 单块2插值权重（默认：1.0） |
+| `single_blocks.3.` | FLOAT | 是 | 0.0 到 1.0 | 单块3插值权重（默认：1.0） |
+| `single_blocks.4.` | FLOAT | 是 | 0.0 到 1.0 | 单块4插值权重（默认：1.0） |
+| `single_blocks.5.` | FLOAT | 是 | 0.0 到 1.0 | 单块5插值权重（默认：1.0） |
+| `single_blocks.6.` | FLOAT | 是 | 0.0 到 1.0 | 单块6插值权重（默认：1.0） |
+| `single_blocks.7.` | FLOAT | 是 | 0.0 到 1.0 | 单块7插值权重（默认：1.0） |
+| `single_blocks.8.` | FLOAT | 是 | 0.0 到 1.0 | 单块8插值权重（默认：1.0） |
+| `single_blocks.9.` | FLOAT | 是 | 0.0 到 1.0 | 单块9插值权重（默认：1.0） |
+| `single_blocks.10.` | FLOAT | 是 | 0.0 到 1.0 | 单块10插值权重（默认：1.0） |
+| `single_blocks.11.` | FLOAT | 是 | 0.0 到 1.0 | 单块11插值权重（默认：1.0） |
+| `single_blocks.12.` | FLOAT | 是 | 0.0 到 1.0 | 单块12插值权重（默认：1.0） |
+| `single_blocks.13.` | FLOAT | 是 | 0.0 到 1.0 | 单块13插值权重（默认：1.0） |
+| `single_blocks.14.` | FLOAT | 是 | 0.0 到 1.0 | 单块14插值权重（默认：1.0） |
+| `single_blocks.15.` | FLOAT | 是 | 0.0 到 1.0 | 单块15插值权重（默认：1.0） |
+| `single_blocks.16.` | FLOAT | 是 | 0.0 到 1.0 | 单块16插值权重（默认：1.0） |
+| `single_blocks.17.` | FLOAT | 是 | 0.0 到 1.0 | 单块17插值权重（默认：1.0） |
+| `single_blocks.18.` | FLOAT | 是 | 0.0 到 1.0 | 单块18插值权重（默认：1.0） |
+| `single_blocks.19.` | FLOAT | 是 | 0.0 到 1.0 | 单块19插值权重（默认：1.0） |
+| `single_blocks.20.` | FLOAT | 是 | 0.0 到 1.0 | 单块20插值权重（默认：1.0） |
+| `single_blocks.21.` | FLOAT | 是 | 0.0 到 1.0 | 单块21插值权重（默认：1.0） |
+| `single_blocks.22.` | FLOAT | 是 | 0.0 到 1.0 | 单块22插值权重（默认：1.0） |
+| `single_blocks.23.` | FLOAT | 是 | 0.0 到 1.0 | 单块23插值权重（默认：1.0） |
+| `single_blocks.24.` | FLOAT | 是 | 0.0 到 1.0 | 单块24插值权重（默认：1.0） |
+| `single_blocks.25.` | FLOAT | 是 | 0.0 到 1.0 | 单块25插值权重（默认：1.0） |
+| `single_blocks.26.` | FLOAT | 是 | 0.0 到 1.0 | 单块26插值权重（默认：1.0） |
+| `single_blocks.27.` | FLOAT | 是 | 0.0 到 1.0 | 单块27插值权重（默认：1.0） |
+| `single_blocks.28.` | FLOAT | 是 | 0.0 到 1.0 | 单块28插值权重（默认：1.0） |
+| `single_blocks.29.` | FLOAT | 是 | 0.0 到 1.0 | 单块29插值权重（默认：1.0） |
+| `single_blocks.30.` | FLOAT | 是 | 0.0 到 1.0 | 单块30插值权重（默认：1.0） |
+| `single_blocks.31.` | FLOAT | 是 | 0.0 到 1.0 | 单块31插值权重（默认：1.0） |
+| `single_blocks.32.` | FLOAT | 是 | 0.0 到 1.0 | 单块32插值权重（默认：1.0） |
+| `single_blocks.33.` | FLOAT | 是 | 0.0 到 1.0 | 单块33插值权重（默认：1.0） |
+| `single_blocks.34.` | FLOAT | 是 | 0.0 到 1.0 | 单块34插值权重（默认：1.0） |
+| `single_blocks.35.` | FLOAT | 是 | 0.0 到 1.0 | 单块35插值权重（默认：1.0） |
+| `single_blocks.36.` | FLOAT | 是 | 0.0 到 1.0 | 单块36插值权重（默认：1.0） |
+| `single_blocks.37.` | FLOAT | 是 | 0.0 到 1.0 | 单块37插值权重（默认：1.0） |
+| `final_layer.` | FLOAT | 是 | 0.0 到 1.0 | 最终层插值权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `model` | MODEL | 融合了两个输入模型特征的合并模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeLTXV.mdx b/zh-CN/built-in-nodes/ModelMergeLTXV.mdx
new file mode 100644
index 000000000..fe5114e91
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeLTXV.mdx
@@ -0,0 +1,56 @@
+---
+title: "ModelMergeLTXV - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeLTXV node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeLTXV"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeLTXV/zh.md)
+
+ModelMergeLTXV 节点执行专为 LTXV 模型架构设计的高级模型合并操作。它允许您通过调整各种模型组件（包括 Transformer 块、投影层和其他专用模块）的插值权重，将两个不同的模型融合在一起。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型1` | MODEL | 是 | - | 要合并的第一个模型 |
+| `模型2` | MODEL | 是 | - | 要合并的第二个模型 |
+| `patchify_proj.` | FLOAT | 是 | 0.0 - 1.0 | 分块投影层的插值权重（默认：1.0） |
+| `adaln_single.` | FLOAT | 是 | 0.0 - 1.0 | 自适应层归一化单层的插值权重（默认：1.0） |
+| `caption_projection.` | FLOAT | 是 | 0.0 - 1.0 | 标题投影层的插值权重（默认：1.0） |
+| `transformer_blocks.0.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 0 的插值权重（默认：1.0） |
+| `transformer_blocks.1.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 1 的插值权重（默认：1.0） |
+| `transformer_blocks.2.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 2 的插值权重（默认：1.0） |
+| `transformer_blocks.3.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 3 的插值权重（默认：1.0） |
+| `transformer_blocks.4.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 4 的插值权重（默认：1.0） |
+| `transformer_blocks.5.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 5 的插值权重（默认：1.0） |
+| `transformer_blocks.6.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 6 的插值权重（默认：1.0） |
+| `transformer_blocks.7.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 7 的插值权重（默认：1.0） |
+| `transformer_blocks.8.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 8 的插值权重（默认：1.0） |
+| `transformer_blocks.9.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 9 的插值权重（默认：1.0） |
+| `transformer_blocks.10.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 10 的插值权重（默认：1.0） |
+| `transformer_blocks.11.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 11 的插值权重（默认：1.0） |
+| `transformer_blocks.12.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 12 的插值权重（默认：1.0） |
+| `transformer_blocks.13.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 13 的插值权重（默认：1.0） |
+| `transformer_blocks.14.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 14 的插值权重（默认：1.0） |
+| `transformer_blocks.15.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 15 的插值权重（默认：1.0） |
+| `transformer_blocks.16.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 16 的插值权重（默认：1.0） |
+| `transformer_blocks.17.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 17 的插值权重（默认：1.0） |
+| `transformer_blocks.18.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 18 的插值权重（默认：1.0） |
+| `transformer_blocks.19.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 19 的插值权重（默认：1.0） |
+| `transformer_blocks.20.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 20 的插值权重（默认：1.0） |
+| `transformer_blocks.21.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 21 的插值权重（默认：1.0） |
+| `transformer_blocks.22.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 22 的插值权重（默认：1.0） |
+| `transformer_blocks.23.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 23 的插值权重（默认：1.0） |
+| `transformer_blocks.24.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 24 的插值权重（默认：1.0） |
+| `transformer_blocks.25.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 25 的插值权重（默认：1.0） |
+| `transformer_blocks.26.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 26 的插值权重（默认：1.0） |
+| `transformer_blocks.27.` | FLOAT | 是 | 0.0 - 1.0 | Transformer 块 27 的插值权重（默认：1.0） |
+| `scale_shift_table` | FLOAT | 是 | 0.0 - 1.0 | 尺度偏移表的插值权重（默认：1.0） |
+| `proj_out.` | FLOAT | 是 | 0.0 - 1.0 | 投影输出层的插值权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 根据指定的插值权重合并两个输入模型特征的融合模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeMochiPreview.mdx b/zh-CN/built-in-nodes/ModelMergeMochiPreview.mdx
new file mode 100644
index 000000000..02666a65b
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeMochiPreview.mdx
@@ -0,0 +1,76 @@
+---
+title: "ModelMergeMochiPreview - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeMochiPreview node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeMochiPreview"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeMochiPreview/zh.md)
+
+此节点采用基于块的方法合并两个AI模型，能够对不同模型组件进行细粒度控制。它允许您通过调整特定部分的插值权重来混合模型，包括位置频率、嵌入层和各个Transformer块。合并过程根据指定的权重值，将两个输入模型的架构和参数进行组合。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型1` | MODEL | 是 | - | 要合并的第一个模型 |
+| `模型2` | MODEL | 是 | - | 要合并的第二个模型 |
+| `pos_frequencies.` | FLOAT | 是 | 0.0 - 1.0 | 位置频率插值权重（默认：1.0） |
+| `t_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入器插值权重（默认：1.0） |
+| `t5_y_embedder.` | FLOAT | 是 | 0.0 - 1.0 | T5-Y嵌入器插值权重（默认：1.0） |
+| `t5_yproj.` | FLOAT | 是 | 0.0 - 1.0 | T5-Y投影插值权重（默认：1.0） |
+| `blocks.0.` | FLOAT | 是 | 0.0 - 1.0 | 块0插值权重（默认：1.0） |
+| `blocks.1.` | FLOAT | 是 | 0.0 - 1.0 | 块1插值权重（默认：1.0） |
+| `blocks.2.` | FLOAT | 是 | 0.0 - 1.0 | 块2插值权重（默认：1.0） |
+| `blocks.3.` | FLOAT | 是 | 0.0 - 1.0 | 块3插值权重（默认：1.0） |
+| `blocks.4.` | FLOAT | 是 | 0.0 - 1.0 | 块4插值权重（默认：1.0） |
+| `blocks.5.` | FLOAT | 是 | 0.0 - 1.0 | 块5插值权重（默认：1.0） |
+| `blocks.6.` | FLOAT | 是 | 0.0 - 1.0 | 块6插值权重（默认：1.0） |
+| `blocks.7.` | FLOAT | 是 | 0.0 - 1.0 | 块7插值权重（默认：1.0） |
+| `blocks.8.` | FLOAT | 是 | 0.0 - 1.0 | 块8插值权重（默认：1.0） |
+| `blocks.9.` | FLOAT | 是 | 0.0 - 1.0 | 块9插值权重（默认：1.0） |
+| `blocks.10.` | FLOAT | 是 | 0.0 - 1.0 | 块10插值权重（默认：1.0） |
+| `blocks.11.` | FLOAT | 是 | 0.0 - 1.0 | 块11插值权重（默认：1.0） |
+| `blocks.12.` | FLOAT | 是 | 0.0 - 1.0 | 块12插值权重（默认：1.0） |
+| `blocks.13.` | FLOAT | 是 | 0.0 - 1.0 | 块13插值权重（默认：1.0） |
+| `blocks.14.` | FLOAT | 是 | 0.0 - 1.0 | 块14插值权重（默认：1.0） |
+| `blocks.15.` | FLOAT | 是 | 0.0 - 1.0 | 块15插值权重（默认：1.0） |
+| `blocks.16.` | FLOAT | 是 | 0.0 - 1.0 | 块16插值权重（默认：1.0） |
+| `blocks.17.` | FLOAT | 是 | 0.0 - 1.0 | 块17插值权重（默认：1.0） |
+| `blocks.18.` | FLOAT | 是 | 0.0 - 1.0 | 块18插值权重（默认：1.0） |
+| `blocks.19.` | FLOAT | 是 | 0.0 - 1.0 | 块19插值权重（默认：1.0） |
+| `blocks.20.` | FLOAT | 是 | 0.0 - 1.0 | 块20插值权重（默认：1.0） |
+| `blocks.21.` | FLOAT | 是 | 0.0 - 1.0 | 块21插值权重（默认：1.0） |
+| `blocks.22.` | FLOAT | 是 | 0.0 - 1.0 | 块22插值权重（默认：1.0） |
+| `blocks.23.` | FLOAT | 是 | 0.0 - 1.0 | 块23插值权重（默认：1.0） |
+| `blocks.24.` | FLOAT | 是 | 0.0 - 1.0 | 块24插值权重（默认：1.0） |
+| `blocks.25.` | FLOAT | 是 | 0.0 - 1.0 | 块25插值权重（默认：1.0） |
+| `blocks.26.` | FLOAT | 是 | 0.0 - 1.0 | 块26插值权重（默认：1.0） |
+| `blocks.27.` | FLOAT | 是 | 0.0 - 1.0 | 块27插值权重（默认：1.0） |
+| `blocks.28.` | FLOAT | 是 | 0.0 - 1.0 | 块28插值权重（默认：1.0） |
+| `blocks.29.` | FLOAT | 是 | 0.0 - 1.0 | 块29插值权重（默认：1.0） |
+| `blocks.30.` | FLOAT | 是 | 0.0 - 1.0 | 块30插值权重（默认：1.0） |
+| `blocks.31.` | FLOAT | 是 | 0.0 - 1.0 | 块31插值权重（默认：1.0） |
+| `blocks.32.` | FLOAT | 是 | 0.0 - 1.0 | 块32插值权重（默认：1.0） |
+| `blocks.33.` | FLOAT | 是 | 0.0 - 1.0 | 块33插值权重（默认：1.0） |
+| `blocks.34.` | FLOAT | 是 | 0.0 - 1.0 | 块34插值权重（默认：1.0） |
+| `blocks.35.` | FLOAT | 是 | 0.0 - 1.0 | 块35插值权重（默认：1.0） |
+| `blocks.36.` | FLOAT | 是 | 0.0 - 1.0 | 块36插值权重（默认：1.0） |
+| `blocks.37.` | FLOAT | 是 | 0.0 - 1.0 | 块37插值权重（默认：1.0） |
+| `blocks.38.` | FLOAT | 是 | 0.0 - 1.0 | 块38插值权重（默认：1.0） |
+| `blocks.39.` | FLOAT | 是 | 0.0 - 1.0 | 块39插值权重（默认：1.0） |
+| `blocks.40.` | FLOAT | 是 | 0.0 - 1.0 | 块40插值权重（默认：1.0） |
+| `blocks.41.` | FLOAT | 是 | 0.0 - 1.0 | 块41插值权重（默认：1.0） |
+| `blocks.42.` | FLOAT | 是 | 0.0 - 1.0 | 块42插值权重（默认：1.0） |
+| `blocks.43.` | FLOAT | 是 | 0.0 - 1.0 | 块43插值权重（默认：1.0） |
+| `blocks.44.` | FLOAT | 是 | 0.0 - 1.0 | 块44插值权重（默认：1.0） |
+| `blocks.45.` | FLOAT | 是 | 0.0 - 1.0 | 块45插值权重（默认：1.0） |
+| `blocks.46.` | FLOAT | 是 | 0.0 - 1.0 | 块46插值权重（默认：1.0） |
+| `blocks.47.` | FLOAT | 是 | 0.0 - 1.0 | 块47插值权重（默认：1.0） |
+| `final_layer.` | FLOAT | 是 | 0.0 - 1.0 | 最终层插值权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 根据指定权重合并两个输入模型特征后的融合模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeQwenImage.mdx b/zh-CN/built-in-nodes/ModelMergeQwenImage.mdx
new file mode 100644
index 000000000..4c6e157a1
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeQwenImage.mdx
@@ -0,0 +1,30 @@
+---
+title: "ModelMergeQwenImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeQwenImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeQwenImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeQwenImage/zh.md)
+
+ModelMergeQwenImage 节点通过以可调节的权重组合两个 AI 模型的组件来合并它们。该节点允许您混合 Qwen 图像模型的特定部分，包括 Transformer 块、位置嵌入和文本处理组件。您可以控制每个模型在合并结果的不同部分中所具有的影响力。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | 是 | - | 要合并的第一个模型（默认：无） |
+| `model2` | MODEL | 是 | - | 要合并的第二个模型（默认：无） |
+| `pos_embeds.` | FLOAT | 是 | 0.0 到 1.0 | 位置嵌入混合的权重（默认：1.0） |
+| `img_in.` | FLOAT | 是 | 0.0 到 1.0 | 图像输入处理混合的权重（默认：1.0） |
+| `txt_norm.` | FLOAT | 是 | 0.0 到 1.0 | 文本归一化混合的权重（默认：1.0） |
+| `txt_in.` | FLOAT | 是 | 0.0 到 1.0 | 文本输入处理混合的权重（默认：1.0） |
+| `time_text_embed.` | FLOAT | 是 | 0.0 到 1.0 | 时间和文本嵌入混合的权重（默认：1.0） |
+| `transformer_blocks.0.` 到 `transformer_blocks.59.` | FLOAT | 是 | 0.0 到 1.0 | 每个 Transformer 块混合的权重（默认：1.0） |
+| `proj_out.` | FLOAT | 是 | 0.0 到 1.0 | 输出投影混合的权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 合并后的模型，包含来自两个输入模型组件按指定权重组合的结果 |
diff --git a/zh-CN/built-in-nodes/ModelMergeSD1.mdx b/zh-CN/built-in-nodes/ModelMergeSD1.mdx
new file mode 100644
index 000000000..2022abe8b
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeSD1.mdx
@@ -0,0 +1,53 @@
+---
+title: "ModelMergeSD1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSD1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSD1"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeSD1/zh.md)
+
+ModelMergeSD1 节点允许您通过调整不同模型组件的影响力，将两个 Stable Diffusion 1.x 模型融合在一起。它提供了对时间嵌入、标签嵌入以及所有输入块、中间块和输出块的独立控制，从而能够针对特定用例进行精细调整的模型融合。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型1` | MODEL | 是 | - | 要融合的第一个模型 |
+| `模型2` | MODEL | 是 | - | 要融合的第二个模型 |
+| `time_embed.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入层融合权重（默认：1.0） |
+| `label_emb.` | FLOAT | 是 | 0.0 - 1.0 | 标签嵌入层融合权重（默认：1.0） |
+| `input_blocks.0.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 0 融合权重（默认：1.0） |
+| `input_blocks.1.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 1 融合权重（默认：1.0） |
+| `input_blocks.2.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 2 融合权重（默认：1.0） |
+| `input_blocks.3.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 3 融合权重（默认：1.0） |
+| `input_blocks.4.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 4 融合权重（默认：1.0） |
+| `input_blocks.5.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 5 融合权重（默认：1.0） |
+| `input_blocks.6.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 6 融合权重（默认：1.0） |
+| `input_blocks.7.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 7 融合权重（默认：1.0） |
+| `input_blocks.8.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 8 融合权重（默认：1.0） |
+| `input_blocks.9.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 9 融合权重（默认：1.0） |
+| `input_blocks.10.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 10 融合权重（默认：1.0） |
+| `input_blocks.11.` | FLOAT | 是 | 0.0 - 1.0 | 输入块 11 融合权重（默认：1.0） |
+| `middle_block.0.` | FLOAT | 是 | 0.0 - 1.0 | 中间块 0 融合权重（默认：1.0） |
+| `middle_block.1.` | FLOAT | 是 | 0.0 - 1.0 | 中间块 1 融合权重（默认：1.0） |
+| `middle_block.2.` | FLOAT | 是 | 0.0 - 1.0 | 中间块 2 融合权重（默认：1.0） |
+| `output_blocks.0.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 0 融合权重（默认：1.0） |
+| `output_blocks.1.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 1 融合权重（默认：1.0） |
+| `output_blocks.2.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 2 融合权重（默认：1.0） |
+| `output_blocks.3.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 3 融合权重（默认：1.0） |
+| `output_blocks.4.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 4 融合权重（默认：1.0） |
+| `output_blocks.5.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 5 融合权重（默认：1.0） |
+| `output_blocks.6.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 6 融合权重（默认：1.0） |
+| `output_blocks.7.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 7 融合权重（默认：1.0） |
+| `output_blocks.8.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 8 融合权重（默认：1.0） |
+| `output_blocks.9.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 9 融合权重（默认：1.0） |
+| `output_blocks.10.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 10 融合权重（默认：1.0） |
+| `output_blocks.11.` | FLOAT | 是 | 0.0 - 1.0 | 输出块 11 融合权重（默认：1.0） |
+| `out.` | FLOAT | 是 | 0.0 - 1.0 | 输出层融合权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | 融合了两个输入模型特征的合并模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeSD35_Large.mdx b/zh-CN/built-in-nodes/ModelMergeSD35_Large.mdx
new file mode 100644
index 000000000..3eb116761
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeSD35_Large.mdx
@@ -0,0 +1,69 @@
+---
+title: "ModelMergeSD35_Large - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSD35_Large node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSD35_Large"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeSD35_Large/zh.md)
+
+ModelMergeSD35_Large 节点允许您通过调整不同模型组件的影响力，将两个 Stable Diffusion 3.5 Large 模型融合在一起。它提供了精确控制第二个模型的每个部分对最终合并模型的贡献程度，从嵌入层到联合块和最终层。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型1` | MODEL | 是 | - | 作为合并基础的主模型 |
+| `模型2` | MODEL | 是 | - | 其组件将被混合到主模型中的辅助模型 |
+| `pos_embed.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的位置嵌入有多少被混合到合并模型中（默认：1.0） |
+| `x_embedder.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的 x 嵌入器有多少被混合到合并模型中（默认：1.0） |
+| `context_embedder.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的上下文嵌入器有多少被混合到合并模型中（默认：1.0） |
+| `y_embedder.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的 y 嵌入器有多少被混合到合并模型中（默认：1.0） |
+| `t_embedder.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的 t 嵌入器有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.0.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 0 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.1.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 1 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.2.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 2 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.3.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 3 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.4.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 4 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.5.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 5 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.6.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 6 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.7.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 7 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.8.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 8 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.9.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 9 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.10.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 10 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.11.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 11 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.12.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 12 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.13.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 13 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.14.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 14 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.15.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 15 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.16.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 16 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.17.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 17 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.18.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 18 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.19.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 19 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.20.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 20 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.21.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 21 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.22.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 22 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.23.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 23 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.24.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 24 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.25.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 25 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.26.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 26 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.27.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 27 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.28.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 28 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.29.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 29 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.30.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 30 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.31.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 31 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.32.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 32 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.33.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 33 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.34.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 34 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.35.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 35 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.36.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 36 有多少被混合到合并模型中（默认：1.0） |
+| `joint_blocks.37.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的联合块 37 有多少被混合到合并模型中（默认：1.0） |
+| `final_layer.` | FLOAT | 是 | 0.0 到 1.0 | 控制 model2 的最终层有多少被混合到合并模型中（默认：1.0） |
+
+**注意：** 所有混合参数接受从 0.0 到 1.0 的值，其中 0.0 表示该特定组件不包含 model2 的贡献，1.0 表示完全使用 model2 的该组件。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 根据指定的混合参数，结合了两个输入模型特征的最终合并模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeSD3_2B.mdx b/zh-CN/built-in-nodes/ModelMergeSD3_2B.mdx
new file mode 100644
index 000000000..3c417fdd9
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeSD3_2B.mdx
@@ -0,0 +1,53 @@
+---
+title: "ModelMergeSD3_2B - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSD3_2B node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSD3_2B"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeSD3_2B/zh.md)
+
+ModelMergeSD3_2B 节点允许您通过以可调节的权重混合两个 Stable Diffusion 3 2B 模型的组件来合并它们。该节点提供了对嵌入层和 Transformer 块的独立控制，从而能够为专门的生成任务进行精细调整的模型组合。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型1` | MODEL | 是 | - | 要合并的第一个模型 |
+| `模型2` | MODEL | 是 | - | 要合并的第二个模型 |
+| `pos_embed.` | FLOAT | 是 | 0.0 - 1.0 | 位置嵌入插值权重（默认：1.0） |
+| `x_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 输入嵌入插值权重（默认：1.0） |
+| `context_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 上下文嵌入插值权重（默认：1.0） |
+| `y_embedder.` | FLOAT | 是 | 0.0 - 1.0 | Y 嵌入插值权重（默认：1.0） |
+| `t_embedder.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入插值权重（默认：1.0） |
+| `joint_blocks.0.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 0 插值权重（默认：1.0） |
+| `joint_blocks.1.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 1 插值权重（默认：1.0） |
+| `joint_blocks.2.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 2 插值权重（默认：1.0） |
+| `joint_blocks.3.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 3 插值权重（默认：1.0） |
+| `joint_blocks.4.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 4 插值权重（默认：1.0） |
+| `joint_blocks.5.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 5 插值权重（默认：1.0） |
+| `joint_blocks.6.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 6 插值权重（默认：1.0） |
+| `joint_blocks.7.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 7 插值权重（默认：1.0） |
+| `joint_blocks.8.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 8 插值权重（默认：1.0） |
+| `joint_blocks.9.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 9 插值权重（默认：1.0） |
+| `joint_blocks.10.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 10 插值权重（默认：1.0） |
+| `joint_blocks.11.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 11 插值权重（默认：1.0） |
+| `joint_blocks.12.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 12 插值权重（默认：1.0） |
+| `joint_blocks.13.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 13 插值权重（默认：1.0） |
+| `joint_blocks.14.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 14 插值权重（默认：1.0） |
+| `joint_blocks.15.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 15 插值权重（默认：1.0） |
+| `joint_blocks.16.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 16 插值权重（默认：1.0） |
+| `joint_blocks.17.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 17 插值权重（默认：1.0） |
+| `joint_blocks.18.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 18 插值权重（默认：1.0） |
+| `joint_blocks.19.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 19 插值权重（默认：1.0） |
+| `joint_blocks.20.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 20 插值权重（默认：1.0） |
+| `joint_blocks.21.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 21 插值权重（默认：1.0） |
+| `joint_blocks.22.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 22 插值权重（默认：1.0） |
+| `joint_blocks.23.` | FLOAT | 是 | 0.0 - 1.0 | 联合块 23 插值权重（默认：1.0） |
+| `final_layer.` | FLOAT | 是 | 0.0 - 1.0 | 最终层插值权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 合并后的模型，结合了两个输入模型的特征 |
diff --git a/zh-CN/built-in-nodes/ModelMergeSDXL.mdx b/zh-CN/built-in-nodes/ModelMergeSDXL.mdx
new file mode 100644
index 000000000..f1c8940b5
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeSDXL.mdx
@@ -0,0 +1,47 @@
+---
+title: "ModelMergeSDXL - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSDXL node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSDXL"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeSDXL/zh.md)
+
+ModelMergeSDXL 节点允许您通过调整两个模型在架构不同部分的影响力，将两个 SDXL 模型融合在一起。您可以控制每个模型对时间嵌入、标签嵌入以及模型结构内各个块的贡献程度，从而创建一个融合了两个输入模型特性的混合模型。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型1` | MODEL | 是 | - | 要合并的第一个 SDXL 模型 |
+| `模型2` | MODEL | 是 | - | 要合并的第二个 SDXL 模型 |
+| `time_embed.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入层的融合权重（默认：1.0） |
+| `label_emb.` | FLOAT | 是 | 0.0 - 1.0 | 标签嵌入层的融合权重（默认：1.0） |
+| `input_blocks.0` | FLOAT | 是 | 0.0 - 1.0 | 输入块 0 的融合权重（默认：1.0） |
+| `input_blocks.1` | FLOAT | 是 | 0.0 - 1.0 | 输入块 1 的融合权重（默认：1.0） |
+| `input_blocks.2` | FLOAT | 是 | 0.0 - 1.0 | 输入块 2 的融合权重（默认：1.0） |
+| `input_blocks.3` | FLOAT | 是 | 0.0 - 1.0 | 输入块 3 的融合权重（默认：1.0） |
+| `input_blocks.4` | FLOAT | 是 | 0.0 - 1.0 | 输入块 4 的融合权重（默认：1.0） |
+| `input_blocks.5` | FLOAT | 是 | 0.0 - 1.0 | 输入块 5 的融合权重（默认：1.0） |
+| `input_blocks.6` | FLOAT | 是 | 0.0 - 1.0 | 输入块 6 的融合权重（默认：1.0） |
+| `input_blocks.7` | FLOAT | 是 | 0.0 - 1.0 | 输入块 7 的融合权重（默认：1.0） |
+| `input_blocks.8` | FLOAT | 是 | 0.0 - 1.0 | 输入块 8 的融合权重（默认：1.0） |
+| `middle_block.0` | FLOAT | 是 | 0.0 - 1.0 | 中间块 0 的融合权重（默认：1.0） |
+| `middle_block.1` | FLOAT | 是 | 0.0 - 1.0 | 中间块 1 的融合权重（默认：1.0） |
+| `middle_block.2` | FLOAT | 是 | 0.0 - 1.0 | 中间块 2 的融合权重（默认：1.0） |
+| `output_blocks.0` | FLOAT | 是 | 0.0 - 1.0 | 输出块 0 的融合权重（默认：1.0） |
+| `output_blocks.1` | FLOAT | 是 | 0.0 - 1.0 | 输出块 1 的融合权重（默认：1.0） |
+| `output_blocks.2` | FLOAT | 是 | 0.0 - 1.0 | 输出块 2 的融合权重（默认：1.0） |
+| `output_blocks.3` | FLOAT | 是 | 0.0 - 1.0 | 输出块 3 的融合权重（默认：1.0） |
+| `output_blocks.4` | FLOAT | 是 | 0.0 - 1.0 | 输出块 4 的融合权重（默认：1.0） |
+| `output_blocks.5` | FLOAT | 是 | 0.0 - 1.0 | 输出块 5 的融合权重（默认：1.0） |
+| `output_blocks.6` | FLOAT | 是 | 0.0 - 1.0 | 输出块 6 的融合权重（默认：1.0） |
+| `output_blocks.7` | FLOAT | 是 | 0.0 - 1.0 | 输出块 7 的融合权重（默认：1.0） |
+| `output_blocks.8` | FLOAT | 是 | 0.0 - 1.0 | 输出块 8 的融合权重（默认：1.0） |
+| `out.` | FLOAT | 是 | 0.0 - 1.0 | 输出层的融合权重（默认：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 融合了两个输入模型特性的 SDXL 模型 |
diff --git a/zh-CN/built-in-nodes/ModelMergeSimple.mdx b/zh-CN/built-in-nodes/ModelMergeSimple.mdx
new file mode 100644
index 000000000..85c1d3742
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeSimple.mdx
@@ -0,0 +1,24 @@
+---
+title: "ModelMergeSimple - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSimple node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSimple"
+icon: "circle"
+mode: wide
+---
+
+这个节点的作用主要是将两个合并成一个模型作为后续的绘图模型输出，当你想使用两个模型的时候，你想要融合他们的特征作为后续的输出时，这个节点就非常有用。
+其中 `ratio` 参数的作用是决定融合的比例，当这个值为 1 时，则输出的模型为 100% 的`model1`,当这个值为 0 时，则输出的模型为100% 的  `model2`
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型1` | `MODEL` | 要合并的第一个模型。它作为基础模型，在其上应用第二个模型的补丁。 |
+| `模型2` | `MODEL` | 应用其补丁到第一个模型的第二个模型，受指定比例的影响。 |
+| `比例`   | `FLOAT`  | 当这个值为 1 时，则输出的模型为 100% 的`模型1`,当这个值为 0 时，则输出的模型为100% 的  `模型2` |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `model`  | MODEL    | 结果融合的模型，根据指定比例整合了两个输入模型的元素。 |
diff --git a/zh-CN/built-in-nodes/ModelMergeSubtract.mdx b/zh-CN/built-in-nodes/ModelMergeSubtract.mdx
new file mode 100644
index 000000000..d471a1b48
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeSubtract.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelMergeSubtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeSubtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeSubtract"
+icon: "circle"
+mode: wide
+---
+
+这个节点设计用于高级模型融合操作，特别是根据指定的乘数从一个模型中减去另一个模型的参数。它允许通过调整一个模型参数对另一个模型的影响来定制模型行为，从而方便创建新的混合模型。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型1` | `MODEL` | 作为基础模型，其参数将被减去。 |
+| `模型2` | `MODEL` | 其参数将从基础模型中减去的模型。 |
+| `乘数` | `FLOAT` | 一个浮点值，用于缩放对基础模型参数的减法效果。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `model` | `MODEL` | 在减去一个模型的参数并乘以乘数后的得到的模型。 |
diff --git a/zh-CN/built-in-nodes/ModelMergeWAN2_1.mdx b/zh-CN/built-in-nodes/ModelMergeWAN2_1.mdx
new file mode 100644
index 000000000..53aa3c0e3
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelMergeWAN2_1.mdx
@@ -0,0 +1,71 @@
+---
+title: "ModelMergeWAN2_1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelMergeWAN2_1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelMergeWAN2_1"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeWAN2_1/zh.md)
+
+ModelMergeWAN2_1 节点通过加权平均的方式融合两个模型的组件来实现模型合并。它支持不同的模型规模，包括包含30个模块的1.3B模型和包含40个模块的14B模型，并对包含额外图像嵌入组件的图像转视频模型进行特殊处理。模型的每个组件都可以单独设置权重，以控制两个输入模型之间的融合比例。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model1` | MODEL | 是 | - | 要合并的第一个模型 |
+| `model2` | MODEL | 是 | - | 要合并的第二个模型 |
+| `patch_embedding.` | FLOAT | 是 | 0.0 - 1.0 | 补丁嵌入组件的权重（默认：1.0） |
+| `time_embedding.` | FLOAT | 是 | 0.0 - 1.0 | 时间嵌入组件的权重（默认：1.0） |
+| `time_projection.` | FLOAT | 是 | 0.0 - 1.0 | 时间投影组件的权重（默认：1.0） |
+| `text_embedding.` | FLOAT | 是 | 0.0 - 1.0 | 文本嵌入组件的权重（默认：1.0） |
+| `img_emb.` | FLOAT | 是 | 0.0 - 1.0 | 图像嵌入组件的权重，用于图像转视频模型（默认：1.0） |
+| `blocks.0.` | FLOAT | 是 | 0.0 - 1.0 | 模块0的权重（默认：1.0） |
+| `blocks.1.` | FLOAT | 是 | 0.0 - 1.0 | 模块1的权重（默认：1.0） |
+| `blocks.2.` | FLOAT | 是 | 0.0 - 1.0 | 模块2的权重（默认：1.0） |
+| `blocks.3.` | FLOAT | 是 | 0.0 - 1.0 | 模块3的权重（默认：1.0） |
+| `blocks.4.` | FLOAT | 是 | 0.0 - 1.0 | 模块4的权重（默认：1.0） |
+| `blocks.5.` | FLOAT | 是 | 0.0 - 1.0 | 模块5的权重（默认：1.0） |
+| `blocks.6.` | FLOAT | 是 | 0.0 - 1.0 | 模块6的权重（默认：1.0） |
+| `blocks.7.` | FLOAT | 是 | 0.0 - 1.0 | 模块7的权重（默认：1.0） |
+| `blocks.8.` | FLOAT | 是 | 0.0 - 1.0 | 模块8的权重（默认：1.0） |
+| `blocks.9.` | FLOAT | 是 | 0.0 - 1.0 | 模块9的权重（默认：1.0） |
+| `blocks.10.` | FLOAT | 是 | 0.0 - 1.0 | 模块10的权重（默认：1.0） |
+| `blocks.11.` | FLOAT | 是 | 0.0 - 1.0 | 模块11的权重（默认：1.0） |
+| `blocks.12.` | FLOAT | 是 | 0.0 - 1.0 | 模块12的权重（默认：1.0） |
+| `blocks.13.` | FLOAT | 是 | 0.0 - 1.0 | 模块13的权重（默认：1.0） |
+| `blocks.14.` | FLOAT | 是 | 0.0 - 1.0 | 模块14的权重（默认：1.0） |
+| `blocks.15.` | FLOAT | 是 | 0.0 - 1.0 | 模块15的权重（默认：1.0） |
+| `blocks.16.` | FLOAT | 是 | 0.0 - 1.0 | 模块16的权重（默认：1.0） |
+| `blocks.17.` | FLOAT | 是 | 0.0 - 1.0 | 模块17的权重（默认：1.0） |
+| `blocks.18.` | FLOAT | 是 | 0.0 - 1.0 | 模块18的权重（默认：1.0） |
+| `blocks.19.` | FLOAT | 是 | 0.0 - 1.0 | 模块19的权重（默认：1.0） |
+| `blocks.20.` | FLOAT | 是 | 0.0 - 1.0 | 模块20的权重（默认：1.0） |
+| `blocks.21.` | FLOAT | 是 | 0.0 - 1.0 | 模块21的权重（默认：1.0） |
+| `blocks.22.` | FLOAT | 是 | 0.0 - 1.0 | 模块22的权重（默认：1.0） |
+| `blocks.23.` | FLOAT | 是 | 0.0 - 1.0 | 模块23的权重（默认：1.0） |
+| `blocks.24.` | FLOAT | 是 | 0.0 - 1.0 | 模块24的权重（默认：1.0） |
+| `blocks.25.` | FLOAT | 是 | 0.0 - 1.0 | 模块25的权重（默认：1.0） |
+| `blocks.26.` | FLOAT | 是 | 0.0 - 1.0 | 模块26的权重（默认：1.0） |
+| `blocks.27.` | FLOAT | 是 | 0.0 - 1.0 | 模块27的权重（默认：1.0） |
+| `blocks.28.` | FLOAT | 是 | 0.0 - 1.0 | 模块28的权重（默认：1.0） |
+| `blocks.29.` | FLOAT | 是 | 0.0 - 1.0 | 模块29的权重（默认：1.0） |
+| `blocks.30.` | FLOAT | 是 | 0.0 - 1.0 | 模块30的权重（默认：1.0） |
+| `blocks.31.` | FLOAT | 是 | 0.0 - 1.0 | 模块31的权重（默认：1.0） |
+| `blocks.32.` | FLOAT | 是 | 0.0 - 1.0 | 模块32的权重（默认：1.0） |
+| `blocks.33.` | FLOAT | 是 | 0.0 - 1.0 | 模块33的权重（默认：1.0） |
+| `blocks.34.` | FLOAT | 是 | 0.0 - 1.0 | 模块34的权重（默认：1.0） |
+| `blocks.35.` | FLOAT | 是 | 0.0 - 1.0 | 模块35的权重（默认：1.0） |
+| `blocks.36.` | FLOAT | 是 | 0.0 - 1.0 | 模块36的权重（默认：1.0） |
+| `blocks.37.` | FLOAT | 是 | 0.0 - 1.0 | 模块37的权重（默认：1.0） |
+| `blocks.38.` | FLOAT | 是 | 0.0 - 1.0 | 模块38的权重（默认：1.0） |
+| `blocks.39.` | FLOAT | 是 | 0.0 - 1.0 | 模块39的权重（默认：1.0） |
+| `head.` | FLOAT | 是 | 0.0 - 1.0 | 头部组件的权重（默认：1.0） |
+
+**注意：** 所有权重参数使用0.0到1.0的范围，步长为0.01。该节点最多支持40个模块以适应不同的模型规模，其中1.3B模型使用30个模块，14B模型使用40个模块。`img_emb.` 参数专门用于图像转视频模型。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 根据指定权重合并两个输入模型组件后得到的融合模型 |
diff --git a/zh-CN/built-in-nodes/ModelPatchLoader.mdx b/zh-CN/built-in-nodes/ModelPatchLoader.mdx
new file mode 100644
index 000000000..48266fdba
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelPatchLoader.mdx
@@ -0,0 +1,24 @@
+---
+title: "ModelPatchLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelPatchLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelPatchLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelPatchLoader/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelPatchLoader/en.md)
+
+ModelPatchLoader 节点从 model_patches 文件夹加载专门的模型补丁。它会自动检测补丁文件的类型并加载相应的模型架构，然后将其封装在 ModelPatcher 中以供工作流使用。此节点支持不同的补丁类型，包括 controlnet 块和特征嵌入器模型。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `name` | STRING | 是 | model_patches 文件夹中所有可用的模型补丁文件 | 要从 model_patches 目录加载的模型补丁文件名 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `MODEL_PATCH` | MODEL_PATCH | 已加载的模型补丁，封装在 ModelPatcher 中供工作流使用 |
diff --git a/zh-CN/built-in-nodes/ModelSamplingAuraFlow.mdx b/zh-CN/built-in-nodes/ModelSamplingAuraFlow.mdx
new file mode 100644
index 000000000..8f5fe2801
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSamplingAuraFlow.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelSamplingAuraFlow - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingAuraFlow node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingAuraFlow"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingAuraFlow/zh.md)
+
+ModelSamplingAuraFlow 节点为扩散模型应用专门的采样配置，特别针对 AuraFlow 模型架构设计。该节点通过应用偏移参数来调整采样分布，从而修改模型的采样行为。此节点继承自 SD3 模型采样框架，并提供对采样过程的精细控制。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用 AuraFlow 采样配置的扩散模型 |
+| `移位` | FLOAT | 是 | 0.0 - 100.0 | 应用于采样分布的偏移值（默认值：1.73） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 已应用 AuraFlow 采样配置的修改后模型 |
diff --git a/zh-CN/built-in-nodes/ModelSamplingContinuousEDM.mdx b/zh-CN/built-in-nodes/ModelSamplingContinuousEDM.mdx
new file mode 100644
index 000000000..175f38d03
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSamplingContinuousEDM.mdx
@@ -0,0 +1,26 @@
+---
+title: "ModelSamplingContinuousEDM - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingContinuousEDM node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingContinuousEDM"
+icon: "circle"
+mode: wide
+---
+
+该节点旨在通过集成连续 EDM（基于能量的扩散模型）采样技术来增强模型的采样能力。它允许动态调整模型采样过程中的噪声水平，提供对生成质量和多样性的更精细控制。
+
+## 输入
+
+### 必填
+
+| 参数名称 | 数据类型 | 作用                                                         |
+| -------- | -------- | ------------------------------------------------------------ |
+| `模型`  | MODEL    | 需要增强连续 EDM 采样能力的模型。它作为应用高级采样技术的基石。 |
+| `采样` | COMBO[STRING] | 指定要应用的采样类型，可以是 'eps' 表示欧拉采样，或 'v_prediction' 表示速度预测，这将影响采样过程中模型的行为。 |
+| `最大西格玛` | `FLOAT` | 噪声水平的最大 sigma 值，允许在采样过程中控制噪声注入的上限。 |
+| `最小西格玛` | `FLOAT` | 噪声水平的最小 sigma 值，设置噪声注入的下限，从而影响模型的采样精度。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                       |
+| -------- | -------- | ------------------------------------------ |
+| `模型`  | MODEL    | 增强后的模型，集成了连续 EDM 采样能力，准备用于生成任务。 |
diff --git a/zh-CN/built-in-nodes/ModelSamplingContinuousV.mdx b/zh-CN/built-in-nodes/ModelSamplingContinuousV.mdx
new file mode 100644
index 000000000..8ed932091
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSamplingContinuousV.mdx
@@ -0,0 +1,25 @@
+---
+title: "ModelSamplingContinuousV - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingContinuousV node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingContinuousV"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingContinuousV/zh.md)
+
+ModelSamplingContinuousV 节点通过应用连续 V-prediction 采样参数来修改模型的采样行为。它会创建输入模型的克隆副本，并使用自定义的 sigma 范围设置进行配置，实现高级采样控制。这允许用户通过特定的最小和最大 sigma 值来微调采样过程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型` | MODEL | 是 | - | 要应用连续 V-prediction 采样进行修改的输入模型 |
+| `采样` | STRING | 是 | "v_prediction" | 要应用的采样方法（当前仅支持 V-prediction） |
+| `最大西格玛` | FLOAT | 是 | 0.0 - 1000.0 | 采样的最大 sigma 值（默认：500.0） |
+| `最小西格玛` | FLOAT | 是 | 0.0 - 1000.0 | 采样的最小 sigma 值（默认：0.03） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `模型` | MODEL | 已应用连续 V-prediction 采样的修改后模型 |
diff --git a/zh-CN/built-in-nodes/ModelSamplingDiscrete.mdx b/zh-CN/built-in-nodes/ModelSamplingDiscrete.mdx
new file mode 100644
index 000000000..82b3f5b37
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSamplingDiscrete.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelSamplingDiscrete - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingDiscrete node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingDiscrete"
+icon: "circle"
+mode: wide
+---
+
+该节点旨在通过应用离散采样策略来修改模型的采样行为。它允许选择不同的采样方法，如 epsilon、v_prediction、lcm 或 x0，并可选地根据零样本噪声比率（zsnr）设置调整模型的噪声降低策略。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+| -------- | -------- | ------------------------------------------------------------ |
+| `模型`  | MODEL    | 将应用离散采样策略的模型。此参数定义了将进行修改的基础模型。 |
+| `采样` | COMBO[STRING] | 指定要应用于模型的离散采样方法。选择的方法影响模型如何生成样本，提供了不同的采样策略。 |
+| `zsnr`    | `BOOLEAN` | 一个布尔标志，启用时根据零样本噪声比率调整模型的噪声减少策略。这可以影响生成样本的质量和特性。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+| -------- | -------- | ------------------------------------------------------------ |
+| `模型`  | MODEL    | 修改后的模型，应用了离散采样策略。现在该模型可以使用指定的方法和调整来生成样本。 |
diff --git a/zh-CN/built-in-nodes/ModelSamplingFlux.mdx b/zh-CN/built-in-nodes/ModelSamplingFlux.mdx
new file mode 100644
index 000000000..e1b7e4d44
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSamplingFlux.mdx
@@ -0,0 +1,26 @@
+---
+title: "ModelSamplingFlux - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingFlux node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingFlux"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingFlux/zh.md)
+
+ModelSamplingFlux 节点通过基于图像尺寸计算偏移参数，对给定模型应用 Flux 模型采样。它会创建一个专门的采样配置，根据指定的宽度、高度和偏移参数调整模型行为，随后返回应用了新采样设置的修改后模型。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用 Flux 采样的模型 |
+| `最大移位` | FLOAT | 是 | 0.0 - 100.0 | 采样计算的最大偏移值（默认：1.15） |
+| `基础移位` | FLOAT | 是 | 0.0 - 100.0 | 采样计算的基础偏移值（默认：0.5） |
+| `宽度` | INT | 是 | 16 - MAX_RESOLUTION | 目标图像的宽度（单位：像素，默认：1024） |
+| `高度` | INT | 是 | 16 - MAX_RESOLUTION | 目标图像的高度（单位：像素，默认：1024） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了 Flux 采样配置的修改后模型 |
diff --git a/zh-CN/built-in-nodes/ModelSamplingLTXV.mdx b/zh-CN/built-in-nodes/ModelSamplingLTXV.mdx
new file mode 100644
index 000000000..e22ce37a2
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSamplingLTXV.mdx
@@ -0,0 +1,25 @@
+---
+title: "ModelSamplingLTXV - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingLTXV node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingLTXV"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingLTXV/zh.md)
+
+ModelSamplingLTXV 节点基于令牌数量对模型应用高级采样参数。它通过在基础偏移值和最大偏移值之间进行线性插值来计算偏移值，该计算取决于输入潜空间中的令牌数量。该节点随后创建一个专门的模型采样配置，并将其应用于输入模型。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用采样参数的输入模型 |
+| `最大移位` | FLOAT | 否 | 0.0 到 100.0 | 计算中使用的最大偏移值（默认：2.05） |
+| `基础移位` | FLOAT | 否 | 0.0 到 100.0 | 计算中使用的基础偏移值（默认：0.95） |
+| `Latent` | LATENT | 否 | - | 可选的潜空间输入，用于确定偏移计算所需的令牌数量 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了采样参数后的修改模型 |
diff --git a/zh-CN/built-in-nodes/ModelSamplingSD3.mdx b/zh-CN/built-in-nodes/ModelSamplingSD3.mdx
new file mode 100644
index 000000000..475f5d8c8
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSamplingSD3.mdx
@@ -0,0 +1,23 @@
+---
+title: "ModelSamplingSD3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingSD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingSD3"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingSD3/zh.md)
+
+ModelSamplingSD3 节点将 Stable Diffusion 3 采样参数应用于模型。该节点通过调整控制采样分布特性的偏移参数，来修改模型的采样行为。它会创建一个应用了指定采样配置的输入模型副本。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用 SD3 采样参数的输入模型 |
+| `移位` | FLOAT | 是 | 0.0 - 100.0 | 控制采样偏移参数（默认值：3.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了 SD3 采样参数的修改后模型 |
diff --git a/zh-CN/built-in-nodes/ModelSamplingStableCascade.mdx b/zh-CN/built-in-nodes/ModelSamplingStableCascade.mdx
new file mode 100644
index 000000000..016518891
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSamplingStableCascade.mdx
@@ -0,0 +1,25 @@
+---
+title: "ModelSamplingStableCascade - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSamplingStableCascade node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSamplingStableCascade"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSamplingStableCascade/zh.md)
+
+## 概述
+
+ModelSamplingStableCascade 节点通过使用偏移值调整采样参数，对模型应用稳定级联采样。它会创建一个经过修改的输入模型版本，该版本具有用于稳定级联生成的自定义采样配置。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用稳定级联采样的输入模型 |
+| `移位` | FLOAT | 是 | 0.0 - 100.0 | 应用于采样参数的偏移值（默认值：2.0） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了稳定级联采样后的修改模型 |
diff --git a/zh-CN/built-in-nodes/ModelSave.mdx b/zh-CN/built-in-nodes/ModelSave.mdx
new file mode 100644
index 000000000..6bd58e3eb
--- /dev/null
+++ b/zh-CN/built-in-nodes/ModelSave.mdx
@@ -0,0 +1,27 @@
+---
+title: "ModelSave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ModelSave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ModelSave"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSave/zh.md)
+
+## 概述
+
+ModelSave 节点可将训练或修改后的模型保存至计算机存储设备。该节点接收模型作为输入，并将其写入到用户指定文件名的文件中。通过此功能，您能够保存工作成果并在未来项目中重复使用这些模型。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 需要保存到磁盘的模型 |
+| `文件名前缀` | STRING | 是 | - | 保存模型文件的文件名和路径前缀（默认值："diffusion_models/ComfyUI"） |
+| `prompt` | PROMPT | 否 | - | 工作流提示信息（自动提供） |
+| `extra_pnginfo` | EXTRA_PNGINFO | 否 | - | 额外的工作流元数据（自动提供） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| *无* | - | 该节点不返回任何输出值 |
diff --git a/zh-CN/built-in-nodes/MoonvalleyImg2VideoNode.mdx b/zh-CN/built-in-nodes/MoonvalleyImg2VideoNode.mdx
new file mode 100644
index 000000000..2bef08400
--- /dev/null
+++ b/zh-CN/built-in-nodes/MoonvalleyImg2VideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "MoonvalleyImg2VideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MoonvalleyImg2VideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MoonvalleyImg2VideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MoonvalleyImg2VideoNode/zh.md)
+
+Moonvalley Marey 图像转视频节点通过 Moonvalley API 将参考图像转换为视频。该节点接收输入图像和文本提示，生成具有指定分辨率、质量设置和创意控制的视频。它处理从图像上传到视频生成和下载的完整流程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 用于生成视频的参考图像 |
+| `prompt` | STRING | 是 | - | 视频生成的文本描述（多行输入） |
+| `negative_prompt` | STRING | 否 | - | 负面提示文本，用于排除不需要的元素（默认：包含广泛的负面提示列表） |
+| `resolution` | COMBO | 否 | "16:9 (1920 x 1080)"<br />"9:16 (1080 x 1920)"<br />"1:1 (1152 x 1152)"<br />"4:3 (1536 x 1152)"<br />"3:4 (1152 x 1536)" | 输出视频的分辨率（默认："16:9 (1920 x 1080)"） |
+| `prompt_adherence` | FLOAT | 否 | 1.0 - 20.0 | 生成控制的引导尺度（默认：4.5，步长：1.0） |
+| `seed` | INT | 否 | 0 - 4294967295 | 随机种子值（默认：9，生成后启用控制） |
+| `steps` | INT | 否 | 1 - 100 | 去噪步骤数（默认：33，步长：1） |
+
+**约束条件：**
+
+- 输入图像的尺寸必须在 300x300 像素与允许的最大高度/宽度之间
+- 提示和负面提示文本长度受限于 Moonvalley Marey 的最大提示长度
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频输出 |
diff --git a/zh-CN/built-in-nodes/MoonvalleyTxt2VideoNode.mdx b/zh-CN/built-in-nodes/MoonvalleyTxt2VideoNode.mdx
new file mode 100644
index 000000000..09b8c6c8f
--- /dev/null
+++ b/zh-CN/built-in-nodes/MoonvalleyTxt2VideoNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "MoonvalleyTxt2VideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MoonvalleyTxt2VideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MoonvalleyTxt2VideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MoonvalleyTxt2VideoNode/zh.md)
+
+## 概述
+
+Moonvalley Marey 文生视频节点通过 Moonvalley API 从文本描述生成视频内容。它接收文本提示词，并根据可自定义的分辨率、质量和风格设置将其转换为视频。该节点处理从发送生成请求到下载最终视频输出的完整流程。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 要生成视频内容的文本描述 |
+| `negative_prompt` | STRING | 否 | - | 负面提示词文本（默认值：包含合成内容、场景切换、伪影、噪点等大量排除元素的列表） |
+| `resolution` | STRING | 否 | "16:9 (1920 x 1080)"<br />"9:16 (1080 x 1920)"<br />"1:1 (1152 x 1152)"<br />"4:3 (1536 x 1152)"<br />"3:4 (1152 x 1536)"<br />"21:9 (2560 x 1080)" | 输出视频的分辨率（默认值："16:9 (1920 x 1080)"） |
+| `prompt_adherence` | FLOAT | 否 | 1.0-20.0 | 生成控制的引导尺度（默认值：4.0） |
+| `seed` | INT | 否 | 0-4294967295 | 随机种子值（默认值：9） |
+| `steps` | INT | 否 | 1-100 | 推理步数（默认值：33） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 基于文本提示词生成的视频输出 |
diff --git a/zh-CN/built-in-nodes/MoonvalleyVideo2VideoNode.mdx b/zh-CN/built-in-nodes/MoonvalleyVideo2VideoNode.mdx
new file mode 100644
index 000000000..19653aa54
--- /dev/null
+++ b/zh-CN/built-in-nodes/MoonvalleyVideo2VideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "MoonvalleyVideo2VideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the MoonvalleyVideo2VideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "MoonvalleyVideo2VideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MoonvalleyVideo2VideoNode/zh.md)
+
+Moonvalley Marey 视频到视频节点能够根据文本描述将输入视频转换为新的视频。它利用 Moonvalley API 生成与您的提示词匹配的视频，同时保留原始视频的运动或姿态特征。您可以通过文本提示词和各种生成参数来控制输出视频的风格和内容。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 描述要生成的视频内容（支持多行输入） |
+| `negative_prompt` | STRING | 否 | - | 负面提示文本（默认：包含大量负面描述符的列表） |
+| `seed` | INT | 是 | 0-4294967295 | 随机种子值（默认：9） |
+| `video` | VIDEO | 是 | - | 用于生成输出视频的参考视频。视频长度必须至少为5秒，超过5秒的视频将被自动裁剪。仅支持 MP4 格式。 |
+| `control_type` | COMBO | 否 | "Motion Transfer"<br />"Pose Transfer" | 控制类型选择（默认："Motion Transfer"） |
+| `motion_intensity` | INT | 否 | 0-100 | 仅在 control_type 为 'Motion Transfer' 时使用（默认：100） |
+| `steps` | INT | 是 | 1-100 | 推理步数（默认：33） |
+
+**注意：** `motion_intensity` 参数仅在 `control_type` 设置为 "Motion Transfer" 时生效。当使用 "Pose Transfer" 时，此参数将被忽略。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频输出 |
diff --git a/zh-CN/built-in-nodes/Morphology.mdx b/zh-CN/built-in-nodes/Morphology.mdx
new file mode 100644
index 000000000..561e21899
--- /dev/null
+++ b/zh-CN/built-in-nodes/Morphology.mdx
@@ -0,0 +1,24 @@
+---
+title: "Morphology - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Morphology node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Morphology"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Morphology/zh.md)
+
+形态学节点对图像应用各种形态学操作，这些是用于处理和分析图像形状的数学运算。它可以使用可自定义的核大小来执行腐蚀、膨胀、开运算、闭运算等操作，以控制效果强度。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 需要处理的输入图像 |
+| `操作` | STRING | 是 | `"erode"`<br />`"dilate"`<br />`"open"`<br />`"close"`<br />`"gradient"`<br />`"bottom_hat"`<br />`"top_hat"` | 要应用的形态学操作类型 |
+| `核心大小` | INT | 否 | 3-999 | 结构元素核的大小（默认值：3） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `图像` | IMAGE | 应用形态学操作后处理完成的图像 |
diff --git a/zh-CN/built-in-nodes/NAGuidance.mdx b/zh-CN/built-in-nodes/NAGuidance.mdx
new file mode 100644
index 000000000..cf007c8c2
--- /dev/null
+++ b/zh-CN/built-in-nodes/NAGuidance.mdx
@@ -0,0 +1,25 @@
+---
+title: "NAGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the NAGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "NAGuidance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NAGuidance/zh.md)
+
+NAGuidance 节点对模型应用归一化注意力引导技术。该技术通过修改采样过程中模型的注意力机制，引导生成过程远离不期望的概念，从而使得蒸馏模型或快速模型能够使用负向提示词。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要应用归一化注意力引导的模型。 |
+| `nag_scale` | FLOAT | 是 | 0.0 - 50.0 | 引导强度因子。值越高，生成结果越远离负向提示词。（默认值：5.0） |
+| `nag_alpha` | FLOAT | 是 | 0.0 - 1.0 | 归一化注意力的混合因子。值为 1.0 时完全替换原始注意力，值为 0.0 时无效果。（默认值：0.5） |
+| `nag_tau` | FLOAT | 是 | 1.0 - 10.0 | 用于限制归一化比率的缩放因子。（默认值：1.5） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 已启用归一化注意力引导的修补后模型。 |
diff --git a/zh-CN/built-in-nodes/NormalizeImages.mdx b/zh-CN/built-in-nodes/NormalizeImages.mdx
new file mode 100644
index 000000000..00ec00d4a
--- /dev/null
+++ b/zh-CN/built-in-nodes/NormalizeImages.mdx
@@ -0,0 +1,24 @@
+---
+title: "NormalizeImages - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the NormalizeImages node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "NormalizeImages"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeImages/zh.md)
+
+此节点通过数学归一化过程调整输入图像的像素值。它会从每个像素中减去指定的均值，然后将结果除以指定的标准差。这是为其他机器学习模型准备图像数据时常见的预处理步骤。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待归一化的输入图像。 |
+| `mean` | FLOAT | 否 | 0.0 - 1.0 | 从图像像素中减去的均值（默认值：0.5）。 |
+| `std` | FLOAT | 否 | 0.001 - 1.0 | 用于除以图像像素的标准差值（默认值：0.5）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 应用归一化处理后得到的图像。 |
diff --git a/zh-CN/built-in-nodes/NormalizeVideoLatentStart.mdx b/zh-CN/built-in-nodes/NormalizeVideoLatentStart.mdx
new file mode 100644
index 000000000..5a24d05b7
--- /dev/null
+++ b/zh-CN/built-in-nodes/NormalizeVideoLatentStart.mdx
@@ -0,0 +1,26 @@
+---
+title: "NormalizeVideoLatentStart - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the NormalizeVideoLatentStart node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "NormalizeVideoLatentStart"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeVideoLatentStart/zh.md)
+
+此节点通过调整视频潜变量的前几帧，使其看起来更像后续帧。它从视频后面的一组参考帧中计算平均值和变化量，并将这些相同的特征应用到起始帧。这有助于在视频开头创建更平滑、更一致的视觉过渡。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `latent` | LATENT | 是 | - | 要处理的视频潜变量表示。 |
+| `start_frame_count` | INT | 否 | 1 到 16384 | 需要标准化的潜变量帧数，从起始位置开始计数（默认值：4）。 |
+| `reference_frame_count` | INT | 否 | 1 到 16384 | 起始帧之后用作参考的潜变量帧数（默认值：5）。 |
+
+**注意：** `reference_frame_count` 会自动限制为起始帧之后可用的帧数。如果视频潜变量只有 1 帧长，则不执行标准化，并原样返回原始潜变量。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `latent` | LATENT | 经过处理、起始帧已标准化的视频潜变量。 |
diff --git a/zh-CN/built-in-nodes/Note.mdx b/zh-CN/built-in-nodes/Note.mdx
new file mode 100644
index 000000000..b497149a8
--- /dev/null
+++ b/zh-CN/built-in-nodes/Note.mdx
@@ -0,0 +1,14 @@
+---
+title: "Note - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Note node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Note"
+icon: "circle"
+mode: wide
+---
+用于向工作流添加注释的节点。
+
+## 输入
+
+## 输出
+
+该节点没有定义输出类型。
diff --git a/zh-CN/built-in-nodes/OpenAIChatConfig.mdx b/zh-CN/built-in-nodes/OpenAIChatConfig.mdx
new file mode 100644
index 000000000..1a4238120
--- /dev/null
+++ b/zh-CN/built-in-nodes/OpenAIChatConfig.mdx
@@ -0,0 +1,24 @@
+---
+title: "OpenAIChatConfig - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIChatConfig node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIChatConfig"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIChatConfig/zh.md)
+
+OpenAIChatConfig 节点用于为 OpenAI Chat 节点设置额外的配置选项。它提供高级设置，用于控制模型生成响应的方式，包括截断行为、输出长度限制和自定义指令。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|----------|-------|-------------|
+| `truncation` | COMBO | 是 | `"auto"`<br />`"disabled"` | 模型响应使用的截断策略。auto：如果本次响应及之前对话的上下文超出模型的上下文窗口大小，模型将通过丢弃对话中间部分的输入项来截断响应以适应上下文窗口。disabled：如果模型响应将超出模型的上下文窗口大小，请求将失败并返回 400 错误（默认值："auto"） |
+| `max_output_tokens` | INT | 否 | 16-16384 | 响应生成的最大令牌数上限，包括可见的输出令牌（默认值：4096） |
+| `instructions` | STRING | 否 | - | 模型响应的附加指令（支持多行输入） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `OPENAI_CHAT_CONFIG` | OPENAI_CHAT_CONFIG | 包含指定设置的配置对象，用于 OpenAI Chat 节点 |
diff --git a/zh-CN/built-in-nodes/OpenAIChatNode.mdx b/zh-CN/built-in-nodes/OpenAIChatNode.mdx
new file mode 100644
index 000000000..14af995c3
--- /dev/null
+++ b/zh-CN/built-in-nodes/OpenAIChatNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "OpenAIChatNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIChatNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIChatNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIChatNode/zh.md)
+
+此节点通过 OpenAI 模型生成文本回复。它允许您通过发送文本提示并接收生成的回复来与 AI 模型进行对话。该节点支持多轮对话，能够记住先前的上下文，并且还可以处理图像和文件作为模型的附加上下文。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 模型的文本输入，用于生成回复（默认：空） |
+| `persist_context` | BOOLEAN | 是 | - | 在多轮对话中保持聊天上下文（默认：True） |
+| `model` | COMBO | 是 | 提供多种 OpenAI 模型 | 用于生成回复的 OpenAI 模型 |
+| `images` | IMAGE | 否 | - | 用作模型上下文的可选图像。要包含多张图像，可以使用批处理图像节点（默认：None） |
+| `files` | OPENAI_INPUT_FILES | 否 | - | 用作模型上下文的可选文件。接受来自 OpenAI 聊天输入文件节点的输入（默认：None） |
+| `advanced_options` | OPENAI_CHAT_CONFIG | 否 | - | 模型的可选配置。接受来自 OpenAI 聊天高级选项节点的输入（默认：None） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output_text` | STRING | 由 OpenAI 模型生成的文本回复 |
diff --git a/zh-CN/built-in-nodes/OpenAIDalle2.mdx b/zh-CN/built-in-nodes/OpenAIDalle2.mdx
new file mode 100644
index 000000000..bb2cd7716
--- /dev/null
+++ b/zh-CN/built-in-nodes/OpenAIDalle2.mdx
@@ -0,0 +1,31 @@
+---
+title: "OpenAIDalle2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIDalle2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIDalle2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIDalle2/zh.md)
+
+通过 OpenAI 的 DALL·E 2 端点同步生成图像。
+
+## 工作原理
+
+此节点连接到 OpenAI 的 DALL·E 2 API，根据文本描述创建图像。当您提供文本提示时，节点会将其发送到 OpenAI 的服务器，服务器生成相应的图像并将其返回给 ComfyUI。该节点可以在两种模式下运行：仅使用文本提示的标准图像生成模式，或在同时提供图像和蒙版时的图像编辑模式。在编辑模式下，它使用蒙版来确定原始图像的哪些部分应被修改，同时保持其他区域不变。
+
+## 输入参数
+
+| 参数 | 数据类型 | 输入类型 | 默认值 | 范围 | 描述 |
+|-----------|-----------|------------|---------|-------|-------------|
+| `提示词` | STRING | 必填 | "" | - | DALL·E 的文本提示 |
+| `种子` | INT | 可选 | 0 | 0 到 2147483647 | 后端尚未实现 |
+| `尺寸` | COMBO | 可选 | "1024x1024" | "256x256", "512x512", "1024x1024" | 图像尺寸 |
+| `数量` | INT | 可选 | 1 | 1 到 8 | 要生成的图像数量 |
+| `参考图像` | IMAGE | 可选 | None | - | 用于图像编辑的可选参考图像。 |
+| `掩码` | MASK | 可选 | None | - | 用于修复的可选蒙版（白色区域将被替换） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 来自 DALL·E 2 的生成或编辑后的图像 |
diff --git a/zh-CN/built-in-nodes/OpenAIDalle3.mdx b/zh-CN/built-in-nodes/OpenAIDalle3.mdx
new file mode 100644
index 000000000..b30bca159
--- /dev/null
+++ b/zh-CN/built-in-nodes/OpenAIDalle3.mdx
@@ -0,0 +1,26 @@
+---
+title: "OpenAIDalle3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIDalle3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIDalle3"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIDalle3/zh.md)
+
+通过 OpenAI 的 DALL·E 3 端点同步生成图像。此节点接收文本提示词，并使用 OpenAI 的 DALL·E 3 模型创建相应图像，允许您指定图像质量、风格和尺寸。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `提示词` | STRING | 是 | - | 用于 DALL·E 的文本提示词（默认：""） |
+| `种子` | INT | 否 | 0 到 2147483647 | 后端尚未实现（默认：0） |
+| `质量` | COMBO | 否 | "standard"<br />"hd" | 图像质量（默认："standard"） |
+| `风格` | COMBO | 否 | "natural"<br />"vivid" | Vivid 会使模型倾向于生成超真实和戏剧化的图像。Natural 会使模型生成更自然、不那么超真实的图像。（默认："natural"） |
+| `尺寸` | COMBO | 否 | "1024x1024"<br />"1024x1792"<br />"1792x1024" | 图像尺寸（默认："1024x1024"） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `IMAGE` | IMAGE | 由 DALL·E 3 生成的图像 |
diff --git a/zh-CN/built-in-nodes/OpenAIGPTImage1.mdx b/zh-CN/built-in-nodes/OpenAIGPTImage1.mdx
new file mode 100644
index 000000000..b247154b0
--- /dev/null
+++ b/zh-CN/built-in-nodes/OpenAIGPTImage1.mdx
@@ -0,0 +1,36 @@
+---
+title: "OpenAIGPTImage1 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIGPTImage1 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIGPTImage1"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIGPTImage1/zh.md)
+
+通过 OpenAI 的 GPT Image 1 端点同步生成图像。此节点可根据文本提示创建新图像，或在提供输入图像和可选遮罩时编辑现有图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `提示词` | STRING | 是 | - | GPT Image 1 的文本提示（默认：""） |
+| `种子` | INT | 否 | 0 至 2147483647 | 生成随机种子（默认：0）- 后端尚未实现 |
+| `质量` | COMBO | 否 | "low"<br />"medium"<br />"high" | 图像质量，影响成本和生成时间（默认："low"） |
+| `背景` | COMBO | 否 | "opaque"<br />"transparent" | 返回带背景或不带背景的图像（默认："opaque"） |
+| `尺寸` | COMBO | 否 | "auto"<br />"1024x1024"<br />"1024x1536"<br />"1536x1024" | 图像尺寸（默认："auto"） |
+| `数量` | INT | 否 | 1 至 8 | 生成图像数量（默认：1） |
+| `参考图像` | IMAGE | 否 | - | 用于图像编辑的可选参考图像（默认：None） |
+| `mask` | MASK | 否 | - | 用于修复的可选遮罩（白色区域将被替换）（默认：None） |
+
+**参数约束：**
+
+- 当提供 `image` 时，节点切换到图像编辑模式
+- 只有在提供 `image` 时才能使用 `mask`
+- 使用 `mask` 时仅支持单张图像（批次大小必须为 1）
+- `mask` 和 `image` 必须具有相同尺寸
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 生成或编辑后的图像 |
diff --git a/zh-CN/built-in-nodes/OpenAIInputFiles.mdx b/zh-CN/built-in-nodes/OpenAIInputFiles.mdx
new file mode 100644
index 000000000..c6ea8ebab
--- /dev/null
+++ b/zh-CN/built-in-nodes/OpenAIInputFiles.mdx
@@ -0,0 +1,31 @@
+---
+title: "OpenAIInputFiles - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIInputFiles node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIInputFiles"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIInputFiles/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIInputFiles/en.md)
+
+加载并格式化用于 OpenAI API 的输入文件。此节点准备文本和 PDF 文件，作为上下文输入提供给 OpenAI 聊天节点。生成响应时，OpenAI 模型将读取这些文件。可以将多个输入文件节点链接在一起，以便在单条消息中包含多个文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `file` | COMBO | 是 | 提供多个选项 | 作为模型上下文输入的文件。目前仅接受文本文件 (.txt) 和 PDF 文件 (.pdf)。文件必须小于 32MB。 |
+| `OPENAI_INPUT_FILES` | OPENAI_INPUT_FILES | 否 | 不适用 | 可选的附加文件，用于与此节点加载的文件批量处理。允许链接输入文件，以便单条消息可以包含多个输入文件。 |
+
+**文件限制：**
+
+- 仅支持 .txt 和 .pdf 文件
+- 最大文件大小：32MB
+- 文件从输入目录加载
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `OPENAI_INPUT_FILES` | OPENAI_INPUT_FILES | 格式化后的输入文件，已准备好用作 OpenAI API 调用的上下文。 |
diff --git a/zh-CN/built-in-nodes/OpenAIVideoSora2.mdx b/zh-CN/built-in-nodes/OpenAIVideoSora2.mdx
new file mode 100644
index 000000000..ba4f67d28
--- /dev/null
+++ b/zh-CN/built-in-nodes/OpenAIVideoSora2.mdx
@@ -0,0 +1,33 @@
+---
+title: "OpenAIVideoSora2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OpenAIVideoSora2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OpenAIVideoSora2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIVideoSora2/zh.md)
+
+OpenAIVideoSora2 节点使用 OpenAI 的 Sora 模型生成视频。它基于文本提示和可选的输入图像创建视频内容，然后返回生成的视频输出。该节点根据所选模型支持不同的视频时长和分辨率。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | "sora-2"<br />"sora-2-pro" | 用于视频生成的 OpenAI Sora 模型（默认："sora-2"） |
+| `prompt` | STRING | 是 | - | 引导文本；如果存在输入图像，可以为空（默认：空） |
+| `size` | COMBO | 是 | "720x1280"<br />"1280x720"<br />"1024x1792"<br />"1792x1024" | 生成视频的分辨率（默认："1280x720"） |
+| `duration` | COMBO | 是 | 4<br />8<br />12 | 生成视频的时长，单位为秒（默认：8） |
+| `image` | IMAGE | 否 | - | 用于视频生成的可选输入图像 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于确定节点是否应重新运行的种子；无论种子值如何，实际结果都是非确定性的（默认：0） |
+
+**约束和限制：**
+
+- "sora-2" 模型仅支持 "720x1280" 和 "1280x720" 分辨率
+- 使用图像参数时仅支持一个输入图像
+- 无论种子值如何，结果都是非确定性的
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频输出 |
diff --git a/zh-CN/built-in-nodes/OptimalStepsScheduler.mdx b/zh-CN/built-in-nodes/OptimalStepsScheduler.mdx
new file mode 100644
index 000000000..258fc460f
--- /dev/null
+++ b/zh-CN/built-in-nodes/OptimalStepsScheduler.mdx
@@ -0,0 +1,28 @@
+---
+title: "OptimalStepsScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the OptimalStepsScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "OptimalStepsScheduler"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OptimalStepsScheduler/zh.md)
+
+## 概述
+
+OptimalStepsScheduler 节点根据所选模型类型和步数配置，为扩散模型计算噪声调度 sigma 值。它会根据去噪参数调整总步数，并插值噪声级别以匹配请求的步数。该节点返回一个 sigma 值序列，用于确定扩散采样过程中使用的噪声水平。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_type` | COMBO | 是 | "FLUX"<br />"Wan"<br />"Chroma" | 用于噪声级别计算的扩散模型类型 |
+| `步数` | INT | 是 | 3-1000 | 要计算的采样总步数（默认值：20） |
+| `去噪` | FLOAT | 否 | 0.0-1.0 | 控制去噪强度，调整有效步数（默认值：1.0） |
+
+**注意：** 当 `denoise` 设置为小于 1.0 时，节点计算有效步数为 `steps * denoise`。如果 `denoise` 设置为 0.0，节点将返回空张量。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | 表示扩散采样噪声调度的 sigma 值序列 |
diff --git a/zh-CN/built-in-nodes/PairConditioningCombine.mdx b/zh-CN/built-in-nodes/PairConditioningCombine.mdx
new file mode 100644
index 000000000..f8ae7ff8d
--- /dev/null
+++ b/zh-CN/built-in-nodes/PairConditioningCombine.mdx
@@ -0,0 +1,26 @@
+---
+title: "PairConditioningCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PairConditioningCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PairConditioningCombine"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningCombine/zh.md)
+
+PairConditioningCombine 节点将两对条件数据（正面和负面）合并为单个条件对。该节点接收两个独立的条件对作为输入，并使用 ComfyUI 的内部条件组合逻辑进行合并。此节点为实验性功能，主要用于高级条件处理工作流。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正面条件_A` | CONDITIONING | 是 | - | 第一个正面条件输入 |
+| `负面条件_A` | CONDITIONING | 是 | - | 第一个负面条件输入 |
+| `正面条件_B` | CONDITIONING | 是 | - | 第二个正面条件输入 |
+| `负面条件_B` | CONDITIONING | 是 | - | 第二个负面条件输入 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 合并后的正面条件输出 |
+| `negative` | CONDITIONING | 合并后的负面条件输出 |
diff --git a/zh-CN/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx b/zh-CN/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx
new file mode 100644
index 000000000..810a7341f
--- /dev/null
+++ b/zh-CN/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx
@@ -0,0 +1,29 @@
+---
+title: "PairConditioningSetDefaultAndCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PairConditioningSetDefaultAndCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PairConditioningSetDefaultAndCombine"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetDefaultAndCombine/zh.md)
+
+## 概述
+
+PairConditioningSetDefaultAndCombine 节点用于设置默认的条件化数值并将其与输入的条件化数据相结合。该节点接收正向和负向条件化输入及其对应的默认值，然后通过 ComfyUI 的钩子系统进行处理，最终生成包含默认值的条件化输出结果。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `positive` | CONDITIONING | 是 | - | 待处理的主正向条件化输入 |
+| `negative` | CONDITIONING | 是 | - | 待处理的主负向条件化输入 |
+| `positive_DEFAULT` | CONDITIONING | 是 | - | 作为备用值的默认正向条件化数据 |
+| `negative_DEFAULT` | CONDITIONING | 是 | - | 作为备用值的默认负向条件化数据 |
+| `hooks` | HOOKS | 否 | - | 用于自定义处理逻辑的可选钩子组 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `positive` | CONDITIONING | 已处理并包含默认值的正向条件化数据 |
+| `negative` | CONDITIONING | 已处理并包含默认值的负向条件化数据 |
diff --git a/zh-CN/built-in-nodes/PairConditioningSetProperties.mdx b/zh-CN/built-in-nodes/PairConditioningSetProperties.mdx
new file mode 100644
index 000000000..2e4220255
--- /dev/null
+++ b/zh-CN/built-in-nodes/PairConditioningSetProperties.mdx
@@ -0,0 +1,29 @@
+---
+title: "PairConditioningSetProperties - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PairConditioningSetProperties node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PairConditioningSetProperties"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetProperties/zh.md)
+
+PairConditioningSetProperties 节点允许您同时修改正向和负向条件对属性。该节点会对两个条件输入同时应用强度调整、条件区域设置以及可选的遮罩或时序控制，并返回修改后的正向和负向条件数据。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|----------|-----------|------|----------|------|
+| `新正面条件` | CONDITIONING | 是 | - | 待修改的正向条件输入 |
+| `新负面条件` | CONDITIONING | 是 | - | 待修改的负向条件输入 |
+| `强度` | FLOAT | 是 | 0.0 至 10.0 | 应用于条件数据的强度乘数（默认值：1.0） |
+| `设置条件区域` | STRING | 是 | "default"<br />"mask bounds" | 决定条件区域的计算方式 |
+| `遮罩` | MASK | 否 | - | 用于约束条件区域的可选遮罩 |
+| `约束` | HOOKS | 否 | - | 用于高级条件修改的可选钩子组 |
+| `间隔` | TIMESTEPS_RANGE | 否 | - | 用于限制条件应用时间的可选时间步范围 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `负面条件` | CONDITIONING | 应用属性修改后的正向条件数据 |
+| `negative` | CONDITIONING | 应用属性修改后的负向条件数据 |
diff --git a/zh-CN/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx b/zh-CN/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx
new file mode 100644
index 000000000..0b5851507
--- /dev/null
+++ b/zh-CN/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx
@@ -0,0 +1,31 @@
+---
+title: "PairConditioningSetPropertiesAndCombine - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PairConditioningSetPropertiesAndCombine node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PairConditioningSetPropertiesAndCombine"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetPropertiesAndCombine/zh.md)
+
+PairConditioningSetPropertiesAndCombine 节点通过将新的条件数据应用到现有的正向和负向条件输入，来修改并组合条件对。它允许您调整所应用条件数据的强度，并控制条件区域的设置方式。该节点在需要将多个条件源混合在一起的高级条件处理工作流中特别有用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正面条件` | CONDITIONING | 是 | - | 原始的正向条件输入 |
+| `负面条件` | CONDITIONING | 是 | - | 原始的负向条件输入 |
+| `新正面条件` | CONDITIONING | 是 | - | 要应用的新正向条件数据 |
+| `新负面条件` | CONDITIONING | 是 | - | 要应用的新负向条件数据 |
+| `强度` | FLOAT | 是 | 0.0 到 10.0 | 应用新条件数据的强度因子（默认值：1.0） |
+| `设置条件区域` | STRING | 是 | "default"<br />"mask bounds" | 控制条件数据的应用方式 |
+| `遮罩` | MASK | 否 | - | 用于限制条件数据应用区域的可选遮罩 |
+| `约束` | HOOKS | 否 | - | 用于高级控制的可选钩子组 |
+| `间隔` | TIMESTEPS_RANGE | 否 | - | 可选的时间步范围规范 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 组合后的正向条件输出 |
+| `负面条件` | CONDITIONING | 组合后的负向条件输出 |
diff --git a/zh-CN/built-in-nodes/PatchModelAddDownscale.mdx b/zh-CN/built-in-nodes/PatchModelAddDownscale.mdx
new file mode 100644
index 000000000..a384bd49f
--- /dev/null
+++ b/zh-CN/built-in-nodes/PatchModelAddDownscale.mdx
@@ -0,0 +1,29 @@
+---
+title: "PatchModelAddDownscale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PatchModelAddDownscale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PatchModelAddDownscale"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PatchModelAddDownscale/zh.md)
+
+PatchModelAddDownscale 节点通过向模型中的特定块应用下采样和上采样操作，实现了 Kohya Deep Shrink 功能。它在处理过程中降低中间特征的分辨率，然后将其恢复到原始尺寸，这可以在保持质量的同时提升性能。该节点允许精确控制在模型执行过程中这些缩放操作的发生时机和方式。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用下采样补丁的模型 |
+| `层编号` | INT | 否 | 1-32 | 将应用下采样的具体块编号（默认值：3） |
+| `收缩系数` | FLOAT | 否 | 0.1-9.0 | 特征下采样的比例因子（默认值：2.0） |
+| `开始百分比` | FLOAT | 否 | 0.0-1.0 | 去噪过程中开始下采样的起始点（默认值：0.0） |
+| `结束百分比` | FLOAT | 否 | 0.0-1.0 | 去噪过程中停止下采样的结束点（默认值：0.35） |
+| `跳过后收缩` | BOOLEAN | 否 | - | 是否在跳跃连接后应用下采样（默认值：True） |
+| `收缩算法` | COMBO | 否 | "bicubic"<br />"nearest-exact"<br />"bilinear"<br />"area"<br />"bislerp" | 用于下采样操作的插值方法 |
+| `放大方法` | COMBO | 否 | "bicubic"<br />"nearest-exact"<br />"bilinear"<br />"area"<br />"bislerp" | 用于上采样操作的插值方法 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了下采样补丁的修改后模型 |
diff --git a/zh-CN/built-in-nodes/PerpNeg.mdx b/zh-CN/built-in-nodes/PerpNeg.mdx
new file mode 100644
index 000000000..583c6adeb
--- /dev/null
+++ b/zh-CN/built-in-nodes/PerpNeg.mdx
@@ -0,0 +1,28 @@
+---
+title: "PerpNeg - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PerpNeg node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PerpNeg"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PerpNeg/zh.md)
+
+> 该文档由 AI 生成，如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PerpNeg/en.md)
+
+PerpNeg 节点对模型的采样过程应用垂直负向引导。该节点通过修改模型的配置函数，使用负向条件和缩放因子来调整噪声预测。此节点已被弃用，并由功能更完善的 PerpNegGuider 节点替代。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型` | MODEL | 是 | - | 要应用垂直负向引导的模型 |
+| `空条件` | CONDITIONING | 是 | - | 用于负向引导计算的空条件 |
+| `负面缩放` | FLOAT | 否 | 0.0 - 100.0 | 负向引导的缩放因子（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `模型` | MODEL | 应用了垂直负向引导的修改后模型 |
+
+**注意**：此节点已被弃用，并已由 PerpNegGuider 节点替代。它被标记为实验性功能，不应在生产工作流中使用。
diff --git a/zh-CN/built-in-nodes/PerpNegGuider.mdx b/zh-CN/built-in-nodes/PerpNegGuider.mdx
new file mode 100644
index 000000000..6da54207c
--- /dev/null
+++ b/zh-CN/built-in-nodes/PerpNegGuider.mdx
@@ -0,0 +1,27 @@
+---
+title: "PerpNegGuider - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PerpNegGuider node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PerpNegGuider"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PerpNegGuider/zh.md)
+
+PerpNegGuider 节点创建了一个引导系统，用于通过垂直负向条件控制图像生成。该节点接收正向、负向和空条件输入，并应用专门的引导算法来指导生成过程。此节点专为测试目的设计，可对引导强度和负向缩放进行精细控制。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 用于引导生成的模型 |
+| `正面条件` | CONDITIONING | 是 | - | 正向条件，引导生成朝向期望内容 |
+| `负面条件` | CONDITIONING | 是 | - | 负向条件，引导生成远离不需要的内容 |
+| `空条件` | CONDITIONING | 是 | - | 用作基准参考的空条件或中性条件 |
+| `cfg` | FLOAT | 否 | 0.0 - 100.0 | 分类器无关引导尺度，控制条件对生成的影响强度（默认值：8.0） |
+| `负面缩放` | FLOAT | 否 | 0.0 - 100.0 | 负向缩放因子，调整负向条件的强度（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `guider` | GUIDER | 配置完成的引导系统，可在生成流水线中直接使用 |
diff --git a/zh-CN/built-in-nodes/PerturbedAttentionGuidance.mdx b/zh-CN/built-in-nodes/PerturbedAttentionGuidance.mdx
new file mode 100644
index 000000000..d2968c1dd
--- /dev/null
+++ b/zh-CN/built-in-nodes/PerturbedAttentionGuidance.mdx
@@ -0,0 +1,25 @@
+---
+title: "PerturbedAttentionGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PerturbedAttentionGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PerturbedAttentionGuidance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PerturbedAttentionGuidance/zh.md)
+
+# PerturbedAttentionGuidance
+
+PerturbedAttentionGuidance 节点对扩散模型应用扰动注意力引导，以提升生成质量。该技术在采样过程中通过将模型的自注意力机制替换为专注于值投影的简化版本，从而调整条件去噪过程，有助于提高生成图像的连贯性和质量。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型` | MODEL | 是 | - | 要应用扰动注意力引导的扩散模型 |
+| `规模` | FLOAT | 否 | 0.0 - 100.0 | 扰动注意力引导效果的强度（默认值：3.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `模型` | MODEL | 应用了扰动注意力引导的修改后模型 |
diff --git a/zh-CN/built-in-nodes/PhotoMakerEncode.mdx b/zh-CN/built-in-nodes/PhotoMakerEncode.mdx
new file mode 100644
index 000000000..8eb3eee6d
--- /dev/null
+++ b/zh-CN/built-in-nodes/PhotoMakerEncode.mdx
@@ -0,0 +1,29 @@
+---
+title: "PhotoMakerEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PhotoMakerEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PhotoMakerEncode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PhotoMakerEncode/zh.md)
+
+# PhotoMakerEncode 节点
+
+PhotoMakerEncode 节点处理图像和文本，为 AI 图像生成生成条件数据。它接收参考图像和文本提示，然后创建可用于基于参考图像的视觉特征来引导图像生成的嵌入向量。该节点专门在文本中查找 "photomaker" 标记，以确定在何处应用基于图像的条件控制。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `photomaker` | PHOTOMAKER | 是 | - | 用于处理图像和生成嵌入向量的 PhotoMaker 模型 |
+| `图像` | IMAGE | 是 | - | 提供条件控制视觉特征的参考图像 |
+| `clip` | CLIP | 是 | - | 用于文本标记化和编码的 CLIP 模型 |
+| `文本` | STRING | 是 | - | 用于生成条件控制的文本提示（默认："photograph of photomaker"） |
+
+**注意：** 当文本包含 "photomaker" 一词时，节点会在提示词中的该位置应用基于图像的条件控制。如果文本中未找到 "photomaker"，节点将生成没有图像影响的标准文本条件控制。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 包含图像和文本嵌入向量的条件数据，用于引导图像生成 |
diff --git a/zh-CN/built-in-nodes/PhotoMakerLoader.mdx b/zh-CN/built-in-nodes/PhotoMakerLoader.mdx
new file mode 100644
index 000000000..b6415dad7
--- /dev/null
+++ b/zh-CN/built-in-nodes/PhotoMakerLoader.mdx
@@ -0,0 +1,22 @@
+---
+title: "PhotoMakerLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PhotoMakerLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PhotoMakerLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PhotoMakerLoader/zh.md)
+
+PhotoMakerLoader 节点从可用的模型文件中加载 PhotoMaker 模型。它会读取指定的模型文件，并准备用于基于身份的图像生成任务的 PhotoMaker ID 编码器。此节点标记为实验性，仅供测试用途。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 是否必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `photomaker模型名称` | STRING | 是 | 提供多个选项 | 要加载的 PhotoMaker 模型文件名。可用选项由 photomaker 文件夹中的模型文件决定。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `photomaker_model` | PHOTOMAKER | 已加载的 PhotoMaker 模型，包含 ID 编码器，可用于身份编码操作。 |
diff --git a/zh-CN/built-in-nodes/PikaImageToVideoNode2_2.mdx b/zh-CN/built-in-nodes/PikaImageToVideoNode2_2.mdx
new file mode 100644
index 000000000..5b676c50b
--- /dev/null
+++ b/zh-CN/built-in-nodes/PikaImageToVideoNode2_2.mdx
@@ -0,0 +1,29 @@
+---
+title: "PikaImageToVideoNode2_2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PikaImageToVideoNode2_2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PikaImageToVideoNode2_2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PikaImageToVideoNode2_2/zh.md)
+
+## 概述
+
+Pika Image to Video 节点将图像和文本提示发送到 Pika API 2.2 版本以生成视频。它根据提供的描述和设置将输入图像转换为视频格式。该节点负责处理 API 通信，并返回生成的视频作为输出。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 要转换为视频的图像 |
+| `提示词` | STRING | 是 | - | 指导视频生成的文本描述 |
+| `反向提示词` | STRING | 是 | - | 描述视频中应避免内容的文本 |
+| `种子` | INT | 是 | - | 用于可重现结果的随机种子值 |
+| `分辨率` | STRING | 是 | - | 输出视频分辨率设置 |
+| `时长` | INT | 是 | - | 生成视频的长度（以秒为单位） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/PikaScenesV2_2.mdx b/zh-CN/built-in-nodes/PikaScenesV2_2.mdx
new file mode 100644
index 000000000..48ae9ad8b
--- /dev/null
+++ b/zh-CN/built-in-nodes/PikaScenesV2_2.mdx
@@ -0,0 +1,35 @@
+---
+title: "PikaScenesV2_2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PikaScenesV2_2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PikaScenesV2_2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PikaScenesV2_2/zh.md)
+
+PikaScenes v2.2 节点通过组合多张输入图像来创建融合所有图像中对象的视频。您最多可以上传五张不同的图像作为素材，生成高质量且无缝融合的视频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `提示词` | STRING | 是 | - | 生成内容的文本描述 |
+| `反向提示词` | STRING | 是 | - | 生成过程中需要避免的内容描述 |
+| `随机种子` | INT | 是 | - | 生成用的随机种子值 |
+| `分辨率` | STRING | 是 | - | 视频输出分辨率 |
+| `时长` | INT | 是 | - | 生成视频的时长 |
+| `素材模式` | COMBO | 否 | "creative"<br />"precise" | 素材组合模式（默认："creative"） |
+| `宽高比` | FLOAT | 否 | 0.4 - 2.5 | 宽高比（宽度/高度）（默认：1.778） |
+| `图片素材 1` | IMAGE | 否 | - | 用作视频素材的图像 |
+| `图片素材 2` | IMAGE | 否 | - | 用作视频素材的图像 |
+| `图片素材 3` | IMAGE | 否 | - | 用作视频素材的图像 |
+| `图片素材 4` | IMAGE | 否 | - | 用作视频素材的图像 |
+| `图片素材 5` | IMAGE | 否 | - | 用作视频素材的图像 |
+
+**注意：** 您最多可以提供5个图像素材，但至少需要一个图像才能生成视频。该节点将使用所有提供的图像来创建最终视频合成。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `output` | VIDEO | 融合所有输入图像后生成的视频 |
diff --git a/zh-CN/built-in-nodes/PikaStartEndFrameNode2_2.mdx b/zh-CN/built-in-nodes/PikaStartEndFrameNode2_2.mdx
new file mode 100644
index 000000000..c6c032e7b
--- /dev/null
+++ b/zh-CN/built-in-nodes/PikaStartEndFrameNode2_2.mdx
@@ -0,0 +1,28 @@
+---
+title: "PikaStartEndFrameNode2_2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PikaStartEndFrameNode2_2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PikaStartEndFrameNode2_2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PikaStartEndFrameNode2_2/zh.md)
+
+PikaFrames v2.2 节点通过组合您的首帧和尾帧来生成视频。您上传两张图像来定义起始点和结束点，AI 会在它们之间创建平滑过渡，从而生成完整的视频。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 是否必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image_start` | IMAGE | 是 | - | 要组合的首帧图像。 |
+| `image_end` | IMAGE | 是 | - | 要组合的尾帧图像。 |
+| `prompt_text` | STRING | 是 | - | 描述期望视频内容的文本提示。 |
+| `negative_prompt` | STRING | 是 | - | 描述视频中应避免内容的文本。 |
+| `seed` | INT | 是 | - | 用于保持生成一致性的随机种子值。 |
+| `resolution` | STRING | 是 | - | 输出视频分辨率。 |
+| `duration` | INT | 是 | - | 生成视频的持续时间。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 通过 AI 过渡将起始帧和结束帧组合后生成的视频。 |
diff --git a/zh-CN/built-in-nodes/PikaTextToVideoNode2_2.mdx b/zh-CN/built-in-nodes/PikaTextToVideoNode2_2.mdx
new file mode 100644
index 000000000..4e5e40d7f
--- /dev/null
+++ b/zh-CN/built-in-nodes/PikaTextToVideoNode2_2.mdx
@@ -0,0 +1,27 @@
+---
+title: "PikaTextToVideoNode2_2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PikaTextToVideoNode2_2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PikaTextToVideoNode2_2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PikaTextToVideoNode2_2/zh.md)
+
+Pika Text2Video v2.2 节点将文本提示发送到 Pika API 2.2 版本以生成视频。该节点通过 Pika 的 AI 视频生成服务将您的文本描述转换为视频。您可以通过该节点自定义视频生成过程的各个方面，包括宽高比、时长和分辨率。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `提示文本` | STRING | 是 | - | 描述您希望在视频中生成内容的主要文本描述 |
+| `反向提示` | STRING | 是 | - | 描述您不希望出现在生成视频中的内容的文本 |
+| `种子` | INT | 是 | - | 控制生成随机性的数字，用于实现可复现的结果 |
+| `分辨率` | STRING | 是 | - | 输出视频的分辨率设置 |
+| `时长` | INT | 是 | - | 视频时长（单位：秒） |
+| `宽高比` | FLOAT | 否 | 0.4 - 2.5 | 宽高比（宽度/高度）（默认值：1.7777777777777777） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 从 Pika API 返回的已生成视频文件 |
diff --git a/zh-CN/built-in-nodes/Pikadditions.mdx b/zh-CN/built-in-nodes/Pikadditions.mdx
new file mode 100644
index 000000000..dce5f69a5
--- /dev/null
+++ b/zh-CN/built-in-nodes/Pikadditions.mdx
@@ -0,0 +1,26 @@
+---
+title: "Pikadditions - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Pikadditions node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Pikadditions"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Pikadditions/zh.md)
+
+Pikadditions 节点允许您将任意对象或图像添加到视频中。您只需上传视频并指定要添加的内容，即可创建无缝集成的效果。该节点利用 Pika API 将图像插入视频，实现自然逼真的融合效果。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `视频` | VIDEO | 是 | - | 需要添加图像的目标视频 |
+| `图像` | IMAGE | 是 | - | 要添加到视频中的图像 |
+| `提示词` | STRING | 是 | - | 描述视频添加内容的文本说明 |
+| `反向提示词` | STRING | 是 | - | 描述视频中需要避免出现内容的文本说明 |
+| `种子` | INT | 是 | 0 至 4294967295 | 用于实现可重复结果的随机种子值 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 已插入图像的处理后视频 |
diff --git a/zh-CN/built-in-nodes/Pikaffects.mdx b/zh-CN/built-in-nodes/Pikaffects.mdx
new file mode 100644
index 000000000..3c37f138d
--- /dev/null
+++ b/zh-CN/built-in-nodes/Pikaffects.mdx
@@ -0,0 +1,26 @@
+---
+title: "Pikaffects - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Pikaffects node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Pikaffects"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Pikaffects/zh.md)
+
+Pikaffects 节点可生成应用了各种视觉效果到输入图像的视频。它利用 Pika 的视频生成 API，将静态图像转换为具有特定效果（如融化、爆炸或悬浮）的动画视频。该节点需要 API 密钥和认证令牌才能访问 Pika 服务。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 要应用 Pikaffect 效果的参考图像。 |
+| `pikaffect` | COMBO | 是 | "Cake-ify"<br />"Crumble"<br />"Crush"<br />"Decapitate"<br />"Deflate"<br />"Dissolve"<br />"Explode"<br />"Eye-pop"<br />"Inflate"<br />"Levitate"<br />"Melt"<br />"Peel"<br />"Poke"<br />"Squish"<br />"Ta-da"<br />"Tear" | 要应用于图像的具体视觉效果（默认："Cake-ify"）。 |
+| `prompt_text` | STRING | 是 | - | 指导视频生成的文本描述。 |
+| `negative_prompt` | STRING | 是 | - | 描述生成视频中应避免内容的文本。 |
+| `seed` | INT | 是 | 0 至 4294967295 | 用于可重现结果的随机种子值。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 应用了 Pikaffect 效果后生成的视频。 |
diff --git a/zh-CN/built-in-nodes/Pikaswaps.mdx b/zh-CN/built-in-nodes/Pikaswaps.mdx
new file mode 100644
index 000000000..77eac9b22
--- /dev/null
+++ b/zh-CN/built-in-nodes/Pikaswaps.mdx
@@ -0,0 +1,29 @@
+---
+title: "Pikaswaps - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Pikaswaps node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Pikaswaps"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Pikaswaps/zh.md)
+
+Pika Swaps 节点允许您将视频中的对象或区域替换为新的图像。您可以使用遮罩或坐标来定义要替换的区域，该节点将在整个视频序列中无缝替换指定内容。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `视频` | VIDEO | 是 | - | 需要进行对象替换的视频。 |
+| `图像` | IMAGE | 是 | - | 用于替换视频中遮罩对象的图像。 |
+| `mask` | MASK | 是 | - | 使用遮罩定义视频中要替换的区域。 |
+| `提示词` | STRING | 是 | - | 描述期望替换效果的文本提示。 |
+| `反向提示词` | STRING | 是 | - | 描述替换中需要避免内容的文本提示。 |
+| `种子` | INT | 是 | 0 到 4294967295 | 用于保证结果一致性的随机种子值。 |
+
+**注意：** 此节点要求提供所有输入参数。`video`、`image` 和 `mask` 共同定义替换操作，其中遮罩指定了视频中哪些区域将被提供的图像替换。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 经过处理且指定对象或区域已被替换的视频。 |
diff --git a/zh-CN/built-in-nodes/PixverseImageToVideoNode.mdx b/zh-CN/built-in-nodes/PixverseImageToVideoNode.mdx
new file mode 100644
index 000000000..b5c7750d2
--- /dev/null
+++ b/zh-CN/built-in-nodes/PixverseImageToVideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "PixverseImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PixverseImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PixverseImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseImageToVideoNode/zh.md)
+
+## 概述
+
+基于输入图像和文本提示生成视频。此节点接收一张图像，并通过应用指定的运动和质量设置，将静态图像转换为动态序列来创建动画视频。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 要转换为视频的输入图像 |
+| `提示词` | STRING | 是 | - | 视频生成的提示词 |
+| `质量` | COMBO | 是 | `res_540p`<br />`res_1080p` | 视频质量设置（默认：res_540p） |
+| `时长（秒）` | COMBO | 是 | `dur_2`<br />`dur_5`<br />`dur_10` | 生成视频的持续时间（秒） |
+| `运动模式` | COMBO | 是 | `normal`<br />`fast`<br />`slow`<br />`zoom_in`<br />`zoom_out`<br />`pan_left`<br />`pan_right`<br />`pan_up`<br />`pan_down`<br />`tilt_up`<br />`tilt_down`<br />`roll_clockwise`<br />`roll_counterclockwise` | 应用于视频生成的运动风格 |
+| `种子` | INT | 是 | 0-2147483647 | 视频生成的随机种子（默认：0） |
+| `反向提示词` | STRING | 否 | - | 图像中不希望出现的元素的可选文本描述 |
+| `PixVerse 模板` | CUSTOM | 否 | - | 影响生成风格的可选模板，由 PixVerse 模板节点创建 |
+
+**注意：** 使用 1080p 质量时，运动模式会自动设置为 normal，且持续时间限制为 5 秒。对于非 5 秒的持续时间，运动模式也会自动设置为 normal。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 基于输入图像和参数生成的视频 |
diff --git a/zh-CN/built-in-nodes/PixverseTemplateNode.mdx b/zh-CN/built-in-nodes/PixverseTemplateNode.mdx
new file mode 100644
index 000000000..3ff229cb7
--- /dev/null
+++ b/zh-CN/built-in-nodes/PixverseTemplateNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "PixverseTemplateNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PixverseTemplateNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PixverseTemplateNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTemplateNode/zh.md)
+
+PixVerse Template 节点允许您从可用的 PixVerse 视频生成模板中进行选择。它会将您选择的模板名称转换为 PixVerse API 创建视频所需的相应模板 ID。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模板` | STRING | 是 | 提供多个选项 | 用于 PixVerse 视频生成的模板。可用选项对应 PixVerse 系统中的预定义模板。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `pixverse_template` | INT | 与所选模板名称对应的模板 ID，可供其他 PixVerse 节点用于视频生成。 |
diff --git a/zh-CN/built-in-nodes/PixverseTextToVideoNode.mdx b/zh-CN/built-in-nodes/PixverseTextToVideoNode.mdx
new file mode 100644
index 000000000..b3994ffd8
--- /dev/null
+++ b/zh-CN/built-in-nodes/PixverseTextToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "PixverseTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PixverseTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PixverseTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTextToVideoNode/zh.md)
+
+基于提示词和输出尺寸生成视频。此节点使用文本描述和各种生成参数通过 PixVerse API 创建视频内容，生成视频输出。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `提示词` | STRING | 是 | - | 视频生成的提示词（默认：""） |
+| `宽高比` | COMBO | 是 | PixverseAspectRatio 的选项 | 生成视频的宽高比 |
+| `质量` | COMBO | 是 | PixverseQuality 的选项 | 视频质量设置（默认：PixverseQuality.res_540p） |
+| `时长（秒）` | COMBO | 是 | PixverseDuration 的选项 | 生成视频的时长（单位：秒） |
+| `运动模式` | COMBO | 是 | PixverseMotionMode 的选项 | 视频生成的运动风格 |
+| `种子` | INT | 是 | 0 到 2147483647 | 视频生成的随机种子（默认：0） |
+| `反向提示词` | STRING | 否 | - | 图像中不希望出现的元素的可选文本描述（默认：""） |
+| `PixVerse 模板` | CUSTOM | 否 | - | 影响生成风格的可选模板，由 PixVerse 模板节点创建 |
+
+**注意：** 当使用 1080p 质量时，运动模式会自动设置为 normal 且时长限制为 5 秒。对于非 5 秒的时长，运动模式也会自动设置为 normal。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/PixverseTransitionVideoNode.mdx b/zh-CN/built-in-nodes/PixverseTransitionVideoNode.mdx
new file mode 100644
index 000000000..d3f4e6590
--- /dev/null
+++ b/zh-CN/built-in-nodes/PixverseTransitionVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "PixverseTransitionVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PixverseTransitionVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PixverseTransitionVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTransitionVideoNode/zh.md)
+
+基于提示词和输出尺寸生成视频。此节点使用 PixVerse API 在两个输入图像之间创建过渡视频，允许您指定视频质量、时长、运动风格和生成参数。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `首帧` | IMAGE | 是 | - | 视频过渡的起始图像 |
+| `末帧` | IMAGE | 是 | - | 视频过渡的结束图像 |
+| `提示词` | STRING | 是 | - | 视频生成的提示词（默认：空字符串） |
+| `质量` | COMBO | 是 | PixVerseQuality 枚举中可用的质量选项<br />默认：res_540p | 视频质量设置 |
+| `时长（秒）` | COMBO | 是 | PixVerseDuration 枚举中可用的时长选项 | 视频时长（秒） |
+| `运动模式` | COMBO | 是 | PixVerseMotionMode 枚举中可用的运动模式选项 | 过渡的运动风格 |
+| `种子` | INT | 是 | 0 到 2147483647 | 视频生成的随机种子（默认：0） |
+| `反向提示词` | STRING | 否 | - | 图像中不希望出现的元素的可选文本描述（默认：空字符串） |
+
+**注意：** 使用 1080p 质量时，运动模式会自动设置为 normal，时长限制为 5 秒。对于非 5 秒的时长，运动模式也会自动设置为 normal。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的过渡视频 |
diff --git a/zh-CN/built-in-nodes/PolyexponentialScheduler.mdx b/zh-CN/built-in-nodes/PolyexponentialScheduler.mdx
new file mode 100644
index 000000000..8a1c3c43a
--- /dev/null
+++ b/zh-CN/built-in-nodes/PolyexponentialScheduler.mdx
@@ -0,0 +1,26 @@
+---
+title: "PolyexponentialScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PolyexponentialScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PolyexponentialScheduler"
+icon: "circle"
+mode: wide
+---
+
+多项式指数调度器（PolyexponentialScheduler）节点旨在基于一个多项式指数噪声计划生成一系列噪声水平（sigmas）。该计划是sigma对数的多项式函数，允许在扩散过程中灵活且可定制地调整噪声水平的进展。
+
+## 输入
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| `步数`    | `INT`    | 指定扩散过程中的步骤数，影响生成噪声水平的粒度。           |
+| `sigma最大值`| `FLOAT`  | 最大噪声水平，设定噪声计划的上限。                         |
+| `sigma最小值`| `FLOAT`  | 最小噪声水平，设定噪声计划的下限。                         |
+| `rho`      | `FLOAT`  | 控制多项式指数噪声计划形状的参数，影响噪声水平在最小值和最大值之间的进展。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `sigmas` | `SIGMAS`| 输出是按照指定的多项式指数噪声计划定制的一系列噪声水平。 |
+
+---
diff --git a/zh-CN/built-in-nodes/PorterDuffImageComposite.mdx b/zh-CN/built-in-nodes/PorterDuffImageComposite.mdx
new file mode 100644
index 000000000..8a7e4a2c9
--- /dev/null
+++ b/zh-CN/built-in-nodes/PorterDuffImageComposite.mdx
@@ -0,0 +1,26 @@
+---
+title: "PorterDuffImageComposite - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PorterDuffImageComposite node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PorterDuffImageComposite"
+icon: "circle"
+mode: wide
+---
+PorterDuffImageComposite 节点旨在使用 Porter-Duff 合成操作符执行图像合成。它允许根据各种混合模式组合源图像和目标图像，通过操纵图像透明度和以创造性的方式叠加图像来实现复杂视觉效果的创建。
+
+## 输入
+
+| 参数名称       | 数据类型 | 作用                                                         |
+|----------------|----------|--------------------------------------------------------------|
+| `来源图像`       | `IMAGE`  | 要合成到目标图像上的源图像张量。它在根据所选合成模式确定最终视觉效果中起着关键作用。 |
+| `来源图像alpha` | `MASK`   | 源图像的 alpha 通道，指定源图像中每个像素的透明度。它影响源图像与目标图像的混合方式。 |
+| `目标图像`  | `IMAGE`  | 作为背景的目标图像张量，其上合成源图像。它根据混合模式对最终合成图像有所贡献。 |
+| `目标图像alpha` | `MASK` | 目标图像的 alpha 通道，定义目标图像像素的透明度。它影响源图像和目标图像的混合。 |
+| `模式`         | COMBO[STRING] | 要应用的 Porter-Duff 合成模式，它决定了源图像和目标图像如何混合在一起。每种模式都会产生不同的视觉效果。 |
+| `PorterDuffMode` | `STRING` | Python 中 Porter-Duff 合成模式的数据类型。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `image`  | `IMAGE`  | 根据指定的 Porter-Duff 模式合成的图像。                     |
+| `mask`   | `MASK`   | 合成图像的 alpha 通道，指示每个像素的透明度。             |
diff --git a/zh-CN/built-in-nodes/Preview3D.mdx b/zh-CN/built-in-nodes/Preview3D.mdx
new file mode 100644
index 000000000..9afbd1d88
--- /dev/null
+++ b/zh-CN/built-in-nodes/Preview3D.mdx
@@ -0,0 +1,108 @@
+---
+title: "Preview3D - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Preview3D node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Preview3D"
+icon: "circle"
+mode: wide
+---
+Preview3D节点主要用来预览3D模型素材输出，这个节点接收两个输入，一个是 Load3D 节点的 `camera_info` 以及 `模型文件` 的路径信息，模型路径输入要求位于 `ComfyUI/output` 文件夹
+
+**支持格式**
+目前该节点支持多种 3D 文件格式，包括 `.gltf`、`.glb`、`.obj`、`.fbx` 和 `.stl`。
+
+**3D 节点预设**
+3D 节点的一些相关偏好设置可以在 ComfyUI 的设置菜单中进行设置，请参考下面的文档了解对应的设置
+[设置菜单](https://docs.comfy.org/zh-CN/interface/settings/3d)
+
+## 输入
+
+| 参数名称 | 数据类型        | 说明                                  |
+| ------- | ------------- | ------------------------------------- |
+| 相机信息 | LOAD3D_CAMERA | 相机信息                                |
+| 模型文件 | STRING | 位于`ComfyUI/output/` 路径下的模型文件路径 |
+
+## 模型画布(Canvas)区说明
+
+目前 ComfyUI 前端中 3D 相关节点 Canvas 部分共用了 canvas 部分的组件，所以除了部分功能差异之外他们的基础功能操作都是一致的。
+
+> 下面内容及界面在制作内容时以 Load3D 节点为主，实际节点界面及功能请参考实际节点界面
+
+Canvas 区域包含了诸多的视图操作，包括：
+
+- 预览视图设置（网格、背景色、预览视图）
+- 相机控制: 控制FOV、相机类型
+- 全局光照强度: 调节光照强度
+- 模型导出: 支持`GLB`、`OBJ`、`STL` 格式
+- 等
+
+![Load 3D 节点UI](/images/built-in-nodes/Preview3D/preview3d_canvas.jpg)
+
+1. 包含了 Load 3D 节点的多个菜单以及隐藏菜单
+2. 3D 视图操作轴
+
+### 1. 视图操作
+
+<video controls width="640" height="360">
+  <source src="https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/view_operations.mp4" type="video/mp4" />
+  您的浏览器不支持视频播放。
+</video>
+
+视图控制操作：
+
+- 鼠标左键点击 + 拖拽： 视图旋转控制
+- 鼠标右键 + 拖拽： 平移视图
+- 鼠标中键： 缩放控制
+- 坐标轴： 切换视图
+
+### 2. 左侧菜单功能
+
+![Menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu.webp)
+
+在预览区域，有些视图操作相关的菜单被隐藏在了菜单里，点击菜单按钮可以展开对应不同的菜单
+
+- 1. 场景（Scene）: 包含预览窗口网格、背景色、缩略图设置
+- 2. 模型（Model）: 模型渲染模式、纹理材质、上方向设置
+- 3. 摄像机（Camera）: 轴测视图和透视视图切换、透视视角大小设置
+- 4. 灯光（Light）: 场景全局光照强度
+- 5. 导出（Export）: 导出模型为其它格式（GLB、OBJ、STL）
+
+#### 场景（Scene）
+
+![scene menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_scene.webp)
+
+场景菜单提供了对场景的一些基础设置功能
+
+1. 显示 / 隐藏网格
+2. 设置背景色
+3. 点击上传设置背景图片
+4. 隐藏缩略预览图
+
+#### 模型(Model)
+
+![Menu_Scene](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_model.webp)
+
+模型菜单提供了一些模型的相关功能
+
+1. **上方向(Up direction)**: 确定模型的哪个轴为上方向
+2. **渲染模式（Material mode）**: 模型渲染模式切换 原始（Original）、法线(Normal)、线框(Wireframe)、线稿(Lineart)
+
+#### 摄像机（Camera）
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_camera.webp)
+
+该菜单提供了轴测视图和透视视图切换、透视视角大小设置
+
+1. **相机（Camera）**: 在轴测视图和正交视图之间快速切换
+2. **视场角(FOV)**: 调整 FOV 视角角度
+
+#### 灯光（Light）
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_light.webp)
+
+通过该菜单可以快速调节模型场景的全局光照强度
+
+#### 导出（Export）
+
+![menu_export](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_export.webp)
+
+该菜单提供了一个快速转换模型格式并导出的能力
diff --git a/zh-CN/built-in-nodes/Preview3DAnimation.mdx b/zh-CN/built-in-nodes/Preview3DAnimation.mdx
new file mode 100644
index 000000000..1c913bc93
--- /dev/null
+++ b/zh-CN/built-in-nodes/Preview3DAnimation.mdx
@@ -0,0 +1,108 @@
+---
+title: "Preview3DAnimation - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Preview3DAnimation node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Preview3DAnimation"
+icon: "circle"
+mode: wide
+---
+Preview3DAnimation节点主要用来预览3D模型素材输出，这个节点接收两个输入，一个是 Load3D 节点的 `camera_info` 以及 `模型文件` 的路径信息，模型路径输入要求位于 `ComfyUI/output` 文件夹
+
+**支持格式**
+目前该节点支持多种 3D 文件格式，包括 `.gltf`、`.glb`、`.obj`、`.fbx` 和 `.stl`。
+
+**3D 节点预设**
+3D 节点的一些相关偏好设置可以在 ComfyUI 的设置菜单中进行设置，请参考下面的文档了解对应的设置
+[设置菜单](https://docs.comfy.org/zh-CN/interface/settings/3d)
+
+## 输入
+
+| 参数名称 | 数据类型        | 说明                                  |
+| ------- | ------------- | ------------------------------------- |
+| 相机信息 | LOAD3D_CAMERA | 相机信息                                |
+| 模型文件 | STRING | 位于`ComfyUI/output/` 路径下的模型文件路径 |
+
+## 模型画布(Canvas)区说明
+
+目前 ComfyUI 前端中 3D 相关节点 Canvas 部分共用了 canvas 部分的组件，所以除了部分功能差异之外他们的基础功能操作都是一致的。
+
+> 下面内容及界面在制作内容时以 Load3D 节点为主，实际节点界面及功能请参考实际节点界面
+
+Canvas 区域包含了诸多的视图操作，包括：
+
+- 预览视图设置（网格、背景色、预览视图）
+- 相机控制: 控制FOV、相机类型
+- 全局光照强度: 调节光照强度
+- 模型导出: 支持`GLB`、`OBJ`、`STL` 格式
+- 等
+
+![Load 3D 节点UI](/images/built-in-nodes/Preview3DAnimation/preview3d_canvas.jpg)
+
+1. 包含了 Load 3D 节点的多个菜单以及隐藏菜单
+2. 3D 视图操作轴
+
+### 1. 视图操作
+
+<video controls width="640" height="360">
+  <source src="https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/view_operations.mp4" type="video/mp4" />
+  您的浏览器不支持视频播放。
+</video>
+
+视图控制操作：
+
+- 鼠标左键点击 + 拖拽： 视图旋转控制
+- 鼠标右键 + 拖拽： 平移视图
+- 鼠标中键： 缩放控制
+- 坐标轴： 切换视图
+
+### 2. 左侧菜单功能
+
+![Menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu.webp)
+
+在预览区域，有些视图操作相关的菜单被隐藏在了菜单里，点击菜单按钮可以展开对应不同的菜单
+
+- 1. 场景（Scene）: 包含预览窗口网格、背景色、缩略图设置
+- 2. 模型（Model）: 模型渲染模式、纹理材质、上方向设置
+- 3. 摄像机（Camera）: 轴测视图和透视视图切换、透视视角大小设置
+- 4. 灯光（Light）: 场景全局光照强度
+- 5. 导出（Export）: 导出模型为其它格式（GLB、OBJ、STL）
+
+#### 场景（Scene）
+
+![scene menu](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_scene.webp)
+
+场景菜单提供了对场景的一些基础设置功能
+
+1. 显示 / 隐藏网格
+2. 设置背景色
+3. 点击上传设置背景图片
+4. 隐藏缩略预览图
+
+#### 模型(Model)
+
+![Menu_Scene](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_model.webp)
+
+模型菜单提供了一些模型的相关功能
+
+1. **上方向(Up direction)**: 确定模型的哪个轴为上方向
+2. **渲染模式（Material mode）**: 模型渲染模式切换 原始（Original）、法线(Normal)、线框(Wireframe)、线稿(Lineart)
+
+#### 摄像机（Camera）
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_camera.webp)
+
+该菜单提供了轴测视图和透视视图切换、透视视角大小设置
+
+1. **相机（Camera）**: 在轴测视图和正交视图之间快速切换
+2. **视场角(FOV)**: 调整 FOV 视角角度
+
+#### 灯光（Light）
+
+![menu_modelmenu_camera](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_light.webp)
+
+通过该菜单可以快速调节模型场景的全局光照强度
+
+#### 导出（Export）
+
+![menu_export](https://raw.githubusercontent.com/Comfy-Org/embedded-docs/refs/heads/main/comfyui_embedded_docs/docs/Load3d/asset/menu_export.webp)
+
+该菜单提供了一个快速转换模型格式并导出的能力
diff --git a/zh-CN/built-in-nodes/PreviewAny.mdx b/zh-CN/built-in-nodes/PreviewAny.mdx
new file mode 100644
index 000000000..9b7ed505b
--- /dev/null
+++ b/zh-CN/built-in-nodes/PreviewAny.mdx
@@ -0,0 +1,22 @@
+---
+title: "PreviewAny - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PreviewAny node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PreviewAny"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAny/zh.md)
+
+PreviewAny 节点以文本格式显示任何输入数据类型的预览。它接受任何数据类型作为输入，并将其转换为可读的字符串表示形式以供查看。该节点通过尝试将不同数据类型（包括字符串、数字、布尔值和复杂对象）序列化为 JSON 格式来自动处理它们。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `源` | ANY | 是 | 任意数据类型 | 接受任意输入数据类型以进行预览显示 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| UI Text Display | TEXT | 在用户界面中显示已转换为文本格式的输入数据 |
diff --git a/zh-CN/built-in-nodes/PreviewAudio.mdx b/zh-CN/built-in-nodes/PreviewAudio.mdx
new file mode 100644
index 000000000..f2d8ae152
--- /dev/null
+++ b/zh-CN/built-in-nodes/PreviewAudio.mdx
@@ -0,0 +1,24 @@
+---
+title: "PreviewAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PreviewAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PreviewAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAudio/zh.md)
+
+PreviewAudio 节点生成临时音频预览文件，可在界面中显示。它继承自 SaveAudio 节点，但会将文件保存至临时目录并使用随机文件名前缀。这使用户能够快速预览音频输出而无需创建永久文件。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `音频` | AUDIO | 是 | - | 需要预览的音频数据 |
+| `prompt` | PROMPT | 否 | - | 内部使用的隐藏参数 |
+| `extra_pnginfo` | EXTRA_PNGINFO | 否 | - | 内部使用的隐藏参数 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `ui` | UI | 在界面中显示音频预览 |
diff --git a/zh-CN/built-in-nodes/PreviewImage.mdx b/zh-CN/built-in-nodes/PreviewImage.mdx
new file mode 100644
index 000000000..d62c248d4
--- /dev/null
+++ b/zh-CN/built-in-nodes/PreviewImage.mdx
@@ -0,0 +1,19 @@
+---
+title: "PreviewImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PreviewImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PreviewImage"
+icon: "circle"
+mode: wide
+---
+
+预览图像节点旨在创建临时预览图像。它自动为每个图像生成一个独特的临时文件名，将图像压缩到指定级别，并将其保存到临时目录中。这个功能特别适用于在处理期间生成图像的预览，而不影响原始文件。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `图像` | `IMAGE`  | `图像` 输入指定要处理并保存为临时预览图像的图像。这是节点的主要输入，决定了哪些图像将经历预览生成过程。 |
+
+## 输出
+
+该节点没有输出类型。
diff --git a/zh-CN/built-in-nodes/PrimitiveBoolean.mdx b/zh-CN/built-in-nodes/PrimitiveBoolean.mdx
new file mode 100644
index 000000000..a398b074b
--- /dev/null
+++ b/zh-CN/built-in-nodes/PrimitiveBoolean.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveBoolean - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveBoolean node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveBoolean"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveBoolean/zh.md)
+
+布尔节点提供了一种简单的方式，用于在工作流中传递布尔值（真/假）。它接收一个布尔输入值并原样输出相同的值，使您能够控制其他节点中的布尔参数。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `值` | BOOLEAN | 是 | true<br />false | 需要通过该节点传递的布尔值 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | BOOLEAN | 与输入值相同的布尔值 |
diff --git a/zh-CN/built-in-nodes/PrimitiveBoundingBox.mdx b/zh-CN/built-in-nodes/PrimitiveBoundingBox.mdx
new file mode 100644
index 000000000..cb5b1d6b2
--- /dev/null
+++ b/zh-CN/built-in-nodes/PrimitiveBoundingBox.mdx
@@ -0,0 +1,25 @@
+---
+title: "PrimitiveBoundingBox - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveBoundingBox node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveBoundingBox"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveBoundingBox/zh.md)
+
+PrimitiveBoundingBox 节点创建一个由其位置和大小定义的简单矩形区域。它接收左上角的 X 和 Y 坐标以及宽度和高度值，并输出一个边界框数据结构，该结构可在工作流中被其他节点使用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `x` | INT | 否 | 0 至 8192 | 边界框左上角的 X 坐标（默认值：0）。 |
+| `y` | INT | 否 | 0 至 8192 | 边界框左上角的 Y 坐标（默认值：0）。 |
+| `width` | INT | 否 | 1 至 8192 | 边界框的宽度（默认值：512）。 |
+| `height` | INT | 否 | 1 至 8192 | 边界框的高度（默认值：512）。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `bounding_box` | BOUNDING_BOX | 一个包含所定义矩形的 `x`、`y`、`width` 和 `height` 属性的数据结构。 |
diff --git a/zh-CN/built-in-nodes/PrimitiveFloat.mdx b/zh-CN/built-in-nodes/PrimitiveFloat.mdx
new file mode 100644
index 000000000..4ce3d7041
--- /dev/null
+++ b/zh-CN/built-in-nodes/PrimitiveFloat.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveFloat - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveFloat node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveFloat"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveFloat/zh.md)
+
+PrimitiveFloat 节点用于创建可在工作流中使用的浮点数值。它接收单个数字输入并输出相同的值，使您能够在 ComfyUI 流程中的不同节点之间定义和传递浮点数值。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `值` | FLOAT | 是 | -sys.maxsize 到 sys.maxsize | 要输出的浮点数值 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | FLOAT | 输入的浮点数值 |
diff --git a/zh-CN/built-in-nodes/PrimitiveInt.mdx b/zh-CN/built-in-nodes/PrimitiveInt.mdx
new file mode 100644
index 000000000..702e6ee15
--- /dev/null
+++ b/zh-CN/built-in-nodes/PrimitiveInt.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveInt - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveInt node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveInt"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveInt/zh.md)
+
+PrimitiveInt 节点为工作流中的整数值处理提供了简洁的解决方案。该节点接收整数输入并输出相同数值，适用于在节点间传递整数参数或为其他操作设定特定数值。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `数值` | INT | 是 | -9223372036854775807 到 9223372036854775807 | 需要输出的整数值 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | INT | 未经修改的输入整数值 |
diff --git a/zh-CN/built-in-nodes/PrimitiveString.mdx b/zh-CN/built-in-nodes/PrimitiveString.mdx
new file mode 100644
index 000000000..30419e05e
--- /dev/null
+++ b/zh-CN/built-in-nodes/PrimitiveString.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveString - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveString node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveString"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveString/zh.md)
+
+字符串节点提供了一种在您的工作流程中输入和传递文本数据的简单方式。它接收一个文本字符串作为输入，并输出未经更改的相同字符串，这对于向需要字符串参数的其他节点提供文本输入非常有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `值` | STRING | 是 | 任意文本 | 需要通过该节点传递的文本字符串 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `output` | STRING | 与输入提供的相同文本字符串 |
diff --git a/zh-CN/built-in-nodes/PrimitiveStringMultiline.mdx b/zh-CN/built-in-nodes/PrimitiveStringMultiline.mdx
new file mode 100644
index 000000000..e44bac8d5
--- /dev/null
+++ b/zh-CN/built-in-nodes/PrimitiveStringMultiline.mdx
@@ -0,0 +1,22 @@
+---
+title: "PrimitiveStringMultiline - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the PrimitiveStringMultiline node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "PrimitiveStringMultiline"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveStringMultiline/zh.md)
+
+PrimitiveStringMultiline 节点提供了一个多行文本输入字段，用于在工作流中输入和传递字符串值。它接受包含多行的文本输入，并原样输出相同的字符串值。当需要输入较长文本内容或跨多行的格式化文本时，此节点非常有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `值` | STRING | 是 | 无限制 | 可跨多行的文本输入值 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 与输入值完全相同的字符串 |
diff --git a/zh-CN/built-in-nodes/QuadrupleCLIPLoader.mdx b/zh-CN/built-in-nodes/QuadrupleCLIPLoader.mdx
new file mode 100644
index 000000000..626a6afed
--- /dev/null
+++ b/zh-CN/built-in-nodes/QuadrupleCLIPLoader.mdx
@@ -0,0 +1,14 @@
+---
+title: "QuadrupleCLIPLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the QuadrupleCLIPLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "QuadrupleCLIPLoader"
+icon: "circle"
+mode: wide
+---
+四重 CLIP 加载器 QuadrupleCLIPLoader 是 ComfyUI 的核心节点之一，最先添加在针对 HiDream I1 版本的模型支持上，如果你发现这个节点缺失，试着更新ComfyUI 版本到最新版本以保证节点支持。
+
+它需要 4 个 CLIP 模型，分别对应 `clip_name1`, `clip_name2`, `clip_name3`, `clip_name4` 这四个参数，并会提供一个 CLIP 模型输出用于后续节点使用。
+
+该节点会检测位于 `ComfyUI/models/text_encoders` 文件夹下的模型，
+同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，
+有时添加模型后你可能需要 **重载 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
diff --git a/zh-CN/built-in-nodes/QwenImageDiffsynthControlnet.mdx b/zh-CN/built-in-nodes/QwenImageDiffsynthControlnet.mdx
new file mode 100644
index 000000000..99c8288a8
--- /dev/null
+++ b/zh-CN/built-in-nodes/QwenImageDiffsynthControlnet.mdx
@@ -0,0 +1,29 @@
+---
+title: "QwenImageDiffsynthControlnet - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the QwenImageDiffsynthControlnet node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "QwenImageDiffsynthControlnet"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/QwenImageDiffsynthControlnet/zh.md)
+
+QwenImageDiffsynthControlnet 节点应用扩散合成控制网络补丁来修改基础模型的行为。它使用图像输入和可选遮罩，通过可调节的强度来指导模型的生成过程，创建一个融合了控制网络影响的修补后模型，以实现更受控的图像合成。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要用控制网络修补的基础模型 |
+| `model_patch` | MODEL_PATCH | 是 | - | 要应用于基础模型的控制网络补丁模型 |
+| `vae` | VAE | 是 | - | 扩散过程中使用的变分自编码器 |
+| `image` | IMAGE | 是 | - | 用于指导控制网络的输入图像（仅使用RGB通道） |
+| `strength` | FLOAT | 是 | -10.0 到 10.0 | 控制网络影响的强度（默认值：1.0） |
+| `mask` | MASK | 否 | - | 可选遮罩，定义控制网络应应用的区域（内部会自动反转） |
+
+**注意：** 当提供遮罩时，系统会自动反转遮罩（1.0 - mask）并重塑其尺寸以匹配控制网络处理的预期维度。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 应用了扩散合成控制网络补丁后的修改模型 |
diff --git a/zh-CN/built-in-nodes/RandomCropImages.mdx b/zh-CN/built-in-nodes/RandomCropImages.mdx
new file mode 100644
index 000000000..bf8c41682
--- /dev/null
+++ b/zh-CN/built-in-nodes/RandomCropImages.mdx
@@ -0,0 +1,27 @@
+---
+title: "RandomCropImages - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RandomCropImages node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RandomCropImages"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RandomCropImages/zh.md)
+
+随机裁剪图像节点会从每个输入图像中随机选择一个矩形区域，并将其裁剪至指定的宽度和高度。这通常用于数据增强，以创建训练图像的变体。裁剪的随机位置由种子值决定，确保可以复现相同的裁剪结果。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待裁剪的图像。 |
+| `width` | INT | 否 | 1 - 8192 | 裁剪区域的宽度（默认值：512）。 |
+| `height` | INT | 否 | 1 - 8192 | 裁剪区域的高度（默认值：512）。 |
+| `seed` | INT | 否 | 0 - 18446744073709551615 | 用于控制裁剪随机位置的数字（默认值：0）。 |
+
+**注意：** `width` 和 `height` 参数必须小于或等于输入图像的尺寸。如果指定的尺寸大于图像尺寸，裁剪将被限制在图像的边界内。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 应用随机裁剪后得到的图像。 |
diff --git a/zh-CN/built-in-nodes/RandomNoise.mdx b/zh-CN/built-in-nodes/RandomNoise.mdx
new file mode 100644
index 000000000..e8d33be83
--- /dev/null
+++ b/zh-CN/built-in-nodes/RandomNoise.mdx
@@ -0,0 +1,24 @@
+---
+title: "RandomNoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RandomNoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RandomNoise"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RandomNoise/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RandomNoise/en.md)
+
+RandomNoise 节点基于种子值生成随机噪声模式。它创建可重现的噪声，可用于各种图像处理和生成任务。相同的种子将始终产生相同的噪声模式，从而确保多次运行结果的一致性。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `噪波随机种` | INT | 是 | 0 到 18446744073709551615 | 用于生成随机噪声模式的种子值（默认值：0）。相同的种子将始终产生相同的噪声输出。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `noise` | NOISE | 基于提供的种子值生成的随机噪声模式。 |
diff --git a/zh-CN/built-in-nodes/RebatchImages.mdx b/zh-CN/built-in-nodes/RebatchImages.mdx
new file mode 100644
index 000000000..1b1487c56
--- /dev/null
+++ b/zh-CN/built-in-nodes/RebatchImages.mdx
@@ -0,0 +1,22 @@
+---
+title: "RebatchImages - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RebatchImages node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RebatchImages"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于将一批图像重新组织成新的批量配置，并根据指定调整批量大小。这一过程对于管理和优化批量操作中图像数据的处理至关重要，确保图像根据所需的批量大小进行分组，以便有效处理。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 要重新批量处理的图像列表。此参数对于确定将经历重新批量处理的输入数据至关重要。 |
+| `批量大小` | `INT` | 指定输出批量的期望大小。此参数直接影响输入图像的分组和处理方式，影响输出的结构。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `image` | `IMAGE` | 输出由图像批量列表组成，根据指定的批量大小重新组织。这允许在批量操作中灵活高效地处理图像数据。 |
diff --git a/zh-CN/built-in-nodes/RebatchLatents.mdx b/zh-CN/built-in-nodes/RebatchLatents.mdx
new file mode 100644
index 000000000..d7b53c7a0
--- /dev/null
+++ b/zh-CN/built-in-nodes/RebatchLatents.mdx
@@ -0,0 +1,22 @@
+---
+title: "RebatchLatents - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RebatchLatents node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RebatchLatents"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于根据指定的批量大小将潜在表示的批量重新组织成新的批量配置。它确保潜在样本被适当分组，处理尺寸和大小的变化，以便于进一步处理或模型推断。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent因素` | `LATENT` | `Latent因素`参数代表要重新批量处理的输入潜在表示。它对于确定输出批量的结构和内容至关重要。 |
+| `批量大小` | `INT` | `批量大小`参数指定输出中每个批量所需的样本数量。它直接影响将输入潜在表示分组和划分为新批量的方式。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 输出是重新组织的潜在表示批量，根据指定的批量大小进行了调整。它便于进一步的处理或分析。 |
diff --git a/zh-CN/built-in-nodes/RecordAudio.mdx b/zh-CN/built-in-nodes/RecordAudio.mdx
new file mode 100644
index 000000000..8cc0a48fe
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecordAudio.mdx
@@ -0,0 +1,24 @@
+---
+title: "RecordAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecordAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecordAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecordAudio/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecordAudio/en.md)
+
+RecordAudio 节点加载通过音频录制界面录制或选择的音频文件。它处理音频文件并将其转换为波形格式，可供工作流中的其他音频处理节点使用。该节点会自动检测采样率并准备音频数据以供进一步处理。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO_RECORD | 是 | N/A | 来自音频录制界面的音频录制输入 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | 包含波形和采样率信息的已处理音频数据 |
diff --git a/zh-CN/built-in-nodes/RecraftColorRGB.mdx b/zh-CN/built-in-nodes/RecraftColorRGB.mdx
new file mode 100644
index 000000000..63b61b3b3
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftColorRGB.mdx
@@ -0,0 +1,25 @@
+---
+title: "RecraftColorRGB - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftColorRGB node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftColorRGB"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftColorRGB/zh.md)
+
+通过选择特定的 RGB 值创建 Recraft 颜色。此节点允许您通过指定独立的红、绿、蓝值来定义颜色，这些值随后会被转换为可在其他 Recraft 操作中使用的 Recraft 颜色格式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `r` | INT | 是 | 0-255 | 颜色的红色值（默认：0） |
+| `g` | INT | 是 | 0-255 | 颜色的绿色值（默认：0） |
+| `b` | INT | 是 | 0-255 | 颜色的蓝色值（默认：0） |
+| `recraft_color` | COLOR | 否 | - | 用于扩展的可选现有 Recraft 颜色 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `recraft_color` | COLOR | 创建的包含指定 RGB 值的 Recraft 颜色对象 |
diff --git a/zh-CN/built-in-nodes/RecraftControls.mdx b/zh-CN/built-in-nodes/RecraftControls.mdx
new file mode 100644
index 000000000..cc51f29c9
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftControls.mdx
@@ -0,0 +1,23 @@
+---
+title: "RecraftControls - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftControls node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftControls"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftControls/zh.md)
+
+创建用于自定义 Recraft 生成的控件。此节点允许您配置将在 Recraft 图像生成过程中使用的颜色设置。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `colors` | COLOR | 否 | - | 主要元素的颜色设置 |
+| `background_color` | COLOR | 否 | - | 背景颜色设置 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `recraft_controls` | CONTROLS | 包含颜色设置的已配置 Recraft 控件 |
diff --git a/zh-CN/built-in-nodes/RecraftCreateStyleNode.mdx b/zh-CN/built-in-nodes/RecraftCreateStyleNode.mdx
new file mode 100644
index 000000000..f82b65a32
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftCreateStyleNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "RecraftCreateStyleNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftCreateStyleNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftCreateStyleNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreateStyleNode/zh.md)
+
+此节点通过上传参考图像来创建用于图像生成的自定义风格。您可以上传1到5张图像来定义新风格，节点将返回一个唯一的风格ID，可用于其他Recraft节点。所有上传图像的总文件大小不得超过5 MB。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `style` | STRING | 是 | `"realistic_image"`<br />`"digital_illustration"` | 生成图像的基础风格。 |
+| `images` | IMAGE | 是 | 1 到 5 张图像 | 用于创建自定义风格的1到5张参考图像集合。 |
+
+**注意：** `images` 输入中所有图像的总文件大小必须小于5 MB。如果超过此限制，节点将执行失败。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `style_id` | STRING | 新创建的自定义风格的唯一标识符。 |
diff --git a/zh-CN/built-in-nodes/RecraftCreativeUpscaleNode.mdx b/zh-CN/built-in-nodes/RecraftCreativeUpscaleNode.mdx
new file mode 100644
index 000000000..5a8b200f4
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftCreativeUpscaleNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecraftCreativeUpscaleNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftCreativeUpscaleNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftCreativeUpscaleNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreativeUpscaleNode/zh.md)
+
+该节点通过提高分辨率来增强栅格图像。它采用"创意放大"流程，专注于改善图像中的微小细节和面部特征。此操作通过外部 API 同步执行。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | | 待放大的输入图像。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `图像` | IMAGE | 经过放大且细节增强的结果图像。 |
diff --git a/zh-CN/built-in-nodes/RecraftCrispUpscaleNode.mdx b/zh-CN/built-in-nodes/RecraftCrispUpscaleNode.mdx
new file mode 100644
index 000000000..fc15ee6cd
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftCrispUpscaleNode.mdx
@@ -0,0 +1,24 @@
+---
+title: "RecraftCrispUpscaleNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftCrispUpscaleNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftCrispUpscaleNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCrispUpscaleNode/zh.md)
+
+同步放大图像。使用"清晰放大"工具增强给定的栅格图像，提高图像分辨率，使图像更清晰、更干净。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 需要放大的输入图像 |
+| `auth_token` | STRING | 否 | - | Recraft API 的认证令牌 |
+| `comfy_api_key` | STRING | 否 | - | Comfy.org 服务的 API 密钥 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `图像` | IMAGE | 经过放大处理后的图像，具有更高的分辨率和清晰度 |
diff --git a/zh-CN/built-in-nodes/RecraftImageInpaintingNode.mdx b/zh-CN/built-in-nodes/RecraftImageInpaintingNode.mdx
new file mode 100644
index 000000000..3e52544a8
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftImageInpaintingNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftImageInpaintingNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftImageInpaintingNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftImageInpaintingNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageInpaintingNode/zh.md)
+
+此节点基于文本提示和遮罩修改图像。它使用 Recraft API 智能编辑您通过遮罩定义的图像特定区域，同时保持图像的其余部分不变。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 待修改的输入图像 |
+| `mask` | MASK | 是 | - | 定义图像中哪些区域应被修改的遮罩 |
+| `提示词` | STRING | 是 | - | 图像生成的提示词（默认：空字符串） |
+| `数量` | INT | 是 | 1-6 | 要生成的图像数量（默认：1，最小值：1，最大值：6） |
+| `种子` | INT | 是 | 0-18446744073709551615 | 用于确定节点是否应重新运行的种子；无论种子如何，实际结果都是非确定性的（默认：0，最小值：0，最大值：18446744073709551615） |
+| `recraft_style` | STYLEV3 | 否 | - | Recraft API 的可选样式参数 |
+| `反向提示词` | STRING | 否 | - | 图像中不希望出现的元素的可选文本描述（默认：空字符串） |
+
+*注意：`image` 和 `mask` 必须同时提供才能进行修复操作。遮罩将自动调整大小以匹配图像尺寸。*
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 基于提示词和遮罩生成的修改后的图像 |
diff --git a/zh-CN/built-in-nodes/RecraftImageToImageNode.mdx b/zh-CN/built-in-nodes/RecraftImageToImageNode.mdx
new file mode 100644
index 000000000..92daf7c9c
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftImageToImageNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "RecraftImageToImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftImageToImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftImageToImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageToImageNode/zh.md)
+
+此节点基于文本提示和强度参数修改现有图像。它使用 Recraft API 根据提供的描述转换输入图像，同时根据强度设置保持与原始图像的一定相似度。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `image` | IMAGE | 是 | - | 待修改的输入图像 |
+| `提示词` | STRING | 是 | - | 图像生成的提示词（默认：""） |
+| `数量` | INT | 是 | 1-6 | 要生成的图像数量（默认：1） |
+| `强度` | FLOAT | 是 | 0.0-1.0 | 定义与原始图像的差异程度，应在 [0, 1] 范围内，0 表示几乎相同，1 表示相似度极低（默认：0.5） |
+| `种子` | INT | 是 | 0-18446744073709551615 | 用于确定节点是否应重新运行的种子值；无论种子值如何，实际结果都是非确定性的（默认：0） |
+| `recraft_style` | STYLEV3 | 否 | - | 图像生成的可选样式选择 |
+| `反向提示词` | STRING | 否 | - | 图像中不希望出现的元素的可选文本描述（默认：""） |
+| `recraft_controls` | CONTROLS | 否 | - | 通过 Recraft Controls 节点对生成过程进行可选额外控制 |
+
+**注意：** `seed` 参数仅触发节点的重新执行，但不能保证确定性结果。强度参数在内部会四舍五入到 2 位小数。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `image` | IMAGE | 基于输入图像和提示词生成的图像 |
diff --git a/zh-CN/built-in-nodes/RecraftRemoveBackgroundNode.mdx b/zh-CN/built-in-nodes/RecraftRemoveBackgroundNode.mdx
new file mode 100644
index 000000000..6e2f90d8d
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftRemoveBackgroundNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "RecraftRemoveBackgroundNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftRemoveBackgroundNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftRemoveBackgroundNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftRemoveBackgroundNode/zh.md)
+
+此节点使用 Recraft API 服务从图像中移除背景。它会处理输入批次中的每张图像，并返回带有透明背景的处理后图像以及指示被移除背景区域的对应 Alpha 蒙版。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 需要进行背景移除处理的输入图像 |
+| `auth_token` | STRING | 否 | - | 用于访问 Recraft API 的身份验证令牌 |
+| `comfy_api_key` | STRING | 否 | - | 用于 Comfy.org 服务集成的 API 密钥 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `图像` | IMAGE | 处理后带有透明背景的图像 |
+| `mask` | MASK | 指示被移除背景区域的 Alpha 通道蒙版 |
diff --git a/zh-CN/built-in-nodes/RecraftReplaceBackgroundNode.mdx b/zh-CN/built-in-nodes/RecraftReplaceBackgroundNode.mdx
new file mode 100644
index 000000000..979dc1a4b
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftReplaceBackgroundNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "RecraftReplaceBackgroundNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftReplaceBackgroundNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftReplaceBackgroundNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftReplaceBackgroundNode/zh.md)
+
+## 概述
+
+根据提供的提示词替换图像背景。该节点使用 Recraft API 根据您的文本描述为图像生成新背景，让您在保持主体完整的同时完全变换背景。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 要处理的输入图像 |
+| `提示词` | STRING | 是 | - | 图像生成的提示词（默认：空） |
+| `数量` | INT | 是 | 1-6 | 要生成的图像数量（默认：1） |
+| `种子` | INT | 是 | 0-18446744073709551615 | 控制节点是否重新运行的种子值；由于外部 API 的特性，实际结果具有不确定性（默认：0） |
+| `recraft 风格` | STYLEV3 | 否 | - | 生成背景的可选样式选择 |
+| `反向提示词` | STRING | 否 | - | 对图像中不希望出现的元素的可选文本描述（默认：空） |
+
+**注意：** `seed` 参数控制节点何时重新执行，但由于外部 API 的特性，无法保证结果的可重复性。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 已替换背景的生成图像 |
diff --git a/zh-CN/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx b/zh-CN/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx
new file mode 100644
index 000000000..39e76ebd3
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecraftStyleV3DigitalIllustration - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3DigitalIllustration node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3DigitalIllustration"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3DigitalIllustration/zh.md)
+
+此节点为 Recraft API 配置一个风格，具体选择 "digital_illustration"（数字插画）风格。它允许您选择一个可选的子风格，以进一步细化生成图像的艺术方向。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `子风格` | STRING | 否 | `"digital_illustration"`<br />`"digital_illustration_anime"`<br />`"digital_illustration_cartoon"`<br />`"digital_illustration_comic"`<br />`"digital_illustration_concept_art"`<br />`"digital_illustration_fantasy"`<br />`"digital_illustration_futuristic"`<br />`"digital_illustration_graffiti"`<br />`"digital_illustration_graphic_novel"`<br />`"digital_illustration_hyperrealistic"`<br />`"digital_illustration_ink"`<br />`"digital_illustration_manga"`<br />`"digital_illustration_minimalist"`<br />`"digital_illustration_pixel_art"`<br />`"digital_illustration_pop_art"`<br />`"digital_illustration_retro"`<br />`"digital_illustration_sci_fi"`<br />`"digital_illustration_sticker"`<br />`"digital_illustration_street_art"`<br />`"digital_illustration_surreal"`<br />`"digital_illustration_vector"` | 一个可选的子风格，用于指定特定类型的数字插画。如果未选择，则使用基础的 "digital_illustration" 风格。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `recraft_style` | STYLEV3 | 一个配置好的风格对象，包含选定的 "digital_illustration" 风格和可选的子风格，可传递给其他 Recraft API 节点使用。 |
diff --git a/zh-CN/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx b/zh-CN/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx
new file mode 100644
index 000000000..08ce67086
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx
@@ -0,0 +1,24 @@
+---
+title: "RecraftStyleV3InfiniteStyleLibrary - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3InfiniteStyleLibrary node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3InfiniteStyleLibrary"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3InfiniteStyleLibrary/zh.md)
+
+此节点允许您使用预先存在的 UUID 从 Recraft 的无限风格库中选择样式。它会根据提供的样式标识符检索样式信息，并返回以供其他 Recraft 节点使用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `style_id` | STRING | 是 | 任何有效的 UUID | 无限风格库中的样式 UUID。 |
+
+**注意：** `style_id` 输入不能为空。如果提供空字符串，节点将引发异常。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `recraft_style` | STYLEV3 | 从 Recraft 无限风格库中选择的样式对象 |
diff --git a/zh-CN/built-in-nodes/RecraftStyleV3LogoRaster.mdx b/zh-CN/built-in-nodes/RecraftStyleV3LogoRaster.mdx
new file mode 100644
index 000000000..fdc18ec14
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftStyleV3LogoRaster.mdx
@@ -0,0 +1,24 @@
+---
+title: "RecraftStyleV3LogoRaster - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3LogoRaster node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3LogoRaster"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3LogoRaster/zh.md)
+
+## 概述
+
+此节点允许您选择徽标栅格样式并从可用的子样式中进行选择。它专门用于生成具有基于栅格的样式选项的徽标设计，为徽标创建提供各种视觉处理效果。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `子风格` | STRING | 是 | 提供多个选项 | 应用于徽标生成的具体徽标栅格子样式 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 应用了所选栅格样式后生成的徽标图像 |
diff --git a/zh-CN/built-in-nodes/RecraftStyleV3RealisticImage.mdx b/zh-CN/built-in-nodes/RecraftStyleV3RealisticImage.mdx
new file mode 100644
index 000000000..da52bd4f1
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftStyleV3RealisticImage.mdx
@@ -0,0 +1,24 @@
+---
+title: "RecraftStyleV3RealisticImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3RealisticImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3RealisticImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3RealisticImage/zh.md)
+
+## 概述
+
+此节点创建用于 Recraft API 的现实主义图像风格配置。它允许您选择 realistic_image 风格，并从多种子风格选项中选择以自定义输出外观。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `子风格` | STRING | 是 | 提供多个选项 | 应用于 realistic_image 风格的具体子风格。如果设置为 "None"，将不应用任何子风格。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `recraft_style` | STYLEV3 | 返回包含 realistic_image 风格和所选子风格设置的 Recraft 风格配置对象。 |
diff --git a/zh-CN/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx b/zh-CN/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx
new file mode 100644
index 000000000..00590d049
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "RecraftStyleV3VectorIllustrationNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftStyleV3VectorIllustrationNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftStyleV3VectorIllustrationNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3VectorIllustrationNode/zh.md)
+
+此节点用于配置 Recraft API 的样式，具体选择 `vector_illustration` 风格。它允许您在该类别中可选地选择更具体的子风格。节点输出一个样式配置对象，可传递给其他 Recraft API 节点。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `substyle` | STRING | 否 | `"vector_illustration"`<br />`"vector_illustration_flat"`<br />`"vector_illustration_3d"`<br />`"vector_illustration_hand_drawn"`<br />`"vector_illustration_retro"`<br />`"vector_illustration_modern"`<br />`"vector_illustration_abstract"`<br />`"vector_illustration_geometric"`<br />`"vector_illustration_organic"`<br />`"vector_illustration_minimalist"`<br />`"vector_illustration_detailed"`<br />`"vector_illustration_colorful"`<br />`"vector_illustration_monochrome"`<br />`"vector_illustration_grayscale"`<br />`"vector_illustration_pastel"`<br />`"vector_illustration_vibrant"`<br />`"vector_illustration_muted"`<br />`"vector_illustration_warm"`<br />`"vector_illustration_cool"`<br />`"vector_illustration_neutral"`<br />`"vector_illustration_bold"`<br />`"vector_illustration_subtle"`<br />`"vector_illustration_playful"`<br />`"vector_illustration_serious"`<br />`"vector_illustration_elegant"`<br />`"vector_illustration_rustic"`<br />`"vector_illustration_urban"`<br />`"vector_illustration_nature"`<br />`"vector_illustration_fantasy"`<br />`"vector_illustration_sci_fi"`<br />`"vector_illustration_historical"`<br />`"vector_illustration_futuristic"`<br />`"vector_illustration_whimsical"`<br />`"vector_illustration_surreal"`<br />`"vector_illustration_realistic"`<br />`"vector_illustration_stylized"`<br />`"vector_illustration_cartoony"`<br />`"vector_illustration_anime"`<br />`"vector_illustration_comic"`<br />`"vector_illustration_pixel"`<br />`"vector_illustration_low_poly"`<br />`"vector_illustration_high_poly"`<br />`"vector_illustration_isometric"`<br />`"vector_illustration_orthographic"`<br />`"vector_illustration_perspective"`<br />`"vector_illustration_2d"`<br />`"vector_illustration_2.5d"`<br />`"vector_illustration_3d"`<br />`"vector_illustration_4d"` | 在 `vector_illustration` 类别中可选的具体子风格。如果未选择，则使用基础的 `vector_illustration` 风格。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `recraft_style` | STYLEV3 | 一个 Recraft API 样式配置对象，包含选定的 `vector_illustration` 风格及可选的子风格。可连接到其他 Recraft 节点。 |
diff --git a/zh-CN/built-in-nodes/RecraftTextToImageNode.mdx b/zh-CN/built-in-nodes/RecraftTextToImageNode.mdx
new file mode 100644
index 000000000..ecf38d3ce
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftTextToImageNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftTextToImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftTextToImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftTextToImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftTextToImageNode/zh.md)
+
+基于提示词和分辨率同步生成图像。此节点连接 Recraft API，根据文本描述和指定的尺寸及风格选项创建图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 用于图像生成的提示词。（默认：""） |
+| `size` | COMBO | 是 | "1024x1024"<br />"1152x896"<br />"896x1152"<br />"1216x832"<br />"832x1216"<br />"1344x768"<br />"768x1344"<br />"1536x640"<br />"640x1536" | 生成图像的尺寸。（默认："1024x1024"） |
+| `n` | INT | 是 | 1-6 | 要生成的图像数量。（默认：1） |
+| `seed` | INT | 是 | 0-18446744073709551615 | 用于确定节点是否应重新运行的种子值；无论种子值如何，实际结果都是非确定性的。（默认：0） |
+| `recraft_style` | COMBO | 否 | 多个可用选项 | 用于图像生成的可选风格选择。 |
+| `negative_prompt` | STRING | 否 | - | 对图像中不希望出现的元素的可选文本描述。（默认：""） |
+| `recraft_controls` | COMBO | 否 | 多个可用选项 | 通过 Recraft Controls 节点对生成过程进行可选额外控制。 |
+
+**注意：** `seed` 参数仅控制节点何时重新运行，但不会使图像生成具有确定性。即使使用相同的种子值，实际输出图像也会有所不同。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 生成的图像，以张量形式输出。 |
diff --git a/zh-CN/built-in-nodes/RecraftTextToVectorNode.mdx b/zh-CN/built-in-nodes/RecraftTextToVectorNode.mdx
new file mode 100644
index 000000000..d2bff34a3
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftTextToVectorNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftTextToVectorNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftTextToVectorNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftTextToVectorNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftTextToVectorNode/zh.md)
+
+根据提示和分辨率同步生成 SVG。此节点通过向 Recraft API 发送文本提示来创建矢量插图，并返回生成的 SVG 内容。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `提示词` | STRING | 是 | - | 用于图像生成的提示词。（默认：""） |
+| `子风格` | COMBO | 是 | 多个可用选项 | 用于生成的具体插图样式。选项由 RecraftStyleV3 中可用的矢量插图子样式决定。 |
+| `尺寸` | COMBO | 是 | 多个可用选项 | 生成图像的尺寸。（默认：1024x1024） |
+| `数量` | INT | 是 | 1-6 | 要生成的图像数量。（默认：1，最小值：1，最大值：6） |
+| `种子` | INT | 是 | 0-18446744073709551615 | 用于确定节点是否应重新运行的种子；无论种子如何，实际结果都是非确定性的。（默认：0，最小值：0，最大值：18446744073709551615） |
+| `反向提示词` | STRING | 否 | - | 可选的对图像中不希望出现的元素的文本描述。（默认：""） |
+| `Recraft 控制` | CONTROLS | 否 | - | 通过 Recraft Controls 节点对生成过程进行可选的额外控制。 |
+
+**注意：** `seed` 参数仅控制节点何时重新运行，但不会使生成结果具有确定性。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `SVG` | SVG | 以 SVG 格式生成的矢量插图 |
diff --git a/zh-CN/built-in-nodes/RecraftV4TextToImageNode.mdx b/zh-CN/built-in-nodes/RecraftV4TextToImageNode.mdx
new file mode 100644
index 000000000..b180605a4
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftV4TextToImageNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftV4TextToImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftV4TextToImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftV4TextToImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftV4TextToImageNode/zh.md)
+
+此节点使用 Recraft V4 或 V4 Pro AI 模型，根据文本描述生成图像。它会将您的提示词发送到外部 API 并返回生成的图像。您可以通过指定模型、图像尺寸和生成数量来控制输出。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | 不适用 | 用于图像生成的提示词。最多 10,000 个字符。 |
+| `negative_prompt` | STRING | 否 | 不适用 | 可选，描述图像中不希望出现的元素的文本。 |
+| `model` | COMBO | 是 | `"recraftv4"`<br />`"recraftv4_pro"` | 用于生成的模型。选择的模型决定了可用的图像尺寸。 |
+| `size` | COMBO | 是 | 随模型变化 | 生成图像的尺寸。可用选项取决于所选的模型。对于 `recraftv4`，默认值为 "1024x1024"。对于 `recraftv4_pro`，默认值为 "2048x2048"。 |
+| `n` | INT | 是 | 1 到 6 | 要生成的图像数量（默认值：1）。 |
+| `seed` | INT | 是 | 0 到 18446744073709551615 | 用于确定节点是否应重新运行的种子值；无论种子值如何，实际结果都是非确定性的（默认值：0）。 |
+| `recraft_controls` | CUSTOM | 否 | 不适用 | 可选，通过 Recraft Controls 节点对生成过程进行额外控制。 |
+
+**注意：** `size` 参数是一个动态输入，其可用选项会根据所选的 `model` 而变化。`seed` 值不能保证图像输出的可复现性。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 生成的单张图像或图像批次。 |
diff --git a/zh-CN/built-in-nodes/RecraftV4TextToVectorNode.mdx b/zh-CN/built-in-nodes/RecraftV4TextToVectorNode.mdx
new file mode 100644
index 000000000..def79516a
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftV4TextToVectorNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "RecraftV4TextToVectorNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftV4TextToVectorNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftV4TextToVectorNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftV4TextToVectorNode/zh.md)
+
+Recraft V4 文本转矢量节点可根据文本描述生成可缩放矢量图形（SVG）插图。它通过连接外部 API 来使用 Recraft V4 或 Recraft V4 Pro 模型进行图像生成。该节点会根据您的提示输出一个或多个 SVG 图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | 不适用 | 用于图像生成的提示词。最多 10,000 个字符。 |
+| `negative_prompt` | STRING | 否 | 不适用 | 对图像中不希望出现的元素的可选文本描述。 |
+| `model` | COMBO | 是 | `"recraftv4"`<br />`"recraftv4_pro"` | 用于生成的模型。选择不同的模型会改变可用的 `size` 选项。 |
+| `size` | COMBO | 是 | 对于 `recraftv4`: `"1024x1024"`, `"1152x896"`, `"896x1152"`, `"1216x832"`, `"832x1216"`, `"1344x768"`, `"768x1344"`, `"1536x640"`, `"640x1536"`<br />对于 `recraftv4_pro`: `"2048x2048"`, `"2304x1792"`, `"1792x2304"`, `"2432x1664"`, `"1664x2432"`, `"2688x1536"`, `"1536x2688"`, `"3072x1280"`, `"1280x3072"` | 生成图像的尺寸。可用选项取决于所选的 `model`。默认值为 `recraftv4` 模型为 `"1024x1024"`，`recraftv4_pro` 模型为 `"2048x2048"`。 |
+| `n` | INT | 是 | 1 到 6 | 要生成的图像数量（默认值：1）。 |
+| `seed` | INT | 是 | 0 到 18446744073709551615 | 用于确定节点是否应重新运行的种子值；无论种子值如何，实际结果都是非确定性的。 |
+| `recraft_controls` | CUSTOM | 否 | 不适用 | 通过 Recraft Controls 节点对生成过程进行可选额外控制。 |
+
+**注意：** `size` 参数是一个动态输入，其可用选项会根据所选的 `model` 而变化。`seed` 值不能保证外部 API 产生可重现的结果。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | SVG | 生成的可缩放矢量图形（SVG）图像。 |
diff --git a/zh-CN/built-in-nodes/RecraftVectorizeImageNode.mdx b/zh-CN/built-in-nodes/RecraftVectorizeImageNode.mdx
new file mode 100644
index 000000000..197a1cb38
--- /dev/null
+++ b/zh-CN/built-in-nodes/RecraftVectorizeImageNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "RecraftVectorizeImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RecraftVectorizeImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RecraftVectorizeImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftVectorizeImageNode/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftVectorizeImageNode/en.md)
+
+从输入图像同步生成 SVG。该节点通过处理输入批次中的每个图像并将结果组合成单个 SVG 输出来将栅格图像转换为矢量图形格式。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 要转换为 SVG 格式的输入图像 |
+| `auth_token` | AUTH_TOKEN_COMFY_ORG | 否 | - | API 访问的认证令牌 |
+| `comfy_api_key` | API_KEY_COMFY_ORG | 否 | - | Comfy.org 服务的 API 密钥 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `SVG` | SVG | 生成的矢量图形输出，包含所有处理后的图像结果 |
diff --git a/zh-CN/built-in-nodes/ReferenceLatent.mdx b/zh-CN/built-in-nodes/ReferenceLatent.mdx
new file mode 100644
index 000000000..630b38941
--- /dev/null
+++ b/zh-CN/built-in-nodes/ReferenceLatent.mdx
@@ -0,0 +1,25 @@
+---
+title: "ReferenceLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ReferenceLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ReferenceLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReferenceLatent/zh.md)
+
+## 概述
+
+此节点为编辑模型设置引导隐变量。它接收条件数据和一个可选的隐变量输入，然后修改条件数据以包含参考隐变量信息。如果模型支持，您可以链接多个 ReferenceLatent 节点来设置多个参考图像。
+
+## 输入
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | 是 | - | 将被修改以包含参考隐变量信息的条件数据 |
+| `latent` | LATENT | 否 | - | 用作编辑模型参考的可选隐变量数据 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | CONDITIONING | 包含参考隐变量信息的已修改条件数据 |
diff --git a/zh-CN/built-in-nodes/ReferenceTimbreAudio.mdx b/zh-CN/built-in-nodes/ReferenceTimbreAudio.mdx
new file mode 100644
index 000000000..ac643dc6c
--- /dev/null
+++ b/zh-CN/built-in-nodes/ReferenceTimbreAudio.mdx
@@ -0,0 +1,23 @@
+---
+title: "ReferenceTimbreAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ReferenceTimbreAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ReferenceTimbreAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReferenceTimbreAudio/zh.md)
+
+此节点为“ace step 1.5”流程设置参考音频音色。其工作原理是接收一个条件输入，并可选择性地接收一个音频的潜在表示，然后将该潜在数据附加到条件数据上，以供工作流中的后续节点使用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | 是 | | 将附加参考音频信息的条件数据。 |
+| `latent` | LATENT | 否 | | 参考音频的可选潜在表示。如果提供，其样本将被添加到条件数据中。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | 修改后的条件数据。如果提供了可选的 `latent` 输入，则现在包含参考音频音色的潜在表示。 |
diff --git a/zh-CN/built-in-nodes/RegexExtract.mdx b/zh-CN/built-in-nodes/RegexExtract.mdx
new file mode 100644
index 000000000..3c19ba2d8
--- /dev/null
+++ b/zh-CN/built-in-nodes/RegexExtract.mdx
@@ -0,0 +1,30 @@
+---
+title: "RegexExtract - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RegexExtract node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RegexExtract"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexExtract/zh.md)
+
+RegexExtract 节点使用正则表达式在文本中搜索模式。它可以查找第一个匹配项、所有匹配项、匹配项中的特定组，或多个匹配项中的所有组。该节点支持多种正则表达式标志，用于控制大小写敏感性、多行匹配和 dotall 行为。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | 是 | - | 要搜索模式的输入文本 |
+| `regex_pattern` | STRING | 是 | - | 要搜索的正则表达式模式 |
+| `mode` | COMBO | 是 | "First Match"<br />"All Matches"<br />"First Group"<br />"All Groups" | 提取模式决定返回匹配项的哪些部分 |
+| `case_insensitive` | BOOLEAN | 否 | - | 匹配时是否忽略大小写（默认：True） |
+| `multiline` | BOOLEAN | 否 | - | 是否将字符串视为多行（默认：False） |
+| `dotall` | BOOLEAN | 否 | - | 点号(.)是否匹配换行符（默认：False） |
+| `group_index` | INT | 否 | 0-100 | 使用组模式时要提取的捕获组索引（默认：1） |
+
+**注意：** 当使用"First Group"或"All Groups"模式时，`group_index` 参数指定要提取的捕获组。组0代表整个匹配项，而组1+代表正则表达式模式中编号的捕获组。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 根据所选模式和参数提取的文本 |
diff --git a/zh-CN/built-in-nodes/RegexMatch.mdx b/zh-CN/built-in-nodes/RegexMatch.mdx
new file mode 100644
index 000000000..ac816eff3
--- /dev/null
+++ b/zh-CN/built-in-nodes/RegexMatch.mdx
@@ -0,0 +1,26 @@
+---
+title: "RegexMatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RegexMatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RegexMatch"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexMatch/zh.md)
+
+RegexMatch 节点用于检查文本字符串是否与指定的正则表达式模式匹配。它会在输入字符串中搜索正则表达式模式的任何出现位置，并返回是否找到匹配项。您可以配置各种正则表达式标志，如大小写敏感性、多行模式和点号匹配模式，以控制模式匹配的行为方式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | 是 | - | 需要搜索匹配项的文本字符串 |
+| `regex_pattern` | STRING | 是 | - | 用于与字符串匹配的正则表达式模式 |
+| `case_insensitive` | BOOLEAN | 否 | - | 匹配时是否忽略大小写（默认值：True） |
+| `multiline` | BOOLEAN | 否 | - | 是否启用正则表达式匹配的多行模式（默认值：False） |
+| `dotall` | BOOLEAN | 否 | - | 是否启用正则表达式匹配的点号匹配模式（默认值：False） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `matches` | BOOLEAN | 如果正则表达式模式匹配输入字符串的任何部分则返回 True，否则返回 False |
diff --git a/zh-CN/built-in-nodes/RegexReplace.mdx b/zh-CN/built-in-nodes/RegexReplace.mdx
new file mode 100644
index 000000000..7495f6b39
--- /dev/null
+++ b/zh-CN/built-in-nodes/RegexReplace.mdx
@@ -0,0 +1,28 @@
+---
+title: "RegexReplace - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RegexReplace node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RegexReplace"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexReplace/zh.md)
+
+RegexReplace 节点使用正则表达式模式在字符串中查找并替换文本。它允许您搜索文本模式并将其替换为新文本，并提供控制模式匹配方式的选项，包括大小写敏感性、多行匹配以及限制替换次数。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | 是 | - | 要进行搜索和替换的输入文本字符串 |
+| `regex_pattern` | STRING | 是 | - | 在输入字符串中搜索的正则表达式模式 |
+| `replace` | STRING | 是 | - | 用于替换匹配模式的文本 |
+| `case_insensitive` | BOOLEAN | 否 | - | 启用时，使模式匹配忽略大小写差异（默认：True） |
+| `multiline` | BOOLEAN | 否 | - | 启用时，改变 ^ 和 $ 的行为，使其匹配每行的开头/结尾，而不仅仅是整个字符串的开头/结尾（默认：False） |
+| `dotall` | BOOLEAN | 否 | - | 启用时，点号 (.) 字符将匹配包括换行符在内的任何字符。禁用时，点号不会匹配换行符（默认：False） |
+| `count` | INT | 否 | 0-100 | 最大替换次数。设置为 0 可替换所有匹配项（默认）。设置为 1 仅替换第一个匹配项，2 替换前两个匹配项，依此类推（默认：0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 应用了指定替换后的修改字符串 |
diff --git a/zh-CN/built-in-nodes/RenormCFG.mdx b/zh-CN/built-in-nodes/RenormCFG.mdx
new file mode 100644
index 000000000..01eb182e0
--- /dev/null
+++ b/zh-CN/built-in-nodes/RenormCFG.mdx
@@ -0,0 +1,24 @@
+---
+title: "RenormCFG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RenormCFG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RenormCFG"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RenormCFG/zh.md)
+
+RenormCFG 节点通过应用条件缩放和归一化来改进扩散模型中的无分类器引导（CFG）过程。它根据指定的时间步阈值和重归一化因子调整去噪过程，从而在图像生成过程中控制条件预测与无条件预测的影响强度。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用重归一化 CFG 的扩散模型 |
+| `cfg_trunc` | FLOAT | 否 | 0.0 - 100.0 | 应用 CFG 缩放的时间步阈值（默认值：100.0） |
+| `renorm_cfg` | FLOAT | 否 | 0.0 - 100.0 | 控制条件引导强度的重归一化因子（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 已应用重归一化 CFG 功能的修改后模型 |
diff --git a/zh-CN/built-in-nodes/RepeatImageBatch.mdx b/zh-CN/built-in-nodes/RepeatImageBatch.mdx
new file mode 100644
index 000000000..debdba656
--- /dev/null
+++ b/zh-CN/built-in-nodes/RepeatImageBatch.mdx
@@ -0,0 +1,22 @@
+---
+title: "RepeatImageBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RepeatImageBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RepeatImageBatch"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于复制指定数量的给定图像，创建一批相同的图像。此功能适用于需要相同图像的多个实例的操作，例如批量处理或数据增强。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | `图像`参数代表要复制的图像。它对于定义将在整个批量中复制的内容至关重要。 |
+| `数量` | `INT` | `数量`参数指定输入图像应复制的次数。它直接影响输出批量的大小，允许灵活地创建批量。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图像` | `IMAGE` | 输出是一批图像，每个图像都与输入图像相同，根据指定的`数量`复制。 |
diff --git a/zh-CN/built-in-nodes/RepeatLatentBatch.mdx b/zh-CN/built-in-nodes/RepeatLatentBatch.mdx
new file mode 100644
index 000000000..e01254627
--- /dev/null
+++ b/zh-CN/built-in-nodes/RepeatLatentBatch.mdx
@@ -0,0 +1,22 @@
+---
+title: "RepeatLatentBatch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RepeatLatentBatch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RepeatLatentBatch"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于复制给定批量的潜在表示指定的次数，可能包括额外的数据，如噪声遮罩和批量索引。此功能对于需要相同潜在数据的多个实例的操作至关重要，例如数据增强或特定的生成任务。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Latent` | `LATENT` | `Latent`参数表示要复制的潜在表示。它对于定义将经历重复的数据至关重要。 |
+| `数量` | `INT` | `数量`参数指定输入样本应重复的次数。它直接影响输出批量的大小，从而影响计算负载和生成数据的多样性。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `latent` | `LATENT` | 输出是根据指定的`数量`复制的输入潜在表示的修改版本。如果适用，它可能包括复制的噪声遮罩和调整后的批量索引。 |
diff --git a/zh-CN/built-in-nodes/ReplaceText.mdx b/zh-CN/built-in-nodes/ReplaceText.mdx
new file mode 100644
index 000000000..d99511514
--- /dev/null
+++ b/zh-CN/built-in-nodes/ReplaceText.mdx
@@ -0,0 +1,24 @@
+---
+title: "ReplaceText - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ReplaceText node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ReplaceText"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReplaceText/zh.md)
+
+Replace Text 节点执行简单的文本替换操作。它在输入文本中搜索指定的文本片段，并将所有匹配项替换为新的文本片段。该操作将应用于提供给节点的所有文本输入。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | 是 | - | 需要处理的文本。 |
+| `find` | STRING | 否 | - | 需要查找并替换的文本（默认：空字符串）。 |
+| `replace` | STRING | 否 | - | 用于替换找到文本的新文本（默认：空字符串）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `text` | STRING | 处理后的文本，其中所有 `find` 文本的匹配项都已替换为 `replace` 文本。 |
diff --git a/zh-CN/built-in-nodes/ReplaceVideoLatentFrames.mdx b/zh-CN/built-in-nodes/ReplaceVideoLatentFrames.mdx
new file mode 100644
index 000000000..8948b757f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ReplaceVideoLatentFrames.mdx
@@ -0,0 +1,29 @@
+---
+title: "ReplaceVideoLatentFrames - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ReplaceVideoLatentFrames node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ReplaceVideoLatentFrames"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReplaceVideoLatentFrames/zh.md)
+
+ReplaceVideoLatentFrames 节点将源潜在视频中的帧插入到目标潜在视频中，从指定的帧索引开始。如果未提供源潜在视频，则目标潜在视频将原样返回。该节点支持负索引，并且如果源帧无法完全放入目标视频中，会发出警告。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `destination` | LATENT | 是 | - | 目标潜在视频，其帧将被替换。 |
+| `source` | LATENT | 否 | - | 提供要插入到目标潜在视频中的帧的源潜在视频。如果未提供，则目标潜在视频将原样返回。 |
+| `index` | INT | 否 | -MAX_RESOLUTION 到 MAX_RESOLUTION | 目标潜在视频中开始放置源潜在视频帧的起始潜在帧索引。负值表示从末尾开始计数（默认值：0）。 |
+
+**约束条件：**
+
+* `index` 必须在目标潜在视频的帧数范围内。如果超出范围，将记录警告并原样返回目标视频。
+* 从指定的 `index` 开始，源潜在视频的帧必须能完全放入目标潜在视频的帧中。如果不能，将记录警告并原样返回目标视频。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | LATENT | 执行帧替换操作后得到的潜在视频。 |
diff --git a/zh-CN/built-in-nodes/Reroute.mdx b/zh-CN/built-in-nodes/Reroute.mdx
new file mode 100644
index 000000000..9a58a4123
--- /dev/null
+++ b/zh-CN/built-in-nodes/Reroute.mdx
@@ -0,0 +1,21 @@
+---
+title: "Reroute - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Reroute node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Reroute"
+icon: "circle"
+mode: wide
+---
+
+节点名称：Reroute 转接点
+节点用途:主要用于整理ComfyUI工作流中过长的连接线逻辑。
+
+## 如何使用 Reroute 转接点
+
+| 菜单选项 | 描述 |
+| --- | --- |
+| 显示类型 (Show Type) | 显示节点的这个类型属性 |
+| 默认隐藏类型 (Hide Type By Default) | 默认隐藏类型，显示节点的这个类型属性 |
+| 设置垂直 (Set Vertical) | 设置节点的连线方向为垂直 |
+| 设置水平 (Set Horizontal) | 设置节点的连线方向为水平 |
+
+当你的连线逻辑过长过于复杂时，如果你想要整理界面，你可以在两个连接点中间插入 ```Reroute``` 节点，这个节点的输入输出不限制类型，默认的样式是水平的，你可以通过右键菜单将连线方向修改成垂直方向。
diff --git a/zh-CN/built-in-nodes/RescaleCFG.mdx b/zh-CN/built-in-nodes/RescaleCFG.mdx
new file mode 100644
index 000000000..fc095be66
--- /dev/null
+++ b/zh-CN/built-in-nodes/RescaleCFG.mdx
@@ -0,0 +1,21 @@
+---
+title: "RescaleCFG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RescaleCFG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RescaleCFG"
+icon: "circle"
+mode: wide
+---
+RescaleCFG 节点旨在根据指定的乘数调整模型输出的条件和非条件比例，目的是实现更加平衡和可控的生成过程。它通过重新调整模型的输出来修改条件和非条件组件的影响，从而可能增强模型的性能或输出质量。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+| -------- | -------- | ------------------------------------------------------------ |
+| `模型`  | MODEL    | 表示要调整的生成模型。节点对模型的输出应用重新缩放函数，直接影响生成过程。 |
+| `乘数` | `FLOAT` | 控制应用于模型输出的重新缩放程度。它决定了原始和重新缩放组件之间的平衡，影响最终输出的特性。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                       |
+| -------- | -------- | ------------------------------------------ |
+| `模型`  | MODEL    | 修改后的模型，调整了条件和非条件比例。预期该模型由于应用的重新缩放，将产生具有潜在增强特性的输出。 |
diff --git a/zh-CN/built-in-nodes/ResizeAndPadImage.mdx b/zh-CN/built-in-nodes/ResizeAndPadImage.mdx
new file mode 100644
index 000000000..62f409cd1
--- /dev/null
+++ b/zh-CN/built-in-nodes/ResizeAndPadImage.mdx
@@ -0,0 +1,26 @@
+---
+title: "ResizeAndPadImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResizeAndPadImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResizeAndPadImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeAndPadImage/zh.md)
+
+ResizeAndPadImage 节点可将图像调整至指定尺寸范围内，同时保持原始宽高比例。该节点会按比例缩放图像以适应目标宽度和高度，随后在边缘区域添加填充以补足剩余空间。用户可自定义填充颜色和插值方法，从而控制填充区域的外观表现和图像缩放质量。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 需要调整尺寸并添加填充的输入图像 |
+| `target_width` | INT | 是 | 1 至 MAX_RESOLUTION | 输出图像的目标宽度（默认值：512） |
+| `target_height` | INT | 是 | 1 至 MAX_RESOLUTION | 输出图像的目标高度（默认值：512） |
+| `padding_color` | COMBO | 是 | "white"<br />"black" | 用于调整后图像周边填充区域的颜色 |
+| `interpolation` | COMBO | 是 | "area"<br />"bicubic"<br />"nearest-exact"<br />"bilinear"<br />"lanczos" | 用于图像尺寸调整的插值方法 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 经过尺寸调整和填充处理后的输出图像 |
diff --git a/zh-CN/built-in-nodes/ResizeImageMaskNode.mdx b/zh-CN/built-in-nodes/ResizeImageMaskNode.mdx
new file mode 100644
index 000000000..9b806cfcb
--- /dev/null
+++ b/zh-CN/built-in-nodes/ResizeImageMaskNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "ResizeImageMaskNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResizeImageMaskNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResizeImageMaskNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImageMaskNode/zh.md)
+
+Resize Image/Mask 节点提供多种方法来改变输入图像或遮罩的尺寸。它可以通过缩放系数、设置特定尺寸、匹配另一输入的尺寸或基于像素数量进行调整，并使用多种插值方法来保证质量。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `input` | IMAGE 或 MASK | 是 | N/A | 待调整尺寸的图像或遮罩。 |
+| `resize_type` | COMBO | 是 | `SCALE_BY`<br />`SCALE_DIMENSIONS`<br />`SCALE_LONGER_DIMENSION`<br />`SCALE_SHORTER_DIMENSION`<br />`SCALE_WIDTH`<br />`SCALE_HEIGHT`<br />`SCALE_TOTAL_PIXELS`<br />`MATCH_SIZE` | 用于确定新尺寸的方法。所需的参数会根据所选类型而变化。 |
+| `multiplier` | FLOAT | 否 | 0.01 到 8.0 | 缩放系数。当 `resize_type` 为 `SCALE_BY` 时必需（默认值：1.00）。 |
+| `width` | INT | 否 | 0 到 8192 | 目标宽度（像素）。当 `resize_type` 为 `SCALE_DIMENSIONS` 或 `SCALE_WIDTH` 时必需（默认值：512）。 |
+| `height` | INT | 否 | 0 到 8192 | 目标高度（像素）。当 `resize_type` 为 `SCALE_DIMENSIONS` 或 `SCALE_HEIGHT` 时必需（默认值：512）。 |
+| `crop` | COMBO | 否 | `"disabled"`<br />`"center"` | 当尺寸与宽高比不匹配时应用的裁剪方法。仅在 `resize_type` 为 `SCALE_DIMENSIONS` 或 `MATCH_SIZE` 时可用（默认值："center"）。 |
+| `longer_size` | INT | 否 | 0 到 8192 | 图像较长边的目标尺寸。当 `resize_type` 为 `SCALE_LONGER_DIMENSION` 时必需（默认值：512）。 |
+| `shorter_size` | INT | 否 | 0 到 8192 | 图像较短边的目标尺寸。当 `resize_type` 为 `SCALE_SHORTER_DIMENSION` 时必需（默认值：512）。 |
+| `megapixels` | FLOAT | 否 | 0.01 到 16.0 | 目标总像素数（百万像素）。当 `resize_type` 为 `SCALE_TOTAL_PIXELS` 时必需（默认值：1.0）。 |
+| `match` | IMAGE 或 MASK | 否 | N/A | 一个图像或遮罩，输入将调整尺寸以匹配其尺寸。当 `resize_type` 为 `MATCH_SIZE` 时必需。 |
+| `scale_method` | COMBO | 是 | `"nearest-exact"`<br />`"bilinear"`<br />`"area"`<br />`"bicubic"`<br />`"lanczos"` | 用于缩放的插值算法（默认值："area"）。 |
+
+**注意：** `crop` 参数仅在 `resize_type` 设置为 `SCALE_DIMENSIONS` 或 `MATCH_SIZE` 时可用且相关。当使用 `SCALE_WIDTH` 或 `SCALE_HEIGHT` 时，另一维度会自动缩放以保持原始宽高比。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `resized` | IMAGE 或 MASK | 调整尺寸后的图像或遮罩，其数据类型与输入一致。 |
diff --git a/zh-CN/built-in-nodes/ResizeImagesByLongerEdge.mdx b/zh-CN/built-in-nodes/ResizeImagesByLongerEdge.mdx
new file mode 100644
index 000000000..37e9e5fc6
--- /dev/null
+++ b/zh-CN/built-in-nodes/ResizeImagesByLongerEdge.mdx
@@ -0,0 +1,25 @@
+---
+title: "ResizeImagesByLongerEdge - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResizeImagesByLongerEdge node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResizeImagesByLongerEdge"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByLongerEdge/zh.md)
+
+## 概述
+
+Resize Images by Longer Edge 节点通过调整图像尺寸，使其最长边与指定的目标长度匹配。该节点会自动判断图像的宽度或高度哪一边更长，并按比例缩放另一维度以保持原始宽高比。此功能适用于基于图像最大维度进行尺寸标准化的场景。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 需要调整尺寸的输入图像或图像批次。 |
+| `longer_edge` | INT | 否 | 1 - 8192 | 最长边的目标长度。较短边将按比例缩放。（默认值：1024） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 调整尺寸后的图像或图像批次。输出的图像数量与输入相同，每张图像的最长边均与指定的 `longer_edge` 长度匹配。 |
diff --git a/zh-CN/built-in-nodes/ResizeImagesByShorterEdge.mdx b/zh-CN/built-in-nodes/ResizeImagesByShorterEdge.mdx
new file mode 100644
index 000000000..58f8741d1
--- /dev/null
+++ b/zh-CN/built-in-nodes/ResizeImagesByShorterEdge.mdx
@@ -0,0 +1,23 @@
+---
+title: "ResizeImagesByShorterEdge - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResizeImagesByShorterEdge node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResizeImagesByShorterEdge"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByShorterEdge/zh.md)
+
+此节点通过调整图像尺寸，使较短边的长度与指定的目标值匹配，从而实现图像缩放。它会计算新的尺寸以保持原始图像的宽高比，并返回缩放后的图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 需要调整尺寸的输入图像。 |
+| `shorter_edge` | INT | 否 | 1 至 8192 | 较短边的目标长度。（默认值：512） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 调整尺寸后的图像。 |
diff --git a/zh-CN/built-in-nodes/ResolutionBucket.mdx b/zh-CN/built-in-nodes/ResolutionBucket.mdx
new file mode 100644
index 000000000..3d18c8148
--- /dev/null
+++ b/zh-CN/built-in-nodes/ResolutionBucket.mdx
@@ -0,0 +1,26 @@
+---
+title: "ResolutionBucket - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ResolutionBucket node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ResolutionBucket"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResolutionBucket/zh.md)
+
+此节点根据分辨率对潜在图像列表及其对应的条件数据进行组织。它将具有相同高度和宽度的项目分组，为每个独特的分辨率创建独立的批次。这一过程有助于为高效训练准备数据，因为它允许模型同时处理多个相同尺寸的项目。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `latents` | LATENT | 是 | N/A | 需要按分辨率进行分桶的潜在字典列表。 |
+| `conditioning` | CONDITIONING | 是 | N/A | 条件列表（长度必须与 `latents` 匹配）。 |
+
+**注意：** `latents` 列表中的项目数量必须与 `conditioning` 列表中的项目数量完全匹配。每个潜在字典可以包含一批样本，而对应的条件列表必须包含与该批次匹配数量的条件项。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `latents` | LATENT | 已分批次处理的潜在字典列表，每个分辨率桶对应一个。 |
+| `conditioning` | CONDITIONING | 条件列表，每个分辨率桶对应一个。 |
diff --git a/zh-CN/built-in-nodes/Rodin3D_Detail.mdx b/zh-CN/built-in-nodes/Rodin3D_Detail.mdx
new file mode 100644
index 000000000..e14f64da3
--- /dev/null
+++ b/zh-CN/built-in-nodes/Rodin3D_Detail.mdx
@@ -0,0 +1,25 @@
+---
+title: "Rodin3D_Detail - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Detail node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Detail"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Detail/zh.md)
+
+Rodin 3D Detail 节点通过 Rodin API 生成精细的 3D 资源。该节点接收输入图像并通过 Rodin 服务进行处理，最终创建具有精细几何结构和材质的高质量 3D 模型。该节点负责处理从任务创建到下载最终 3D 模型文件的完整工作流程。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | 是 | - | 用于生成 3D 模型的输入图像 |
+| `Seed` | INT | 是 | - | 用于可重复结果的随机种子值 |
+| `Material_Type` | STRING | 是 | - | 应用于 3D 模型的材质类型 |
+| `Polygon_count` | STRING | 是 | - | 生成 3D 模型的目标多边形数量 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | 生成的 3D 模型文件路径 |
diff --git a/zh-CN/built-in-nodes/Rodin3D_Gen2.mdx b/zh-CN/built-in-nodes/Rodin3D_Gen2.mdx
new file mode 100644
index 000000000..8557b322a
--- /dev/null
+++ b/zh-CN/built-in-nodes/Rodin3D_Gen2.mdx
@@ -0,0 +1,26 @@
+---
+title: "Rodin3D_Gen2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Gen2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Gen2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen2/zh.md)
+
+Rodin3D_Gen2 节点使用 Rodin API 生成 3D 资源。它接收输入图像并将其转换为具有不同材质类型和多边形数量的 3D 模型。该节点自动处理整个生成过程，包括任务创建、状态轮询和文件下载。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | 是 | - | 用于 3D 模型生成的输入图像 |
+| `Seed` | INT | 否 | 0-65535 | 生成用的随机种子值（默认：0） |
+| `Material_Type` | COMBO | 否 | "PBR"<br />"Shaded" | 应用于 3D 模型的材质类型（默认："PBR"） |
+| `Polygon_count` | COMBO | 否 | "4K-Quad"<br />"8K-Quad"<br />"18K-Quad"<br />"50K-Quad"<br />"2K-Triangle"<br />"20K-Triangle"<br />"150K-Triangle"<br />"500K-Triangle" | 生成 3D 模型的目标多边形数量（默认："500K-Triangle"） |
+| `TAPose` | BOOLEAN | 否 | - | 是否应用 TAPose 处理（默认：False） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | 生成的 3D 模型文件路径 |
diff --git a/zh-CN/built-in-nodes/Rodin3D_Regular.mdx b/zh-CN/built-in-nodes/Rodin3D_Regular.mdx
new file mode 100644
index 000000000..11ae93f82
--- /dev/null
+++ b/zh-CN/built-in-nodes/Rodin3D_Regular.mdx
@@ -0,0 +1,25 @@
+---
+title: "Rodin3D_Regular - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Regular node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Regular"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Regular/zh.md)
+
+Rodin 3D Regular 节点通过 Rodin API 生成 3D 资源。该节点接收输入图像并通过 Rodin 服务进行处理以创建 3D 模型。该节点处理从任务创建到下载最终 3D 模型文件的完整工作流程。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | 是 | - | 用于 3D 模型生成的输入图像 |
+| `Seed` | INT | 是 | - | 用于可重现结果的随机种子值 |
+| `Material_Type` | STRING | 是 | - | 应用于 3D 模型的材质类型 |
+| `Polygon_count` | STRING | 是 | - | 生成 3D 模型的目标多边形数量 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | 生成的 3D 模型文件路径 |
diff --git a/zh-CN/built-in-nodes/Rodin3D_Sketch.mdx b/zh-CN/built-in-nodes/Rodin3D_Sketch.mdx
new file mode 100644
index 000000000..2cf875281
--- /dev/null
+++ b/zh-CN/built-in-nodes/Rodin3D_Sketch.mdx
@@ -0,0 +1,23 @@
+---
+title: "Rodin3D_Sketch - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Sketch node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Sketch"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Sketch/zh.md)
+
+此节点使用 Rodin API 生成 3D 资源。它接收输入图像并通过外部服务将其转换为 3D 模型。该节点处理从任务创建到下载最终 3D 模型文件的整个流程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | 是 | - | 待转换为 3D 模型的输入图像 |
+| `Seed` | INT | 否 | 0-65535 | 生成用的随机种子值（默认值：0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | 生成的 3D 模型文件路径 |
diff --git a/zh-CN/built-in-nodes/Rodin3D_Smooth.mdx b/zh-CN/built-in-nodes/Rodin3D_Smooth.mdx
new file mode 100644
index 000000000..c5cb9a104
--- /dev/null
+++ b/zh-CN/built-in-nodes/Rodin3D_Smooth.mdx
@@ -0,0 +1,25 @@
+---
+title: "Rodin3D_Smooth - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Rodin3D_Smooth node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Rodin3D_Smooth"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Smooth/zh.md)
+
+Rodin 3D Smooth 节点通过处理输入图像并将其转换为平滑的 3D 模型，使用 Rodin API 生成 3D 资源。该节点接收多张图像作为输入，并生成可下载的 3D 模型文件。该节点自动处理整个生成过程，包括任务创建、状态轮询和文件下载。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Images` | IMAGE | 是 | - | 用于 3D 模型生成的输入图像 |
+| `Seed` | INT | 是 | - | 用于生成一致性的随机种子值 |
+| `Material_Type` | STRING | 是 | - | 应用于 3D 模型的材质类型 |
+| `Polygon_count` | STRING | 是 | - | 生成 3D 模型的目标多边形数量 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `3D Model Path` | STRING | 下载的 3D 模型文件路径 |
diff --git a/zh-CN/built-in-nodes/RunwayFirstLastFrameNode.mdx b/zh-CN/built-in-nodes/RunwayFirstLastFrameNode.mdx
new file mode 100644
index 000000000..fbe6fe3de
--- /dev/null
+++ b/zh-CN/built-in-nodes/RunwayFirstLastFrameNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "RunwayFirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RunwayFirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RunwayFirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayFirstLastFrameNode/zh.md)
+
+Runway 首尾帧转视频节点通过上传首尾关键帧和文本提示来生成视频。它使用 Runway 的 Gen-3 模型在提供的起始帧和结束帧之间创建平滑过渡。这对于结束帧与起始帧差异较大的复杂过渡特别有用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | 无 | 用于生成的文本提示（默认：空字符串） |
+| `start_frame` | IMAGE | 是 | 无 | 用于视频的起始帧 |
+| `end_frame` | IMAGE | 是 | 无 | 用于视频的结束帧。仅支持 gen3a_turbo 模型 |
+| `duration` | COMBO | 是 | 多个可用选项 | 从可用的时长选项中选择视频时长 |
+| `ratio` | COMBO | 是 | 多个可用选项 | 从可用的 RunwayGen3aAspectRatio 选项中选择宽高比 |
+| `seed` | INT | 否 | 0-4294967295 | 用于生成的随机种子（默认：0） |
+
+**参数约束：**
+
+- `prompt` 必须包含至少 1 个字符
+- `start_frame` 和 `end_frame` 的最大尺寸必须为 7999x7999 像素
+- `start_frame` 和 `end_frame` 的宽高比必须在 0.5 到 2.0 之间
+- `end_frame` 参数仅在使用 gen3a_turbo 模型时受支持
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 在起始帧和结束帧之间过渡生成的视频 |
diff --git a/zh-CN/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx b/zh-CN/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx
new file mode 100644
index 000000000..a0eb00ac6
--- /dev/null
+++ b/zh-CN/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx
@@ -0,0 +1,32 @@
+---
+title: "RunwayImageToVideoNodeGen3a - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RunwayImageToVideoNodeGen3a node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RunwayImageToVideoNodeGen3a"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayImageToVideoNodeGen3a/zh.md)
+
+Runway Image to Video (Gen3a Turbo) 节点使用 Runway 的 Gen3a Turbo 模型从单个起始帧生成视频。它接收文本提示和初始图像帧，然后根据指定的持续时间和宽高比创建视频序列。此节点通过连接 Runway 的 API 进行远程生成处理。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | 无 | 用于生成的文本提示（默认：""） |
+| `start_frame` | IMAGE | 是 | 无 | 用于视频生成的起始帧 |
+| `duration` | COMBO | 是 | 多个可用选项 | 从可用选项中选择视频时长 |
+| `ratio` | COMBO | 是 | 多个可用选项 | 从可用选项中选择宽高比 |
+| `seed` | INT | 否 | 0-4294967295 | 用于生成的随机种子（默认：0） |
+
+**参数约束：**
+
+- `start_frame` 的尺寸不得超过 7999x7999 像素
+- `start_frame` 的宽高比必须在 0.5 到 2.0 之间
+- `prompt` 必须包含至少一个字符（不能为空）
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频序列 |
diff --git a/zh-CN/built-in-nodes/RunwayImageToVideoNodeGen4.mdx b/zh-CN/built-in-nodes/RunwayImageToVideoNodeGen4.mdx
new file mode 100644
index 000000000..1ba848e7f
--- /dev/null
+++ b/zh-CN/built-in-nodes/RunwayImageToVideoNodeGen4.mdx
@@ -0,0 +1,32 @@
+---
+title: "RunwayImageToVideoNodeGen4 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RunwayImageToVideoNodeGen4 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RunwayImageToVideoNodeGen4"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayImageToVideoNodeGen4/zh.md)
+
+Runway Image to Video (Gen4 Turbo) 节点使用 Runway 的 Gen4 Turbo 模型，从单个起始帧生成视频。它接收文本提示和初始图像帧，然后根据提供的持续时间和宽高比设置创建视频序列。该节点负责将起始帧上传到 Runway 的 API 并返回生成的视频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 用于生成的文本提示（默认：空字符串） |
+| `start_frame` | IMAGE | 是 | - | 用于视频的起始帧 |
+| `duration` | COMBO | 是 | 多个可用选项 | 从可用持续时间选项中选择视频时长 |
+| `ratio` | COMBO | 是 | 多个可用选项 | 从可用的 Gen4 Turbo 宽高比选项中选择画面比例 |
+| `seed` | INT | 否 | 0 到 4294967295 | 用于生成的随机种子（默认：0） |
+
+**参数约束：**
+
+- `start_frame` 图像的尺寸不得超过 7999x7999 像素
+- `start_frame` 图像的宽高比必须在 0.5 到 2.0 之间
+- `prompt` 必须至少包含一个字符
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 基于输入帧和提示生成的视频 |
diff --git a/zh-CN/built-in-nodes/RunwayTextToImageNode.mdx b/zh-CN/built-in-nodes/RunwayTextToImageNode.mdx
new file mode 100644
index 000000000..8db460fad
--- /dev/null
+++ b/zh-CN/built-in-nodes/RunwayTextToImageNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "RunwayTextToImageNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the RunwayTextToImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "RunwayTextToImageNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayTextToImageNode/zh.md)
+
+Runway 文生图节点使用 Runway 的 Gen 4 模型，根据文本提示生成图像。您可以提供文本描述，并可选择包含参考图像来指导图像生成过程。该节点负责处理 API 通信并返回生成的图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `prompt` | STRING | 是 | - | 用于生成的文本提示（默认：""） |
+| `ratio` | COMBO | 是 | "16:9"<br />"1:1"<br />"21:9"<br />"2:3"<br />"3:2"<br />"4:5"<br />"5:4"<br />"9:16"<br />"9:21" | 生成图像的宽高比 |
+| `reference_image` | IMAGE | 否 | - | 可选的参考图像，用于指导生成过程 |
+
+**注意：** 参考图像的尺寸不得超过 7999x7999 像素，宽高比需在 0.5 到 2.0 之间。当提供参考图像时，它会指导图像生成过程。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `output` | IMAGE | 基于文本提示和可选参考图像生成的图像 |
diff --git a/zh-CN/built-in-nodes/SDTurboScheduler.mdx b/zh-CN/built-in-nodes/SDTurboScheduler.mdx
new file mode 100644
index 000000000..5a63aab2d
--- /dev/null
+++ b/zh-CN/built-in-nodes/SDTurboScheduler.mdx
@@ -0,0 +1,23 @@
+---
+title: "SDTurboScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SDTurboScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SDTurboScheduler"
+icon: "circle"
+mode: wide
+---
+
+SDTurbo调度器旨在为图像采样生成一系列sigma值，根据指定的去噪级别和步骤数调整序列。它利用特定模型的采样能力来产生这些sigma值，这些值对于控制在图像生成过程中的去噪过程至关重要。
+
+## 输入
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| `模型`    | `MODEL`  | 模型参数指定用于生成sigma值的生成模型。这对于确定调度器的具体采样行为和能力至关重要。 |
+| `步数`    | `INT`    | 步骤参数决定了要生成的sigma序列的长度，直接影响去噪过程的粒度。 |
+| `降噪`  | `FLOAT`  | 去噪参数调整sigma序列的起始点，允许在图像生成期间对应用的去噪级别进行更精细的控制。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `sigmas` | `SIGMAS`| 根据指定的模型、步骤和去噪级别生成的一系列sigma值。这些值对于控制在图像生成过程中的去噪过程至关重要。 |
diff --git a/zh-CN/built-in-nodes/SD_4XUpscale_Conditioning.mdx b/zh-CN/built-in-nodes/SD_4XUpscale_Conditioning.mdx
new file mode 100644
index 000000000..04c0fdfe9
--- /dev/null
+++ b/zh-CN/built-in-nodes/SD_4XUpscale_Conditioning.mdx
@@ -0,0 +1,28 @@
+---
+title: "SD_4XUpscale_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SD_4XUpscale_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SD_4XUpscale_Conditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SD_4XUpscale_Conditioning/zh.md)
+
+SD_4XUpscale_Conditioning 节点用于为使用扩散模型的图像超分辨率处理准备条件数据。该节点接收输入图像和条件数据，然后应用缩放和噪声增强来创建指导超分辨率过程的修改后条件数据。节点输出包含正向和负向条件数据，以及超分辨率后尺寸的潜在表示。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `图片` | IMAGE | 是 | - | 需要进行超分辨率处理的输入图像 |
+| `正面条件` | CONDITIONING | 是 | - | 正向条件数据，引导生成过程朝向期望内容 |
+| `负面条件` | CONDITIONING | 是 | - | 负向条件数据，使生成过程远离不需要的内容 |
+| `缩放比例` | FLOAT | 否 | 0.0 - 10.0 | 应用于输入图像的缩放因子（默认值：4.0） |
+| `噪波增强` | FLOAT | 否 | 0.0 - 1.0 | 超分辨率过程中添加的噪声量（默认值：0.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `负面条件` | CONDITIONING | 应用了超分辨率信息后的修改正向条件数据 |
+| `Latent` | CONDITIONING | 应用了超分辨率信息后的修改负向条件数据 |
+| `latent` | LATENT | 与超分辨率后尺寸匹配的空潜在表示 |
diff --git a/zh-CN/built-in-nodes/SV3D_Conditioning.mdx b/zh-CN/built-in-nodes/SV3D_Conditioning.mdx
new file mode 100644
index 000000000..7694d02d8
--- /dev/null
+++ b/zh-CN/built-in-nodes/SV3D_Conditioning.mdx
@@ -0,0 +1,30 @@
+---
+title: "SV3D_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SV3D_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SV3D_Conditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SV3D_Conditioning/zh.md)
+
+SV3D_Conditioning 节点用于为 SV3D 模型的 3D 视频生成准备条件数据。它接收初始图像，通过 CLIP 视觉编码器和 VAE 编码器进行处理，生成正向和负向条件数据以及潜在表示。该节点根据指定的视频帧数生成相机仰角和方位角序列，用于多帧视频生成。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|--------|-----------|------|----------|------|
+| `clip视觉` | CLIP_VISION | 是 | - | 用于编码输入图像的 CLIP 视觉模型 |
+| `初始图像` | IMAGE | 是 | - | 作为 3D 视频生成起点的初始图像 |
+| `vae` | VAE | 是 | - | 用于将图像编码到潜在空间的 VAE 模型 |
+| `宽度` | INT | 否 | 16 到 MAX_RESOLUTION | 生成视频帧的输出宽度（默认：576，必须能被 8 整除） |
+| `高度` | INT | 否 | 16 到 MAX_RESOLUTION | 生成视频帧的输出高度（默认：576，必须能被 8 整除） |
+| `帧数` | INT | 否 | 1 到 4096 | 视频序列要生成的帧数（默认：21） |
+| `俯仰角` | FLOAT | 否 | -90.0 到 90.0 | 3D 视图中相机仰角的角度（单位：度，默认：0.0） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `负面条件` | CONDITIONING | 包含图像嵌入和相机参数的正向条件数据，用于生成过程 |
+| `Latent` | CONDITIONING | 带有零值嵌入的负向条件数据，用于对比生成 |
+| `latent` | LATENT | 空潜在张量，其维度与指定的视频帧数和分辨率相匹配 |
diff --git a/zh-CN/built-in-nodes/SVD_img2vid_Conditioning.mdx b/zh-CN/built-in-nodes/SVD_img2vid_Conditioning.mdx
new file mode 100644
index 000000000..55055bc20
--- /dev/null
+++ b/zh-CN/built-in-nodes/SVD_img2vid_Conditioning.mdx
@@ -0,0 +1,32 @@
+---
+title: "SVD_img2vid_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SVD_img2vid_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SVD_img2vid_Conditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SVD_img2vid_Conditioning/zh.md)
+
+SVD_img2vid_Conditioning 节点用于为 Stable Video Diffusion 视频生成准备条件数据。该节点接收初始图像，通过 CLIP 视觉编码器和 VAE 编码器进行处理，创建正负条件对以及用于视频生成的空潜空间。此节点设置了控制生成视频中运动量、帧率和增强级别的必要参数。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip视觉` | CLIP_VISION | 是 | - | 用于编码输入图像的 CLIP 视觉模型 |
+| `初始图像` | IMAGE | 是 | - | 作为视频生成起点的初始图像 |
+| `vae` | VAE | 是 | - | 用于将图像编码到潜空间的 VAE 模型 |
+| `宽度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频宽度（默认：1024，步长：8） |
+| `高度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频高度（默认：576，步长：8） |
+| `帧数` | INT | 是 | 1 至 4096 | 视频生成帧数（默认：14） |
+| `动态bucketID` | INT | 是 | 1 至 1023 | 控制生成视频中的运动量（默认：127） |
+| `帧率` | INT | 是 | 1 至 1024 | 生成视频的帧率（默认：6） |
+| `增强` | FLOAT | 是 | 0.0 至 10.0 | 应用于输入图像的噪声增强级别（默认：0.0，步长：0.01） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 包含图像嵌入和视频参数的正向条件数据 |
+| `Latent` | CONDITIONING | 带有归零嵌入和视频参数的负向条件数据 |
+| `latent` | LATENT | 准备用于视频生成的空潜空间张量 |
diff --git a/zh-CN/built-in-nodes/SamplerCustom.mdx b/zh-CN/built-in-nodes/SamplerCustom.mdx
new file mode 100644
index 000000000..234d84dde
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerCustom.mdx
@@ -0,0 +1,30 @@
+---
+title: "SamplerCustom - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerCustom node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerCustom"
+icon: "circle"
+mode: wide
+---
+
+`SamplerCustom` 节点旨在为各种应用提供灵活且可定制的采样机制。它允许用户选择并配置不同的采样策略，以满足其特定需求，从而增强采样过程的适应性和效率。
+
+## 输入
+
+| 参数名称       | 数据类型 | 作用                                                         |
+|----------------|----------|--------------------------------------------------------------|
+| `模型`        | MODEL    | `模型` 输入类型指定用于采样的模型，对确定采样行为和输出起着关键作用。 |
+| `添加噪波`    | BOOLEAN  | `添加噪波` 输入类型允许用户指定是否应在采样过程中添加噪声，影响生成样本的多样性和特性。 |
+| `噪波种子`   | INT      | `噪波种子` 输入类型为噪声生成提供种子，确保在添加噪声时采样过程的可复现性和一致性。 |
+| `cfg`          | FLOAT    | `cfg` 输入类型设置采样过程的配置，允许微调采样参数和行为。                     |
+| `正面条件`     | CONDITIONING | `正面条件` 输入类型代表正面条件信息，指导采样过程生成符合指定正面属性的样本。 |
+| `负面条件`     | CONDITIONING | `负面条件` 输入类型代表负面条件信息，引导采样过程避免生成显示指定负面属性的样本。 |
+| `采样器`      | SAMPLER  | `采样器` 输入类型选择要使用的特定采样策略，直接影响生成样本的性质和质量。   |
+| `Sigmas`       | SIGMAS   | `Sigmas` 输入类型定义采样过程中要使用的噪声水平，影响样本空间的探索和输出的多样性。 |
+| `Latent` | LATENT   | `Latent` 输入类型为采样过程提供初始潜在图像，作为样本生成的起点。     |
+
+## 输出
+
+| 参数名称         | 数据类型 | 作用                                                         |
+|-----------------|----------|--------------------------------------------------------------|
+| `降噪Latent`        | LATENT   | `output` 代表采样过程的主要结果，包含生成的样本。             |
+| `denoised_output` | LATENT   | `denoised_output` 代表应用去噪过程后的样本，可能增强生成样本的清晰度和质量。 |
diff --git a/zh-CN/built-in-nodes/SamplerCustomAdvanced.mdx b/zh-CN/built-in-nodes/SamplerCustomAdvanced.mdx
new file mode 100644
index 000000000..031f3852d
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerCustomAdvanced.mdx
@@ -0,0 +1,27 @@
+---
+title: "SamplerCustomAdvanced - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerCustomAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerCustomAdvanced"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerCustomAdvanced/zh.md)
+
+SamplerCustomAdvanced 节点使用自定义噪声、引导和采样配置执行高级潜空间采样。该节点通过可自定义噪声生成和 sigma 调度的引导采样过程处理潜像，生成最终采样输出，并在可用时提供去噪版本。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `噪波` | NOISE | 是 | - | 为采样过程提供初始噪声模式和种子的噪声生成器 |
+| `引导器` | GUIDER | 是 | - | 引导采样过程朝向期望输出的引导模型 |
+| `采样器` | SAMPLER | 是 | - | 定义生成过程中潜空间遍历方式的采样算法 |
+| `西格玛` | SIGMAS | 是 | - | 控制整个采样步骤中噪声水平的 sigma 调度表 |
+| `Latent图像` | LATENT | 是 | - | 作为采样起点的初始潜表示 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `降噪Latent` | LATENT | 完成采样过程后的最终采样潜表示 |
+| `denoised_output` | LATENT | 可用时的去噪输出版本，否则返回与 output 相同的内容 |
diff --git a/zh-CN/built-in-nodes/SamplerDPMAdaptative.mdx b/zh-CN/built-in-nodes/SamplerDPMAdaptative.mdx
new file mode 100644
index 000000000..6433cbef9
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerDPMAdaptative.mdx
@@ -0,0 +1,31 @@
+---
+title: "SamplerDPMAdaptative - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMAdaptative node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMAdaptative"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMAdaptative/zh.md)
+
+SamplerDPMAdaptative 节点实现了一种自适应 DPM（扩散概率模型）采样器，能够在采样过程中自动调整步长。它采用基于容差的误差控制机制来确定最优步长，在计算效率与采样精度之间取得平衡。这种自适应方法有助于保持生成质量，同时可能减少所需的采样步数。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `order` | INT | 是 | 2-3 | 采样器方法的阶数（默认值：3） |
+| `rtol` | FLOAT | 是 | 0.0-100.0 | 误差控制的相对容差（默认值：0.05） |
+| `atol` | FLOAT | 是 | 0.0-100.0 | 误差控制的绝对容差（默认值：0.0078） |
+| `h_init` | FLOAT | 是 | 0.0-100.0 | 初始步长（默认值：0.05） |
+| `pcoeff` | FLOAT | 是 | 0.0-100.0 | 步长控制的比例系数（默认值：0.0） |
+| `icoeff` | FLOAT | 是 | 0.0-100.0 | 步长控制的积分系数（默认值：1.0） |
+| `dcoeff` | FLOAT | 是 | 0.0-100.0 | 步长控制的微分系数（默认值：0.0） |
+| `accept_safety` | FLOAT | 是 | 0.0-100.0 | 步长接受的安全系数（默认值：0.81） |
+| `eta` | FLOAT | 是 | 0.0-100.0 | 随机性参数（默认值：0.0） |
+| `s_noise` | FLOAT | 是 | 0.0-100.0 | 噪声缩放因子（默认值：1.0） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `sampler` | SAMPLER | 返回配置完成的 DPM 自适应采样器实例 |
diff --git a/zh-CN/built-in-nodes/SamplerDPMPP_2M_SDE.mdx b/zh-CN/built-in-nodes/SamplerDPMPP_2M_SDE.mdx
new file mode 100644
index 000000000..2d120de74
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerDPMPP_2M_SDE.mdx
@@ -0,0 +1,25 @@
+---
+title: "SamplerDPMPP_2M_SDE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMPP_2M_SDE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMPP_2M_SDE"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMPP_2M_SDE/zh.md)
+
+SamplerDPMPP_2M_SDE 节点为扩散模型创建 DPM++ 2M SDE 采样器。该采样器使用带有随机微分方程的二阶微分方程求解器来生成样本。它提供不同的求解器类型和噪声处理选项以控制采样过程。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `求解器类型` | STRING | 是 | `"midpoint"`<br />`"heun"` | 用于采样过程的微分方程求解器类型 |
+| `eta` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程的随机性（默认值：1.0） |
+| `s_noise` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程中添加的噪声量（默认值：1.0） |
+| `噪波设备` | STRING | 是 | `"gpu"`<br />`"cpu"` | 执行噪声计算的设备 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | 已配置的采样器对象，可在采样流程中使用 |
diff --git a/zh-CN/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx b/zh-CN/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx
new file mode 100644
index 000000000..e17a053bf
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx
@@ -0,0 +1,23 @@
+---
+title: "SamplerDPMPP_2S_Ancestral - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMPP_2S_Ancestral node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMPP_2S_Ancestral"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMPP_2S_Ancestral/zh.md)
+
+SamplerDPMPP_2S_Ancestral 节点创建了一个使用 DPM++ 2S Ancestral 采样方法生成图像的采样器。该采样器结合了确定性和随机性元素，在保持一定一致性的同时产生多样化的结果。它允许您在采样过程中控制随机性和噪声水平。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `eta` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程中添加的随机噪声量（默认值：1.0） |
+| `s_noise` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程中应用的噪声尺度（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | 返回一个配置好的采样器对象，可在采样流程中使用 |
diff --git a/zh-CN/built-in-nodes/SamplerDPMPP_3M_SDE.mdx b/zh-CN/built-in-nodes/SamplerDPMPP_3M_SDE.mdx
new file mode 100644
index 000000000..191228725
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerDPMPP_3M_SDE.mdx
@@ -0,0 +1,24 @@
+---
+title: "SamplerDPMPP_3M_SDE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMPP_3M_SDE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMPP_3M_SDE"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMPP_3M_SDE/zh.md)
+
+SamplerDPMPP_3M_SDE 节点创建一个 DPM++ 3M SDE 采样器，用于采样过程。该采样器采用三阶多步随机微分方程方法，并具有可配置的噪声参数。该节点允许您选择在 GPU 或 CPU 上执行噪声计算。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `eta` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程的随机性（默认值：1.0） |
+| `s_noise` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程中添加的噪声量（默认值：1.0） |
+| `噪波设备` | COMBO | 是 | "gpu"<br />"cpu" | 选择噪声计算设备，可以是 GPU 或 CPU |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `sampler` | SAMPLER | 返回一个配置好的采样器对象，用于采样工作流 |
diff --git a/zh-CN/built-in-nodes/SamplerDPMPP_SDE.mdx b/zh-CN/built-in-nodes/SamplerDPMPP_SDE.mdx
new file mode 100644
index 000000000..937111061
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerDPMPP_SDE.mdx
@@ -0,0 +1,25 @@
+---
+title: "SamplerDPMPP_SDE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDPMPP_SDE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDPMPP_SDE"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerDPMPP_SDE/zh.md)
+
+SamplerDPMPP_SDE 节点创建了一个用于采样过程的 DPM++ SDE（随机微分方程）采样器。该采样器提供了一种可配置噪声参数和设备选择的随机采样方法，它会返回一个可在采样流程中使用的采样器对象。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `eta` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程的随机性（默认值：1.0） |
+| `s_noise` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程中添加的噪声量（默认值：1.0） |
+| `r` | FLOAT | 是 | 0.0 - 100.0 | 影响采样行为的参数（默认值：0.5） |
+| `噪波设备` | COMBO | 是 | "gpu"<br />"cpu" | 选择执行噪声计算的设备 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `sampler` | SAMPLER | 返回一个已配置的 DPM++ SDE 采样器对象，用于采样流程 |
diff --git a/zh-CN/built-in-nodes/SamplerDpmpp2mSde.mdx b/zh-CN/built-in-nodes/SamplerDpmpp2mSde.mdx
new file mode 100644
index 000000000..f10f0cae0
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerDpmpp2mSde.mdx
@@ -0,0 +1,24 @@
+---
+title: "SamplerDpmpp2mSde - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDpmpp2mSde node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDpmpp2mSde"
+icon: "circle"
+mode: wide
+---
+
+此节点旨在为 DPMPP_2M_SDE 模型生成采样器，允许根据指定的求解器类型、噪声水平和计算设备偏好创建样本。它抽象了采样器配置的复杂性，提供了一个简化的接口，用于生成具有定制设置的样本。
+
+## 输入
+
+| 参数名称       | 数据类型 | 作用                                                         |
+|----------------|----------|--------------------------------------------------------------|
+| `solver_type`  | COMBO[STRING] | 在采样过程中使用的求解器类型，提供 'midpoint' 和 'heun' 两种选择。此选择影响采样期间应用的数值积分方法。 |
+| `eta`          | `FLOAT`  | 确定数值积分中的步长，影响采样过程的粒度。较高的值表示较大的步长。                     |
+| `s_noise`      | `FLOAT`  | 控制采样过程中引入的噪声水平，影响生成样本的可变性。                           |
+| `noise_device` | COMBO[STRING] | 指示噪声生成过程执行的计算设备（'gpu' 或 'cpu'），影响性能和效率。             |
+
+## 输出
+
+| 参数名称   | 数据类型 | 作用                                       |
+|------------|----------|--------------------------------------------|
+| `sampler`  | `SAMPLER` | 根据指定参数配置的采样器，准备就绪，可用于生成样本。 |
diff --git a/zh-CN/built-in-nodes/SamplerDpmppSde.mdx b/zh-CN/built-in-nodes/SamplerDpmppSde.mdx
new file mode 100644
index 000000000..97b01cf1c
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerDpmppSde.mdx
@@ -0,0 +1,24 @@
+---
+title: "SamplerDpmppSde - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerDpmppSde node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerDpmppSde"
+icon: "circle"
+mode: wide
+---
+
+此节点旨在为DPM++ SDE（随机微分方程）模型生成采样器。它适配CPU和GPU执行环境，并根据可用硬件优化采样器的实现。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `eta` | FLOAT | 指定SDE求解器的步长，影响采样过程的粒度。 |
+| `s_noise` | FLOAT | 确定采样过程中应用的噪声水平，影响生成样本的多样性。 |
+| `r` | FLOAT | 控制采样过程中噪声减少的比例，影响生成样本的清晰度和质量。 |
+| `noise_device` | COMBO[STRING] | 选择采样器的执行环境（CPU或GPU），基于可用硬件优化性能。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `sampler` | SAMPLER | 配置了指定参数的生成采样器，准备用于采样操作。 |
diff --git a/zh-CN/built-in-nodes/SamplerER_SDE.mdx b/zh-CN/built-in-nodes/SamplerER_SDE.mdx
new file mode 100644
index 000000000..61a33e025
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerER_SDE.mdx
@@ -0,0 +1,30 @@
+---
+title: "SamplerER_SDE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerER_SDE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerER_SDE"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerER_SDE/zh.md)
+
+SamplerER_SDE 节点为扩散模型提供专门的采样方法，提供不同的求解器类型，包括 ER-SDE、逆时 SDE 和 ODE 方法。它允许控制采样过程的随机行为和计算阶段。该节点会根据所选求解器类型自动调整参数以确保正常功能。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `solver_type` | COMBO | 是 | "ER-SDE"<br />"Reverse-time SDE"<br />"ODE" | 用于采样的求解器类型。决定扩散过程的数学方法。 |
+| `max_stage` | INT | 是 | 1-3 | 采样过程的最大阶段数（默认：3）。控制计算复杂度和质量。 |
+| `eta` | FLOAT | 是 | 0.0-100.0 | 逆时 SDE 的随机强度（默认：1.0）。当 eta=0 时，简化为确定性 ODE。此设置不适用于 ER-SDE 求解器类型。 |
+| `s_noise` | FLOAT | 是 | 0.0-100.0 | 采样过程的噪声缩放因子（默认：1.0）。控制采样过程中应用的噪声量。 |
+
+**参数约束：**
+
+- 当 `solver_type` 设置为 "ODE" 或使用 "Reverse-time SDE" 且 `eta`=0 时，无论用户输入值如何，`eta` 和 `s_noise` 都会自动设置为 0。
+- `eta` 参数仅影响 "Reverse-time SDE" 求解器类型，对 "ER-SDE" 求解器类型没有影响。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | 配置好的采样器对象，可在采样流水线中使用，具有指定的求解器设置。 |
diff --git a/zh-CN/built-in-nodes/SamplerEulerAncestral.mdx b/zh-CN/built-in-nodes/SamplerEulerAncestral.mdx
new file mode 100644
index 000000000..2475e4a7e
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerEulerAncestral.mdx
@@ -0,0 +1,23 @@
+---
+title: "SamplerEulerAncestral - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerEulerAncestral node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerEulerAncestral"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerEulerAncestral/zh.md)
+
+SamplerEulerAncestral 节点用于创建欧拉祖先采样器以生成图像。该采样器采用特定的数学方法，结合欧拉积分与祖先采样技术来生成图像变体。通过调整控制生成过程中随机性和步长的参数，您可以配置该采样器的行为。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `eta` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程的步长和随机性（默认值：1.0） |
+| `s噪波` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程中添加的噪声量（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | 返回一个已配置的欧拉祖先采样器，可在采样管道中使用 |
diff --git a/zh-CN/built-in-nodes/SamplerEulerAncestralCFGPP.mdx b/zh-CN/built-in-nodes/SamplerEulerAncestralCFGPP.mdx
new file mode 100644
index 000000000..32cfb7056
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerEulerAncestralCFGPP.mdx
@@ -0,0 +1,23 @@
+---
+title: "SamplerEulerAncestralCFGPP - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerEulerAncestralCFGPP node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerEulerAncestralCFGPP"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerEulerAncestralCFGPP/zh.md)
+
+SamplerEulerAncestralCFGPP 节点创建了一个专用采样器，用于使用带分类器自由引导的 Euler Ancestral 方法生成图像。该采样器结合了祖先采样技术和引导条件处理，可在保持连贯性的同时生成多样化的图像变体。它通过控制噪声和步长调整的参数，允许对采样过程进行微调。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `eta` | FLOAT | 是 | 0.0 - 1.0 | 控制采样过程中的步长，值越高更新越激进（默认值：1.0） |
+| `s噪波` | FLOAT | 是 | 0.0 - 10.0 | 调整采样过程中添加的噪声量（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | 返回一个配置好的采样器对象，可在图像生成流程中使用 |
diff --git a/zh-CN/built-in-nodes/SamplerEulerCFGpp.mdx b/zh-CN/built-in-nodes/SamplerEulerCFGpp.mdx
new file mode 100644
index 000000000..c632d6d94
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerEulerCFGpp.mdx
@@ -0,0 +1,22 @@
+---
+title: "SamplerEulerCFGpp - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerEulerCFGpp node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerEulerCFGpp"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerEulerCFGpp/zh.md)
+
+SamplerEulerCFGpp 节点提供了一种用于生成输出的 Euler CFG++ 采样方法。该节点提供了两种不同实现版本的 Euler CFG++ 采样器，用户可根据偏好进行选择。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `版本` | STRING | 是 | `"regular"`<br />`"alternative"` | 要使用的 Euler CFG++ 采样器的实现版本 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | 返回一个配置好的 Euler CFG++ 采样器实例 |
diff --git a/zh-CN/built-in-nodes/SamplerLCMUpscale.mdx b/zh-CN/built-in-nodes/SamplerLCMUpscale.mdx
new file mode 100644
index 000000000..1e29ccc7e
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerLCMUpscale.mdx
@@ -0,0 +1,26 @@
+---
+title: "SamplerLCMUpscale - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerLCMUpscale node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerLCMUpscale"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerLCMUpscale/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerLCMUpscale/en.md)
+
+SamplerLCMUpscale 节点提供了一种专门的采样方法，将潜在一致性模型（LCM）采样与图像放大功能相结合。它允许您在采样过程中使用各种插值方法放大图像，有助于在保持图像质量的同时生成更高分辨率的输出。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `缩放比例` | FLOAT | 否 | 0.1 - 20.0 | 放大过程中应用的缩放因子（默认：1.0） |
+| `缩放步数` | INT | 否 | -1 - 1000 | 放大过程使用的步数。使用 -1 表示自动计算（默认：-1） |
+| `缩放方法` | COMBO | 是 | "bislerp"<br />"nearest-exact"<br />"bilinear"<br />"area"<br />"bicubic" | 用于图像放大的插值方法 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `sampler` | SAMPLER | 返回一个配置好的采样器对象，可在采样管道中使用 |
diff --git a/zh-CN/built-in-nodes/SamplerLMS.mdx b/zh-CN/built-in-nodes/SamplerLMS.mdx
new file mode 100644
index 000000000..87ce93686
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerLMS.mdx
@@ -0,0 +1,22 @@
+---
+title: "SamplerLMS - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerLMS node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerLMS"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerLMS/zh.md)
+
+SamplerLMS 节点创建了一个用于扩散模型的最小均方（LMS）采样器。它生成一个可在采样过程中使用的采样器对象，允许您控制 LMS 算法的阶数以实现数值稳定性和准确性。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `顺序` | INT | 是 | 1 到 100 | LMS 采样器算法的阶数参数，控制数值方法的精度和稳定性（默认值：4） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | 已配置的 LMS 采样器对象，可在采样流程中使用 |
diff --git a/zh-CN/built-in-nodes/SamplerSASolver.mdx b/zh-CN/built-in-nodes/SamplerSASolver.mdx
new file mode 100644
index 000000000..fe3be8e1a
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerSASolver.mdx
@@ -0,0 +1,30 @@
+---
+title: "SamplerSASolver - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerSASolver node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerSASolver"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerSASolver/zh.md)
+
+SamplerSASolver 节点为扩散模型实现了一种自定义采样算法。它采用预测器-校正器方法，通过可配置的阶数设置和随机微分方程（SDE）参数，从输入模型中生成样本。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `model` | MODEL | 是 | - | 用于采样的扩散模型 |
+| `eta` | FLOAT | 是 | 0.0 - 10.0 | 控制步长缩放因子（默认值：1.0） |
+| `sde_start_percent` | FLOAT | 是 | 0.0 - 1.0 | SDE 采样的起始百分比（默认值：0.2） |
+| `sde_end_percent` | FLOAT | 是 | 0.0 - 1.0 | SDE 采样的结束百分比（默认值：0.8） |
+| `s_noise` | FLOAT | 是 | 0.0 - 100.0 | 控制采样过程中添加的噪声量（默认值：1.0） |
+| `predictor_order` | INT | 是 | 1 - 6 | 求解器中预测器组件的阶数（默认值：3） |
+| `corrector_order` | INT | 是 | 0 - 6 | 求解器中校正器组件的阶数（默认值：4） |
+| `use_pece` | BOOLEAN | 是 | - | 启用或禁用 PECE（预测-评估-校正-评估）方法 |
+| `simple_order_2` | BOOLEAN | 是 | - | 启用或禁用简化的二阶计算 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `sampler` | SAMPLER | 已配置的采样器对象，可用于扩散模型 |
diff --git a/zh-CN/built-in-nodes/SamplerSEEDS2.mdx b/zh-CN/built-in-nodes/SamplerSEEDS2.mdx
new file mode 100644
index 000000000..6de5d9c9e
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplerSEEDS2.mdx
@@ -0,0 +1,25 @@
+---
+title: "SamplerSEEDS2 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplerSEEDS2 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplerSEEDS2"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerSEEDS2/zh.md)
+
+此节点提供了一个可配置的采样器，用于生成图像。它实现了 SEEDS-2 算法，这是一种随机微分方程（SDE）求解器。通过调整其参数，您可以将其配置为模拟多种特定采样器的行为，包括 `seeds_2`、`exp_heun_2_x0` 和 `exp_heun_2_x0_sde`。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `solver_type` | COMBO | 是 | `"phi_1"`<br />`"phi_2"` | 选择采样器使用的基础求解器算法。 |
+| `eta` | FLOAT | 否 | 0.0 - 100.0 | 随机强度（默认值：1.0）。 |
+| `s_noise` | FLOAT | 否 | 0.0 - 100.0 | SDE 噪声乘数（默认值：1.0）。 |
+| `r` | FLOAT | 否 | 0.01 - 1.0 | 中间阶段（c2 节点）的相对步长（默认值：0.5）。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sampler` | SAMPLER | 一个已配置的采样器对象，可以传递给其他采样节点。 |
diff --git a/zh-CN/built-in-nodes/SamplingPercentToSigma.mdx b/zh-CN/built-in-nodes/SamplingPercentToSigma.mdx
new file mode 100644
index 000000000..663c0c3f5
--- /dev/null
+++ b/zh-CN/built-in-nodes/SamplingPercentToSigma.mdx
@@ -0,0 +1,26 @@
+---
+title: "SamplingPercentToSigma - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SamplingPercentToSigma node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SamplingPercentToSigma"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplingPercentToSigma/zh.md)
+
+## 概述
+
+SamplingPercentToSigma 节点使用模型的采样参数将采样百分比值转换为对应的 sigma 值。它接收一个介于 0.0 到 1.0 之间的百分比值，并将其映射到模型噪声调度中的适当 sigma 值，同时提供返回计算得到的 sigma 值或边界处的实际最大/最小 sigma 值的选项。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 包含用于转换的采样参数的模型 |
+| `sampling_percent` | FLOAT | 是 | 0.0 到 1.0 | 要转换为 sigma 的采样百分比（默认：0.0） |
+| `return_actual_sigma` | BOOLEAN | 是 | - | 返回实际的 sigma 值，而非用于区间检查的值。这仅影响 0.0 和 1.0 处的计算结果（默认：False） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigma_value` | FLOAT | 与输入采样百分比对应的转换后的 sigma 值 |
diff --git a/zh-CN/built-in-nodes/SaveAnimatedPNG.mdx b/zh-CN/built-in-nodes/SaveAnimatedPNG.mdx
new file mode 100644
index 000000000..8722564ee
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveAnimatedPNG.mdx
@@ -0,0 +1,26 @@
+---
+title: "SaveAnimatedPNG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAnimatedPNG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAnimatedPNG"
+icon: "circle"
+mode: wide
+---
+
+此节点设计用于从一系列帧创建和保存动画PNG图像。它处理将单独的图像帧组装成连贯的动画，并允许自定义帧持续时间、循环和包含元数据。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图片` | `IMAGE` | 要处理并保存为动画PNG的图像列表。列表中的每个图像代表动画中的一帧。 |
+| `文件名前缀` | STRING   | 指定输出文件的基本名称，将用作生成的动画PNG文件的前缀。 |
+| `帧率` | `FLOAT` | 动画的每秒帧数率，控制帧显示的速度。 |
+| `压缩级别` | `INT` | 应用于动画PNG文件的压缩级别，影响文件大小和图像清晰度。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `ui` | - | 提供一个UI组件，展示生成的动画PNG图像，并指示动画是单帧还是多帧。 |
+
+---
diff --git a/zh-CN/built-in-nodes/SaveAnimatedWEBP.mdx b/zh-CN/built-in-nodes/SaveAnimatedWEBP.mdx
new file mode 100644
index 000000000..beb7e777e
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveAnimatedWEBP.mdx
@@ -0,0 +1,27 @@
+---
+title: "SaveAnimatedWEBP - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAnimatedWEBP node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAnimatedWEBP"
+icon: "circle"
+mode: wide
+---
+此节点设计用于将一系列图像保存为动画WEBP文件。它处理将单独的帧聚合成连贯的动画，应用指定的元数据，并基于质量和压缩设置优化输出。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `图片` | `IMAGE` | 要作为动画WEBP帧保存的图像列表。此参数对于定义动画的视觉内容至关重要。 |
+| `文件名前缀` | STRING   | 指定输出文件的基本名称，将与计数器和“.webp”扩展名一起附加。此参数对于识别和组织保存的文件至关重要。 |
+| `帧率` | `FLOAT` | 动画的每秒帧数率，影响播放速度。 |
+| `无损` | `BOOLEAN` | 布尔值，指示是否使用无损压缩，影响动画的文件大小和质量。 |
+| `质量` | `INT` | 0到100之间的值，设置压缩质量级别，值越高，图像质量越好，但文件大小越大。 |
+| `方法` | COMBO[STRING] | 指定要使用的压缩方法，这可以影响编码速度和文件大小。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `ui` | - | 提供一个UI组件，展示保存的动画WEBP图像及其元数据，并指示是否启用了动画。 |
+
+---
diff --git a/zh-CN/built-in-nodes/SaveAudio.mdx b/zh-CN/built-in-nodes/SaveAudio.mdx
new file mode 100644
index 000000000..f5d53750c
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveAudio.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudio/zh.md)
+
+SaveAudio 节点将音频数据以 FLAC 格式保存到文件中。它接收音频输入，并使用给定的文件名前缀将其写入指定的输出目录。该节点会自动处理文件命名，并确保音频被正确保存以供后续使用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `音频` | AUDIO | 是 | - | 需要保存的音频数据 |
+| `文件名前缀` | STRING | 否 | - | 输出文件名的前缀（默认为 "audio/ComfyUI"） |
+
+*注意：`prompt` 和 `extra_pnginfo` 参数为隐藏参数，由系统自动处理。*
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| *无* | - | 此节点不返回任何输出数据，但会将音频文件保存到输出目录 |
diff --git a/zh-CN/built-in-nodes/SaveAudioMP3.mdx b/zh-CN/built-in-nodes/SaveAudioMP3.mdx
new file mode 100644
index 000000000..666fbc5d6
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveAudioMP3.mdx
@@ -0,0 +1,28 @@
+---
+title: "SaveAudioMP3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAudioMP3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAudioMP3"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioMP3/zh.md)
+
+# SaveAudioMP3
+
+SaveAudioMP3 节点将音频数据保存为 MP3 文件。它接收音频输入，并将其导出到指定的输出目录，支持自定义文件名和质量设置。该节点自动处理文件命名和格式转换，以创建可播放的 MP3 文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `audio` | AUDIO | 是 | - | 要保存为 MP3 文件的音频数据 |
+| `filename_prefix` | STRING | 否 | - | 输出文件名的前缀（默认："audio/ComfyUI"） |
+| `quality` | STRING | 否 | "V0"<br />"128k"<br />"320k" | MP3 文件的音频质量设置（默认："V0"） |
+| `prompt` | PROMPT | 否 | - | 内部提示数据（由系统自动提供） |
+| `extra_pnginfo` | EXTRA_PNGINFO | 否 | - | 额外的 PNG 信息（由系统自动提供） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| *无* | - | 此节点不返回任何输出数据，但会将音频文件保存到输出目录 |
diff --git a/zh-CN/built-in-nodes/SaveAudioOpus.mdx b/zh-CN/built-in-nodes/SaveAudioOpus.mdx
new file mode 100644
index 000000000..ee0e380f0
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveAudioOpus.mdx
@@ -0,0 +1,26 @@
+---
+title: "SaveAudioOpus - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveAudioOpus node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveAudioOpus"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioOpus/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioOpus/en.md)
+
+SaveAudioOpus 节点将音频数据保存为 Opus 格式文件。它接收音频输入，并将其导出为具有可配置质量设置的压缩 Opus 文件。该节点自动处理文件命名，并将输出保存到指定的输出目录。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `audio` | AUDIO | 是 | - | 要保存为 Opus 文件的音频数据 |
+| `filename_prefix` | STRING | 否 | - | 输出文件名的前缀（默认："audio/ComfyUI"） |
+| `quality` | COMBO | 否 | "64k"<br />"96k"<br />"128k"<br />"192k"<br />"320k" | Opus 文件的音频质量设置（默认："128k"） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| - | - | 此节点不返回任何输出值。其主要功能是将音频文件保存到磁盘。 |
diff --git a/zh-CN/built-in-nodes/SaveGLB.mdx b/zh-CN/built-in-nodes/SaveGLB.mdx
new file mode 100644
index 000000000..de648798a
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveGLB.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveGLB - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveGLB node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveGLB"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveGLB/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveGLB/en.md)
+
+SaveGLB 节点将 3D 网格数据保存为 GLB 文件，这是一种常见的 3D 模型格式。它接收网格数据作为输入，并使用指定的文件名前缀将其导出到输出目录。如果输入包含多个网格对象，该节点可以保存多个网格，并且在启用元数据时会自动向文件添加元数据。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `网格` | MESH | 是 | - | 要保存为 GLB 文件的 3D 网格数据 |
+| `文件名前缀` | STRING | 否 | - | 输出文件名的前缀（默认："mesh/ComfyUI"） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `ui` | UI | 在用户界面中显示保存的 GLB 文件，包含文件名和子文件夹信息 |
diff --git a/zh-CN/built-in-nodes/SaveImage.mdx b/zh-CN/built-in-nodes/SaveImage.mdx
new file mode 100644
index 000000000..6222c7382
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveImage.mdx
@@ -0,0 +1,23 @@
+---
+title: "SaveImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImage/zh.md)
+
+此节点将接收到的图像保存到您的 `ComfyUI/output` 目录中。它将每张图像保存为 PNG 文件，并可以将工作流元数据（例如提示词）嵌入到保存的文件中，以供将来参考。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图片` | IMAGE | 是 | - | 要保存的图像。 |
+| `文件名前缀` | STRING | 是 | - | 保存文件的名称前缀。可以包含格式化信息，例如 `%date:yyyy-MM-dd%` 或 `%Empty Latent Image.width%`，以包含来自节点的值（默认值："ComfyUI"）。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `ui` | UI_RESULT | 此节点输出一个 UI 结果，其中包含已保存图像及其文件名和子文件夹的列表。它不输出用于连接到其他节点的数据。 |
diff --git a/zh-CN/built-in-nodes/SaveImageDataSetToFolder.mdx b/zh-CN/built-in-nodes/SaveImageDataSetToFolder.mdx
new file mode 100644
index 000000000..8813b5146
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveImageDataSetToFolder.mdx
@@ -0,0 +1,24 @@
+---
+title: "SaveImageDataSetToFolder - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveImageDataSetToFolder node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveImageDataSetToFolder"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageDataSetToFolder/zh.md)
+
+此节点将图像列表保存到 ComfyUI 输出目录内的指定文件夹中。它接收多张图像作为输入，并以可自定义的文件名前缀将它们写入磁盘。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | N/A | 要保存的图像列表。 |
+| `folder_name` | STRING | 否 | N/A | 用于保存图像的文件夹名称（位于输出目录内）。默认值为 "dataset"。 |
+| `filename_prefix` | STRING | 否 | N/A | 已保存图像文件名的前缀。默认值为 "image"。 |
+
+**注意：** `images` 输入是一个列表，这意味着它可以一次接收和处理多张图像。`folder_name` 和 `filename_prefix` 参数是标量值；如果连接了列表，则仅使用该列表中的第一个值。
+
+## 输出参数
+
+此节点没有任何输出。它是一个执行文件系统保存操作的输出节点。
diff --git a/zh-CN/built-in-nodes/SaveImageTextDataSetToFolder.mdx b/zh-CN/built-in-nodes/SaveImageTextDataSetToFolder.mdx
new file mode 100644
index 000000000..729058eca
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveImageTextDataSetToFolder.mdx
@@ -0,0 +1,27 @@
+---
+title: "SaveImageTextDataSetToFolder - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveImageTextDataSetToFolder node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveImageTextDataSetToFolder"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageTextDataSetToFolder/zh.md)
+
+Save Image and Text Dataset to Folder 节点将一系列图像及其对应的文本描述保存到 ComfyUI 输出目录内的指定文件夹中。对于每个保存为 PNG 文件的图像，都会创建一个具有相同基础名称的匹配文本文件来存储其描述。这对于创建包含生成图像及其描述的有序数据集非常有用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | - | 要保存的图像列表。 |
+| `texts` | STRING | 是 | - | 要保存的文本描述列表。 |
+| `folder_name` | STRING | 否 | - | 用于保存图像的文件夹名称（位于输出目录内）。(默认值: "dataset") |
+| `filename_prefix` | STRING | 否 | - | 保存图像文件名的前缀。(默认值: "image") |
+
+**注意：** `images` 和 `texts` 输入是列表。节点期望提供的文本描述数量与图像数量相匹配。每个描述将被保存到一个与其配对的图像对应的 `.txt` 文件中。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| - | - | 此节点没有任何输出。它直接将文件保存到文件系统。 |
diff --git a/zh-CN/built-in-nodes/SaveLatent.mdx b/zh-CN/built-in-nodes/SaveLatent.mdx
new file mode 100644
index 000000000..ba2904406
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveLatent.mdx
@@ -0,0 +1,27 @@
+---
+title: "SaveLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLatent/zh.md)
+
+## 概述
+
+SaveLatent 节点将潜在张量以文件形式保存到磁盘，供后续使用或共享。该节点接收潜在样本并将其保存到输出目录，同时可包含提示信息等元数据。节点会自动处理文件命名和组织，同时保留潜在数据结构。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Latent` | LATENT | 是 | - | 需要保存到磁盘的潜在样本 |
+| `文件名前缀` | STRING | 否 | - | 输出文件名的前缀（默认："latents/ComfyUI"） |
+| `prompt` | PROMPT | 否 | - | 要包含在元数据中的提示信息（隐藏参数） |
+| `extra_pnginfo` | EXTRA_PNGINFO | 否 | - | 要包含在元数据中的额外PNG信息（隐藏参数） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `ui` | UI | 在 ComfyUI 界面中提供已保存潜在文件的位置信息 |
diff --git a/zh-CN/built-in-nodes/SaveLoRA.mdx b/zh-CN/built-in-nodes/SaveLoRA.mdx
new file mode 100644
index 000000000..c3d854dfe
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveLoRA.mdx
@@ -0,0 +1,26 @@
+---
+title: "SaveLoRA - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveLoRA node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveLoRA"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLoRA/zh.md)
+
+SaveLoRA 节点用于将 LoRA（低秩自适应）模型保存至文件。该节点接收一个 LoRA 模型作为输入，并将其写入输出目录中的 `.safetensors` 文件。您可以指定文件名前缀，并可选择包含训练步数以构成最终文件名。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `lora` | MODEL | 是 | 不适用 | 需要保存的 LoRA 模型。请勿使用已应用了 LoRA 层的模型。 |
+| `prefix` | STRING | 是 | 不适用 | 保存的 LoRA 文件使用的前缀（默认："loras/ComfyUI_trained_lora"）。 |
+| `steps` | INT | 否 | 不适用 | 可选：LoRA 已训练的步数，用于命名保存的文件。 |
+
+**注意：** `lora` 输入必须是一个纯 LoRA 模型。请勿提供已应用了 LoRA 层的基础模型。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| *无* | 不适用 | 此节点不会向工作流输出任何数据。它是一个输出节点，负责将文件保存到磁盘。 |
diff --git a/zh-CN/built-in-nodes/SaveLoRANode.mdx b/zh-CN/built-in-nodes/SaveLoRANode.mdx
new file mode 100644
index 000000000..c5fa92546
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveLoRANode.mdx
@@ -0,0 +1,24 @@
+---
+title: "SaveLoRANode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveLoRANode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveLoRANode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLoRANode/zh.md)
+
+SaveLoRA 节点可将 LoRA（低秩自适应）模型保存至输出目录。该节点接收 LoRA 模型作为输入，并生成带有自动生成文件名的 safetensors 文件。您可自定义文件名前缀，并可选地在文件名中包含训练步数以便更好地进行组织管理。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|--------|----------|------|----------|------|
+| `lora` | LORA_MODEL | 是 | - | 待保存的 LoRA 模型。请勿使用带有 LoRA 层的模型。 |
+| `prefix` | STRING | 是 | - | 保存的 LoRA 文件使用的前缀（默认："loras/ComfyUI_trained_lora"）。 |
+| `steps` | INT | 否 | - | 可选参数：LoRA 已训练的步数，用于命名保存的文件。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| *无* | - | 该节点不返回任何输出，但会将 LoRA 模型保存到输出目录。 |
diff --git a/zh-CN/built-in-nodes/SaveSVGNode.mdx b/zh-CN/built-in-nodes/SaveSVGNode.mdx
new file mode 100644
index 000000000..bc9cc37f6
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveSVGNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveSVGNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveSVGNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveSVGNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveSVGNode/zh.md)
+
+将 SVG 文件保存到磁盘。此节点接收 SVG 数据作为输入，并将其保存到您的输出目录，可选择嵌入元数据。该节点自动处理带计数器后缀的文件命名，并可将工作流提示信息直接嵌入 SVG 文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `svg` | SVG | 是 | - | 要保存到磁盘的 SVG 数据 |
+| `filename_prefix` | STRING | 是 | - | 保存文件的前缀。可包含格式化信息，例如 `%date:yyyy-MM-dd%` 或 `%Empty Latent Image.width%` 以包含来自节点的值。（默认值："svg/ComfyUI"） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `ui` | DICT | 返回文件信息，包括文件名、子文件夹和类型，用于在 ComfyUI 界面中显示 |
+
+**注意：** 此节点在可用时会自动将工作流元数据（提示信息和额外的 PNG 信息）嵌入 SVG 文件。元数据以 CDATA 段的形式插入到 SVG 的 metadata 元素中。
diff --git a/zh-CN/built-in-nodes/SaveTrainingDataset.mdx b/zh-CN/built-in-nodes/SaveTrainingDataset.mdx
new file mode 100644
index 000000000..bf02da8b4
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveTrainingDataset.mdx
@@ -0,0 +1,25 @@
+---
+title: "SaveTrainingDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveTrainingDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveTrainingDataset"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveTrainingDataset/zh.md)
+
+此节点将准备好的训练数据集保存到计算机硬盘。它接收已编码的数据（包括图像潜变量及其对应的文本条件信息），并将其组织成多个称为分片的较小文件以便于管理。该节点会在输出目录中自动创建文件夹，并同时保存数据文件和描述数据集的元数据文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `latents` | LATENT | 是 | N/A | 来自 MakeTrainingDataset 节点的潜变量字典列表。 |
+| `conditioning` | CONDITIONING | 是 | N/A | 来自 MakeTrainingDataset 节点的条件信息列表。 |
+| `folder_name` | STRING | 否 | N/A | 保存数据集的文件夹名称（位于输出目录内）。(默认值: "training_dataset") |
+| `shard_size` | INT | 否 | 1 至 100000 | 每个分片文件包含的样本数量。(默认值: 1000) |
+
+**注意：** `latents` 列表中的项目数量必须与 `conditioning` 列表中的项目数量完全一致。如果数量不匹配，节点将报错。
+
+## 输出
+
+此节点不产生任何输出数据。其功能是将文件保存到磁盘。
diff --git a/zh-CN/built-in-nodes/SaveVideo.mdx b/zh-CN/built-in-nodes/SaveVideo.mdx
new file mode 100644
index 000000000..7956c29b5
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveVideo.mdx
@@ -0,0 +1,27 @@
+---
+title: "SaveVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveVideo/zh.md)
+
+## 概述
+
+SaveVideo 节点将输入的视频内容保存到您的 ComfyUI 输出目录中。它允许您指定保存文件的文件名前缀、视频格式和编解码器。该节点会自动处理带计数器递增的文件命名，并可在保存的视频中包含工作流元数据。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `视频` | VIDEO | 是 | - | 要保存的视频。 |
+| `文件名前缀` | STRING | 否 | - | 保存文件的前缀。可以包含格式化信息，例如 `%date:yyyy-MM-dd%` 或 `%Empty Latent Image.width%` 以包含来自节点的值（默认值："video/ComfyUI"）。 |
+| `格式` | COMBO | 否 | 提供多个选项 | 保存视频的格式（默认值："auto"）。 |
+| `编码器` | COMBO | 否 | 提供多个选项 | 用于视频的编解码器（默认值："auto"）。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| *无输出* | - | 此节点不返回任何输出数据。 |
diff --git a/zh-CN/built-in-nodes/SaveWEBM.mdx b/zh-CN/built-in-nodes/SaveWEBM.mdx
new file mode 100644
index 000000000..d5542bec1
--- /dev/null
+++ b/zh-CN/built-in-nodes/SaveWEBM.mdx
@@ -0,0 +1,26 @@
+---
+title: "SaveWEBM - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SaveWEBM node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SaveWEBM"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveWEBM/zh.md)
+
+SaveWEBM 节点将图像序列保存为 WEBM 视频文件。该节点接收多个输入图像，并使用可配置质量设置和帧率的 VP9 或 AV1 编解码器将其编码为视频。生成的视频文件将保存到输出目录，并包含提示信息等元数据。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 要编码为视频帧的输入图像序列 |
+| `文件名前缀` | STRING | 否 | - | 输出文件名的前缀（默认："ComfyUI"） |
+| `编解码器` | COMBO | 是 | "vp9"<br />"av1" | 用于编码的视频编解码器 |
+| `帧率` | FLOAT | 否 | 0.01-1000.0 | 输出视频的帧率（默认：24.0） |
+| `crf` | FLOAT | 否 | 0-63.0 | 质量设置，crf 值越高表示质量越低但文件体积越小，crf 值越低表示质量越高但文件体积越大（默认：32.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `ui` | PREVIEW | 显示已保存 WEBM 文件的视频预览 |
diff --git a/zh-CN/built-in-nodes/ScaleROPE.mdx b/zh-CN/built-in-nodes/ScaleROPE.mdx
new file mode 100644
index 000000000..73b150731
--- /dev/null
+++ b/zh-CN/built-in-nodes/ScaleROPE.mdx
@@ -0,0 +1,28 @@
+---
+title: "ScaleROPE - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ScaleROPE node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ScaleROPE"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ScaleROPE/zh.md)
+
+ScaleROPE 节点允许您通过对其 X、Y 和 T（时间）分量分别应用缩放和偏移因子来修改模型的旋转位置嵌入（ROPE）。这是一个高级的、实验性的节点，用于调整模型的位置编码行为。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 将要修改其 ROPE 参数的模型。 |
+| `scale_x` | FLOAT | 否 | 0.0 - 100.0 | 应用于 ROPE X 分量的缩放因子（默认值：1.0）。 |
+| `shift_x` | FLOAT | 否 | -256.0 - 256.0 | 应用于 ROPE X 分量的偏移值（默认值：0.0）。 |
+| `scale_y` | FLOAT | 否 | 0.0 - 100.0 | 应用于 ROPE Y 分量的缩放因子（默认值：1.0）。 |
+| `shift_y` | FLOAT | 否 | -256.0 - 256.0 | 应用于 ROPE Y 分量的偏移值（默认值：0.0）。 |
+| `scale_t` | FLOAT | 否 | 0.0 - 100.0 | 应用于 ROPE T（时间）分量的缩放因子（默认值：1.0）。 |
+| `shift_t` | FLOAT | 否 | -256.0 - 256.0 | 应用于 ROPE T（时间）分量的偏移值（默认值：0.0）。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 应用了新的 ROPE 缩放和偏移参数的模型。 |
diff --git a/zh-CN/built-in-nodes/Sd4xupscaleConditioning.mdx b/zh-CN/built-in-nodes/Sd4xupscaleConditioning.mdx
new file mode 100644
index 000000000..cedbfd90c
--- /dev/null
+++ b/zh-CN/built-in-nodes/Sd4xupscaleConditioning.mdx
@@ -0,0 +1,26 @@
+---
+title: "Sd4xupscaleConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Sd4xupscaleConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Sd4xupscaleConditioning"
+icon: "circle"
+mode: wide
+---
+此节点专门通过4倍放大过程增强图像分辨率，同时结合条件元素来细化输出。它利用扩散技术在放大图像的同时，允许调整缩放比率和噪声增强，以微调增强过程。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `images` | `IMAGE` | 要放大的输入图像。此参数至关重要，因为它直接影响输出图像的质量和分辨率。 |
+| `positive` | `CONDITIONING` | 正面条件元素，指导放大过程朝着输出图像中的期望属性或特征发展。 |
+| `negative` | `CONDITIONING` | 负面条件元素，放大过程应避免这些元素，有助于引导输出远离不希望的属性或特征。 |
+| `scale_ratio` | `FLOAT` | 确定图像分辨率增加的因子。更高的缩放比率会产生更大的输出图像，允许更详细和清晰的细节。 |
+| `noise_augmentation` | `FLOAT` | 控制放大过程中应用的噪声增强水平。这可以用来引入变异性并提高输出图像的鲁棒性。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `positive` | `CONDITIONING` | 放大过程后得到的精细正面条件元素。 |
+| `negative` | `CONDITIONING` | 放大过程后得到的精细负面条件元素。 |
+| `latent` | `LATENT` | 在放大过程中生成的潜在表示，可用于进一步处理或模型训练。 |
diff --git a/zh-CN/built-in-nodes/SelfAttentionGuidance.mdx b/zh-CN/built-in-nodes/SelfAttentionGuidance.mdx
new file mode 100644
index 000000000..6d100b01d
--- /dev/null
+++ b/zh-CN/built-in-nodes/SelfAttentionGuidance.mdx
@@ -0,0 +1,28 @@
+---
+title: "SelfAttentionGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SelfAttentionGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SelfAttentionGuidance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SelfAttentionGuidance/zh.md)
+
+> 本文档由 AI 生成，如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SelfAttentionGuidance/en.md)
+
+自注意力引导节点通过在采样过程中修改注意力机制，为扩散模型施加引导。它从无条件去噪步骤中捕获注意力分数，并使用这些分数创建影响最终输出的模糊引导图。此技术通过利用模型自身的注意力模式来引导生成过程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用自注意力引导的扩散模型 |
+| `缩放` | FLOAT | 否 | -2.0 到 5.0 | 自注意力引导效果的强度（默认值：0.5） |
+| `模糊Sigma` | FLOAT | 否 | 0.0 到 10.0 | 用于创建引导图的模糊程度（默认值：2.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了自注意力引导的修改后模型 |
+
+**注意：** 此节点目前处于实验阶段，在处理分块批次时存在限制。它只能保存一次 UNet 调用的注意力分数，可能无法正确处理较大的批次大小。
diff --git a/zh-CN/built-in-nodes/SetClipHooks.mdx b/zh-CN/built-in-nodes/SetClipHooks.mdx
new file mode 100644
index 000000000..b500a6609
--- /dev/null
+++ b/zh-CN/built-in-nodes/SetClipHooks.mdx
@@ -0,0 +1,27 @@
+---
+title: "SetClipHooks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetClipHooks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetClipHooks"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetClipHooks/zh.md)
+
+## 概述
+
+SetClipHooks 节点允许您向 CLIP 模型应用自定义钩子，从而能够对其行为进行高级修改。该节点可将钩子应用于条件输出，并可选择启用剪辑调度功能。此节点会创建输入 CLIP 模型的克隆副本，并应用指定的钩子配置。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | - | 要应用钩子的 CLIP 模型 |
+| `应用于条件` | BOOLEAN | 是 | - | 是否对条件输出应用钩子（默认值：True） |
+| `安排clip` | BOOLEAN | 是 | - | 是否启用剪辑调度功能（默认值：False） |
+| `约束` | HOOKS | 否 | - | 可选的要应用于 CLIP 模型的钩子组 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `clip` | CLIP | 应用了指定钩子的 CLIP 模型克隆副本 |
diff --git a/zh-CN/built-in-nodes/SetFirstSigma.mdx b/zh-CN/built-in-nodes/SetFirstSigma.mdx
new file mode 100644
index 000000000..69038d18d
--- /dev/null
+++ b/zh-CN/built-in-nodes/SetFirstSigma.mdx
@@ -0,0 +1,23 @@
+---
+title: "SetFirstSigma - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetFirstSigma node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetFirstSigma"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetFirstSigma/zh.md)
+
+SetFirstSigma 节点通过将序列中的第一个 sigma 值替换为自定义值来修改 sigma 值序列。它接收现有的 sigma 序列和新的 sigma 值作为输入，然后返回一个新的 sigma 序列，其中仅第一个元素被更改，而其他所有 sigma 值保持不变。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `sigmas` | SIGMAS | 是 | - | 待修改的输入 sigma 值序列 |
+| `sigma` | FLOAT | 是 | 0.0 至 20000.0 | 设置为序列中第一个元素的新 sigma 值（默认值：136.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `sigmas` | SIGMAS | 经过修改的 sigma 序列，其中第一个元素已被自定义 sigma 值替换 |
diff --git a/zh-CN/built-in-nodes/SetHookKeyframes.mdx b/zh-CN/built-in-nodes/SetHookKeyframes.mdx
new file mode 100644
index 000000000..f58836d26
--- /dev/null
+++ b/zh-CN/built-in-nodes/SetHookKeyframes.mdx
@@ -0,0 +1,25 @@
+---
+title: "SetHookKeyframes - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetHookKeyframes node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetHookKeyframes"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetHookKeyframes/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetHookKeyframes/en.md)
+
+Set Hook Keyframes 节点允许您对现有的钩子组应用关键帧调度功能。它接收一个钩子组，并可选择性地应用关键帧时间信息来控制不同钩子在生成过程中的执行时机。当提供关键帧时，该节点会克隆钩子组并为组内的所有钩子设置关键帧时间。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `约束` | HOOKS | 是 | - | 将要应用关键帧调度的钩子组 |
+| `约束关键帧` | HOOK_KEYFRAMES | 否 | - | 包含钩子执行时间信息的可选关键帧组 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `约束` | HOOKS | 应用了关键帧调度的修改后钩子组（如果提供了关键帧则会克隆） |
diff --git a/zh-CN/built-in-nodes/SetLatentNoiseMask.mdx b/zh-CN/built-in-nodes/SetLatentNoiseMask.mdx
new file mode 100644
index 000000000..07cf69187
--- /dev/null
+++ b/zh-CN/built-in-nodes/SetLatentNoiseMask.mdx
@@ -0,0 +1,34 @@
+---
+title: "SetLatentNoiseMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetLatentNoiseMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetLatentNoiseMask"
+icon: "circle"
+mode: wide
+---
+此节点旨在对一组潜在样本应用噪波遮罩。它通过整合指定的遮罩来修改输入样本，从而改变它们的噪声特性。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `Latent` | `LATENT` | 将应用噪波遮罩的潜在样本。此参数对于确定将被修改的基础内容至关重要。 |
+| `遮罩`    | `MASK`   | 要应用于潜在样本的遮罩。它定义了样本内噪声变化的区域和强度。       |
+
+## 输出
+
+|
+该节点主要用于对图像编码后的latent图像在遮罩区域添加额外的噪声来进行局部的重绘，根据采样器设置的```denoise降噪```的值的不同，当设置的值越小时，生成的图像会保持和原图越高的相似度。
+
+不同```denoise降噪```值设置下使用该节点输出图像效果如下
+**Input-输入**
+
+|参数名称 | 作用|
+|-----------------------|---------------------|
+|samples | 需要进行重绘的图像的Latent输入|
+|mask-遮罩  | 加载图像中需要进行重绘的区域|
+
+**Output-输出**
+
+|参数名称 | 作用|
+-----------------------|---------------------|
+|LATENT  | 转换后的潜空间图像   |
diff --git a/zh-CN/built-in-nodes/SetModelHooksOnCond.mdx b/zh-CN/built-in-nodes/SetModelHooksOnCond.mdx
new file mode 100644
index 000000000..cacb833f4
--- /dev/null
+++ b/zh-CN/built-in-nodes/SetModelHooksOnCond.mdx
@@ -0,0 +1,23 @@
+---
+title: "SetModelHooksOnCond - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetModelHooksOnCond node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetModelHooksOnCond"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetModelHooksOnCond/zh.md)
+
+此节点将自定义钩子附加到条件数据，允许您在模型执行过程中拦截和修改条件处理过程。它接收一组钩子并将其应用于提供的条件数据，从而实现对文生图工作流程的高级定制。附加了钩子的修改后条件数据将返回以供后续处理步骤使用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `conditioning` | CONDITIONING | 是 | - | 将要附加钩子的条件数据 |
+| `hooks` | HOOKS | 是 | - | 将应用于条件数据的钩子定义 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | 附加了钩子的修改后条件数据 |
diff --git a/zh-CN/built-in-nodes/SetUnionControlNetType.mdx b/zh-CN/built-in-nodes/SetUnionControlNetType.mdx
new file mode 100644
index 000000000..c2a83879b
--- /dev/null
+++ b/zh-CN/built-in-nodes/SetUnionControlNetType.mdx
@@ -0,0 +1,23 @@
+---
+title: "SetUnionControlNetType - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SetUnionControlNetType node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SetUnionControlNetType"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetUnionControlNetType/zh.md)
+
+SetUnionControlNetType 节点允许您指定用于条件控制的控制网络类型。该节点接收现有的控制网络，根据您的选择设置其控制类型，从而创建具有指定类型配置的控制网络修改副本。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `ControlNet` | CONTROL_NET | 是 | - | 需要设置新类型参数的控制网络 |
+| `类型` | STRING | 是 | `"auto"`<br />所有可用的 UNION_CONTROLNET_TYPES 键值 | 要应用的控制网络类型。使用 "auto" 进行自动类型检测，或从可用选项中选择特定的控制网络类型 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `ControlNet` | CONTROL_NET | 应用了指定类型设置的修改后控制网络 |
diff --git a/zh-CN/built-in-nodes/ShuffleDataset.mdx b/zh-CN/built-in-nodes/ShuffleDataset.mdx
new file mode 100644
index 000000000..191c641ca
--- /dev/null
+++ b/zh-CN/built-in-nodes/ShuffleDataset.mdx
@@ -0,0 +1,23 @@
+---
+title: "ShuffleDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ShuffleDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ShuffleDataset"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ShuffleDataset/zh.md)
+
+Shuffle Dataset 节点接收一个图像列表并随机改变它们的顺序。它使用种子值来控制随机性，确保可以重现相同的洗牌顺序。这在处理前对数据集中的图像序列进行随机化时非常有用。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | - | 待洗牌的图像列表。 |
+| `seed` | INT | 否 | 0 到 18446744073709551615 | 随机种子。值为 0 时，每次都会产生不同的洗牌顺序。(默认值: 0) |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `images` | IMAGE | 相同的图像列表，但处于一个新的、随机洗牌后的顺序。 |
diff --git a/zh-CN/built-in-nodes/ShuffleImageTextDataset.mdx b/zh-CN/built-in-nodes/ShuffleImageTextDataset.mdx
new file mode 100644
index 000000000..176b74b38
--- /dev/null
+++ b/zh-CN/built-in-nodes/ShuffleImageTextDataset.mdx
@@ -0,0 +1,27 @@
+---
+title: "ShuffleImageTextDataset - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ShuffleImageTextDataset node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ShuffleImageTextDataset"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ShuffleImageTextDataset/zh.md)
+
+此节点将图像列表和文本列表一起打乱，同时保持它们的配对关系不变。它使用随机种子来确定打乱顺序，确保相同的输入列表在每次重用种子时都会以相同的方式被打乱。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | - | 需要打乱的图像列表。 |
+| `texts` | STRING | 是 | - | 需要打乱的文本列表。 |
+| `seed` | INT | 否 | 0 到 18446744073709551615 | 随机种子。打乱顺序由此值决定（默认值：0）。 |
+
+**注意：** `images` 和 `texts` 输入必须是长度相同的列表。节点在将这些配对一起打乱之前，会将第一张图像与第一个文本配对，第二张图像与第二个文本配对，依此类推。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `images` | IMAGE | 打乱后的图像列表。 |
+| `texts` | STRING | 打乱后的文本列表，保持其与图像的原始配对关系。 |
diff --git a/zh-CN/built-in-nodes/SkipLayerGuidanceDiT.mdx b/zh-CN/built-in-nodes/SkipLayerGuidanceDiT.mdx
new file mode 100644
index 000000000..71766d41f
--- /dev/null
+++ b/zh-CN/built-in-nodes/SkipLayerGuidanceDiT.mdx
@@ -0,0 +1,32 @@
+---
+title: "SkipLayerGuidanceDiT - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SkipLayerGuidanceDiT node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SkipLayerGuidanceDiT"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SkipLayerGuidanceDiT/zh.md)
+
+## 概述
+
+通过使用另一组跳过层的 CFG 负向提示来增强对细节结构的引导。这个通用版本的 SkipLayerGuidance 可用于所有 DiT 模型，其灵感来源于扰动注意力引导。原始实验性实现是为 SD3 创建的。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|------|-----------|------|------|-------------|
+| `模型` | MODEL | 是 | - | 要应用跳过层引导的模型 |
+| `双层` | STRING | 是 | - | 要跳过的双块层的逗号分隔层号（默认："7, 8, 9"） |
+| `单层` | STRING | 是 | - | 要跳过的单块层的逗号分隔层号（默认："7, 8, 9"） |
+| `缩放` | FLOAT | 是 | 0.0 - 10.0 | 引导缩放因子（默认：3.0） |
+| `开始百分比` | FLOAT | 是 | 0.0 - 1.0 | 引导应用的起始百分比（默认：0.01） |
+| `结束百分比` | FLOAT | 是 | 0.0 - 1.0 | 引导应用的结束百分比（默认：0.15） |
+| `重新缩放比例` | FLOAT | 是 | 0.0 - 10.0 | 重新缩放因子（默认：0.0） |
+
+**注意：** 如果 `double_layers` 和 `single_layers` 都为空（不包含任何层号），节点将返回原始模型而不应用任何引导。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `模型` | MODEL | 应用了跳过层引导的修改后模型 |
diff --git a/zh-CN/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx b/zh-CN/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx
new file mode 100644
index 000000000..fceddb9a1
--- /dev/null
+++ b/zh-CN/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx
@@ -0,0 +1,28 @@
+---
+title: "SkipLayerGuidanceDiTSimple - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SkipLayerGuidanceDiTSimple node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SkipLayerGuidanceDiTSimple"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SkipLayerGuidanceDiTSimple/zh.md)
+
+SkipLayerGuidanceDiT 节点的简化版本，仅在去噪过程中修改无条件传递。该节点通过根据指定的时序和层参数，在无条件传递期间选择性跳过特定层，从而对 DiT（扩散变换器）模型中的特定变换器层应用跳跃层引导。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要应用跳跃层引导的模型 |
+| `double_layers` | STRING | 是 | - | 要跳过的双块层索引的逗号分隔列表（默认："7, 8, 9"） |
+| `single_layers` | STRING | 是 | - | 要跳过的单块层索引的逗号分隔列表（默认："7, 8, 9"） |
+| `start_percent` | FLOAT | 是 | 0.0 - 1.0 | 跳跃层引导开始的去噪过程起始百分比（默认：0.0） |
+| `end_percent` | FLOAT | 是 | 0.0 - 1.0 | 跳跃层引导停止的去噪过程结束百分比（默认：1.0） |
+
+**注意：** 仅当 `double_layers` 和 `single_layers` 都包含有效层索引时才会应用跳跃层引导。如果两者均为空，节点将返回未修改的原始模型。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 已对指定层应用跳跃层引导的修改后模型 |
diff --git a/zh-CN/built-in-nodes/SkipLayerGuidanceSD3.mdx b/zh-CN/built-in-nodes/SkipLayerGuidanceSD3.mdx
new file mode 100644
index 000000000..bf349abc3
--- /dev/null
+++ b/zh-CN/built-in-nodes/SkipLayerGuidanceSD3.mdx
@@ -0,0 +1,28 @@
+---
+title: "SkipLayerGuidanceSD3 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SkipLayerGuidanceSD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SkipLayerGuidanceSD3"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SkipLayerGuidanceSD3/zh.md)
+
+# SkipLayerGuidanceSD3 节点
+
+SkipLayerGuidanceSD3 节点通过应用一组额外的跳层无分类器引导来增强对细节结构的引导。该实验性实现受到扰动注意力引导的启发，通过在负向条件处理过程中选择性绕过特定层，以改善生成输出中的结构细节。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型` | MODEL | 是 | - | 要应用跳层引导的模型 |
+| `层` | STRING | 是 | - | 要跳过的层索引逗号分隔列表（默认："7, 8, 9"） |
+| `缩放` | FLOAT | 是 | 0.0 - 10.0 | 跳层引导效果的强度（默认：3.0） |
+| `开始百分比` | FLOAT | 是 | 0.0 - 1.0 | 引导应用的起始点，以总步数的百分比表示（默认：0.01） |
+| `结束百分比` | FLOAT | 是 | 0.0 - 1.0 | 引导应用的结束点，以总步数的百分比表示（默认：0.15） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `模型` | MODEL | 应用了跳层引导的修改后模型 |
diff --git a/zh-CN/built-in-nodes/SolidMask.mdx b/zh-CN/built-in-nodes/SolidMask.mdx
new file mode 100644
index 000000000..d32e247ee
--- /dev/null
+++ b/zh-CN/built-in-nodes/SolidMask.mdx
@@ -0,0 +1,23 @@
+---
+title: "SolidMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SolidMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SolidMask"
+icon: "circle"
+mode: wide
+---
+
+纯块遮罩节点用于生成一个具有指定值的均匀纯色的遮罩，覆盖其整个区域。它旨在创建具有特定尺寸和强度的遮罩，在各种图像处理和遮罩任务中非常有用。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `明度` | FLOAT | 指定遮罩的强度值，影响其整体外观以及在后续操作中的实用性。 |
+| `宽度` | INT | 确定生成遮罩的宽度，直接影响其大小和宽高比。 |
+| `高度` | INT | 设置生成遮罩的高度，影响其大小和宽高比。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `mask` | MASK | 输出一个具有指定尺寸和值的均匀遮罩。 |
diff --git a/zh-CN/built-in-nodes/SplitAudioChannels.mdx b/zh-CN/built-in-nodes/SplitAudioChannels.mdx
new file mode 100644
index 000000000..c8ddfdfe7
--- /dev/null
+++ b/zh-CN/built-in-nodes/SplitAudioChannels.mdx
@@ -0,0 +1,25 @@
+---
+title: "SplitAudioChannels - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SplitAudioChannels node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SplitAudioChannels"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitAudioChannels/zh.md)
+
+SplitAudioChannels 节点用于将立体声音频分离为独立的左右声道。它接收包含两个声道的立体声音频输入，并输出两个独立的音频流，分别对应左声道和右声道。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | 是 | - | 需要分离声道的立体声音频输入 |
+
+**注意：** 输入音频必须恰好包含两个声道（立体声）。如果输入音频只有一个声道，节点将报错。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `left` | AUDIO | 分离后的左声道音频 |
+| `right` | AUDIO | 分离后的右声道音频 |
diff --git a/zh-CN/built-in-nodes/SplitImageWithAlpha.mdx b/zh-CN/built-in-nodes/SplitImageWithAlpha.mdx
new file mode 100644
index 000000000..cb4143c08
--- /dev/null
+++ b/zh-CN/built-in-nodes/SplitImageWithAlpha.mdx
@@ -0,0 +1,21 @@
+---
+title: "SplitImageWithAlpha - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SplitImageWithAlpha node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SplitImageWithAlpha"
+icon: "circle"
+mode: wide
+---
+SplitImageWithAlpha 节点旨在分离图像的颜色和 alpha（透明度）组件。它处理输入的图像张量，提取 RGB 通道作为颜色组件，以及 alpha 通道作为透明度组件，从而便于对这些不同的图像方面进行操作。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `图片`  | `IMAGE`  | 'image' 参数代表要从中分离出 RGB 和 alpha 通道的输入图像张量。它对操作至关重要，因为它提供了拆分的源数据。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `图片`  | `IMAGE`  | 'image' 输出代表输入图像分离出的 RGB 通道，提供了不包含透明度信息的颜色组件。 |
+| `mask`   | `MASK`   | 'mask' 输出代表输入图像分离出的 alpha 通道，提供了透明度信息。   |
diff --git a/zh-CN/built-in-nodes/SplitSigmas.mdx b/zh-CN/built-in-nodes/SplitSigmas.mdx
new file mode 100644
index 000000000..ce432250d
--- /dev/null
+++ b/zh-CN/built-in-nodes/SplitSigmas.mdx
@@ -0,0 +1,21 @@
+---
+title: "SplitSigmas - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SplitSigmas node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SplitSigmas"
+icon: "circle"
+mode: wide
+---
+`SplitSigmas` 节点旨在将一系列 sigma 值根据指定的步骤分割成两部分。这一功能对于需要对 sigma 序列的初始部分和后续部分进行不同处理或处理的操作至关重要，它允许对这些值进行更灵活和针对性的操作。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `Sigmas` | SIGMAS   | `Sigmas` 参数代表要被分割的 sigma 值序列。它对于确定分割点和结果的两个 sigma 值序列至关重要，影响节点的执行和结果。 |
+| `步数`   | INT      | `步数` 参数指定应在何处分割 sigma 序列。它在定义两个结果 sigma 序列之间的边界时起着关键作用，影响节点的功能和输出的特性。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `低方差` | SIGMAS   | 节点输出两个 sigma 值序列，每个序列代表在指定步骤处分割的原始序列的一部分。这些输出对于需要对 sigma 值进行差异化处理的后续操作至关重要。 |
diff --git a/zh-CN/built-in-nodes/SplitSigmasDenoise.mdx b/zh-CN/built-in-nodes/SplitSigmasDenoise.mdx
new file mode 100644
index 000000000..5550e4a19
--- /dev/null
+++ b/zh-CN/built-in-nodes/SplitSigmasDenoise.mdx
@@ -0,0 +1,24 @@
+---
+title: "SplitSigmasDenoise - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SplitSigmasDenoise node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SplitSigmasDenoise"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitSigmasDenoise/zh.md)
+
+SplitSigmasDenoise 节点根据去噪强度参数将一系列 sigma 值划分为两部分。它将输入的 sigma 序列分割为高 sigma 序列和低 sigma 序列，分割点由总步数乘以去噪因子确定。这样可以将噪声调度分离到不同的强度范围，以便进行专门处理。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Sigmas` | SIGMAS | 是 | - | 表示噪声调度的输入 sigma 值序列 |
+| `降噪` | FLOAT | 是 | 0.0 - 1.0 | 决定 sigma 序列分割点的去噪强度因子（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `低方差` | SIGMAS | 包含较高 sigma 值的 sigma 序列前半部分 |
+| `low_sigmas` | SIGMAS | 包含较低 sigma 值的 sigma 序列后半部分 |
diff --git a/zh-CN/built-in-nodes/StabilityAudioInpaint.mdx b/zh-CN/built-in-nodes/StabilityAudioInpaint.mdx
new file mode 100644
index 000000000..01ab4b210
--- /dev/null
+++ b/zh-CN/built-in-nodes/StabilityAudioInpaint.mdx
@@ -0,0 +1,31 @@
+---
+title: "StabilityAudioInpaint - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityAudioInpaint node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityAudioInpaint"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityAudioInpaint/zh.md)
+
+使用文本指令对现有音频样本的特定部分进行转换。该节点允许您通过提供描述性提示来修改音频的特定段落，有效地对选定部分进行"修复"或重新生成，同时保留音频的其余部分。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `model` | COMBO | 是 | "stable-audio-2.5"<br /> | 用于音频修复的AI模型。 |
+| `prompt` | STRING | 是 |  | 指导音频转换方式的文本描述（默认：空）。 |
+| `audio` | AUDIO | 是 |  | 要转换的输入音频文件。音频长度必须在6到190秒之间。 |
+| `duration` | INT | 否 | 1-190 | 控制生成音频的时长（单位：秒）（默认：190）。 |
+| `seed` | INT | 否 | 0-4294967294 | 用于生成的随机种子（默认：0）。 |
+| `steps` | INT | 否 | 4-8 | 控制采样步数（默认：8）。 |
+| `mask_start` | INT | 否 | 0-190 | 要转换的音频段起始位置（单位：秒）（默认：30）。 |
+| `mask_end` | INT | 否 | 0-190 | 要转换的音频段结束位置（单位：秒）（默认：190）。 |
+
+**注意：** `mask_end` 值必须大于 `mask_start` 值。输入音频的时长必须在6到190秒之间。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `audio` | AUDIO | 根据提示修改指定段落后的转换音频输出。 |
diff --git a/zh-CN/built-in-nodes/StabilityAudioToAudio.mdx b/zh-CN/built-in-nodes/StabilityAudioToAudio.mdx
new file mode 100644
index 000000000..3a2f4f232
--- /dev/null
+++ b/zh-CN/built-in-nodes/StabilityAudioToAudio.mdx
@@ -0,0 +1,30 @@
+---
+title: "StabilityAudioToAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityAudioToAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityAudioToAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityAudioToAudio/zh.md)
+
+使用文本指令将现有音频样本转换为新的高质量音频作品。该节点接收输入音频文件，并根据您的文本提示对其进行修改，从而创建新的音频内容。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | "stable-audio-2.5"<br /> | 用于音频转换的AI模型 |
+| `prompt` | STRING | 是 |  | 描述如何转换音频的文本指令（默认：空） |
+| `audio` | AUDIO | 是 |  | 音频时长必须在6到190秒之间 |
+| `duration` | INT | 否 | 1-190 | 控制生成音频的时长（单位：秒）（默认：190） |
+| `seed` | INT | 否 | 0-4294967294 | 用于生成的随机种子（默认：0） |
+| `steps` | INT | 否 | 4-8 | 控制采样步数（默认：8） |
+| `strength` | FLOAT | 否 | 0.01-1.0 | 控制音频参数对生成音频的影响程度（默认：1.0） |
+
+**注意：** 输入音频的时长必须在6到190秒之间。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 基于输入音频和文本提示生成的转换后音频 |
diff --git a/zh-CN/built-in-nodes/StabilityStableImageSD_3_5Node.mdx b/zh-CN/built-in-nodes/StabilityStableImageSD_3_5Node.mdx
new file mode 100644
index 000000000..b0826bdea
--- /dev/null
+++ b/zh-CN/built-in-nodes/StabilityStableImageSD_3_5Node.mdx
@@ -0,0 +1,32 @@
+---
+title: "StabilityStableImageSD_3_5Node - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityStableImageSD_3_5Node node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityStableImageSD_3_5Node"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityStableImageSD_3_5Node/zh.md)
+
+此节点使用 Stability AI 的 Stable Diffusion 3.5 模型同步生成图像。它基于文本提示创建图像，并在提供输入图像时能够修改现有图像。该节点支持多种宽高比和风格预设以自定义输出。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 期望在输出图像中看到的内容。一个强有力、描述性的提示，能清晰定义元素、颜色和主体，将带来更好的结果。（默认值：空字符串） |
+| `model` | COMBO | 是 | 提供多个选项 | 用于生成的 Stable Diffusion 3.5 模型。 |
+| `aspect_ratio` | COMBO | 是 | 提供多个选项 | 生成图像的宽高比。（默认值：1:1 比例） |
+| `style_preset` | COMBO | 否 | 提供多个选项 | 生成图像的可选期望风格。 |
+| `cfg_scale` | FLOAT | 是 | 1.0 到 10.0 | 扩散过程遵循提示文本的严格程度（值越高，图像越接近提示内容）。（默认值：4.0） |
+| `seed` | INT | 是 | 0 到 4294967294 | 用于创建噪声的随机种子。（默认值：0） |
+| `image` | IMAGE | 否 | - | 用于图生图生成的可选输入图像。 |
+| `negative_prompt` | STRING | 否 | - | 不希望出现在输出图像中的关键词。此为高级功能。（默认值：空字符串） |
+| `image_denoise` | FLOAT | 否 | 0.0 到 1.0 | 输入图像的去噪强度；0.0 产生与输入完全相同的图像，1.0 相当于完全没有提供图像。（默认值：0.5） |
+
+**注意：** 当提供 `image` 时，节点将切换到图生图生成模式，且 `aspect_ratio` 参数会自动根据输入图像确定。当未提供 `image` 时，`image_denoise` 参数将被忽略。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 生成或修改后的图像。 |
diff --git a/zh-CN/built-in-nodes/StabilityStableImageUltraNode.mdx b/zh-CN/built-in-nodes/StabilityStableImageUltraNode.mdx
new file mode 100644
index 000000000..34692d8f4
--- /dev/null
+++ b/zh-CN/built-in-nodes/StabilityStableImageUltraNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "StabilityStableImageUltraNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityStableImageUltraNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityStableImageUltraNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityStableImageUltraNode/zh.md)
+
+基于提示词和分辨率同步生成图像。此节点使用 Stability AI 的 Stable Image Ultra 模型创建图像，处理您的文本提示词并生成具有指定宽高比和风格的对应图像。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 您希望在输出图像中看到的内容。一个清晰描述元素、颜色和主体的强有力提示词将带来更好的结果。要控制特定词的权重，请使用格式 `(单词:权重)`，其中 `单词` 是您想要控制权重的词，`权重` 是介于 0 到 1 之间的值。例如：`天空是清新的 (蓝色:0.3) 和 (绿色:0.8)` 将呈现一个蓝色和绿色的天空，但绿色比蓝色更多。 |
+| `aspect_ratio` | COMBO | 是 | 多个选项可用 | 生成图像的宽高比。 |
+| `style_preset` | COMBO | 否 | 多个选项可用 | 生成图像的可选期望风格。 |
+| `seed` | INT | 是 | 0-4294967294 | 用于创建噪声的随机种子。 |
+| `image` | IMAGE | 否 | - | 可选的输入图像。 |
+| `negative_prompt` | STRING | 否 | - | 描述您不希望出现在输出图像中的文本内容。这是一个高级功能。 |
+| `image_denoise` | FLOAT | 否 | 0.0-1.0 | 输入图像的去噪程度；0.0 产生与输入完全相同的图像，1.0 则如同完全没有提供图像。默认值：0.5 |
+
+**注意：** 当未提供输入图像时，`image_denoise` 参数会自动禁用。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 基于输入参数生成的图像。 |
diff --git a/zh-CN/built-in-nodes/StabilityTextToAudio.mdx b/zh-CN/built-in-nodes/StabilityTextToAudio.mdx
new file mode 100644
index 000000000..913fe64e9
--- /dev/null
+++ b/zh-CN/built-in-nodes/StabilityTextToAudio.mdx
@@ -0,0 +1,26 @@
+---
+title: "StabilityTextToAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityTextToAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityTextToAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityTextToAudio/zh.md)
+
+根据文本描述生成高质量的音乐和音效。此节点采用 Stability AI 的音频生成技术，基于您的文本提示创建音频内容。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 参数说明 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"stable-audio-2.5"` | 使用的音频生成模型（默认值："stable-audio-2.5"） |
+| `prompt` | STRING | 是 | - | 用于生成音频内容的文本描述（默认值：空字符串） |
+| `duration` | INT | 否 | 1-190 | 控制生成音频的时长（单位：秒）（默认值：190） |
+| `seed` | INT | 否 | 0-4294967294 | 用于生成的随机种子（默认值：0） |
+| `steps` | INT | 否 | 4-8 | 控制采样步数（默认值：8） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 说明 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 基于文本提示生成的音频文件 |
diff --git a/zh-CN/built-in-nodes/StabilityUpscaleConservativeNode.mdx b/zh-CN/built-in-nodes/StabilityUpscaleConservativeNode.mdx
new file mode 100644
index 000000000..e0fb6f933
--- /dev/null
+++ b/zh-CN/built-in-nodes/StabilityUpscaleConservativeNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "StabilityUpscaleConservativeNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityUpscaleConservativeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityUpscaleConservativeNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleConservativeNode/zh.md)
+
+# ## 概述
+
+以最小改动将图像放大至 4K 分辨率。此节点使用 Stability AI 的保守放大技术来提升图像分辨率，同时保留原始内容并仅进行细微调整。
+
+# ## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 需要放大的输入图像 |
+| `提示词` | STRING | 是 | - | 期望在输出图像中看到的内容。使用强描述性提示词，明确定义元素、颜色和主体，将获得更好的效果。（默认：空字符串） |
+| `创造性` | FLOAT | 是 | 0.2-0.5 | 控制创建不受初始图像严格约束的额外细节的可能性。（默认：0.35） |
+| `种子` | INT | 是 | 0-4294967294 | 用于创建噪声的随机种子。（默认：0） |
+| `反向提示词` | STRING | 否 | - | 不希望出现在输出图像中的关键词。此为高级功能。（默认：空字符串） |
+
+# ## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 4K 分辨率的放大图像 |
diff --git a/zh-CN/built-in-nodes/StabilityUpscaleCreativeNode.mdx b/zh-CN/built-in-nodes/StabilityUpscaleCreativeNode.mdx
new file mode 100644
index 000000000..17326c6a7
--- /dev/null
+++ b/zh-CN/built-in-nodes/StabilityUpscaleCreativeNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "StabilityUpscaleCreativeNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityUpscaleCreativeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityUpscaleCreativeNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleCreativeNode/zh.md)
+
+## 概述
+
+将图像放大至 4K 分辨率，同时保持最小程度的改动。此节点采用 Stability AI 的创意放大技术，在提升图像分辨率的同时保留原始内容并添加细腻的创意细节。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 需要放大的输入图像 |
+| `提示词` | STRING | 是 | - | 期望在输出图像中看到的内容。使用强描述性提示词明确定义元素、颜色和主体将获得更佳效果。（默认：空字符串） |
+| `创造性` | FLOAT | 是 | 0.1-0.5 | 控制创建不受初始图像严格约束的附加细节的可能性。（默认：0.3） |
+| `风格预设` | COMBO | 是 | 提供多种选项 | 可选的目标生成图像风格预设。包含 Stability AI 提供的多种风格预设选项。 |
+| `随机种子` | INT | 是 | 0-4294967294 | 用于生成噪声的随机种子。（默认：0） |
+| `反向提示词` | STRING | 否 | - | 不希望出现在输出图像中的关键词。此为高级功能。（默认：空字符串） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `图像` | IMAGE | 放大至 4K 分辨率的图像 |
diff --git a/zh-CN/built-in-nodes/StabilityUpscaleFastNode.mdx b/zh-CN/built-in-nodes/StabilityUpscaleFastNode.mdx
new file mode 100644
index 000000000..b60ba74cf
--- /dev/null
+++ b/zh-CN/built-in-nodes/StabilityUpscaleFastNode.mdx
@@ -0,0 +1,22 @@
+---
+title: "StabilityUpscaleFastNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StabilityUpscaleFastNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StabilityUpscaleFastNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleFastNode/zh.md)
+
+通过调用 Stability API 快速将图像放大至原始尺寸的 4 倍。此节点专门用于通过将低质量或压缩图像发送至 Stability AI 的快速放大服务来实现图像放大。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 是否必填 | 取值范围 | 功能说明 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 待放大的输入图像 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 功能说明 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 从 Stability AI API 返回的放大后图像 |
diff --git a/zh-CN/built-in-nodes/StableCascade_EmptyLatentImage.mdx b/zh-CN/built-in-nodes/StableCascade_EmptyLatentImage.mdx
new file mode 100644
index 000000000..f28901e57
--- /dev/null
+++ b/zh-CN/built-in-nodes/StableCascade_EmptyLatentImage.mdx
@@ -0,0 +1,26 @@
+---
+title: "StableCascade_EmptyLatentImage - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableCascade_EmptyLatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableCascade_EmptyLatentImage"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_EmptyLatentImage/zh.md)
+
+StableCascade_EmptyLatentImage 节点为 Stable Cascade 模型创建空潜在张量。它生成两个独立的潜在表示——一个用于阶段 C，另一个用于阶段 B——根据输入分辨率和压缩设置具有适当的维度。该节点为 Stable Cascade 生成流程提供了起点。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `宽度` | INT | 是 | 256 至 MAX_RESOLUTION | 输出图像的宽度（单位：像素）（默认值：1024，步长：8） |
+| `高度` | INT | 是 | 256 至 MAX_RESOLUTION | 输出图像的高度（单位：像素）（默认值：1024，步长：8） |
+| `压缩` | INT | 是 | 4 至 128 | 决定阶段 C 潜在维度的压缩因子（默认值：42，步长：1） |
+| `批量大小` | INT | 否 | 1 至 4096 | 单批次生成的潜在样本数量（默认值：1） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `阶段B` | LATENT | 阶段 C 潜在张量，维度为 [batch_size, 16, height//compression, width//compression] |
+| `stage_b` | LATENT | 阶段 B 潜在张量，维度为 [batch_size, 4, height//4, width//4] |
diff --git a/zh-CN/built-in-nodes/StableCascade_StageB_Conditioning.mdx b/zh-CN/built-in-nodes/StableCascade_StageB_Conditioning.mdx
new file mode 100644
index 000000000..74f0f8ffa
--- /dev/null
+++ b/zh-CN/built-in-nodes/StableCascade_StageB_Conditioning.mdx
@@ -0,0 +1,23 @@
+---
+title: "StableCascade_StageB_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableCascade_StageB_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableCascade_StageB_Conditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_StageB_Conditioning/zh.md)
+
+StableCascade_StageB_Conditioning 节点通过将现有条件信息与来自 Stage C 的先验潜在表示相结合，为 Stable Cascade Stage B 生成准备条件数据。该节点会修改条件数据以包含来自 Stage C 的潜在样本，使生成过程能够利用先验信息来获得更连贯的输出。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `条件` | CONDITIONING | 是 | - | 待修改的条件数据，将加入 Stage C 先验信息 |
+| `阶段c` | LATENT | 是 | - | 来自 Stage C 的潜在表示，包含用于条件处理的先验样本 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 已整合 Stage C 先验信息的修改后条件数据 |
diff --git a/zh-CN/built-in-nodes/StableCascade_StageC_VAEEncode.mdx b/zh-CN/built-in-nodes/StableCascade_StageC_VAEEncode.mdx
new file mode 100644
index 000000000..66d100437
--- /dev/null
+++ b/zh-CN/built-in-nodes/StableCascade_StageC_VAEEncode.mdx
@@ -0,0 +1,27 @@
+---
+title: "StableCascade_StageC_VAEEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableCascade_StageC_VAEEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableCascade_StageC_VAEEncode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_StageC_VAEEncode/zh.md)
+
+## 概述
+
+StableCascade_StageC_VAEEncode 节点通过 VAE 编码器处理图像，为 Stable Cascade 模型生成潜在表示。它接收输入图像并使用指定的 VAE 模型进行压缩，然后输出两个潜在表示：一个用于阶段 C，另一个是阶段 B 的占位符。压缩参数控制在编码前图像被缩小的程度。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 需要编码到潜在空间的输入图像 |
+| `vae` | VAE | 是 | - | 用于图像编码的 VAE 模型 |
+| `压缩` | INT | 否 | 4-128 | 编码前应用于图像的压缩因子（默认值：42） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `阶段B` | LATENT | 为 Stable Cascade 模型阶段 C 编码的潜在表示 |
+| `stage_b` | LATENT | 阶段 B 的占位符潜在表示（当前返回零值） |
diff --git a/zh-CN/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx b/zh-CN/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx
new file mode 100644
index 000000000..387ddb334
--- /dev/null
+++ b/zh-CN/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx
@@ -0,0 +1,27 @@
+---
+title: "StableCascade_SuperResolutionControlnet - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableCascade_SuperResolutionControlnet node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableCascade_SuperResolutionControlnet"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_SuperResolutionControlnet/zh.md)
+
+## 概述
+
+StableCascade_SuperResolutionControlnet 节点为 Stable Cascade 超分辨率处理准备输入数据。它接收输入图像并使用 VAE 进行编码以创建控制网络输入，同时为 Stable Cascade 流程的 C 阶段和 B 阶段生成占位符潜在表示。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | IMAGE | 是 | - | 用于超分辨率处理的输入图像 |
+| `vae` | VAE | 是 | - | 用于编码输入图像的 VAE 模型 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `阶段C` | IMAGE | 适用于控制网络输入的编码图像表示 |
+| `阶段B` | LATENT | 用于 Stable Cascade 处理 C 阶段的占位符潜在表示 |
+| `stage_b` | LATENT | 用于 Stable Cascade 处理 B 阶段的占位符潜在表示 |
diff --git a/zh-CN/built-in-nodes/StableZero123_Conditioning.mdx b/zh-CN/built-in-nodes/StableZero123_Conditioning.mdx
new file mode 100644
index 000000000..36fa7d0a9
--- /dev/null
+++ b/zh-CN/built-in-nodes/StableZero123_Conditioning.mdx
@@ -0,0 +1,33 @@
+---
+title: "StableZero123_Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableZero123_Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableZero123_Conditioning"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning/zh.md)
+
+StableZero123_Conditioning 节点通过处理输入图像和相机角度，生成用于3D模型生成的条件数据和潜在表示。该节点使用CLIP视觉模型对图像特征进行编码，将其基于仰角和方位角的相机嵌入信息相结合，并为下游3D生成任务生成正向/负向条件数据及潜在表示。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|--------|-----------|------|----------|------|
+| `clip视觉` | CLIP_VISION | 是 | - | 用于编码图像特征的CLIP视觉模型 |
+| `初始图像` | IMAGE | 是 | - | 待处理和编码的输入图像 |
+| `vae` | VAE | 是 | - | 用于将像素编码到潜在空间的VAE模型 |
+| `宽度` | INT | 否 | 16至MAX_RESOLUTION | 潜在表示的输出宽度（默认：256，必须能被8整除） |
+| `高度` | INT | 否 | 16至MAX_RESOLUTION | 潜在表示的输出高度（默认：256，必须能被8整除） |
+| `批量大小` | INT | 否 | 1至4096 | 批次中生成的样本数量（默认：1） |
+| `俯仰角` | FLOAT | 否 | -180.0至180.0 | 相机仰角（单位：度，默认：0.0） |
+| `方位角` | FLOAT | 否 | -180.0至180.0 | 相机方位角（单位：度，默认：0.0） |
+
+**注意：** `width`和`height`参数必须能被8整除，因为节点会自动将其除以8来创建潜在表示维度。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `负面条件` | CONDITIONING | 结合图像特征和相机嵌入的正向条件数据 |
+| `Latent` | CONDITIONING | 零初始化特征的负向条件数据 |
+| `latent` | LATENT | 维度为[batch_size, 4, height//8, width//8]的潜在表示 |
diff --git a/zh-CN/built-in-nodes/StableZero123_Conditioning_Batched.mdx b/zh-CN/built-in-nodes/StableZero123_Conditioning_Batched.mdx
new file mode 100644
index 000000000..0c4ed47ee
--- /dev/null
+++ b/zh-CN/built-in-nodes/StableZero123_Conditioning_Batched.mdx
@@ -0,0 +1,35 @@
+---
+title: "StableZero123_Conditioning_Batched - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StableZero123_Conditioning_Batched node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StableZero123_Conditioning_Batched"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning_Batched/zh.md)
+
+StableZero123_Conditioning_Batched 节点处理输入图像并生成用于 3D 模型生成的条件数据。它使用 CLIP 视觉和 VAE 模型对图像进行编码，然后根据仰角和方位角创建相机嵌入，以生成正向和负向条件数据以及用于批处理的潜在表示。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip视觉` | CLIP_VISION | 是 | - | 用于编码输入图像的 CLIP 视觉模型 |
+| `初始图像` | IMAGE | 是 | - | 待处理和编码的初始输入图像 |
+| `vae` | VAE | 是 | - | 用于将图像像素编码到潜在空间的 VAE 模型 |
+| `宽度` | INT | 否 | 16 到 MAX_RESOLUTION | 处理后图像的输出宽度（默认：256，必须能被 8 整除） |
+| `高度` | INT | 否 | 16 到 MAX_RESOLUTION | 处理后图像的输出高度（默认：256，必须能被 8 整除） |
+| `批量大小` | INT | 否 | 1 到 4096 | 批处理中要生成的条件样本数量（默认：1） |
+| `俯仰角` | FLOAT | 否 | -180.0 到 180.0 | 初始相机仰角（单位：度，默认：0.0） |
+| `方位角` | FLOAT | 否 | -180.0 到 180.0 | 初始相机方位角（单位：度，默认：0.0） |
+| `俯仰角增量` | FLOAT | 否 | -180.0 到 180.0 | 每个批次项的仰角增量（默认：0.0） |
+| `方位角增量` | FLOAT | 否 | -180.0 到 180.0 | 每个批次项的方位角增量（默认：0.0） |
+
+**注意：** `width` 和 `height` 参数必须能被 8 整除，因为节点在内部会将这些尺寸除以 8 以生成潜在空间。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面条件` | CONDITIONING | 包含图像嵌入和相机参数的正向条件数据 |
+| `Latent` | CONDITIONING | 包含零初始化嵌入的负向条件数据 |
+| `latent` | LATENT | 带有批次索引信息的处理后图像的潜在表示 |
diff --git a/zh-CN/built-in-nodes/Stablezero123Conditioning.mdx b/zh-CN/built-in-nodes/Stablezero123Conditioning.mdx
new file mode 100644
index 000000000..3a8fe2dd9
--- /dev/null
+++ b/zh-CN/built-in-nodes/Stablezero123Conditioning.mdx
@@ -0,0 +1,29 @@
+---
+title: "Stablezero123Conditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Stablezero123Conditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Stablezero123Conditioning"
+icon: "circle"
+mode: wide
+---
+此节点设计用于处理和为StableZero123模型使用的条件数据，专注于以特定格式准备输入，这些格式与这些模型兼容并经过优化。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `clip_vision` | `CLIP_VISION` | 处理视觉数据以符合模型要求，增强模型对视觉上下文的理解。 |
+| `init_image` | `IMAGE` | 作为模型的初始图像输入，为进一步基于图像的操作设定基线。 |
+| `vae` | `VAE` | 集成变分自编码器输出，促进模型生成或修改图像的能力。 |
+| `width` | `INT` | 指定输出图像的宽度，允许根据模型需求动态调整大小。 |
+| `height` | `INT` | 确定输出图像的高度，实现输出尺寸的定制化。 |
+| `batch_size` | `INT` | 控制单批次处理的图像数量，优化计算效率。 |
+| `elevation` | `FLOAT` | 调整3D模型渲染的仰角，增强模型的空间理解。 |
+| `azimuth` | `FLOAT` | 修改3D模型可视化的方位角，改善模型对方向的感知。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `positive` | `CONDITIONING` | 生成正面条件向量，帮助模型加强正面特征。 |
+| `negative` | `CONDITIONING` | 产生负面条件向量，协助模型避免某些特征。 |
+| `latent` | `LATENT` | 创建潜在表示，促进模型对数据的深入理解。 |
diff --git a/zh-CN/built-in-nodes/Stablezero123ConditioningBatched.mdx b/zh-CN/built-in-nodes/Stablezero123ConditioningBatched.mdx
new file mode 100644
index 000000000..fa19239ab
--- /dev/null
+++ b/zh-CN/built-in-nodes/Stablezero123ConditioningBatched.mdx
@@ -0,0 +1,31 @@
+---
+title: "Stablezero123ConditioningBatched - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Stablezero123ConditioningBatched node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Stablezero123ConditioningBatched"
+icon: "circle"
+mode: wide
+---
+此节点专为StableZero123模型设计，以批量方式处理条件信息。它专注于同时高效处理多组条件数据，为批量处理至关重要的场景优化工作流程。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `clip_vision` | `CLIP_VISION` | 提供条件过程的视觉上下文的CLIP视觉嵌入。 |
+| `init_image` | `IMAGE` | 要进行条件处理的初始图像，作为生成过程的起点。 |
+| `vae` | `VAE` | 用于条件过程中编码和解码图像的变分自编码器。 |
+| `width` | `INT` | 输出图像的宽度。 |
+| `height` | `INT` | 输出图像的高度。 |
+| `batch_size` | `INT` | 单批次中要处理的条件集数量。 |
+| `elevation` | `FLOAT` | 3D模型条件的仰角，影响生成图像的视角。 |
+| `azimuth` | `FLOAT` | 3D模型条件的方位角，影响生成图像的方向。 |
+| `elevation_batch_increment` | `FLOAT` | 仰角在批量中的增量变化，允许不同的视角。 |
+| `azimuth_batch_increment` | `FLOAT` | 方位角在批量中的增量变化，允许不同的方向。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `positive` | `CONDITIONING` | 正面条件输出，专为促进生成内容中的某些特征或方面而定制。 |
+| `negative` | `CONDITIONING` | 负面条件输出，专为降低生成内容中的某些特征或方面而定制。 |
+| `latent` | `LATENT` | 来自条件过程的潜在表示，可供进一步处理或生成步骤使用。 |
diff --git a/zh-CN/built-in-nodes/StringCompare.mdx b/zh-CN/built-in-nodes/StringCompare.mdx
new file mode 100644
index 000000000..6c26ed446
--- /dev/null
+++ b/zh-CN/built-in-nodes/StringCompare.mdx
@@ -0,0 +1,25 @@
+---
+title: "StringCompare - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringCompare node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringCompare"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringCompare/zh.md)
+
+StringCompare 节点使用不同的比较方法来比较两个文本字符串。它可以检查一个字符串是否以另一个字符串开头、是否以另一个字符串结尾，或者两个字符串是否完全相等。比较时可以选择是否考虑字母大小写差异。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string_a` | STRING | 是 | - | 要比较的第一个字符串 |
+| `string_b` | STRING | 是 | - | 用于比较的第二个字符串 |
+| `mode` | COMBO | 是 | "Starts With"<br />"Ends With"<br />"Equal" | 使用的比较方法 |
+| `case_sensitive` | BOOLEAN | 否 | - | 比较时是否考虑字母大小写（默认值：true） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | BOOLEAN | 如果满足比较条件则返回 true，否则返回 false |
diff --git a/zh-CN/built-in-nodes/StringConcatenate.mdx b/zh-CN/built-in-nodes/StringConcatenate.mdx
new file mode 100644
index 000000000..1f63bfa61
--- /dev/null
+++ b/zh-CN/built-in-nodes/StringConcatenate.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringConcatenate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringConcatenate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringConcatenate"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringConcatenate/zh.md)
+
+StringConcatenate 节点通过指定的分隔符将两个文本字符串合并为一个。它接收两个输入字符串和一个分隔字符或字符串，然后输出单个字符串，其中两个输入字符串通过分隔符连接在一起。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string_a` | STRING | 是 | - | 要连接的第一个文本字符串 |
+| `string_b` | STRING | 是 | - | 要连接的第二个文本字符串 |
+| `delimiter` | STRING | 否 | - | 在两个输入字符串之间插入的字符或字符串（默认为空字符串） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 在 string_a 和 string_b 之间插入分隔符后的组合字符串 |
diff --git a/zh-CN/built-in-nodes/StringContains.mdx b/zh-CN/built-in-nodes/StringContains.mdx
new file mode 100644
index 000000000..cb8f19925
--- /dev/null
+++ b/zh-CN/built-in-nodes/StringContains.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringContains - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringContains node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringContains"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringContains/zh.md)
+
+StringContains 节点用于检查给定字符串是否包含指定的子字符串。该节点支持区分大小写或不区分大小写的匹配方式，并返回布尔值结果来指示是否在主字符串中找到了子字符串。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | 是 | - | 要搜索的主文本字符串 |
+| `substring` | STRING | 是 | - | 在主字符串中要搜索的文本内容 |
+| `case_sensitive` | BOOLEAN | 否 | - | 决定搜索是否区分大小写（默认值：true） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `contains` | BOOLEAN | 如果在字符串中找到子字符串则返回 true，否则返回 false |
diff --git a/zh-CN/built-in-nodes/StringLength.mdx b/zh-CN/built-in-nodes/StringLength.mdx
new file mode 100644
index 000000000..dd84d5b78
--- /dev/null
+++ b/zh-CN/built-in-nodes/StringLength.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringLength - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringLength node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringLength"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringLength/zh.md)
+
+## 概述
+
+StringLength 节点用于计算文本字符串中的字符数量。它接收任意文本输入并返回字符总数，包括空格和标点符号。此功能适用于测量文本长度或验证字符串大小要求。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | 是 | 无限制 | 需要测量长度的文本字符串。支持多行输入。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `length` | INT | 输入字符串中的字符总数，包括空格和特殊字符。 |
diff --git a/zh-CN/built-in-nodes/StringReplace.mdx b/zh-CN/built-in-nodes/StringReplace.mdx
new file mode 100644
index 000000000..e219b4d6a
--- /dev/null
+++ b/zh-CN/built-in-nodes/StringReplace.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringReplace - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringReplace node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringReplace"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringReplace/zh.md)
+
+StringReplace 节点对输入字符串执行文本替换操作。它会在输入文本中搜索指定的子字符串，并将所有匹配项替换为不同的子字符串。该节点返回应用了所有替换操作后的修改字符串。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | 是 | - | 将执行替换操作的输入文本字符串 |
+| `find` | STRING | 是 | - | 在输入文本中要搜索的子字符串 |
+| `replace` | STRING | 是 | - | 用于替换所有找到的匹配项的文本内容 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 经过修改的字符串，其中所有查找到的文本均已被替换文本替换 |
diff --git a/zh-CN/built-in-nodes/StringSubstring.mdx b/zh-CN/built-in-nodes/StringSubstring.mdx
new file mode 100644
index 000000000..b50a84bd4
--- /dev/null
+++ b/zh-CN/built-in-nodes/StringSubstring.mdx
@@ -0,0 +1,24 @@
+---
+title: "StringSubstring - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringSubstring node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringSubstring"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringSubstring/zh.md)
+
+StringSubstring 节点用于从较长的文本字符串中提取部分内容。它通过起始位置和结束位置来定义需要提取的文本区间，并返回这两个位置之间的文本内容。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|--------|----------|------|----------|------|
+| `string` | STRING | 是 | - | 用于提取子串的输入文本字符串 |
+| `start` | INT | 是 | - | 子串的起始位置索引 |
+| `end` | INT | 是 | - | 子串的结束位置索引 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|----------|------|
+| `output` | STRING | 从输入文本中提取出的子串 |
diff --git a/zh-CN/built-in-nodes/StringTrim.mdx b/zh-CN/built-in-nodes/StringTrim.mdx
new file mode 100644
index 000000000..d53a495b3
--- /dev/null
+++ b/zh-CN/built-in-nodes/StringTrim.mdx
@@ -0,0 +1,23 @@
+---
+title: "StringTrim - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StringTrim node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StringTrim"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringTrim/zh.md)
+
+StringTrim 节点用于移除文本字符串开头、结尾或两侧的空白字符。您可以选择从字符串的左侧、右侧或两侧进行修剪。这对于通过移除不需要的空格、制表符或换行符来清理文本输入非常有用。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `string` | STRING | 是 | - | 要处理的文本字符串。支持多行输入。 |
+| `mode` | COMBO | 是 | "Both"<br />"Left"<br />"Right" | 指定要修剪字符串的哪一侧。"Both" 移除两端的空白字符，"Left" 仅移除开头的空白字符，"Right" 仅移除末尾的空白字符。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 根据所选模式移除空白字符后的修剪文本字符串。 |
diff --git a/zh-CN/built-in-nodes/StripWhitespace.mdx b/zh-CN/built-in-nodes/StripWhitespace.mdx
new file mode 100644
index 000000000..36c497866
--- /dev/null
+++ b/zh-CN/built-in-nodes/StripWhitespace.mdx
@@ -0,0 +1,22 @@
+---
+title: "StripWhitespace - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StripWhitespace node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StripWhitespace"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StripWhitespace/zh.md)
+
+此节点会移除文本字符串开头和结尾的所有多余空格、制表符或换行符。它接收一个文本输入，并返回经过清理的版本，其中开头和结尾的空白字符已被修剪。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | 是 | N/A | 需要移除开头和结尾空白字符的文本字符串。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `text` | STRING | 处理后的文本，所有开头和结尾的空白字符已被移除。 |
diff --git a/zh-CN/built-in-nodes/StyleModelApply.mdx b/zh-CN/built-in-nodes/StyleModelApply.mdx
new file mode 100644
index 000000000..4a03042dc
--- /dev/null
+++ b/zh-CN/built-in-nodes/StyleModelApply.mdx
@@ -0,0 +1,23 @@
+---
+title: "StyleModelApply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StyleModelApply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StyleModelApply"
+icon: "circle"
+mode: wide
+---
+
+此节点将风格模型应用于给定的条件，基于CLIP视觉模型的输出增强或改变其风格。它将风格模型的条件整合到现有条件中，允许在生成过程中风格无缝融合。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 原始条件数据，用于对文本进行编码的CLIP模型将应用风格模型的条件。它对于定义将被增强或改变的基础上下文或风格至关重要。 |
+| `风格模型` | `STYLE_MODEL` | 用于基于CLIP视觉模型的输出生成新条件的风格模型。它在定义要应用的新风格中起着关键作用。 |
+| `clip视觉输出` | `CLIP_VISION_OUTPUT` | 来自CLIP视觉模型的输出，风格模型用它来生成新条件。它为风格应用提供了必要的视觉上下文。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 增强或改变的条件，融入了风格模型的输出。它代表了最终的风格化条件，准备进行进一步处理或生成。 |
diff --git a/zh-CN/built-in-nodes/StyleModelLoader.mdx b/zh-CN/built-in-nodes/StyleModelLoader.mdx
new file mode 100644
index 000000000..faec8fa60
--- /dev/null
+++ b/zh-CN/built-in-nodes/StyleModelLoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "StyleModelLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the StyleModelLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "StyleModelLoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/style_models` 文件夹下的模型，
+同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，
+有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+风格模型加载节点旨在从指定路径加载一个风格模型。它专注于检索和初始化可以用于将特定艺术风格应用于图像的风格模型，从而实现基于加载的风格模型定制视觉输出。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `风格模型名称` | COMBO[STRING] | 指定要加载的风格模型的名称。此名称用于在预定义的目录结构中定位模型文件，允许根据用户输入或应用程序需求动态加载不同的风格模型。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `style_model` | STYLE_MODEL | 返回加载的风格模型，准备用于将风格应用于图像。这使得通过应用不同的艺术风格动态定制视觉输出成为可能。 |
+
+---
diff --git a/zh-CN/built-in-nodes/SvdImg2vidConditioning.mdx b/zh-CN/built-in-nodes/SvdImg2vidConditioning.mdx
new file mode 100644
index 000000000..72136d2c7
--- /dev/null
+++ b/zh-CN/built-in-nodes/SvdImg2vidConditioning.mdx
@@ -0,0 +1,31 @@
+---
+title: "SvdImg2vidConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the SvdImg2vidConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "SvdImg2vidConditioning"
+icon: "circle"
+mode: wide
+---
+
+此节点旨在为视频生成任务生成条件数据，特别适用于SVD_img2vid模型。它接受各种输入，包括初始图像、视频参数和VAE模型，以产生可用于指导视频帧生成的条件数据。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `clip_vision` | `CLIP_VISION` | 用于从初始图像编码视觉特征的CLIP视觉模型，对理解图像内容和视频生成上下文至关重要。 |
+| `init_image` | `IMAGE` | 视频将从中生成的初始图像，作为视频生成过程的起点。 |
+| `vae` | `VAE` | 用于将初始图像编码到潜在空间的变分自编码器（VAE）模型，有助于生成连贯和连续的视频帧。 |
+| `width` | `INT` | 要生成的视频帧的期望宽度，允许自定义视频的分辨率。 |
+| `height` | `INT` | 要生成的视频帧的高度，可以控制视频的宽高比和分辨率。 |
+| `video_frames` | `INT` | 为视频生成的帧数，决定视频的长度。 |
+| `motion_bucket_id` | `INT` | 用于分类将要应用的视频生成中运动类型的标识符，有助于创造动态和吸引人的视频。 |
+| `fps` | `INT` | 视频的每秒帧数（fps），影响生成视频的平滑度和真实感。 |
+| `augmentation_level` | `FLOAT` | 控制应用于初始图像的增强水平的参数，影响生成视频帧的多样性和可变性。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `positive` | `CONDITIONING` | 正面条件数据，由编码特征和参数组成，指导视频生成过程朝着期望的方向发展。 |
+| `negative` | `CONDITIONING` | 负面条件数据，与正面条件形成对比，可用于避免生成视频中的某些模式或特征。 |
+| `latent` | `LATENT` | 为视频中的每一帧生成的潜在表示，作为视频生成过程的基础组成部分。 |
diff --git a/zh-CN/built-in-nodes/T5TokenizerOptions.mdx b/zh-CN/built-in-nodes/T5TokenizerOptions.mdx
new file mode 100644
index 000000000..e982f19b2
--- /dev/null
+++ b/zh-CN/built-in-nodes/T5TokenizerOptions.mdx
@@ -0,0 +1,24 @@
+---
+title: "T5TokenizerOptions - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the T5TokenizerOptions node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "T5TokenizerOptions"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/T5TokenizerOptions/zh.md)
+
+T5TokenizerOptions 节点允许您为各种 T5 模型类型配置分词器设置。它为多个 T5 模型变体（包括 t5xxl、pile_t5xl、t5base、mt5xl 和 umt5xxl）设置最小填充和最小长度参数。该节点接收 CLIP 输入，并返回应用了指定分词器选项的修改后 CLIP 模型。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | - | 需要配置分词器选项的 CLIP 模型 |
+| `最小填充` | INT | 否 | 0-10000 | 为所有 T5 模型类型设置的最小填充值（默认值：0） |
+| `最小长度` | INT | 否 | 0-10000 | 为所有 T5 模型类型设置的最小长度值（默认值：0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | CLIP | 应用了更新后分词器选项的修改版 CLIP 模型，该选项已应用于所有 T5 变体 |
diff --git a/zh-CN/built-in-nodes/TCFG.mdx b/zh-CN/built-in-nodes/TCFG.mdx
new file mode 100644
index 000000000..6f86efda7
--- /dev/null
+++ b/zh-CN/built-in-nodes/TCFG.mdx
@@ -0,0 +1,22 @@
+---
+title: "TCFG - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TCFG node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TCFG"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TCFG/zh.md)
+
+TCFG（切向阻尼 CFG）实现了一种引导技术，通过优化无条件（负面）预测以更好地与条件（正面）预测对齐。该方法基于参考文献 2503.18137 的研究论文，通过对无条件引导施加切向阻尼来提升输出质量。该节点通过调整分类器自由引导过程中无条件预测的处理方式，来修改模型的采样行为。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要应用切向阻尼 CFG 的模型 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | 已应用切向阻尼 CFG 的修改后模型 |
diff --git a/zh-CN/built-in-nodes/TemporalScoreRescaling.mdx b/zh-CN/built-in-nodes/TemporalScoreRescaling.mdx
new file mode 100644
index 000000000..f9ce234fb
--- /dev/null
+++ b/zh-CN/built-in-nodes/TemporalScoreRescaling.mdx
@@ -0,0 +1,24 @@
+---
+title: "TemporalScoreRescaling - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TemporalScoreRescaling node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TemporalScoreRescaling"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TemporalScoreRescaling/zh.md)
+
+此节点对扩散模型应用时序分数重缩放（TSR）。它通过在去噪过程中重新缩放预测的噪声或分数来修改模型的采样行为，从而引导生成输出的多样性。该功能以后置CFG（无分类器引导）函数的形式实现。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 需要应用TSR函数进行修补的扩散模型。 |
+| `tsr_k` | FLOAT | 否 | 0.01 - 100.0 | 控制重缩放的强度。较低的k值会产生更详细的结果；较高的k值在图像生成中会产生更平滑的结果。设置 k = 1 将禁用重缩放。（默认值：0.95） |
+| `tsr_sigma` | FLOAT | 否 | 0.01 - 100.0 | 控制重缩放效果何时开始生效。数值越大，效果生效越早。（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `patched_model` | MODEL | 输入模型，现已在其采样过程中应用了时序分数重缩放函数进行修补。 |
diff --git a/zh-CN/built-in-nodes/Tencent3DPartNode.mdx b/zh-CN/built-in-nodes/Tencent3DPartNode.mdx
new file mode 100644
index 000000000..762984c0d
--- /dev/null
+++ b/zh-CN/built-in-nodes/Tencent3DPartNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "Tencent3DPartNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Tencent3DPartNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Tencent3DPartNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DPartNode/zh.md)
+
+此节点使用腾讯混元3D API，自动分析一个3D模型并根据其结构生成或识别其组件。它会处理模型并返回一个新的FBX文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_3d` | FILE3D | 是 | FBX, Any | 要处理的3D模型。模型应为FBX格式，且面数少于30000。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于控制节点是否应重新运行的种子值。无论种子值如何，结果都是非确定性的。（默认值：0） |
+
+**注意：** `model_3d` 输入仅支持 FBX 格式的文件。如果提供了其他3D文件格式，节点将引发错误。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `FBX` | FILE3DFBX | 处理后的3D模型，以FBX文件形式返回。 |
diff --git a/zh-CN/built-in-nodes/Tencent3DTextureEditNode.mdx b/zh-CN/built-in-nodes/Tencent3DTextureEditNode.mdx
new file mode 100644
index 000000000..224891db9
--- /dev/null
+++ b/zh-CN/built-in-nodes/Tencent3DTextureEditNode.mdx
@@ -0,0 +1,27 @@
+---
+title: "Tencent3DTextureEditNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Tencent3DTextureEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Tencent3DTextureEditNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DTextureEditNode/zh.md)
+
+此节点使用腾讯混元3D API来编辑3D模型的纹理。您提供一个3D模型和所需更改的文本描述，节点将返回模型的新版本，其纹理会根据您的提示重新绘制。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_3d` | FILE3D | 是 | FBX, Any | FBX格式的3D模型。模型面数应少于100000个。 |
+| `prompt` | STRING | 是 | | 描述纹理编辑的提示词。最多支持1024个UTF-8字符。 |
+| `seed` | INT | 否 | 0 至 2147483647 | 种子控制节点是否应重新运行；无论种子如何，结果都是非确定性的。(默认值: 0) |
+
+**注意：** `model_3d` 输入必须是FBX格式的文件。此节点不支持其他3D文件格式。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `GLB` | FILE3D | 处理后的3D模型，格式为GLB。 |
+| `FBX` | FILE3D | 处理后的3D模型，格式为FBX。 |
diff --git a/zh-CN/built-in-nodes/TencentImageToModelNode.mdx b/zh-CN/built-in-nodes/TencentImageToModelNode.mdx
new file mode 100644
index 000000000..6ef10eea0
--- /dev/null
+++ b/zh-CN/built-in-nodes/TencentImageToModelNode.mdx
@@ -0,0 +1,35 @@
+---
+title: "TencentImageToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TencentImageToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TencentImageToModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentImageToModelNode/zh.md)
+
+此节点使用腾讯的 Hunyuan3D Pro API，根据一张或多张输入图像生成 3D 模型。它会处理图像，将其发送到 API，并以 GLB 和 OBJ 格式返回生成的 3D 模型文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"3.0"`<br />`"3.1"` | 要使用的 Hunyuan3D 模型版本。`3.1` 模型不支持 LowPoly 选项。 |
+| `image` | IMAGE | 是 | - | 用于生成 3D 模型的主要输入图像。 |
+| `image_left` | IMAGE | 否 | - | 用于多视角生成的可选图像，展示物体左侧。 |
+| `image_right` | IMAGE | 否 | - | 用于多视角生成的可选图像，展示物体右侧。 |
+| `image_back` | IMAGE | 否 | - | 用于多视角生成的可选图像，展示物体背面。 |
+| `face_count` | INT | 是 | 40000 - 1500000 | 生成的 3D 模型的目标面数（默认值：500000）。 |
+| `generate_type` | DYNAMICCOMBO | 是 | `"Normal"`<br />`"LowPoly"`<br />`"Geometry"` | 要生成的 3D 模型类型。选择某个选项会显示其相关的附加参数。 |
+| `generate_type.pbr` | BOOLEAN | 否 | - | 启用基于物理的渲染（PBR）材质生成。此参数仅在 `generate_type` 设置为 "Normal" 或 "LowPoly" 时可见（默认值：False）。 |
+| `generate_type.polygon_type` | COMBO | 否 | `"triangle"`<br />`"quadrilateral"` | 用于网格的多边形类型。此参数仅在 `generate_type` 设置为 "LowPoly" 时可见。 |
+| `seed` | INT | 是 | 0 - 2147483647 | 生成过程的种子值。种子控制节点是否应重新运行；无论种子如何，结果都是非确定性的（默认值：0）。 |
+
+**注意：** 所有输入图像的最小宽度和高度必须为 128 像素。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 用于向后兼容的遗留输出。 |
+| `GLB` | FILE3DGLB | 生成的 3D 模型，格式为 GLB（二进制 GL 传输格式）文件。 |
+| `OBJ` | FILE3DOBJ | 生成的 3D 模型，格式为 OBJ（Wavefront）文件。 |
diff --git a/zh-CN/built-in-nodes/TencentModelTo3DUVNode.mdx b/zh-CN/built-in-nodes/TencentModelTo3DUVNode.mdx
new file mode 100644
index 000000000..a6b551f4a
--- /dev/null
+++ b/zh-CN/built-in-nodes/TencentModelTo3DUVNode.mdx
@@ -0,0 +1,25 @@
+---
+title: "TencentModelTo3DUVNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TencentModelTo3DUVNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TencentModelTo3DUVNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentModelTo3DUVNode/zh.md)
+
+此节点使用腾讯混元3D API对3D模型进行UV展开。它接收一个3D模型文件作为输入，将其发送至API进行处理，并返回处理后的OBJ和FBX格式模型文件以及生成的UV纹理图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_3d` | FILE3D | 是 | GLB<br />OBJ<br />FBX | 输入的3D模型文件（GLB、OBJ或FBX格式）。模型面数必须少于30000个。 |
+| `seed` | INT | 否 | 0 至 2147483647 | 随机种子值（默认值：1）。此值控制节点是否应重新运行，但无论种子值如何，结果均非确定性。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `OBJ` | FILE3D | 处理后的3D模型文件，OBJ格式。 |
+| `FBX` | FILE3D | 处理后的3D模型文件，FBX格式。 |
+| `Image` | IMAGE | 生成的UV纹理图像。 |
diff --git a/zh-CN/built-in-nodes/TencentTextToModelNode.mdx b/zh-CN/built-in-nodes/TencentTextToModelNode.mdx
new file mode 100644
index 000000000..9810a8b2b
--- /dev/null
+++ b/zh-CN/built-in-nodes/TencentTextToModelNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "TencentTextToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TencentTextToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TencentTextToModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentTextToModelNode/zh.md)
+
+此节点使用腾讯的 Hunyuan3D Pro API，根据文本描述生成 3D 模型。它会发送请求创建生成任务，轮询结果，并下载 GLB 和 OBJ 格式的最终模型文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"3.0"`<br />`"3.1"` | 要使用的 Hunyuan3D 模型版本。`3.1` 模型不支持 LowPoly 选项。 |
+| `prompt` | STRING | 是 | - | 要生成的 3D 模型的文本描述。最多支持 1024 个字符。 |
+| `face_count` | INT | 是 | 40000 - 1500000 | 生成的 3D 模型的目标面数。默认值：500000。 |
+| `generate_type` | DYNAMICCOMBO | 是 | `"Normal"`<br />`"LowPoly"`<br />`"Geometry"` | 要生成的 3D 模型类型。可用选项及其关联参数如下：<br />- **Normal**：生成标准模型。包含 `pbr` 参数（默认值：`False`）。<br />- **LowPoly**：生成低多边形模型。包含 `polygon_type`（`"triangle"` 或 `"quadrilateral"`）和 `pbr`（默认值：`False`）参数。<br />- **Geometry**：生成仅包含几何结构的模型。 |
+| `seed` | INT | 否 | 0 - 2147483647 | 用于生成的种子值。无论种子如何设置，结果都是非确定性的。设置新的种子值控制节点是否应重新运行。默认值：0。 |
+
+**注意：** `generate_type` 参数是动态的。选择 `"LowPoly"` 将显示 `polygon_type` 和 `pbr` 的额外输入。选择 `"Normal"` 将显示 `pbr` 的输入。选择 `"Geometry"` 不会显示任何额外输入。
+
+**约束：** `"LowPoly"` 生成类型不能与 `"3.1"` 模型一起使用。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 用于向后兼容的遗留输出。 |
+| `GLB` | FILE3DGLB | 生成的 3D 模型，格式为 GLB 文件。 |
+| `OBJ` | FILE3DOBJ | 生成的 3D 模型，格式为 OBJ 文件。 |
diff --git a/zh-CN/built-in-nodes/TerminalLog.mdx b/zh-CN/built-in-nodes/TerminalLog.mdx
new file mode 100644
index 000000000..b5c892bc8
--- /dev/null
+++ b/zh-CN/built-in-nodes/TerminalLog.mdx
@@ -0,0 +1,9 @@
+---
+title: "TerminalLog - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TerminalLog node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TerminalLog"
+icon: "circle"
+mode: wide
+---
+Terminal Log 这个节点主要用于在 ComfyUI 界面展示 ComfyUI 的在CMD终端的运行信息，如需使用，需要将```mode模式``` 设置为 **logging**模式，则可以在图片生成任务进行时记录对应的日志信息，如```mode```设置为**stop**模式，则不会记录日志信息。
+当你是采用远程连接或者局域网连接的方式来访问和使用 ComfyUI 时，这个节点的作用就很明显，它让你可以直接在ComfyUI的界面中就可以直接看到 CMD 中的报错信息，更方便你了解当前 ComfyUI 的运行状态。
diff --git a/zh-CN/built-in-nodes/TextEncodeAceStepAudio.mdx b/zh-CN/built-in-nodes/TextEncodeAceStepAudio.mdx
new file mode 100644
index 000000000..93e91ced5
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextEncodeAceStepAudio.mdx
@@ -0,0 +1,27 @@
+---
+title: "TextEncodeAceStepAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeAceStepAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeAceStepAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeAceStepAudio/zh.md)
+
+## 概述
+
+TextEncodeAceStepAudio 节点通过将标签和歌词组合成令牌，并使用可调节的歌词强度进行编码，从而处理用于音频条件化的文本输入。该节点接收 CLIP 模型以及文本描述和歌词，将它们一起进行令牌化，并生成适用于音频生成任务的条件化数据。该节点允许通过控制歌词对最终输出影响程度的强度参数来微调歌词的影响力。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | - | 用于令牌化和编码的 CLIP 模型 |
+| `tags` | STRING | 是 | - | 用于音频条件化的文本标签或描述（支持多行输入和动态提示） |
+| `lyrics` | STRING | 是 | - | 用于音频条件化的歌词文本（支持多行输入和动态提示） |
+| `lyrics_strength` | FLOAT | 否 | 0.0 - 10.0 | 控制歌词对条件化输出影响的强度（默认值：1.0，步长：0.01） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `conditioning` | CONDITIONING | 包含已处理文本令牌并应用了歌词强度的编码条件化数据 |
diff --git a/zh-CN/built-in-nodes/TextEncodeAceStepAudio1.5.mdx b/zh-CN/built-in-nodes/TextEncodeAceStepAudio1.5.mdx
new file mode 100644
index 000000000..b297a60b4
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextEncodeAceStepAudio1.5.mdx
@@ -0,0 +1,35 @@
+---
+title: "TextEncodeAceStepAudio1.5 - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeAceStepAudio1.5 node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeAceStepAudio1.5"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeAceStepAudio1.5/zh.md)
+
+TextEncodeAceStepAudio1.5 节点用于为 AceStepAudio 1.5 模型准备文本和音频相关的元数据。它接收描述性标签、歌词和音乐参数，然后使用 CLIP 模型将其转换为适用于音频生成的调节格式。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | N/A | 用于对输入文本进行分词和编码的 CLIP 模型。 |
+| `tags` | STRING | 是 | N/A | 音频的描述性标签，例如流派、情绪或乐器。支持多行输入和动态提示。 |
+| `lyrics` | STRING | 是 | N/A | 音轨的歌词。支持多行输入和动态提示。 |
+| `seed` | INT | 否 | 0 到 18446744073709551615 | 用于可重复生成的随机种子值。带有 control_after_generate 控件。默认值：0。 |
+| `bpm` | INT | 否 | 10 到 300 | 生成音频的每分钟节拍数 (BPM)。默认值：120。 |
+| `duration` | FLOAT | 否 | 0.0 到 2000.0 | 期望的音频时长（秒）。默认值：120.0。 |
+| `timesignature` | COMBO | 否 | `"2"`<br />`"3"`<br />`"4"`<br />`"6"` | 音乐拍号。 |
+| `language` | COMBO | 否 | `"en"`<br />`"ja"`<br />`"zh"`<br />`"es"`<br />`"de"`<br />`"fr"`<br />`"pt"`<br />`"ru"`<br />`"it"`<br />`"nl"`<br />`"pl"`<br />`"tr"`<br />`"vi"`<br />`"cs"`<br />`"fa"`<br />`"id"`<br />`"ko"`<br />`"uk"`<br />`"hu"`<br />`"ar"`<br />`"sv"`<br />`"ro"`<br />`"el"` | 输入文本的语言。 |
+| `keyscale` | COMBO | 否 | `"C major"`<br />`"C minor"`<br />`"C# major"`<br />`"C# minor"`<br />`"Db major"`<br />`"Db minor"`<br />`"D major"`<br />`"D minor"`<br />`"D# major"`<br />`"D# minor"`<br />`"Eb major"`<br />`"Eb minor"`<br />`"E major"`<br />`"E minor"`<br />`"F major"`<br />`"F minor"`<br />`"F# major"`<br />`"F# minor"`<br />`"Gb major"`<br />`"Gb minor"`<br />`"G major"`<br />`"G minor"`<br />`"G# major"`<br />`"G# minor"`<br />`"Ab major"`<br />`"Ab minor"`<br />`"A major"`<br />`"A minor"`<br />`"A# major"`<br />`"A# minor"`<br />`"Bb major"`<br />`"Bb minor"`<br />`"B major"`<br />`"B minor"` | 音乐的调性和音阶（大调或小调）。 |
+| `generate_audio_codes` | BOOLEAN | 否 | N/A | 启用生成音频代码的 LLM。这可能会比较慢，但会提高生成音频的质量。如果为模型提供音频参考，请关闭此选项。默认值：True。 |
+| `cfg_scale` | FLOAT | 否 | 0.0 到 100.0 | 分类器自由引导尺度。值越高，输出越紧密遵循提示。默认值：2.0。 |
+| `temperature` | FLOAT | 否 | 0.0 到 2.0 | 采样温度。值越低，输出越具有确定性。默认值：0.85。 |
+| `top_p` | FLOAT | 否 | 0.0 到 2000.0 | 核心采样概率 (top-p)。默认值：0.9。 |
+| `top_k` | INT | 否 | 0 到 100 | 要考虑的最高概率标记的数量 (top-k)。默认值：0。 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 调节数据，其中包含为 AceStepAudio 1.5 模型编码的文本和音频参数。 |
diff --git a/zh-CN/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx b/zh-CN/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx
new file mode 100644
index 000000000..d4480a96c
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx
@@ -0,0 +1,25 @@
+---
+title: "TextEncodeHunyuanVideo_ImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeHunyuanVideo_ImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeHunyuanVideo_ImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeHunyuanVideo_ImageToVideo/zh.md)
+
+TextEncodeHunyuanVideo_ImageToVideo 节点通过将文本提示与图像嵌入相结合，为视频生成创建条件数据。它使用 CLIP 模型处理文本输入和来自 CLIP 视觉输出的视觉信息，然后根据指定的图像交错设置生成融合这两个来源的令牌。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|-------------|
+| `clip` | CLIP | 是 | - | 用于令牌化和编码的 CLIP 模型 |
+| `clip视觉输出` | CLIP_VISION_OUTPUT | 是 | - | 来自 CLIP 视觉模型的视觉嵌入，提供图像上下文 |
+| `提示` | STRING | 是 | - | 指导视频生成的文本描述，支持多行输入和动态提示 |
+| `图像交错` | INT | 是 | 1-512 | 图像相对于文本提示的影响程度。数值越高表示文本提示的影响越大。（默认值：2） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 结合文本和图像信息用于视频生成的条件数据 |
diff --git a/zh-CN/built-in-nodes/TextEncodeQwenImageEdit.mdx b/zh-CN/built-in-nodes/TextEncodeQwenImageEdit.mdx
new file mode 100644
index 000000000..a53c65494
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextEncodeQwenImageEdit.mdx
@@ -0,0 +1,27 @@
+---
+title: "TextEncodeQwenImageEdit - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeQwenImageEdit node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeQwenImageEdit"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeQwenImageEdit/zh.md)
+
+TextEncodeQwenImageEdit 节点处理文本提示词和可选图像，以生成用于图像生成或编辑的条件数据。它使用 CLIP 模型对输入进行标记化，并可以选择性地使用 VAE 对参考图像进行编码以创建参考潜在表示。当提供图像时，它会自动调整图像尺寸以保持一致的处理维度。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | - | 用于文本和图像标记化的 CLIP 模型 |
+| `prompt` | STRING | 是 | - | 用于条件生成的文本提示词，支持多行输入和动态提示词 |
+| `vae` | VAE | 否 | - | 用于将参考图像编码为潜在表示的可选 VAE 模型 |
+| `image` | IMAGE | 否 | - | 用于参考或编辑目的的可选输入图像 |
+
+**注意：** 当同时提供 `image` 和 `vae` 时，节点会将图像编码为参考潜在表示并将其附加到条件输出中。图像会自动调整尺寸以保持大约 1024x1024 像素的一致处理尺度。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 包含文本标记和可选参考潜在表示的条件数据，用于图像生成 |
diff --git a/zh-CN/built-in-nodes/TextEncodeQwenImageEditPlus.mdx b/zh-CN/built-in-nodes/TextEncodeQwenImageEditPlus.mdx
new file mode 100644
index 000000000..281c45f83
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextEncodeQwenImageEditPlus.mdx
@@ -0,0 +1,29 @@
+---
+title: "TextEncodeQwenImageEditPlus - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeQwenImageEditPlus node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeQwenImageEditPlus"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeQwenImageEditPlus/zh.md)
+
+TextEncodeQwenImageEditPlus 节点处理文本提示和可选图像，为图像生成或编辑任务生成条件数据。它使用专用模板分析输入图像并理解文本指令应如何修改它们，然后将这些信息编码以供后续生成步骤使用。该节点最多可处理三个输入图像，并在提供 VAE 时可选生成参考潜在表示。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | - | 用于标记化和编码的 CLIP 模型 |
+| `prompt` | STRING | 是 | - | 描述所需图像修改的文本指令（支持多行输入和动态提示） |
+| `vae` | VAE | 否 | - | 用于从输入图像生成参考潜在表示的可选 VAE 模型 |
+| `image1` | IMAGE | 否 | - | 用于分析和修改的第一个可选输入图像 |
+| `image2` | IMAGE | 否 | - | 用于分析和修改的第二个可选输入图像 |
+| `image3` | IMAGE | 否 | - | 用于分析和修改的第三个可选输入图像 |
+
+**注意：** 当提供 VAE 时，节点会从所有输入图像生成参考潜在表示。该节点最多可同时处理三个图像，图像会自动调整尺寸以适应处理需求。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 包含文本标记和可选参考潜在表示的编码条件数据，用于图像生成 |
diff --git a/zh-CN/built-in-nodes/TextEncodeZImageOmni.mdx b/zh-CN/built-in-nodes/TextEncodeZImageOmni.mdx
new file mode 100644
index 000000000..341aab8fe
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextEncodeZImageOmni.mdx
@@ -0,0 +1,31 @@
+---
+title: "TextEncodeZImageOmni - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextEncodeZImageOmni node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextEncodeZImageOmni"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeZImageOmni/zh.md)
+
+TextEncodeZImageOmni 节点是一个高级条件编码节点，可将文本提示词与可选参考图像一同编码为适用于图像生成模型的条件格式。它最多可处理三张图像，可选择使用视觉编码器和/或 VAE 对图像进行编码以生成参考潜变量，并通过特定的模板结构将这些视觉参考与文本提示词进行整合。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | | 用于对文本提示词进行分词和编码的 CLIP 模型。 |
+| `image_encoder` | CLIPVision | 否 | | 可选的视觉编码器模型。若提供，将用于编码输入图像，并将生成的嵌入向量添加到条件信息中。 |
+| `prompt` | STRING | 是 | | 待编码的文本提示词。此字段支持多行输入和动态提示词。 |
+| `auto_resize_images` | BOOLEAN | 否 | | 启用时（默认：True），输入图像在传递给 VAE 编码前会根据其像素面积自动调整尺寸。 |
+| `vae` | VAE | 否 | | 可选的 VAE 模型。若提供，将用于将输入图像编码为潜变量表示，这些潜变量将作为参考潜变量添加到条件信息中。 |
+| `image1` | IMAGE | 否 | | 第一张可选参考图像。 |
+| `image2` | IMAGE | 否 | | 第二张可选参考图像。 |
+| `image3` | IMAGE | 否 | | 第三张可选参考图像。 |
+
+**注意：** 该节点最多可接受三张图像（`image1`、`image2`、`image3`）。仅当至少提供一张图像时，`image_encoder` 和 `vae` 输入才会被使用。当 `auto_resize_images` 为 True 且连接了 `vae` 时，图像在编码前会被调整尺寸，使其总像素面积接近 1024x1024。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CONDITIONING` | CONDITIONING | 最终的条件输出，包含编码后的文本提示词，若提供了图像，还可能包含编码后的图像嵌入向量和/或参考潜变量。 |
diff --git a/zh-CN/built-in-nodes/TextGenerate.mdx b/zh-CN/built-in-nodes/TextGenerate.mdx
new file mode 100644
index 000000000..f110d1276
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextGenerate.mdx
@@ -0,0 +1,34 @@
+---
+title: "TextGenerate - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextGenerate node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextGenerate"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerate/zh.md)
+
+TextGenerate 节点使用 CLIP 模型根据用户的提示词生成文本。它可以选择性地使用图像作为视觉参考来引导文本生成。您可以控制输出的长度，并选择是否使用带有各种设置的随机采样，或是在不采样的情况下生成文本。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | 不适用 | 用于对提示词进行分词和生成文本的 CLIP 模型。 |
+| `prompt` | STRING | 是 | 不适用 | 用于引导生成的文本提示词。此字段支持多行和动态提示词。默认值为空字符串。 |
+| `image` | IMAGE | 否 | 不适用 | 可选的图像，可与文本提示词一起使用，以影响生成的文本。 |
+| `max_length` | INT | 是 | 1 到 2048 | 模型将生成的最大令牌数。默认值为 256。 |
+| `sampling_mode` | COMBO | 是 | `"on"`<br />`"off"` | 控制文本生成期间是否使用随机采样。设置为 "on" 时，用于控制采样的附加参数将变为可用。默认为 "on"。 |
+| `temperature` | FLOAT | 否 | 0.01 到 2.0 | 控制输出的随机性。较低的值使输出更可预测，较高的值使其更具创造性。此参数仅在 `sampling_mode` 为 "on" 时可用。默认值为 0.7。 |
+| `top_k` | INT | 否 | 0 到 1000 | 将采样池限制为最可能的前 K 个下一个令牌。值为 0 则禁用此过滤器。此参数仅在 `sampling_mode` 为 "on" 时可用。默认值为 64。 |
+| `top_p` | FLOAT | 否 | 0.0 到 1.0 | 使用核心采样，将选择限制在累积概率小于此值的令牌上。此参数仅在 `sampling_mode` 为 "on" 时可用。默认值为 0.95。 |
+| `min_p` | FLOAT | 否 | 0.0 到 1.0 | 设置令牌被考虑的最低概率阈值。此参数仅在 `sampling_mode` 为 "on" 时可用。默认值为 0.05。 |
+| `repetition_penalty` | FLOAT | 否 | 0.0 到 5.0 | 对已生成的令牌施加惩罚以减少重复。值为 1.0 时不施加惩罚。此参数仅在 `sampling_mode` 为 "on" 时可用。默认值为 1.05。 |
+| `seed` | INT | 否 | 0 到 18446744073709551615 | 当采样为 "on" 时，用于初始化随机数生成器以获得可重现结果的数字。默认值为 0。 |
+
+**注意：** 参数 `temperature`、`top_k`、`top_p`、`min_p`、`repetition_penalty` 和 `seed` 仅在 `sampling_mode` 设置为 "on" 时在节点界面中处于活动状态并可见。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `generated_text` | STRING | 模型根据输入提示词和可选图像生成的文本。 |
diff --git a/zh-CN/built-in-nodes/TextGenerateLTX2Prompt.mdx b/zh-CN/built-in-nodes/TextGenerateLTX2Prompt.mdx
new file mode 100644
index 000000000..aeb5fba0c
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextGenerateLTX2Prompt.mdx
@@ -0,0 +1,28 @@
+---
+title: "TextGenerateLTX2Prompt - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextGenerateLTX2Prompt node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextGenerateLTX2Prompt"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerateLTX2Prompt/zh.md)
+
+TextGenerateLTX2Prompt 节点是一个专门化的文本生成节点。它接收用户的文本提示，在发送给语言模型进行增强或补全之前，会自动使用特定的系统指令对其进行格式化。该节点可在两种模式下运行：纯文本模式或带图像参考模式，每种情况使用不同的系统提示。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `clip` | CLIP | 是 | | 用于文本编码的 CLIP 模型。 |
+| `prompt` | STRING | 是 | | 来自用户的原始文本输入，将被增强或补全。 |
+| `max_length` | INT | 是 | | 允许语言模型生成的最大令牌数量。 |
+| `sampling_mode` | COMBO | 是 | `"greedy"`<br />`"top_k"`<br />`"top_p"`<br />`"temperature"` | 在文本生成过程中用于选择下一个令牌的采样策略。 |
+| `image` | IMAGE | 否 | | 可选的输入图像。当提供时，节点会使用一个包含图像上下文占位符的不同系统提示。 |
+
+**注意：** 节点的行为会根据 `image` 输入是否存在而改变。如果提供了图像，生成的提示将被格式化为图像到视频任务。如果未提供图像，则格式化为文本到视频任务。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | STRING | 由语言模型生成的增强或补全后的文本字符串。 |
diff --git a/zh-CN/built-in-nodes/TextToLowercase.mdx b/zh-CN/built-in-nodes/TextToLowercase.mdx
new file mode 100644
index 000000000..6882893f4
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextToLowercase.mdx
@@ -0,0 +1,22 @@
+---
+title: "TextToLowercase - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextToLowercase node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextToLowercase"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToLowercase/zh.md)
+
+Text to Lowercase 节点接收一个文本字符串作为输入，并将其所有字符转换为小写。这是一个用于标准化文本大小写的简单工具。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | 是 | 任意文本字符串 | 需要转换为小写的文本字符串。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `text` | STRING | 所有字符已转换为小写的输入文本。 |
diff --git a/zh-CN/built-in-nodes/TextToUppercase.mdx b/zh-CN/built-in-nodes/TextToUppercase.mdx
new file mode 100644
index 000000000..78ad5d7ac
--- /dev/null
+++ b/zh-CN/built-in-nodes/TextToUppercase.mdx
@@ -0,0 +1,22 @@
+---
+title: "TextToUppercase - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TextToUppercase node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TextToUppercase"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToUppercase/zh.md)
+
+Text to Uppercase 节点接收一个文本输入，并将其所有字符转换为大写。它是一个简单的文本处理工具，用于修改所提供字符串的大小写。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | 是 | N/A | 需要转换为大写的文本字符串。 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `text` | STRING | 所有字符已转换为大写的结果文本。 |
diff --git a/zh-CN/built-in-nodes/ThresholdMask.mdx b/zh-CN/built-in-nodes/ThresholdMask.mdx
new file mode 100644
index 000000000..93c8a0792
--- /dev/null
+++ b/zh-CN/built-in-nodes/ThresholdMask.mdx
@@ -0,0 +1,23 @@
+---
+title: "ThresholdMask - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ThresholdMask node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ThresholdMask"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ThresholdMask/zh.md)
+
+ThresholdMask 节点通过应用阈值将遮罩转换为二值遮罩。它会将输入遮罩中的每个像素与指定的阈值进行比较，并创建一个新的遮罩，其中高于阈值的像素变为 1（白色），低于或等于阈值的像素变为 0（黑色）。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `遮罩` | MASK | 是 | - | 待处理的输入遮罩 |
+| `值` | FLOAT | 是 | 0.0 - 1.0 | 用于二值化的阈值（默认值：0.5） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `遮罩` | MASK | 经过阈值处理后的二值遮罩 |
diff --git a/zh-CN/built-in-nodes/TomePatchModel.mdx b/zh-CN/built-in-nodes/TomePatchModel.mdx
new file mode 100644
index 000000000..601b5e9da
--- /dev/null
+++ b/zh-CN/built-in-nodes/TomePatchModel.mdx
@@ -0,0 +1,23 @@
+---
+title: "TomePatchModel - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TomePatchModel node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TomePatchModel"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TomePatchModel/zh.md)
+
+TomePatchModel 节点对扩散模型应用令牌合并（ToMe）技术，以降低推理过程中的计算需求。该技术通过在注意力机制中有选择地合并相似令牌，使模型能够处理更少的令牌同时保持图像质量。这种方法有助于在不显著损失质量的情况下加速生成过程。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用令牌合并的扩散模型 |
+| `比率` | FLOAT | 否 | 0.0 - 1.0 | 要合并的令牌比例（默认值：0.3） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了令牌合并的修改后模型 |
diff --git a/zh-CN/built-in-nodes/TopazImageEnhance.mdx b/zh-CN/built-in-nodes/TopazImageEnhance.mdx
new file mode 100644
index 000000000..7b8d3093b
--- /dev/null
+++ b/zh-CN/built-in-nodes/TopazImageEnhance.mdx
@@ -0,0 +1,36 @@
+---
+title: "TopazImageEnhance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TopazImageEnhance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TopazImageEnhance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazImageEnhance/zh.md)
+
+Topaz Image Enhance 节点提供行业标准的图像放大和增强功能。它通过基于云的 AI 模型处理单个输入图像，以提升画质、细节和分辨率。该节点提供对增强过程的精细控制，包括创意引导、主体聚焦和面部保留等选项。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"Reimagine"` | 用于图像增强的 AI 模型。 |
+| `image` | IMAGE | 是 | - | 待增强的输入图像。仅支持单张图像。 |
+| `prompt` | STRING | 否 | - | 用于创意放大引导的可选文本提示（默认：空）。 |
+| `subject_detection` | COMBO | 否 | `"All"`<br />`"Foreground"`<br />`"Background"` | 控制增强过程聚焦于图像的哪个部分（默认："All"）。 |
+| `face_enhancement` | BOOLEAN | 否 | - | 启用后，如果图像中存在人脸，则对其进行增强（默认：True）。 |
+| `face_enhancement_creativity` | FLOAT | 否 | 0.0 - 1.0 | 设置人脸增强的创意级别（默认：0.0）。 |
+| `face_enhancement_strength` | FLOAT | 否 | 0.0 - 1.0 | 控制增强后的人脸相对于背景的锐利程度（默认：1.0）。 |
+| `crop_to_fill` | BOOLEAN | 否 | - | 默认情况下，当输出宽高比不同时，图像会添加黑边。启用此选项将裁剪图像以填充输出尺寸（默认：False）。 |
+| `output_width` | INT | 否 | 0 - 32000 | 输出图像的期望宽度。值为 0 表示自动计算，通常基于原始尺寸或指定的 `output_height`（默认：0）。 |
+| `output_height` | INT | 否 | 0 - 32000 | 输出图像的期望高度。值为 0 表示自动计算，通常基于原始尺寸或指定的 `output_width`（默认：0）。 |
+| `creativity` | INT | 否 | 1 - 9 | 控制增强的整体创意级别（默认：3）。 |
+| `face_preservation` | BOOLEAN | 否 | - | 保留图像中人物的面部特征（默认：True）。 |
+| `color_preservation` | BOOLEAN | 否 | - | 保留输入图像的原始颜色（默认：True）。 |
+
+**注意：** 此节点只能处理单张输入图像。提供包含多张图像的批次将导致错误。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 增强后的输出图像。 |
diff --git a/zh-CN/built-in-nodes/TopazVideoEnhance.mdx b/zh-CN/built-in-nodes/TopazVideoEnhance.mdx
new file mode 100644
index 000000000..76336070b
--- /dev/null
+++ b/zh-CN/built-in-nodes/TopazVideoEnhance.mdx
@@ -0,0 +1,35 @@
+---
+title: "TopazVideoEnhance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TopazVideoEnhance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TopazVideoEnhance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazVideoEnhance/zh.md)
+
+Topaz Video Enhance 节点使用外部 API 来提升视频质量。它可以放大视频分辨率、通过插值提高帧率，并应用压缩。该节点处理输入的 MP4 视频，并根据所选设置返回增强后的版本。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | 是 | - | 待增强的输入视频文件。 |
+| `upscaler_enabled` | BOOLEAN | 是 | - | 启用或禁用视频放大功能（默认：True）。 |
+| `upscaler_model` | COMBO | 是 | `"Proteus v3"`<br />`"Artemis v13"`<br />`"Artemis v14"`<br />`"Artemis v15"`<br />`"Gaia v6"`<br />`"Theia v3"`<br />`"Starlight (Astra) Creative"`<br />`"Starlight (Astra) Optimized"`<br />`"Starlight (Astra) Balanced"`<br />`"Starlight (Astra) Quality"`<br />`"Starlight (Astra) Speed"` | 用于视频放大的 AI 模型。 |
+| `upscaler_resolution` | COMBO | 是 | `"FullHD (1080p)"`<br />`"4K (2160p)"` | 放大视频的目标分辨率。 |
+| `upscaler_creativity` | COMBO | 否 | `"low"`<br />`"middle"`<br />`"high"` | 创意水平（仅适用于 Starlight (Astra) Creative 模型）。（默认："low"） |
+| `interpolation_enabled` | BOOLEAN | 否 | - | 启用或禁用帧插值功能（默认：False）。 |
+| `interpolation_model` | COMBO | 否 | `"apo-8"` | 用于帧插值的模型（默认："apo-8"）。 |
+| `interpolation_slowmo` | INT | 否 | 1 到 16 | 应用于输入视频的慢动作因子。例如，2 会使输出速度减半，时长加倍。（默认：1） |
+| `interpolation_frame_rate` | INT | 否 | 15 到 240 | 输出帧率。（默认：60） |
+| `interpolation_duplicate` | BOOLEAN | 否 | - | 分析输入视频中的重复帧并将其移除。（默认：False） |
+| `interpolation_duplicate_threshold` | FLOAT | 否 | 0.001 到 0.1 | 重复帧检测的敏感度。（默认：0.01） |
+| `dynamic_compression_level` | COMBO | 否 | `"Low"`<br />`"Mid"`<br />`"High"` | CQP 级别。（默认："Low"） |
+
+**注意：** 必须至少启用一项增强功能。如果 `upscaler_enabled` 和 `interpolation_enabled` 都设置为 `False`，节点将引发错误。输入视频必须是 MP4 格式。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 增强后的输出视频文件。 |
diff --git a/zh-CN/built-in-nodes/TorchCompileModel.mdx b/zh-CN/built-in-nodes/TorchCompileModel.mdx
new file mode 100644
index 000000000..01a512173
--- /dev/null
+++ b/zh-CN/built-in-nodes/TorchCompileModel.mdx
@@ -0,0 +1,23 @@
+---
+title: "TorchCompileModel - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TorchCompileModel node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TorchCompileModel"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TorchCompileModel/zh.md)
+
+TorchCompileModel 节点对模型应用 PyTorch 编译以优化其性能。它会创建输入模型的副本，并使用指定的后端通过 PyTorch 的编译功能对其进行封装。这可以提高模型在推理过程中的执行速度。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 待编译和优化的模型 |
+| `后端` | STRING | 是 | "inductor"<br />"cudagraphs" | 用于优化的 PyTorch 编译后端 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了 PyTorch 编译的已编译模型 |
diff --git a/zh-CN/built-in-nodes/TrainLoraNode.mdx b/zh-CN/built-in-nodes/TrainLoraNode.mdx
new file mode 100644
index 000000000..b7054e424
--- /dev/null
+++ b/zh-CN/built-in-nodes/TrainLoraNode.mdx
@@ -0,0 +1,42 @@
+---
+title: "TrainLoraNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TrainLoraNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TrainLoraNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrainLoraNode/zh.md)
+
+TrainLoraNode 使用提供的潜空间数据和条件数据，在扩散模型上创建并训练 LoRA（低秩适应）模型。该节点允许您使用自定义训练参数、优化器和损失函数来微调模型。节点输出应用了 LoRA 的训练后模型、LoRA 权重、训练损失指标以及完成的总训练步数。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要训练 LoRA 的基础模型。 |
+| `latents` | LATENT | 是 | - | 用于训练的潜空间数据，作为模型的数据集/输入。 |
+| `positive` | CONDITIONING | 是 | - | 用于训练的正向条件数据。 |
+| `batch_size` | INT | 是 | 1-10000 | 训练时使用的批大小（默认值：1）。 |
+| `grad_accumulation_steps` | INT | 是 | 1-1024 | 训练时使用的梯度累积步数（默认值：1）。 |
+| `steps` | INT | 是 | 1-100000 | 训练 LoRA 的步数（默认值：16）。 |
+| `learning_rate` | FLOAT | 是 | 0.0000001-1.0 | 训练时使用的学习率（默认值：0.0005）。 |
+| `rank` | INT | 是 | 1-128 | LoRA 层的秩（默认值：8）。 |
+| `optimizer` | COMBO | 是 | "AdamW"<br />"Adam"<br />"SGD"<br />"RMSprop" | 训练时使用的优化器（默认值："AdamW"）。 |
+| `loss_function` | COMBO | 是 | "MSE"<br />"L1"<br />"Huber"<br />"SmoothL1" | 训练时使用的损失函数（默认值："MSE"）。 |
+| `seed` | INT | 是 | 0-18446744073709551615 | 训练时使用的随机种子（用于 LoRA 权重初始化和噪声采样的生成器）（默认值：0）。 |
+| `training_dtype` | COMBO | 是 | "bf16"<br />"fp32" | 训练时使用的数据类型（默认值："bf16"）。 |
+| `lora_dtype` | COMBO | 是 | "bf16"<br />"fp32" | LoRA 使用的数据类型（默认值："bf16"）。 |
+| `algorithm` | COMBO | 是 | 多种可选算法 | 训练时使用的算法。 |
+| `gradient_checkpointing` | BOOLEAN | 是 | - | 训练时是否使用梯度检查点（默认值：True）。 |
+| `existing_lora` | COMBO | 是 | 多种可选选项 | 要附加到的现有 LoRA。设置为 None 表示创建新的 LoRA（默认值："[None]"）。 |
+
+**注意：** 正向条件数据的数量必须与潜空间图像的数量匹配。如果只提供了一个正向条件数据但有多个图像，该条件数据将自动为所有图像重复使用。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_with_lora` | MODEL | 应用了训练后 LoRA 的原始模型。 |
+| `lora` | LORA_MODEL | 训练后的 LoRA 权重，可以保存或应用于其他模型。 |
+| `loss` | LOSS_MAP | 包含随时间变化的训练损失值的字典。 |
+| `steps` | INT | 完成的总训练步数（包括现有 LoRA 的任何先前步数）。 |
diff --git a/zh-CN/built-in-nodes/TrimAudioDuration.mdx b/zh-CN/built-in-nodes/TrimAudioDuration.mdx
new file mode 100644
index 000000000..4431ed8d4
--- /dev/null
+++ b/zh-CN/built-in-nodes/TrimAudioDuration.mdx
@@ -0,0 +1,26 @@
+---
+title: "TrimAudioDuration - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TrimAudioDuration node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TrimAudioDuration"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrimAudioDuration/zh.md)
+
+TrimAudioDuration 节点允许您从音频文件中截取特定时间段。您可以指定开始裁剪的时间点以及生成音频片段的时长。该节点通过将时间值转换为音频帧位置并提取相应的音频波形部分来实现此功能。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `audio` | AUDIO | 是 | - | 需要裁剪的音频输入 |
+| `start_index` | FLOAT | 是 | -0xffffffffffffffff 到 0xffffffffffffffff | 开始时间（秒），可为负值表示从末尾倒计时（支持亚秒级精度）。默认值：0.0 |
+| `duration` | FLOAT | 是 | 0.0 到 0xffffffffffffffff | 持续时间（秒）。默认值：60.0 |
+
+**注意：** 开始时间必须小于结束时间且在音频长度范围内。负的开始时间值表示从音频末尾向前倒计时。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `audio` | AUDIO | 具有指定开始时间和持续时间的裁剪后音频片段 |
diff --git a/zh-CN/built-in-nodes/TrimVideoLatent.mdx b/zh-CN/built-in-nodes/TrimVideoLatent.mdx
new file mode 100644
index 000000000..0e047f23d
--- /dev/null
+++ b/zh-CN/built-in-nodes/TrimVideoLatent.mdx
@@ -0,0 +1,25 @@
+---
+title: "TrimVideoLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TrimVideoLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TrimVideoLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrimVideoLatent/zh.md)
+
+> 本文档由 AI 生成，如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrimVideoLatent/en.md)
+
+TrimVideoLatent 节点从视频潜在表示的起始位置移除帧。它接收一个潜在视频样本，并从开始处裁剪指定数量的帧，返回视频的剩余部分。这使您能够通过移除初始帧来缩短视频序列。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | 是 | - | 输入的视频潜在表示，包含待裁剪的帧 |
+| `trim_amount` | INT | 否 | 0 至 99999 | 从视频起始位置移除的帧数量（默认值：0） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | LATENT | 经过裁剪的潜在视频表示，已从起始位置移除指定数量的帧 |
diff --git a/zh-CN/built-in-nodes/TripleCLIPLoader.mdx b/zh-CN/built-in-nodes/TripleCLIPLoader.mdx
new file mode 100644
index 000000000..993bd9e7c
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripleCLIPLoader.mdx
@@ -0,0 +1,28 @@
+---
+title: "TripleCLIPLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripleCLIPLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripleCLIPLoader"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripleCLIPLoader/zh.md)
+
+## 概述
+
+TripleCLIPLoader 节点可同时加载三个不同的文本编码器模型，并将它们组合成单个 CLIP 模型。这在需要多个文本编码器的高级文本编码场景中非常有用，例如在需要 clip-l、clip-g 和 t5 模型协同工作的 SD3 工作流中。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `CLIP名称1` | STRING | 是 | 提供多个选项 | 从可用文本编码器中加载的第一个文本编码器模型 |
+| `CLIP名称2` | STRING | 是 | 提供多个选项 | 从可用文本编码器中加载的第二个文本编码器模型 |
+| `CLIP名称3` | STRING | 是 | 提供多个选项 | 从可用文本编码器中加载的第三个文本编码器模型 |
+
+**注意：** 所有三个文本编码器参数都必须从系统中可用的文本编码器模型中选择。该节点将加载所有三个模型，并将它们组合成单个 CLIP 模型进行处理。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `CLIP` | CLIP | 包含所有三个已加载文本编码器的组合 CLIP 模型 |
diff --git a/zh-CN/built-in-nodes/TripoConversionNode.mdx b/zh-CN/built-in-nodes/TripoConversionNode.mdx
new file mode 100644
index 000000000..3ecb77157
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripoConversionNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "TripoConversionNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoConversionNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoConversionNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoConversionNode/zh.md)
+
+TripoConversionNode 使用 Tripo API 在不同文件格式之间转换 3D 模型。它接收先前 Tripo 操作的任务 ID，并将结果模型转换为所需的格式，提供多种导出选项。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `original_model_task_id` | MODEL_TASK_ID,RIG_TASK_ID,RETARGET_TASK_ID | 是 | MODEL_TASK_ID<br />RIG_TASK_ID<br />RETARGET_TASK_ID | 来自先前 Tripo 操作（模型生成、骨骼绑定或重定向）的任务 ID |
+| `format` | COMBO | 是 | GLTF<br />USDZ<br />FBX<br />OBJ<br />STL<br />3MF | 转换后 3D 模型的目标文件格式 |
+| `quad` | BOOLEAN | 否 | True/False | 是否将三角形转换为四边形（默认值：False） |
+| `face_limit` | INT | 否 | -1 到 500000 | 输出模型中的最大面数，使用 -1 表示无限制（默认值：-1） |
+| `texture_size` | INT | 否 | 128 到 4096 | 输出纹理的像素尺寸（默认值：4096） |
+| `texture_format` | COMBO | 否 | BMP<br />DPX<br />HDR<br />JPEG<br />OPEN_EXR<br />PNG<br />TARGA<br />TIFF<br />WEBP | 导出纹理的格式（默认值：JPEG） |
+
+**注意：** `original_model_task_id` 必须是来自先前 Tripo 操作（模型生成、骨骼绑定或重定向）的有效任务 ID。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| *无命名输出* | - | 此节点异步处理转换，并通过 Tripo API 系统返回结果 |
diff --git a/zh-CN/built-in-nodes/TripoImageToModelNode.mdx b/zh-CN/built-in-nodes/TripoImageToModelNode.mdx
new file mode 100644
index 000000000..dac66c0fa
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripoImageToModelNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "TripoImageToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoImageToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoImageToModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImageToModelNode/zh.md)
+
+使用 Tripo 的 API 基于单张图像同步生成 3D 模型。此节点接收输入图像，并将其转换为 3D 模型，提供纹理、质量和模型属性的多种自定义选项。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 用于生成 3D 模型的输入图像 |
+| `model_version` | COMBO | 否 | 提供多个选项 | 用于生成的 Tripo 模型版本 |
+| `style` | COMBO | 否 | 提供多个选项 | 生成模型的风格设置（默认："None"） |
+| `texture` | BOOLEAN | 否 | - | 是否为模型生成纹理（默认：True） |
+| `pbr` | BOOLEAN | 否 | - | 是否使用基于物理的渲染（默认：True） |
+| `model_seed` | INT | 否 | - | 模型生成的随机种子（默认：42） |
+| `orientation` | COMBO | 否 | 提供多个选项 | 生成模型的方向设置 |
+| `texture_seed` | INT | 否 | - | 纹理生成的随机种子（默认：42） |
+| `texture_quality` | COMBO | 否 | "standard"<br />"detailed" | 纹理生成的质量级别（默认："standard"） |
+| `texture_alignment` | COMBO | 否 | "original_image"<br />"geometry" | 纹理映射的对齐方法（默认："original_image"） |
+| `face_limit` | INT | 否 | -1 到 500000 | 生成模型中的最大面数，-1 表示无限制（默认：-1） |
+| `quad` | BOOLEAN | 否 | - | 是否使用四边形面而非三角形面（默认：False） |
+
+**注意：** `image` 参数是必需的，必须提供才能使节点正常工作。如果未提供图像，节点将引发 RuntimeError。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的 3D 模型文件 |
+| `model task_id` | MODEL_TASK_ID | 用于跟踪模型生成过程的任务 ID |
diff --git a/zh-CN/built-in-nodes/TripoMultiviewToModelNode.mdx b/zh-CN/built-in-nodes/TripoMultiviewToModelNode.mdx
new file mode 100644
index 000000000..e9089e5a4
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripoMultiviewToModelNode.mdx
@@ -0,0 +1,38 @@
+---
+title: "TripoMultiviewToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoMultiviewToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoMultiviewToModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoMultiviewToModelNode/zh.md)
+
+此节点通过处理最多四张展示物体不同视角的图像，使用 Tripo 的 API 同步生成 3D 模型。它需要一张正面图像和至少一张额外视角（左侧、背面或右侧）图像，以创建具有纹理和材质选项的完整 3D 模型。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `image` | IMAGE | 是 | - | 物体的正面视角图像（必需） |
+| `image_left` | IMAGE | 否 | - | 物体的左侧视角图像 |
+| `image_back` | IMAGE | 否 | - | 物体的背面视角图像 |
+| `image_right` | IMAGE | 否 | - | 物体的右侧视角图像 |
+| `model_version` | COMBO | 否 | 提供多个选项 | 用于生成的 Tripo 模型版本 |
+| `orientation` | COMBO | 否 | 提供多个选项 | 3D 模型的方向设置 |
+| `texture` | BOOLEAN | 否 | - | 是否为模型生成纹理（默认：True） |
+| `pbr` | BOOLEAN | 否 | - | 是否生成 PBR（基于物理的渲染）材质（默认：True） |
+| `model_seed` | INT | 否 | - | 模型生成的随机种子（默认：42） |
+| `texture_seed` | INT | 否 | - | 纹理生成的随机种子（默认：42） |
+| `texture_quality` | COMBO | 否 | "standard"<br />"detailed" | 纹理生成的质量级别（默认："standard"） |
+| `texture_alignment` | COMBO | 否 | "original_image"<br />"geometry" | 将纹理对齐到模型的方法（默认："original_image"） |
+| `face_limit` | INT | 否 | -1 到 500000 | 生成模型中的最大面数，-1 表示无限制（默认：-1） |
+| `quad` | BOOLEAN | 否 | - | 是否生成基于四边形的几何体而非三角形（默认：False） |
+
+**注意：** 正面图像（`image`）始终是必需的。必须提供至少一张额外的视角图像（`image_left`、`image_back` 或 `image_right`）以进行多视角处理。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的 3D 模型的文件路径或标识符 |
+| `model task_id` | MODEL_TASK_ID | 用于跟踪模型生成过程的任务标识符 |
diff --git a/zh-CN/built-in-nodes/TripoRefineNode.mdx b/zh-CN/built-in-nodes/TripoRefineNode.mdx
new file mode 100644
index 000000000..766b36db0
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripoRefineNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "TripoRefineNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoRefineNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoRefineNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/zh.md)
+
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/en.md)
+
+TripoRefineNode 用于优化专门由 v1.4 版 Tripo 模型创建的 3D 模型草稿。它接收一个模型任务 ID，通过 Tripo API 进行处理，生成模型的改进版本。此节点专门设计用于处理由 Tripo v1.4 模型生成的草稿模型。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_task_id` | MODEL_TASK_ID | 是 | - | 必须是 v1.4 版 Tripo 模型 |
+| `auth_token` | AUTH_TOKEN_COMFY_ORG | 否 | - | Comfy.org API 的认证令牌 |
+| `comfy_api_key` | API_KEY_COMFY_ORG | 否 | - | Comfy.org 服务的 API 密钥 |
+| `unique_id` | UNIQUE_ID | 否 | - | 操作的唯一标识符 |
+
+**注意：** 此节点仅接受由 Tripo v1.4 模型创建的草稿模型。使用其他版本的模型可能会导致错误。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 优化后模型的文件路径或引用 |
+| `model task_id` | MODEL_TASK_ID | 优化模型操作的任务标识符 |
diff --git a/zh-CN/built-in-nodes/TripoRetargetNode.mdx b/zh-CN/built-in-nodes/TripoRetargetNode.mdx
new file mode 100644
index 000000000..12ee7562c
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripoRetargetNode.mdx
@@ -0,0 +1,29 @@
+---
+title: "TripoRetargetNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoRetargetNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoRetargetNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRetargetNode/zh.md)
+
+> 本文档由 AI 生成，如果您发现任何错误或有改进建议，请随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRetargetNode/en.md)
+
+TripoRetargetNode 通过重新定向运动数据，将预定义的动画应用到 3D 角色模型上。该节点接收一个先前处理过的 3D 模型，并应用多个预设动画之一，生成一个动画化的 3D 模型文件作为输出。该节点通过与 Tripo API 通信来处理动画重定向操作。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `original_model_task_id` | RIG_TASK_ID | 是 | - | 要应用动画的先前处理过的 3D 模型的任务 ID |
+| `animation` | STRING | 是 | "preset:idle"<br />"preset:walk"<br />"preset:climb"<br />"preset:jump"<br />"preset:slash"<br />"preset:shoot"<br />"preset:hurt"<br />"preset:fall"<br />"preset:turn" | 要应用到 3D 模型上的动画预设 |
+| `auth_token` | AUTH_TOKEN_COMFY_ORG | 否 | - | 用于访问 Comfy.org API 的认证令牌 |
+| `comfy_api_key` | API_KEY_COMFY_ORG | 否 | - | 用于访问 Comfy.org 服务的 API 密钥 |
+| `unique_id` | UNIQUE_ID | 否 | - | 用于跟踪操作的唯一标识符 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的动画化 3D 模型文件 |
+| `retarget task_id` | RETARGET_TASK_ID | 用于跟踪重定向操作的任务 ID |
diff --git a/zh-CN/built-in-nodes/TripoRigNode.mdx b/zh-CN/built-in-nodes/TripoRigNode.mdx
new file mode 100644
index 000000000..1cb4b7bad
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripoRigNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "TripoRigNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoRigNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoRigNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRigNode/zh.md)
+
+## 概述
+
+TripoRigNode 通过原始模型任务 ID 生成带骨骼绑定的 3D 模型。该节点会向 Tripo API 发送请求，使用 Tripo 规范创建 GLB 格式的动画骨骼绑定，然后持续轮询 API 直到骨骼绑定生成任务完成。
+
+## 输入
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `original_model_task_id` | MODEL_TASK_ID | 是 | - | 待绑定骨骼的原始 3D 模型的任务 ID |
+| `auth_token` | AUTH_TOKEN_COMFY_ORG | 否 | - | 用于访问 Comfy.org API 的认证令牌 |
+| `comfy_api_key` | API_KEY_COMFY_ORG | 否 | - | 用于 Comfy.org 服务认证的 API 密钥 |
+| `unique_id` | UNIQUE_ID | 否 | - | 用于跟踪操作的唯一标识符 |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的带骨骼绑定的 3D 模型文件 |
+| `rig task_id` | RIG_TASK_ID | 用于跟踪骨骼绑定生成过程的任务 ID |
diff --git a/zh-CN/built-in-nodes/TripoTextToModelNode.mdx b/zh-CN/built-in-nodes/TripoTextToModelNode.mdx
new file mode 100644
index 000000000..76f367801
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripoTextToModelNode.mdx
@@ -0,0 +1,36 @@
+---
+title: "TripoTextToModelNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoTextToModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoTextToModelNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextToModelNode/zh.md)
+
+使用 Tripo 的 API 根据文本提示同步生成 3D 模型。此节点接收文本描述并创建具有可选纹理和材质属性的 3D 模型。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 用于生成 3D 模型的文本描述（多行输入） |
+| `negative_prompt` | STRING | 否 | - | 描述生成模型中应避免内容的文本（多行输入） |
+| `model_version` | COMBO | 否 | 多个可用选项 | 用于生成的 Tripo 模型版本 |
+| `style` | COMBO | 否 | 多个可用选项 | 生成模型的风格设置（默认："None"） |
+| `texture` | BOOLEAN | 否 | - | 是否为模型生成纹理（默认：True） |
+| `pbr` | BOOLEAN | 否 | - | 是否生成 PBR（基于物理的渲染）材质（默认：True） |
+| `image_seed` | INT | 否 | - | 图像生成的随机种子（默认：42） |
+| `model_seed` | INT | 否 | - | 模型生成的随机种子（默认：42） |
+| `texture_seed` | INT | 否 | - | 纹理生成的随机种子（默认：42） |
+| `texture_quality` | COMBO | 否 | "standard"<br />"detailed" | 纹理生成的质量级别（默认："standard"） |
+| `face_limit` | INT | 否 | -1 到 500000 | 生成模型中的最大面数，-1 表示无限制（默认：-1） |
+| `quad` | BOOLEAN | 否 | - | 是否生成基于四边形的几何体而非三角形（默认：False） |
+
+**注意：** `prompt` 参数是必需的，不能为空。如果未提供提示，节点将引发错误。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 生成的 3D 模型文件 |
+| `model task_id` | MODEL_TASK_ID | 模型生成过程的唯一任务标识符 |
diff --git a/zh-CN/built-in-nodes/TripoTextureNode.mdx b/zh-CN/built-in-nodes/TripoTextureNode.mdx
new file mode 100644
index 000000000..f365e4ec7
--- /dev/null
+++ b/zh-CN/built-in-nodes/TripoTextureNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "TripoTextureNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TripoTextureNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TripoTextureNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextureNode/zh.md)
+
+TripoTextureNode 使用 Tripo API 生成带纹理的 3D 模型。它接收模型任务 ID，并通过包括 PBR 材质、纹理质量设置和对齐方法在内的多种选项应用纹理生成功能。该节点通过与 Tripo API 通信来处理纹理生成请求，并返回生成的模型文件和任务 ID。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model_task_id` | MODEL_TASK_ID | 是 | - | 要应用纹理的模型任务 ID |
+| `texture` | BOOLEAN | 否 | - | 是否生成纹理（默认值：True） |
+| `pbr` | BOOLEAN | 否 | - | 是否生成 PBR（基于物理的渲染）材质（默认值：True） |
+| `texture_seed` | INT | 否 | - | 纹理生成的随机种子（默认值：42） |
+| `texture_quality` | COMBO | 否 | "standard"<br />"detailed" | 纹理生成的质量级别（默认值："standard"） |
+| `texture_alignment` | COMBO | 否 | "original_image"<br />"geometry" | 纹理对齐方法（默认值："original_image"） |
+
+*注意：此节点需要认证令牌和 API 密钥，这些由系统自动处理。*
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model_file` | STRING | 应用纹理后生成的模型文件 |
+| `model task_id` | MODEL_TASK_ID | 用于跟踪纹理生成过程的任务 ID |
diff --git a/zh-CN/built-in-nodes/TruncateText.mdx b/zh-CN/built-in-nodes/TruncateText.mdx
new file mode 100644
index 000000000..c8d1437b8
--- /dev/null
+++ b/zh-CN/built-in-nodes/TruncateText.mdx
@@ -0,0 +1,23 @@
+---
+title: "TruncateText - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the TruncateText node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "TruncateText"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TruncateText/zh.md)
+
+此节点通过将文本截断至指定最大长度来缩短文本。它接收任意输入文本，仅返回您设置字符数以内的前段内容。这是一种确保文本不超过特定大小的简单方法。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `text` | STRING | 是 | 不适用 | 需要被截断的文本字符串。 |
+| `max_length` | INT | 否 | 1 至 10000 | 文本的最大长度。文本将在此数量的字符后被截断（默认值：77）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `string` | STRING | 截断后的文本，仅包含输入文本的前 `max_length` 个字符。 |
diff --git a/zh-CN/built-in-nodes/UNETLoader.mdx b/zh-CN/built-in-nodes/UNETLoader.mdx
new file mode 100644
index 000000000..fe4f0452d
--- /dev/null
+++ b/zh-CN/built-in-nodes/UNETLoader.mdx
@@ -0,0 +1,33 @@
+---
+title: "UNETLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UNETLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UNETLoader"
+icon: "circle"
+mode: wide
+---
+UNETLoader 节点旨在通过名称加载 U-Net 模型，方便在系统中使用预训练的 U-Net 架构。
+这个节点名称已更新为 `Load Diffusion Model`.
+
+该节点会自动检测位于 `ComfyUI/models/diffusion_models` 文件夹中的模型。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+| -------- | -------- | ------------------------------------------------------------ |
+| `UNet名称` | COMBO[STRING] | 指定要加载的 U-Net 模型的名称。此名称用于在预定义的目录结构内定位模型，从而实现不同 U-Net 模型的动态加载。 |
+| `数据类型` | ... |  |
+
+fp8_e4m3fn和fp9_e5m2  表示不同精度和动态范围
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                       |
+| -------- | -------- | ------------------------------------------ |
+| `model`  | MODEL    | 返回加载的 U-Net 模型，允许在系统中用于进一步处理或推理。 |
+
+## UNET Loader Guide | Load Diffusion Model Workflow Example
+
+1. 安装 UNET 模型
+2. 下载工作流文件
+3. 在 ComfyUI 中导入工作流
+4. 选择 UNET 模型并运行工作流
diff --git a/zh-CN/built-in-nodes/UNetCrossAttentionMultiply.mdx b/zh-CN/built-in-nodes/UNetCrossAttentionMultiply.mdx
new file mode 100644
index 000000000..b97d41eaa
--- /dev/null
+++ b/zh-CN/built-in-nodes/UNetCrossAttentionMultiply.mdx
@@ -0,0 +1,26 @@
+---
+title: "UNetCrossAttentionMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UNetCrossAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UNetCrossAttentionMultiply"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/UNetCrossAttentionMultiply/zh.md)
+
+UNetCrossAttentionMultiply 节点用于对 UNet 模型中的交叉注意力机制应用乘法因子。它允许您缩放交叉注意力层的查询、键、值和输出组件，以实验不同的注意力行为与效果。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `模型` | MODEL | 是 | - | 需要应用注意力缩放因子的 UNet 模型 |
+| `q` | FLOAT | 否 | 0.0 - 10.0 | 交叉注意力中查询组件的缩放因子（默认值：1.0） |
+| `k` | FLOAT | 否 | 0.0 - 10.0 | 交叉注意力中键组件的缩放因子（默认值：1.0） |
+| `v` | FLOAT | 否 | 0.0 - 10.0 | 交叉注意力中值组件的缩放因子（默认值：1.0） |
+| `输出` | FLOAT | 否 | 0.0 - 10.0 | 交叉注意力中输出组件的缩放因子（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `模型` | MODEL | 经过交叉注意力组件缩放处理后的 UNet 模型 |
diff --git a/zh-CN/built-in-nodes/UNetSelfAttentionMultiply.mdx b/zh-CN/built-in-nodes/UNetSelfAttentionMultiply.mdx
new file mode 100644
index 000000000..9470907a3
--- /dev/null
+++ b/zh-CN/built-in-nodes/UNetSelfAttentionMultiply.mdx
@@ -0,0 +1,26 @@
+---
+title: "UNetSelfAttentionMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UNetSelfAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UNetSelfAttentionMultiply"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/UNetSelfAttentionMultiply/zh.md)
+
+UNetSelfAttentionMultiply 节点用于对 UNet 模型中的自注意力机制的查询、键、值和输出组件应用乘法因子。通过调整注意力计算不同部分的缩放比例，您可以探索注意力权重如何影响模型的行为表现。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 需要应用注意力缩放因子的 UNet 模型 |
+| `q` | FLOAT | 否 | 0.0 - 10.0 | 查询组件的乘法因子（默认值：1.0） |
+| `k` | FLOAT | 否 | 0.0 - 10.0 | 键组件的乘法因子（默认值：1.0） |
+| `v` | FLOAT | 否 | 0.0 - 10.0 | 值组件的乘法因子（默认值：1.0） |
+| `输出` | FLOAT | 否 | 0.0 - 10.0 | 输出组件的乘法因子（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `MODEL` | MODEL | 经过注意力组件缩放处理后的 UNet 模型 |
diff --git a/zh-CN/built-in-nodes/UNetTemporalAttentionMultiply.mdx b/zh-CN/built-in-nodes/UNetTemporalAttentionMultiply.mdx
new file mode 100644
index 000000000..0d6b14dbd
--- /dev/null
+++ b/zh-CN/built-in-nodes/UNetTemporalAttentionMultiply.mdx
@@ -0,0 +1,26 @@
+---
+title: "UNetTemporalAttentionMultiply - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UNetTemporalAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UNetTemporalAttentionMultiply"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/UNetTemporalAttentionMultiply/zh.md)
+
+UNetTemporalAttentionMultiply 节点用于对时序 UNet 模型中的不同类型的注意力机制应用乘法因子。该节点通过调整自注意力和交叉注意力层的权重来修改模型，并区分结构组件和时序组件。这样可以微调每种注意力类型对模型输出的影响程度。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 需要应用注意力乘数进行修改的输入模型 |
+| `自我结构` | FLOAT | 否 | 0.0 - 10.0 | 自注意力结构组件的乘数（默认值：1.0） |
+| `自我时间` | FLOAT | 否 | 0.0 - 10.0 | 自注意力时序组件的乘数（默认值：1.0） |
+| `交叉结构` | FLOAT | 否 | 0.0 - 10.0 | 交叉注意力结构组件的乘数（默认值：1.0） |
+| `交叉时间` | FLOAT | 否 | 0.0 - 10.0 | 交叉注意力时序组件的乘数（默认值：1.0） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 经过注意力权重调整后的修改模型 |
diff --git a/zh-CN/built-in-nodes/USOStyleReference.mdx b/zh-CN/built-in-nodes/USOStyleReference.mdx
new file mode 100644
index 000000000..f7163dc5d
--- /dev/null
+++ b/zh-CN/built-in-nodes/USOStyleReference.mdx
@@ -0,0 +1,24 @@
+---
+title: "USOStyleReference - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the USOStyleReference node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "USOStyleReference"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/USOStyleReference/zh.md)
+
+USOStyleReference 节点使用来自 CLIP 视觉输出的编码图像特征，将风格参考补丁应用于模型。它通过从视觉输入中提取的风格信息创建输入模型的修改版本，从而实现风格迁移或基于参考的生成功能。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 要应用风格参考补丁的基础模型 |
+| `model_patch` | MODEL_PATCH | 是 | - | 包含风格参考信息的模型补丁 |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | 是 | - | 从 CLIP 视觉处理中提取的编码视觉特征 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 应用了风格参考补丁的修改后模型 |
diff --git a/zh-CN/built-in-nodes/UpscaleModelLoader.mdx b/zh-CN/built-in-nodes/UpscaleModelLoader.mdx
new file mode 100644
index 000000000..ce6c42274
--- /dev/null
+++ b/zh-CN/built-in-nodes/UpscaleModelLoader.mdx
@@ -0,0 +1,24 @@
+---
+title: "UpscaleModelLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the UpscaleModelLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "UpscaleModelLoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/upscale_models` 文件夹下的模型，
+同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，
+有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+放大模型加载节点旨在从指定目录加载放大模型。它便于检索和准备放大模型以用于图像放大任务，确保模型被正确加载和配置以进行评估。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `模型名称` | COMBO[STRING] | 指定要加载的放大模型的名称。此参数对于从放大模型目录中识别和检索正确的模型文件至关重要。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `upscale_model` | UPSCALE_MODEL | 返回已加载和准备好的放大模型，准备用于图像放大任务。 |
diff --git a/zh-CN/built-in-nodes/VAEDecode.mdx b/zh-CN/built-in-nodes/VAEDecode.mdx
new file mode 100644
index 000000000..3b236d638
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEDecode.mdx
@@ -0,0 +1,22 @@
+---
+title: "VAEDecode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecode"
+icon: "circle"
+mode: wide
+---
+
+VAEDecode节点旨在使用指定的变分自编码器（VAE）将潜在表示解码成图像。它的目的是从压缩的数据表示生成图像，从而促进从它们的潜在空间编码重建图像。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `Latent` | LATENT   | `Latent` 参数代表要解码成图像的潜在表示。它对解码过程至关重要，因为它提供了重建图像的压缩数据。 |
+| `vae`     | VAE      | `vae` 参数指定用于将潜在表示解码成图像的变分自编码器模型。它对确定解码机制和重建图像的质量至关重要。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `image`  | IMAGE    | 输出是使用指定的VAE模型从提供的潜在表示重建的图像。       |
diff --git a/zh-CN/built-in-nodes/VAEDecodeAudio.mdx b/zh-CN/built-in-nodes/VAEDecodeAudio.mdx
new file mode 100644
index 000000000..1552ab22f
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEDecodeAudio.mdx
@@ -0,0 +1,23 @@
+---
+title: "VAEDecodeAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecodeAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecodeAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeAudio/zh.md)
+
+VAEDecodeAudio 节点使用变分自编码器将潜在表示转换回音频波形。它接收编码的音频样本，通过 VAE 进行处理以重建原始音频，并应用归一化来确保输出电平的一致性。生成的音频以 44100 Hz 的标准采样率返回。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Latent` | LATENT | 是 | - | 潜在空间中已编码的音频样本，将被解码回音频波形 |
+| `vae` | VAE | 是 | - | 用于将潜在样本解码为音频的变分自编码器模型 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `AUDIO` | AUDIO | 已解码的音频波形，具有归一化音量和 44100 Hz 采样率 |
diff --git a/zh-CN/built-in-nodes/VAEDecodeAudioTiled.mdx b/zh-CN/built-in-nodes/VAEDecodeAudioTiled.mdx
new file mode 100644
index 000000000..5e9d582e5
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEDecodeAudioTiled.mdx
@@ -0,0 +1,25 @@
+---
+title: "VAEDecodeAudioTiled - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecodeAudioTiled node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecodeAudioTiled"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeAudioTiled/zh.md)
+
+此节点使用变分自编码器（VAE）将压缩的音频表示（潜在样本）转换回音频波形。它通过处理较小且重叠的片段（图块）来管理内存使用，使其适合处理较长的音频序列。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `samples` | LATENT | 是 | 不适用 | 待解码音频的压缩潜在表示。 |
+| `vae` | VAE | 是 | 不适用 | 用于执行解码的变分自编码器模型。 |
+| `tile_size` | INT | 否 | 32 至 8192 | 每个处理图块的大小。音频按此长度的片段进行解码以节省内存（默认值：512）。 |
+| `overlap` | INT | 否 | 0 至 1024 | 相邻图块重叠的样本数。这有助于减少图块边界处的伪影（默认值：64）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | AUDIO | 解码后的音频波形。 |
diff --git a/zh-CN/built-in-nodes/VAEDecodeHunyuan3D.mdx b/zh-CN/built-in-nodes/VAEDecodeHunyuan3D.mdx
new file mode 100644
index 000000000..304b252fb
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEDecodeHunyuan3D.mdx
@@ -0,0 +1,25 @@
+---
+title: "VAEDecodeHunyuan3D - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecodeHunyuan3D node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecodeHunyuan3D"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeHunyuan3D/zh.md)
+
+VAEDecodeHunyuan3D 节点使用 VAE 解码器将潜在表示转换为 3D 体素数据。它通过可配置的分块和分辨率设置，利用 VAE 模型处理潜在样本，生成适用于 3D 应用的体数据。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `样本` | LATENT | 是 | - | 待解码为 3D 体素数据的潜在表示 |
+| `vae` | VAE | 是 | - | 用于解码潜在样本的 VAE 模型 |
+| `块数` | INT | 是 | 1000-500000 | 为内存管理将处理过程分割的块数（默认：8000） |
+| `八叉树分辨率` | INT | 是 | 16-512 | 用于 3D 体素生成的八叉树结构分辨率（默认：256） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `voxels` | VOXEL | 从解码后的潜在表示生成的 3D 体素数据 |
diff --git a/zh-CN/built-in-nodes/VAEDecodeTiled.mdx b/zh-CN/built-in-nodes/VAEDecodeTiled.mdx
new file mode 100644
index 000000000..07403e512
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEDecodeTiled.mdx
@@ -0,0 +1,29 @@
+---
+title: "VAEDecodeTiled - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEDecodeTiled node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEDecodeTiled"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeTiled/zh.md)
+
+VAEDecodeTiled 节点使用分块方法将潜在表示解码为图像，以高效处理大尺寸图像。它通过将输入分割成较小的图块进行处理，在保持图像质量的同时有效管理内存使用。该节点还支持视频 VAE，通过带重叠的帧块处理来实现平滑过渡。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `Latent` | LATENT | 是 | - | 待解码为图像的潜在表示 |
+| `vae` | VAE | 是 | - | 用于解码潜在样本的 VAE 模型 |
+| `分块尺寸` | INT | 是 | 64-4096 (步长: 32) | 处理时每个图块的尺寸（默认: 512） |
+| `重叠` | INT | 是 | 0-4096 (步长: 32) | 相邻图块之间的重叠量（默认: 64） |
+| `时间尺寸` | INT | 是 | 8-4096 (步长: 4) | 仅用于视频 VAE：单次解码的帧数（默认: 64） |
+| `时间重叠` | INT | 是 | 4-4096 (步长: 4) | 仅用于视频 VAE：帧重叠量（默认: 8） |
+
+**注意：** 如果重叠值超过实际限制，节点会自动调整。如果 `tile_size` 小于 `overlap` 的 4 倍，重叠量将减少为图块尺寸的四分之一。同样地，如果 `temporal_size` 小于 `temporal_overlap` 的 2 倍，时间重叠量将减半。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 从潜在表示解码生成的一张或多张图像 |
diff --git a/zh-CN/built-in-nodes/VAEEncode.mdx b/zh-CN/built-in-nodes/VAEEncode.mdx
new file mode 100644
index 000000000..eef240c94
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEEncode.mdx
@@ -0,0 +1,23 @@
+---
+title: "VAEEncode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEEncode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEEncode"
+icon: "circle"
+mode: wide
+---
+
+用于将图像从像素空间编码至潜空间进行编码
+此节点设计用于将图像编码为潜在空间表示，使用指定的变分自编码器（VAE）模型。它简化了编码过程的复杂性，提供了一种直接的方法将图像转换为它们的潜在表示。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `像素` | `IMAGE` | 代表要编码到潜在空间的图像数据，作为编码过程的直接输入，对确定输出潜在表示至关重要。 |
+| `变分自编码器` | `VAE` | 指定用于编码图像数据到潜在空间的变分自编码器模型，定义了编码机制和生成的潜在表示的特征。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `潜在表示` | `LATENT` | 输出是输入图像的潜在空间表示，以压缩形式封装了图像的基本特征。 |
diff --git a/zh-CN/built-in-nodes/VAEEncodeAudio.mdx b/zh-CN/built-in-nodes/VAEEncodeAudio.mdx
new file mode 100644
index 000000000..a7692cb27
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEEncodeAudio.mdx
@@ -0,0 +1,25 @@
+---
+title: "VAEEncodeAudio - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEEncodeAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEEncodeAudio"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEEncodeAudio/zh.md)
+
+VAEEncodeAudio 节点使用变分自编码器（VAE）将音频数据转换为潜在表示。该节点接收音频输入，并通过 VAE 进行处理，生成压缩的潜在样本，这些样本可用于进一步的音频生成或处理任务。在编码前，节点会根据需要自动将音频重新采样至 44100 Hz。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `音频` | AUDIO | 是 | - | 待编码的音频数据，包含波形和采样率信息 |
+| `vae` | VAE | 是 | - | 用于将音频编码到潜在空间的变分自编码器模型 |
+
+**注意：** 如果原始采样率与 44100 Hz 不同，音频输入将自动重新采样至该值。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `LATENT` | LATENT | 潜在空间中的编码音频表示，包含压缩样本 |
diff --git a/zh-CN/built-in-nodes/VAEEncodeForInpaint.mdx b/zh-CN/built-in-nodes/VAEEncodeForInpaint.mdx
new file mode 100644
index 000000000..715e4ce9a
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEEncodeForInpaint.mdx
@@ -0,0 +1,28 @@
+---
+title: "VAEEncodeForInpaint - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEEncodeForInpaint node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEEncodeForInpaint"
+icon: "circle"
+mode: wide
+---
+
+VAE内补编码器节点，主要用于将已有的需要修改的图像转换为潜空间图像，除了和**VAE编码器** 一样需要VAE和图像的输入信息之外，它需要额外提供遮罩提供给模型，让采样器知道该对哪个部分进行去噪（重新生成）在我的使用过程中，我感觉这个节点适合用于对于局部重绘替换成与原始图像完全不相关的内容。
+>
+    **注意**
+    使用此节点时，请勿将采样器中的 ```denoise降噪```设置过低，否则将出现重绘后图像蒙版区域为灰白色块情况
+不同```denoise降噪```值设置下使用该节点输出图像效果如下
+
+## 输入
+
+| 参数名称       | 数据类型 | 作用                                                         |
+|----------------|----------|--------------------------------------------------------------|
+| `像素`       | `IMAGE`  | 要编码的输入图像。在编码之前，此图像将进行预处理和调整大小以匹配VAE模型的预期输入尺寸。 |
+| `vae`          | `VAE`    | 用于将图像编码为其潜在表示的VAE模型。它在转换过程中起着关键作用，决定了输出潜在空间的质量和特性。 |
+| `遮罩`         | `MASK`   | 一个遮罩，指示输入图像中要进行修复的区域。它用于在编码前修改图像，确保VAE专注于相关区域。       |
+| `扩展遮罩` | `INT`    | 指定扩展修复遮罩的程度，以确保潜在空间中的无缝过渡。较大的值会增加修复影响的区域。       |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                       |
+|----------|----------|--------------------------------------------|
+| `latent` | `LATENT` | 输出包括图像的编码潜在表示和噪声遮罩，这两者对于后续的修复任务都至关重要。 |
diff --git a/zh-CN/built-in-nodes/VAEEncodeTiled.mdx b/zh-CN/built-in-nodes/VAEEncodeTiled.mdx
new file mode 100644
index 000000000..4896288ae
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAEEncodeTiled.mdx
@@ -0,0 +1,29 @@
+---
+title: "VAEEncodeTiled - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAEEncodeTiled node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAEEncodeTiled"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEEncodeTiled/zh.md)
+
+VAEEncodeTiled 节点通过将图像分割成较小的图块并使用变分自编码器进行编码来处理图像。这种分块方法可以处理可能超出内存限制的大图像。该节点支持图像和视频 VAE，并具有针对空间和时间维度的独立分块控制。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `像素` | IMAGE | 是 | - | 待编码的输入图像数据 |
+| `vae` | VAE | 是 | - | 用于编码的变分自编码器模型 |
+| `分块尺寸` | INT | 是 | 64-4096 (步长: 64) | 空间处理时每个图块的尺寸（默认: 512） |
+| `重叠` | INT | 是 | 0-4096 (步长: 32) | 相邻图块之间的重叠量（默认: 64） |
+| `时间尺寸` | INT | 是 | 8-4096 (步长: 4) | 仅用于视频 VAE：单次编码的帧数（默认: 64） |
+| `时间重叠` | INT | 是 | 4-4096 (步长: 4) | 仅用于视频 VAE：重叠的帧数（默认: 8） |
+
+**注意：** `temporal_size` 和 `temporal_overlap` 参数仅在使用视频 VAE 时相关，对标准图像 VAE 没有影响。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `LATENT` | LATENT | 输入图像经过编码后的潜在表示 |
diff --git a/zh-CN/built-in-nodes/VAELoader.mdx b/zh-CN/built-in-nodes/VAELoader.mdx
new file mode 100644
index 000000000..199c4f7a0
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAELoader.mdx
@@ -0,0 +1,26 @@
+---
+title: "VAELoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAELoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAELoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/vae` 文件夹下的模型，
+同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，
+有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+变分自编码器（VAE）加载节点专门用于加载变分自编码器模型，特别适用于处理标准和近似变分自编码器。它支持通过名称加载VAE，包括对 'taesd' 和 'taesdxl' 模型的专门处理，并根据VAE的特定配置动态调整。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `vae名称` | COMBO[STRING] | 指定要加载的VAE的名称。此参数决定了将获取和加载哪个VAE模型，支持一系列预定义的VAE名称，包括 'taesd' 和 'taesdxl'。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `vae` | VAE | 返回加载的VAE模型，准备进行进一步的操作，如编码或解码。输出是一个模型对象，封装了加载模型的状态。 |
+
+---
diff --git a/zh-CN/built-in-nodes/VAESave.mdx b/zh-CN/built-in-nodes/VAESave.mdx
new file mode 100644
index 000000000..3465d7637
--- /dev/null
+++ b/zh-CN/built-in-nodes/VAESave.mdx
@@ -0,0 +1,20 @@
+---
+title: "VAESave - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VAESave node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VAESave"
+icon: "circle"
+mode: wide
+---
+
+VAESave 节点旨在将变分自编码器（VAE）模型及其元数据（包括提示和附加的PNG信息）保存到指定的输出目录中。它封装了将模型状态和相关信息序列化到文件的功能，便于保存和共享训练好的模型。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+|----------|----------|------|
+| `vae`    | VAE      | 要保存的VAE模型。此参数至关重要，因为它代表了要序列化并存储状态的模型。 |
+| `文件名前缀` | STRING   | 用于保存模型及其元数据的文件名前缀。这允许有序存储和轻松检索模型。 |
+
+## 输出
+
+该节点没有输出类型。
diff --git a/zh-CN/built-in-nodes/VPScheduler.mdx b/zh-CN/built-in-nodes/VPScheduler.mdx
new file mode 100644
index 000000000..e57e63973
--- /dev/null
+++ b/zh-CN/built-in-nodes/VPScheduler.mdx
@@ -0,0 +1,24 @@
+---
+title: "VPScheduler - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VPScheduler node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VPScheduler"
+icon: "circle"
+mode: wide
+---
+
+方差保持调度器（VPScheduler）节点旨在基于方差保持（Variance Preserving, VP）调度方法生成一系列噪声水平（sigmas）。该序列对于引导扩散模型中的去噪过程至关重要，允许对图像或其他数据类型的生成进行控制。
+
+## 输入
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| `步数`    | `INT`    | 指定扩散过程中的步骤数，影响生成噪声水平的粒度。           |
+| `beta_d`   | `FLOAT`  | 确定整体噪声水平分布，影响生成噪声水平的方差。             |
+| `beta_min` | `FLOAT`  | 设置噪声水平的最小边界，确保噪声不会低于某个阈值。         |
+| `eps_s`    | `FLOAT`  | 调整起始的epsilon值，微调扩散过程中的初始噪声水平。       |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用                                                         |
+|----------|----------|--------------------------------------------------------------|
+| `sigmas` | `SIGMAS`| 基于VP调度方法生成的一系列噪声水平，用于引导扩散模型中的去噪过程。 |
diff --git a/zh-CN/built-in-nodes/Veo3FirstLastFrameNode.mdx b/zh-CN/built-in-nodes/Veo3FirstLastFrameNode.mdx
new file mode 100644
index 000000000..50c129581
--- /dev/null
+++ b/zh-CN/built-in-nodes/Veo3FirstLastFrameNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "Veo3FirstLastFrameNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Veo3FirstLastFrameNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Veo3FirstLastFrameNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3FirstLastFrameNode/zh.md)
+
+Veo3FirstLastFrameNode 使用 Google 的 Veo 3 模型来生成视频。它基于文本提示创建视频，并使用提供的第一帧和最后一帧来引导序列的开始和结束。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | N/A | 视频的文本描述（默认：空字符串）。 |
+| `negative_prompt` | STRING | 否 | N/A | 用于引导视频中应避免内容的负面文本提示（默认：空字符串）。 |
+| `resolution` | COMBO | 是 | `"720p"`<br />`"1080p"` | 输出视频的分辨率。 |
+| `aspect_ratio` | COMBO | 否 | `"16:9"`<br />`"9:16"` | 输出视频的宽高比（默认："16:9"）。 |
+| `duration` | INT | 否 | 4 到 8 | 输出视频的时长，单位为秒（默认：8）。 |
+| `seed` | INT | 否 | 0 到 4294967295 | 用于视频生成的随机种子（默认：0）。 |
+| `first_frame` | IMAGE | 是 | N/A | 视频的起始帧。 |
+| `last_frame` | IMAGE | 是 | N/A | 视频的结束帧。 |
+| `model` | COMBO | 否 | `"veo-3.1-generate"`<br />`"veo-3.1-fast-generate"` | 用于生成视频的特定 Veo 3 模型（默认："veo-3.1-fast-generate"）。 |
+| `generate_audio` | BOOLEAN | 否 | N/A | 是否为视频生成音频（默认：True）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/Veo3VideoGenerationNode.mdx b/zh-CN/built-in-nodes/Veo3VideoGenerationNode.mdx
new file mode 100644
index 000000000..871142a02
--- /dev/null
+++ b/zh-CN/built-in-nodes/Veo3VideoGenerationNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "Veo3VideoGenerationNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Veo3VideoGenerationNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Veo3VideoGenerationNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3VideoGenerationNode/zh.md)
+
+使用 Google 的 Veo 3 API 从文本提示生成视频。此节点支持两种 Veo 3 模型：veo-3.0-generate-001 和 veo-3.0-fast-generate-001。它扩展了基础 Veo 节点的功能，增加了 Veo 3 特有的特性，包括音频生成和固定的 8 秒时长。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 视频的文本描述（默认：""） |
+| `aspect_ratio` | COMBO | 是 | "16:9"<br />"9:16" | 输出视频的宽高比（默认："16:9"） |
+| `negative_prompt` | STRING | 否 | - | 负面文本提示，用于引导视频中应避免的内容（默认：""） |
+| `duration_seconds` | INT | 否 | 8-8 | 输出视频的时长（单位：秒）（Veo 3 仅支持 8 秒）（默认：8） |
+| `enhance_prompt` | BOOLEAN | 否 | - | 是否使用 AI 辅助增强提示（默认：True） |
+| `person_generation` | COMBO | 否 | "ALLOW"<br />"BLOCK" | 是否允许在视频中生成人物（默认："ALLOW"） |
+| `seed` | INT | 否 | 0-4294967295 | 视频生成的随机种子（0 表示随机）（默认：0） |
+| `image` | IMAGE | 否 | - | 用于引导视频生成的可选参考图像 |
+| `model` | COMBO | 否 | "veo-3.0-generate-001"<br />"veo-3.0-fast-generate-001" | 用于视频生成的 Veo 3 模型（默认："veo-3.0-generate-001"） |
+| `generate_audio` | BOOLEAN | 否 | - | 为视频生成音频。所有 Veo 3 模型均支持此功能。（默认：False） |
+
+**注意：** 对于所有 Veo 3 模型，`duration_seconds` 参数固定为 8 秒且无法更改。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/VeoVideoGenerationNode.mdx b/zh-CN/built-in-nodes/VeoVideoGenerationNode.mdx
new file mode 100644
index 000000000..d45b3678b
--- /dev/null
+++ b/zh-CN/built-in-nodes/VeoVideoGenerationNode.mdx
@@ -0,0 +1,32 @@
+---
+title: "VeoVideoGenerationNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VeoVideoGenerationNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VeoVideoGenerationNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VeoVideoGenerationNode/zh.md)
+
+使用 Google 的 Veo API 从文本提示生成视频。此节点可以根据文本描述和可选的图像输入创建视频，并支持控制宽高比、时长等参数。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `prompt` | STRING | 是 | - | 视频的文本描述（默认：空） |
+| `aspect_ratio` | COMBO | 是 | "16:9"<br />"9:16" | 输出视频的宽高比（默认："16:9"） |
+| `negative_prompt` | STRING | 否 | - | 负面文本提示，用于引导视频中应避免的内容（默认：空） |
+| `duration_seconds` | INT | 否 | 5-8 | 输出视频的时长（单位：秒）（默认：5） |
+| `enhance_prompt` | BOOLEAN | 否 | - | 是否使用 AI 辅助增强提示词（默认：True） |
+| `person_generation` | COMBO | 否 | "ALLOW"<br />"BLOCK" | 是否允许在视频中生成人物（默认："ALLOW"） |
+| `seed` | INT | 否 | 0-4294967295 | 视频生成的随机种子（0 表示随机）（默认：0） |
+| `image` | IMAGE | 否 | - | 用于引导视频生成的可选参考图像 |
+| `model` | COMBO | 否 | "veo-2.0-generate-001" | 用于视频生成的 Veo 2 模型（默认："veo-2.0-generate-001"） |
+
+**注意：** `generate_audio` 参数仅适用于 Veo 3.0 模型，节点会根据所选模型自动处理该参数。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/Video Slice.mdx b/zh-CN/built-in-nodes/Video Slice.mdx
new file mode 100644
index 000000000..e100b628a
--- /dev/null
+++ b/zh-CN/built-in-nodes/Video Slice.mdx	
@@ -0,0 +1,25 @@
+---
+title: "Video Slice - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Video Slice node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Video Slice"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Video%20Slice/zh.md)
+
+Video Slice 节点允许您从视频中提取特定片段。您可以定义起始时间和持续时间来裁剪视频，或直接跳过开头的帧。如果请求的持续时间超过剩余视频长度，该节点可以返回可用部分或引发错误。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | 是 | - | 待裁剪的输入视频。 |
+| `start_time` | FLOAT | 否 | -1e5 到 1e5 | 开始裁剪的起始时间（单位：秒）。负值将从视频开头跳过相应帧数。（默认值：0.0） |
+| `duration` | FLOAT | 否 | 0.0 及以上 | 裁剪片段的长度（单位：秒）。值为 0.0 表示节点将返回从起始时间到视频结尾的所有内容。（默认值：0.0） |
+| `strict_duration` | BOOLEAN | 否 | - | 若设为 True，当无法满足请求的持续时间（例如，裁剪范围超出视频结尾）时，节点将引发错误。若为 False，则返回直到视频结尾的可用部分。（默认值：False） |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 裁剪后的视频片段。 |
diff --git a/zh-CN/built-in-nodes/VideoLinearCFGGuidance.mdx b/zh-CN/built-in-nodes/VideoLinearCFGGuidance.mdx
new file mode 100644
index 000000000..4f8463ebc
--- /dev/null
+++ b/zh-CN/built-in-nodes/VideoLinearCFGGuidance.mdx
@@ -0,0 +1,22 @@
+---
+title: "VideoLinearCFGGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VideoLinearCFGGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VideoLinearCFGGuidance"
+icon: "circle"
+mode: wide
+---
+
+这个节点在 ComfyUI 中的作用是稍微改善视频模型的采样过程。它通过在不同帧之间线性缩放 cfg 参数来实现这一点。具体来说，远离初始帧的帧会逐渐获得更高的 cfg 值，从而使得视频的后续帧与初始帧相比，会有更明显的视觉效果变化。这种方法有助于生成更加流畅和动态的视频内容
+
+## Input 输入
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| model      | MODEL    | 应用线性CFG引导的视频模型，定义基础模型并用引导比例尺修改。 |
+| min_cfg    | FLOAT    | 指定线性比例尺调整的最小条件引导比例尺，影响模型输出的下限。 |
+
+## Output 输出
+
+| 参数名称   | 数据类型 | 作用                                                         |
+|------------|----------|--------------------------------------------------------------|
+| model      | MODEL    | 输出修改后的模型，应用了线性CFG引导比例尺，可生成不同条件化程度的输出。 |
diff --git a/zh-CN/built-in-nodes/VideoTriangleCFGGuidance.mdx b/zh-CN/built-in-nodes/VideoTriangleCFGGuidance.mdx
new file mode 100644
index 000000000..f96b80107
--- /dev/null
+++ b/zh-CN/built-in-nodes/VideoTriangleCFGGuidance.mdx
@@ -0,0 +1,25 @@
+---
+title: "VideoTriangleCFGGuidance - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VideoTriangleCFGGuidance node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VideoTriangleCFGGuidance"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VideoTriangleCFGGuidance/zh.md)
+
+## 概述
+
+VideoTriangleCFGGuidance 节点对视频模型应用三角形无分类器引导缩放模式。它使用在最小 CFG 值和原始条件缩放值之间振荡的三角波函数，随时间调整条件缩放比例。这种动态引导模式有助于提升视频生成的一致性和质量。
+
+## 输入
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `模型` | MODEL | 是 | - | 要应用三角形 CFG 引导的视频模型 |
+| `最小配置` | FLOAT | 是 | 0.0 - 100.0 | 三角形模式的最小 CFG 缩放值（默认值：1.0） |
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `模型` | MODEL | 应用了三角形 CFG 引导的修改后模型 |
diff --git a/zh-CN/built-in-nodes/Vidu2ImageToVideoNode.mdx b/zh-CN/built-in-nodes/Vidu2ImageToVideoNode.mdx
new file mode 100644
index 000000000..429fa38d9
--- /dev/null
+++ b/zh-CN/built-in-nodes/Vidu2ImageToVideoNode.mdx
@@ -0,0 +1,34 @@
+---
+title: "Vidu2ImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu2ImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu2ImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2ImageToVideoNode/zh.md)
+
+Vidu2 图像转视频生成节点能够从单张输入图像开始创建视频序列。它使用指定的 Vidu2 模型，根据可选的文本提示对场景进行动画处理，并控制视频的长度、分辨率和运动强度。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"viduq2-pro-fast"`<br />`"viduq2-pro"`<br />`"viduq2-turbo"` | 用于视频生成的 Vidu2 模型。不同模型在速度和质量之间有不同的权衡。 |
+| `image` | IMAGE | 是 | - | 用作生成视频起始帧的图像。仅允许输入一张图像。 |
+| `prompt` | STRING | 否 | - | 用于视频生成的可选文本提示（最多 2000 个字符）。默认为空字符串。 |
+| `duration` | INT | 是 | 1 到 10 | 生成视频的长度，单位为秒。默认为 5。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于随机数生成的种子值，以确保结果可复现。默认为 1。 |
+| `resolution` | COMBO | 是 | `"720p"`<br />`"1080p"` | 生成视频的输出分辨率。 |
+| `movement_amplitude` | COMBO | 是 | `"auto"`<br />`"small"`<br />`"medium"`<br />`"large"` | 画面中物体的运动幅度。 |
+
+**约束条件：**
+
+* `image` 输入必须恰好包含一张图像。
+* 输入图像的宽高比必须在 1:4 到 4:1 之间。
+* `prompt` 文本最多限制为 2000 个字符。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/Vidu2ReferenceVideoNode.mdx b/zh-CN/built-in-nodes/Vidu2ReferenceVideoNode.mdx
new file mode 100644
index 000000000..3979f6369
--- /dev/null
+++ b/zh-CN/built-in-nodes/Vidu2ReferenceVideoNode.mdx
@@ -0,0 +1,38 @@
+---
+title: "Vidu2ReferenceVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu2ReferenceVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu2ReferenceVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2ReferenceVideoNode/zh.md)
+
+Vidu2 参考视频生成节点可根据文本提示词和多张参考图像创建视频。您可以定义最多七个主体，每个主体可提供一组参考图像，并在提示词中使用 `@subject{subject_id}` 来引用它们。该节点可生成时长、宽高比和运动幅度均可配置的视频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"viduq2"` | 用于视频生成的 AI 模型。 |
+| `subjects` | AUTOGROW | 是 | N/A | 为每个主体提供最多 3 张参考图像（所有主体的图像总数不超过 7 张）。在提示词中通过 `@subject{subject_id}` 引用它们。 |
+| `prompt` | STRING | 是 | N/A | 用于指导视频生成的文本描述。当启用 `audio` 参数时，视频将包含基于此提示词生成的语音和背景音乐。 |
+| `audio` | BOOLEAN | 否 | N/A | 启用后，视频将包含基于提示词生成的语音和背景音乐（默认值：`False`）。 |
+| `duration` | INT | 否 | 1 到 10 | 生成视频的时长，单位为秒（默认值：`5`）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于控制生成随机性的数字，以获得可重现的结果（默认值：`1`）。 |
+| `aspect_ratio` | COMBO | 否 | `"16:9"`<br />`"9:16"`<br />`"4:3"`<br />`"3:4"`<br />`"1:1"` | 视频画面的宽高比。 |
+| `resolution` | COMBO | 否 | `"720p"`<br />`"1080p"` | 输出视频的像素分辨率。 |
+| `movement_amplitude` | COMBO | 否 | `"auto"`<br />`"small"`<br />`"medium"`<br />`"large"` | 控制画面中物体的运动幅度。 |
+
+**约束条件：**
+
+* `prompt` 的长度必须在 1 到 2000 个字符之间。
+* 可以定义多个主体，但所有主体的参考图像总数不得超过 7 张。
+* 每个主体最多只能有 3 张参考图像。
+* 每张参考图像的宽高比必须在 1:4 到 4:1 之间。
+* 每张参考图像的宽度和高度都必须至少为 128 像素。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/Vidu2StartEndToVideoNode.mdx b/zh-CN/built-in-nodes/Vidu2StartEndToVideoNode.mdx
new file mode 100644
index 000000000..3c427334d
--- /dev/null
+++ b/zh-CN/built-in-nodes/Vidu2StartEndToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "Vidu2StartEndToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu2StartEndToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu2StartEndToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2StartEndToVideoNode/zh.md)
+
+此节点通过在提供的起始帧和结束帧之间进行插值，并依据文本提示的引导来生成视频。它使用指定的 Vidu 模型，在设定的持续时间内创建两幅图像之间的平滑过渡。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"viduq2-pro-fast"`<br />`"viduq2-pro"`<br />`"viduq2-turbo"` | 用于视频生成的 Vidu 模型。 |
+| `first_frame` | IMAGE | 是 | - | 视频序列的起始图像。仅允许单张图像。 |
+| `end_frame` | IMAGE | 是 | - | 视频序列的结束图像。仅允许单张图像。 |
+| `prompt` | STRING | 是 | - | 引导视频生成的文本描述（最多 2000 个字符）。 |
+| `duration` | INT | 否 | 2 到 8 | 生成视频的时长，单位为秒（默认值：5）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于初始化随机生成过程的种子值，以确保结果可复现（默认值：1）。 |
+| `resolution` | COMBO | 否 | `"720p"`<br />`"1080p"` | 生成视频的输出分辨率。 |
+| `movement_amplitude` | COMBO | 否 | `"auto"`<br />`"small"`<br />`"medium"`<br />`"large"` | 画面中物体的运动幅度。 |
+
+**注意：** `first_frame` 和 `end_frame` 图像必须具有相似的长宽比。节点会验证它们的长宽比是否在 0.8 到 1.25 的相对范围内。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/Vidu2TextToVideoNode.mdx b/zh-CN/built-in-nodes/Vidu2TextToVideoNode.mdx
new file mode 100644
index 000000000..090e259ce
--- /dev/null
+++ b/zh-CN/built-in-nodes/Vidu2TextToVideoNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "Vidu2TextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu2TextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu2TextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2TextToVideoNode/zh.md)
+
+Vidu2 文本转视频生成节点可根据文本描述创建视频。它连接到外部 API，根据您的提示生成视频内容，允许您控制视频的时长、视觉风格和格式。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"viduq2"` | 用于视频生成的 AI 模型。目前仅有一个模型可用。 |
+| `prompt` | STRING | 是 | - | 用于视频生成的文本描述，最大长度为 2000 个字符。 |
+| `duration` | INT | 否 | 1 到 10 | 生成视频的时长，单位为秒。可通过滑块调整该值（默认值：5）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于控制生成随机性的数字，可实现可复现的结果。可在生成后进行控制（默认值：1）。 |
+| `aspect_ratio` | COMBO | 否 | `"16:9"`<br />`"9:16"`<br />`"3:4"`<br />`"4:3"`<br />`"1:1"` | 视频宽度与高度的比例关系。 |
+| `resolution` | COMBO | 否 | `"720p"`<br />`"1080p"` | 生成视频的像素尺寸。 |
+| `background_music` | BOOLEAN | 否 | - | 是否为生成的视频添加背景音乐（默认值：False）。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/Vidu3ImageToVideoNode.mdx b/zh-CN/built-in-nodes/Vidu3ImageToVideoNode.mdx
new file mode 100644
index 000000000..c0dad6931
--- /dev/null
+++ b/zh-CN/built-in-nodes/Vidu3ImageToVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "Vidu3ImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu3ImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu3ImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3ImageToVideoNode/zh.md)
+
+Vidu Q3 图像转视频生成节点可从输入图像开始创建视频序列。它使用 Vidu Q3 Pro 模型为图像添加动画效果，并可选择性地通过文本提示进行引导，最终输出一个视频文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"viduq3-pro"` | 用于视频生成的模型。 |
+| `model.resolution` | COMBO | 是 | `"720p"`<br />`"1080p"`<br />`"2K"` | 输出视频的分辨率。 |
+| `model.duration` | INT | 是 | 1 到 16 | 输出视频的时长（单位：秒）（默认值：5）。 |
+| `model.audio` | BOOLEAN | 是 | `True` / `False` | 启用后，输出带声音（包括对话和音效）的视频（默认值：False）。 |
+| `image` | IMAGE | 是 | - | 用作生成视频起始帧的图像。 |
+| `prompt` | STRING | 否 | - | 用于视频生成的可选文本提示（最多 2000 个字符）（默认值：空）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于控制生成随机性的种子值（默认值：1）。 |
+
+**注意：** `image` 的宽高比必须在 1:4 到 4:1 之间（从竖屏到横屏）。`prompt` 是可选的，但不能超过 2000 个字符。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/Vidu3StartEndToVideoNode.mdx b/zh-CN/built-in-nodes/Vidu3StartEndToVideoNode.mdx
new file mode 100644
index 000000000..28f9db24f
--- /dev/null
+++ b/zh-CN/built-in-nodes/Vidu3StartEndToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "Vidu3StartEndToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu3StartEndToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu3StartEndToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3StartEndToVideoNode/zh.md)
+
+此节点通过在一个提供的起始帧和一个结束帧之间进行插值，并在文本提示的引导下生成视频。它使用 Vidu Q3 模型在两个图像之间创建无缝过渡，生成指定时长和分辨率的视频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"viduq3-pro"`<br />`"viduq3-turbo"` | 用于视频生成的模型。选择一个选项后会显示 `resolution`、`duration` 和 `audio` 的额外配置参数。 |
+| `model.resolution` | COMBO | 是 | `"720p"`<br />`"1080p"` | 输出视频的分辨率。此参数在选择 `model` 后显示。 |
+| `model.duration` | INT | 是 | 1 到 16 | 输出视频的时长，单位为秒（默认值：5）。此参数在选择 `model` 后显示。 |
+| `model.audio` | BOOLEAN | 是 | `True` / `False` | 启用时，输出带声音（包括对话和音效）的视频（默认值：False）。此参数在选择 `model` 后显示。 |
+| `first_frame` | IMAGE | 是 | - | 视频序列的起始图像。 |
+| `end_frame` | IMAGE | 是 | - | 视频序列的结束图像。 |
+| `prompt` | STRING | 是 | - | 指导视频生成的文本描述（最多 2000 个字符）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于控制生成随机性的种子值（默认值：1）。 |
+
+**注意：** 为获得最佳效果，`first_frame` 和 `end_frame` 图像应具有相似的长宽比。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/Vidu3TextToVideoNode.mdx b/zh-CN/built-in-nodes/Vidu3TextToVideoNode.mdx
new file mode 100644
index 000000000..3d0ebd104
--- /dev/null
+++ b/zh-CN/built-in-nodes/Vidu3TextToVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "Vidu3TextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Vidu3TextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Vidu3TextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3TextToVideoNode/zh.md)
+
+Vidu Q3 文生视频节点可根据文本描述生成视频。它使用 Vidu Q3 Pro 模型，基于您的提示词生成视频内容，并允许您控制视频的长度、分辨率和宽高比。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"viduq3-pro"` | 用于视频生成的模型。选择此选项将显示宽高比、分辨率、时长和音频等额外配置参数。 |
+| `model.aspect_ratio` | COMBO | 是* | `"16:9"`<br />`"9:16"`<br />`"3:4"`<br />`"4:3"`<br />`"1:1"` | 输出视频的宽高比。此参数在选择 `model` 后显示。 |
+| `model.resolution` | COMBO | 是* | `"720p"`<br />`"1080p"` | 输出视频的分辨率。此参数在选择 `model` 后显示。 |
+| `model.duration` | INT | 是* | 1 到 16 | 输出视频的时长（单位：秒，默认值：5）。此参数在选择 `model` 后显示。 |
+| `model.audio` | BOOLEAN | 是* | True/False | 启用后，输出带声音（包括对话和音效）的视频（默认值：False）。此参数在选择 `model` 后显示。 |
+| `prompt` | STRING | 是 | N/A | 用于视频生成的文本描述，最大长度为 2000 个字符。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于控制生成随机性的种子值（默认值：1）。 |
+
+*注意：一旦选择了 `model`，参数 `aspect_ratio`、`resolution`、`duration` 和 `audio` 即为必填项，因为它们是模型配置的一部分。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `video` | VIDEO | 生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/ViduExtendVideoNode.mdx b/zh-CN/built-in-nodes/ViduExtendVideoNode.mdx
new file mode 100644
index 000000000..25b0983d7
--- /dev/null
+++ b/zh-CN/built-in-nodes/ViduExtendVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "ViduExtendVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduExtendVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduExtendVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduExtendVideoNode/zh.md)
+
+ViduExtendVideoNode 可生成额外的帧以延长现有视频的长度。它使用指定的 AI 模型，基于源视频和可选的文本提示，创建无缝的延续内容。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"viduq2-pro"`<br />`"viduq2-turbo"` | 用于视频延展的 AI 模型。选择模型后会显示其特定的时长和分辨率设置。 |
+| `model.duration` | INT | 是 | 1 到 7 | 延展后视频的时长（单位：秒，默认值：4）。此设置在选择模型后出现。 |
+| `model.resolution` | COMBO | 是 | `"720p"`<br />`"1080p"` | 输出视频的分辨率。此设置在选择模型后出现。 |
+| `video` | VIDEO | 是 | - | 需要延展的源视频。 |
+| `prompt` | STRING | 否 | - | 用于引导延展视频内容的可选文本提示（最多 2000 个字符，默认值：空）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于控制生成随机性的种子值（默认值：1）。 |
+| `end_frame` | IMAGE | 否 | - | 用作延展目标结束帧的可选图像。如果提供，其宽高比必须在 1:4 到 4:1 之间，且尺寸至少为 128x128 像素。 |
+
+**注意：** 源 `video` 的时长必须在 4 到 55 秒之间。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 包含延展片段的新生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/ViduImageToVideoNode.mdx b/zh-CN/built-in-nodes/ViduImageToVideoNode.mdx
new file mode 100644
index 000000000..02fde164f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ViduImageToVideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "ViduImageToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduImageToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduImageToVideoNode/zh.md)
+
+Vidu 图像转视频生成节点可根据起始图像和可选的文本描述创建视频。它使用 AI 模型从提供的图像帧开始生成视频内容。该节点将图像和参数发送到外部服务，并返回生成的视频。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `vidu_q1`<br />*其他 VideoModelName 选项* | 模型名称（默认值：vidu_q1） |
+| `image` | IMAGE | 是 | - | 用作生成视频起始帧的图像 |
+| `prompt` | STRING | 否 | - | 用于视频生成的文本描述（默认值：空） |
+| `duration` | INT | 否 | 5-5 | 输出视频的时长（单位：秒）（默认值：5，固定为 5 秒） |
+| `seed` | INT | 否 | 0-2147483647 | 视频生成的随机种子（0 表示随机）（默认值：0） |
+| `resolution` | COMBO | 否 | `r_1080p`<br />*其他 Resolution 选项* | 支持的取值可能因模型和时长而异（默认值：r_1080p） |
+| `movement_amplitude` | COMBO | 否 | `auto`<br />*其他 MovementAmplitude 选项* | 画面中物体的运动幅度（默认值：auto） |
+
+**约束条件：**
+
+- 仅允许输入单张图像（无法处理多张图像）
+- 输入图像的宽高比必须在 1:4 到 4:1 之间
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频输出 |
diff --git a/zh-CN/built-in-nodes/ViduMultiFrameVideoNode.mdx b/zh-CN/built-in-nodes/ViduMultiFrameVideoNode.mdx
new file mode 100644
index 000000000..16b1b6725
--- /dev/null
+++ b/zh-CN/built-in-nodes/ViduMultiFrameVideoNode.mdx
@@ -0,0 +1,33 @@
+---
+title: "ViduMultiFrameVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduMultiFrameVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduMultiFrameVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduMultiFrameVideoNode/zh.md)
+
+此节点通过在多个关键帧之间创建过渡来生成视频。它从初始图像开始，通过一系列用户定义的结束图像和提示词进行动画处理，最终输出单个视频文件。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+| :--- | :--- | :--- | :--- | :--- |
+| `model` | COMBO | 是 | `"viduq2-pro"`<br />`"viduq2-turbo"` | 用于视频生成的 Vidu 模型。 |
+| `start_image` | IMAGE | 是 | - | 起始帧图像。宽高比必须在 1:4 到 4:1 之间。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于随机数生成的种子值，以确保结果可复现（默认值：1）。 |
+| `resolution` | COMBO | 是 | `"720p"`<br />`"1080p"` | 输出视频的分辨率。 |
+| `frames` | DYNAMICCOMBO | 是 | `"2"`<br />`"3"`<br />`"4"`<br />`"5"`<br />`"6"`<br />`"7"`<br />`"8"`<br />`"9"` | 关键帧过渡的数量（2-9）。选择一个值会动态显示每个帧所需的输入参数。 |
+
+**帧输入参数（动态显示）：**
+当您为 `frames` 选择一个值（例如 "3"）时，节点将显示每个过渡对应的一组必需输入参数。对于从 1 到所选数量的每个帧 `i`，您必须提供：
+
+* `end_image{i}` (IMAGE)：此过渡的目标图像。宽高比必须在 1:4 到 4:1 之间。
+* `prompt{i}` (STRING)：指导过渡到此帧的文本描述（最多 2000 个字符）。
+* `duration{i}` (INT)：此特定过渡片段的持续时间（以秒为单位）。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+| :--- | :--- | :--- |
+| `output` | VIDEO | 生成的包含所有动画过渡的视频文件。 |
diff --git a/zh-CN/built-in-nodes/ViduReferenceVideoNode.mdx b/zh-CN/built-in-nodes/ViduReferenceVideoNode.mdx
new file mode 100644
index 000000000..30ab8f66f
--- /dev/null
+++ b/zh-CN/built-in-nodes/ViduReferenceVideoNode.mdx
@@ -0,0 +1,37 @@
+---
+title: "ViduReferenceVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduReferenceVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduReferenceVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduReferenceVideoNode/zh.md)
+
+Vidu 参考视频节点可根据多张参考图像和文本提示生成视频。该节点利用 AI 模型，基于提供的图像和描述创建具有一致性的视频内容。支持多种视频设置，包括时长、宽高比、分辨率及运动控制。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|--------|-----------|------|----------|------|
+| `model` | COMBO | 是 | `"vidu_q1"` | 用于视频生成的模型名称（默认值："vidu_q1"） |
+| `images` | IMAGE | 是 | - | 用作参考的图像，用于生成具有一致主体的视频（最多 7 张图像） |
+| `prompt` | STRING | 是 | - | 用于视频生成的文本描述 |
+| `duration` | INT | 否 | 5-5 | 输出视频的时长（单位：秒）（默认值：5） |
+| `seed` | INT | 否 | 0-2147483647 | 视频生成的随机种子（0 表示随机）（默认值：0） |
+| `aspect_ratio` | COMBO | 否 | `"16:9"`<br />`"9:16"`<br />`"1:1"`<br />`"4:3"`<br />`"3:4"`<br />`"21:9"`<br />`"9:21"` | 输出视频的宽高比（默认值："16:9"） |
+| `resolution` | COMBO | 否 | `"480p"`<br />`"720p"`<br />`"1080p"`<br />`"1440p"`<br />`"2160p"` | 支持的值可能因模型和时长而异（默认值："1080p"） |
+| `movement_amplitude` | COMBO | 否 | `"auto"`<br />`"low"`<br />`"medium"`<br />`"high"` | 画面中物体的运动幅度（默认值："auto"） |
+
+**约束与限制：**
+
+- `prompt` 字段为必填项，不能为空
+- 最多允许使用 7 张参考图像
+- 每张图像的宽高比必须在 1:4 到 4:1 之间
+- 每张图像的最小尺寸必须为 128x128 像素
+- 视频时长固定为 5 秒
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `output` | VIDEO | 基于参考图像和提示生成的视频 |
diff --git a/zh-CN/built-in-nodes/ViduStartEndToVideoNode.mdx b/zh-CN/built-in-nodes/ViduStartEndToVideoNode.mdx
new file mode 100644
index 000000000..0702a4375
--- /dev/null
+++ b/zh-CN/built-in-nodes/ViduStartEndToVideoNode.mdx
@@ -0,0 +1,31 @@
+---
+title: "ViduStartEndToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduStartEndToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduStartEndToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduStartEndToVideoNode/zh.md)
+
+Vidu Start End To Video Generation 节点通过在起始帧和结束帧之间生成帧来创建视频。它使用文本提示来指导视频生成过程，并支持具有不同分辨率和运动设置的各种视频模型。该节点在处理前会验证起始帧和结束帧是否具有兼容的宽高比。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 是否必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"vidu_q1"`<br />[VideoModelName 枚举中的其他模型值] | 模型名称（默认值："vidu_q1"） |
+| `first_frame` | IMAGE | 是 | - | 起始帧 |
+| `end_frame` | IMAGE | 是 | - | 结束帧 |
+| `prompt` | STRING | 否 | - | 用于视频生成的文本描述 |
+| `duration` | INT | 否 | 5-5 | 输出视频的时长（单位：秒）（默认值：5，固定为5秒） |
+| `seed` | INT | 否 | 0-2147483647 | 视频生成的随机种子（0表示随机）（默认值：0） |
+| `resolution` | COMBO | 否 | `"1080p"`<br />[Resolution 枚举中的其他分辨率值] | 支持的值可能因模型和时长而异（默认值："1080p"） |
+| `movement_amplitude` | COMBO | 否 | `"auto"`<br />[MovementAmplitude 枚举中的其他运动幅度值] | 画面中物体的运动幅度（默认值："auto"） |
+
+**注意：** 起始帧和结束帧必须具有兼容的宽高比（使用 min_rel=0.8, max_rel=1.25 的比率容差进行验证）。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 生成的视频文件 |
diff --git a/zh-CN/built-in-nodes/ViduTextToVideoNode.mdx b/zh-CN/built-in-nodes/ViduTextToVideoNode.mdx
new file mode 100644
index 000000000..f847cf1e0
--- /dev/null
+++ b/zh-CN/built-in-nodes/ViduTextToVideoNode.mdx
@@ -0,0 +1,30 @@
+---
+title: "ViduTextToVideoNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ViduTextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ViduTextToVideoNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduTextToVideoNode/zh.md)
+
+Vidu 文本转视频生成节点能够根据文本描述创建视频。它使用多种视频生成模型，将您的文本提示转换为视频内容，并提供可自定义的时长、宽高比和视觉风格设置。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `vidu_q1`<br />*其他 VideoModelName 选项* | 模型名称（默认值：vidu_q1） |
+| `prompt` | STRING | 是 | - | 用于视频生成的文本描述 |
+| `duration` | INT | 否 | 5-5 | 输出视频的时长（单位：秒）（默认值：5） |
+| `seed` | INT | 否 | 0-2147483647 | 视频生成的随机种子（0 表示随机）（默认值：0） |
+| `aspect_ratio` | COMBO | 否 | `r_16_9`<br />*其他 AspectRatio 选项* | 输出视频的宽高比（默认值：r_16_9） |
+| `resolution` | COMBO | 否 | `r_1080p`<br />*其他 Resolution 选项* | 支持的数值可能因模型和时长而异（默认值：r_1080p） |
+| `movement_amplitude` | COMBO | 否 | `auto`<br />*其他 MovementAmplitude 选项* | 画面中物体的运动幅度（默认值：auto） |
+
+**注意：** `prompt` 字段为必填项且不能为空。`duration` 参数当前固定为 5 秒。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 基于文本提示生成的视频 |
diff --git a/zh-CN/built-in-nodes/VoxelToMesh.mdx b/zh-CN/built-in-nodes/VoxelToMesh.mdx
new file mode 100644
index 000000000..b374a841c
--- /dev/null
+++ b/zh-CN/built-in-nodes/VoxelToMesh.mdx
@@ -0,0 +1,24 @@
+---
+title: "VoxelToMesh - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VoxelToMesh node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VoxelToMesh"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VoxelToMesh/zh.md)
+
+VoxelToMesh 节点使用不同算法将三维体素数据转换为网格几何体。该节点处理体素网格并生成构成三维网格表示的顶点和面。该节点支持多种转换算法，并允许调整阈值以控制表面提取。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `voxel` | VOXEL | 是 | - | 要转换为网格几何体的输入体素数据 |
+| `算法` | COMBO | 是 | "surface net"<br />"basic" | 用于从体素数据转换网格的算法 |
+| `阈值` | FLOAT | 是 | -1.0 到 1.0 | 表面提取的阈值（默认值：0.6） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `MESH` | MESH | 生成的包含顶点和面的三维网格 |
diff --git a/zh-CN/built-in-nodes/VoxelToMeshBasic.mdx b/zh-CN/built-in-nodes/VoxelToMeshBasic.mdx
new file mode 100644
index 000000000..0a925f1d0
--- /dev/null
+++ b/zh-CN/built-in-nodes/VoxelToMeshBasic.mdx
@@ -0,0 +1,23 @@
+---
+title: "VoxelToMeshBasic - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the VoxelToMeshBasic node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "VoxelToMeshBasic"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VoxelToMeshBasic/zh.md)
+
+VoxelToMeshBasic 节点可将三维体素数据转换为网格几何体。该节点通过应用阈值来处理体素体积，以确定体积的哪些部分在生成的网格中成为实体表面。该节点输出包含顶点和面的完整网格结构，可用于三维渲染和建模。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `体素` | VOXEL | 是 | - | 要转换为网格的三维体素数据 |
+| `阈值` | FLOAT | 是 | -1.0 到 1.0 | 用于确定哪些体素成为网格表面部分的阈值（默认值：0.6） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `MESH` | MESH | 生成的包含顶点和面的三维网格 |
diff --git a/zh-CN/built-in-nodes/Wan22FunControlToVideo.mdx b/zh-CN/built-in-nodes/Wan22FunControlToVideo.mdx
new file mode 100644
index 000000000..71fbf2fa9
--- /dev/null
+++ b/zh-CN/built-in-nodes/Wan22FunControlToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "Wan22FunControlToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Wan22FunControlToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Wan22FunControlToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22FunControlToVideo/zh.md)
+
+Wan22FunControlToVideo 节点使用 Wan 视频模型架构为视频生成准备条件输入和潜在表示。该节点处理正向和负向条件输入，以及可选的参考图像和控制视频，以创建视频合成所需的潜在空间表示。该节点处理空间缩放和时间维度，为视频模型生成适当的条件数据。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 用于引导视频生成的正向条件输入 |
+| `negative` | CONDITIONING | 是 | - | 用于引导视频生成的负向条件输入 |
+| `vae` | VAE | 是 | - | 用于将图像编码到潜在空间的 VAE 模型 |
+| `width` | INT | 否 | 16 到 MAX_RESOLUTION | 输出视频宽度（像素）（默认：832，步长：16） |
+| `height` | INT | 否 | 16 到 MAX_RESOLUTION | 输出视频高度（像素）（默认：480，步长：16） |
+| `length` | INT | 否 | 1 到 MAX_RESOLUTION | 视频序列中的帧数（默认：81，步长：4） |
+| `batch_size` | INT | 否 | 1 到 4096 | 要生成的视频序列数量（默认：1） |
+| `ref_image` | IMAGE | 否 | - | 用于提供视觉引导的可选参考图像 |
+| `control_video` | IMAGE | 否 | - | 用于引导生成过程的可选控制视频 |
+
+**注意：** `length` 参数按 4 帧的块进行处理，节点会自动处理潜在空间的时间缩放。当提供 `ref_image` 时，它会通过参考潜在表示影响条件输入。当提供 `control_video` 时，它会直接影响条件输入中使用的拼接潜在表示。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 包含视频特定潜在数据的修改后正向条件输入 |
+| `negative` | CONDITIONING | 包含视频特定潜在数据的修改后负向条件输入 |
+| `latent` | LATENT | 具有适当视频生成维度的空潜在张量 |
diff --git a/zh-CN/built-in-nodes/Wan22ImageToVideoLatent.mdx b/zh-CN/built-in-nodes/Wan22ImageToVideoLatent.mdx
new file mode 100644
index 000000000..9f5d7b8b5
--- /dev/null
+++ b/zh-CN/built-in-nodes/Wan22ImageToVideoLatent.mdx
@@ -0,0 +1,30 @@
+---
+title: "Wan22ImageToVideoLatent - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the Wan22ImageToVideoLatent node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "Wan22ImageToVideoLatent"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22ImageToVideoLatent/zh.md)
+
+Wan22ImageToVideoLatent 节点可从图像创建视频潜空间表示。它会生成具有指定尺寸的空白视频潜空间，并可选择性地将起始图像序列编码到起始帧中。当提供起始图像时，节点会将图像编码到潜空间中，并为修复区域创建相应的噪声遮罩。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `vae` | VAE | 是 | - | 用于将图像编码到潜空间的 VAE 模型 |
+| `width` | INT | 否 | 32 至 MAX_RESOLUTION | 输出视频的宽度（单位：像素，默认值：1280，步长：32） |
+| `height` | INT | 否 | 32 至 MAX_RESOLUTION | 输出视频的高度（单位：像素，默认值：704，步长：32） |
+| `length` | INT | 否 | 1 至 MAX_RESOLUTION | 视频序列的帧数（默认值：49，步长：4） |
+| `batch_size` | INT | 否 | 1 至 4096 | 要生成的批次数量（默认值：1） |
+| `start_image` | IMAGE | 否 | - | 可选的起始图像序列，将被编码到视频潜空间中 |
+
+**注意：** 当提供 `start_image` 时，节点会将图像序列编码到潜空间的起始帧，并生成相应的噪声遮罩。宽度和高度参数必须能被 16 整除，以确保正确的潜空间维度。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `samples` | LATENT | 生成的视频潜空间表示 |
+| `noise_mask` | LATENT | 指示在生成过程中应对哪些区域进行去噪的噪声遮罩 |
diff --git a/zh-CN/built-in-nodes/WanAnimateToVideo.mdx b/zh-CN/built-in-nodes/WanAnimateToVideo.mdx
new file mode 100644
index 000000000..d5e7a6cc9
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanAnimateToVideo.mdx
@@ -0,0 +1,51 @@
+---
+title: "WanAnimateToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanAnimateToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanAnimateToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanAnimateToVideo/zh.md)
+
+WanAnimateToVideo 节点通过结合包括姿态参考、面部表情和背景元素在内的多重条件输入来生成视频内容。它处理各种视频输入以创建连贯的动画序列，同时保持帧间的时间一致性。该节点处理潜在空间操作，并可通过延续运动模式来扩展现有视频。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 用于引导生成期望内容的正向条件输入 |
+| `negative` | CONDITIONING | 是 | - | 用于避免生成不需要内容的负向条件输入 |
+| `vae` | VAE | 是 | - | 用于编码和解码图像数据的 VAE 模型 |
+| `width` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频宽度（像素）（默认：832，步长：16） |
+| `height` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频高度（像素）（默认：480，步长：16） |
+| `length` | INT | 否 | 1 至 MAX_RESOLUTION | 要生成的帧数（默认：77，步长：4） |
+| `batch_size` | INT | 否 | 1 至 4096 | 同时生成的视频数量（默认：1） |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | 否 | - | 用于附加条件输入的 CLIP 视觉模型输出（可选） |
+| `reference_image` | IMAGE | 否 | - | 用作生成起点的参考图像 |
+| `face_video` | IMAGE | 否 | - | 提供面部表情指导的视频输入 |
+| `pose_video` | IMAGE | 否 | - | 提供姿态和运动指导的视频输入 |
+| `continue_motion_max_frames` | INT | 否 | 1 至 MAX_RESOLUTION | 从先前运动延续的最大帧数（默认：5，步长：4） |
+| `background_video` | IMAGE | 否 | - | 与生成内容合成的背景视频 |
+| `character_mask` | MASK | 否 | - | 定义选择性处理角色区域的蒙版 |
+| `continue_motion` | IMAGE | 否 | - | 用于保持时间一致性的先前运动序列延续 |
+| `video_frame_offset` | INT | 否 | 0 至 MAX_RESOLUTION | 在所有输入视频中跳过的帧数。用于分块生成长视频。连接到前一个节点的 video_frame_offset 输出以扩展视频。（默认：0，步长：1） |
+
+**参数约束：**
+
+- 当提供 `pose_video` 且 `trim_to_pose_video` 逻辑激活时，输出长度将调整为匹配姿态视频时长
+- `face_video` 在处理时会自动调整为 512x512 分辨率
+- `continue_motion` 帧数受 `continue_motion_max_frames` 参数限制
+- 输入视频（`face_video`、`pose_video`、`background_video`、`character_mask`）在处理前会按 `video_frame_offset` 进行偏移
+- 如果 `character_mask` 仅包含单帧，该帧将在所有帧中重复使用
+- 当提供 `clip_vision_output` 时，它会同时应用于正向和负向条件输入
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 包含附加视频上下文的修改后正向条件输入 |
+| `negative` | CONDITIONING | 包含附加视频上下文的修改后负向条件输入 |
+| `latent` | LATENT | 潜在空间格式的生成视频内容 |
+| `trim_latent` | INT | 用于下游处理的潜在空间修剪信息 |
+| `trim_image` | INT | 参考运动帧的图像空间修剪信息 |
+| `video_frame_offset` | INT | 用于分块继续视频生成的更新帧偏移量 |
diff --git a/zh-CN/built-in-nodes/WanCameraEmbedding.mdx b/zh-CN/built-in-nodes/WanCameraEmbedding.mdx
new file mode 100644
index 000000000..2da913f6c
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanCameraEmbedding.mdx
@@ -0,0 +1,33 @@
+---
+title: "WanCameraEmbedding - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanCameraEmbedding node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanCameraEmbedding"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraEmbedding/zh.md)
+
+WanCameraEmbedding 节点基于相机运动参数，使用 Plücker 嵌入生成相机轨迹嵌入。它会创建模拟不同相机运动的相机姿态序列，并将其转换为适用于视频生成流程的嵌入张量。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|------|-----------|------|----------|------|
+| `camera_pose` | COMBO | 是 | "Static"<br />"Pan Up"<br />"Pan Down"<br />"Pan Left"<br />"Pan Right"<br />"Zoom In"<br />"Zoom Out"<br />"Anti Clockwise (ACW)"<br />"ClockWise (CW)" | 要模拟的相机运动类型（默认："Static"） |
+| `width` | INT | 是 | 16 至 MAX_RESOLUTION | 输出的宽度（像素）（默认：832，步长：16） |
+| `height` | INT | 是 | 16 至 MAX_RESOLUTION | 输出的高度（像素）（默认：480，步长：16） |
+| `length` | INT | 是 | 1 至 MAX_RESOLUTION | 相机轨迹序列的长度（默认：81，步长：4） |
+| `speed` | FLOAT | 否 | 0.0 至 10.0 | 相机运动的速度（默认：1.0，步长：0.1） |
+| `fx` | FLOAT | 否 | 0.0 至 1.0 | 焦距 x 参数（默认：0.5，步长：0.000000001） |
+| `fy` | FLOAT | 否 | 0.0 至 1.0 | 焦距 y 参数（默认：0.5，步长：0.000000001） |
+| `cx` | FLOAT | 否 | 0.0 至 1.0 | 主点 x 坐标（默认：0.5，步长：0.01） |
+| `cy` | FLOAT | 否 | 0.0 至 1.0 | 主点 y 坐标（默认：0.5，步长：0.01） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `camera_embedding` | TENSOR | 生成的包含轨迹序列的相机嵌入张量 |
+| `width` | INT | 处理过程中使用的宽度值 |
+| `height` | INT | 处理过程中使用的高度值 |
+| `length` | INT | 处理过程中使用的长度值 |
diff --git a/zh-CN/built-in-nodes/WanCameraImageToVideo.mdx b/zh-CN/built-in-nodes/WanCameraImageToVideo.mdx
new file mode 100644
index 000000000..7b3818696
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanCameraImageToVideo.mdx
@@ -0,0 +1,35 @@
+---
+title: "WanCameraImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanCameraImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanCameraImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraImageToVideo/zh.md)
+
+WanCameraImageToVideo 节点通过生成视频生成的潜在表示，将图像转换为视频序列。它处理条件输入和可选的起始图像，以创建可用于视频模型的视频潜在表示。该节点支持相机条件和 CLIP 视觉输出，以增强视频生成的控制。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 用于视频生成的正向条件提示 |
+| `negative` | CONDITIONING | 是 | - | 视频生成中需要避免的负向条件提示 |
+| `vae` | VAE | 是 | - | 用于将图像编码到潜在空间的 VAE 模型 |
+| `width` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的宽度（像素）（默认：832，步长：16） |
+| `height` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的高度（像素）（默认：480，步长：16） |
+| `length` | INT | 是 | 1 至 MAX_RESOLUTION | 视频序列中的帧数（默认：81，步长：4） |
+| `batch_size` | INT | 是 | 1 至 4096 | 同时生成的视频数量（默认：1） |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | 否 | - | 可选的 CLIP 视觉输出，用于附加条件控制 |
+| `start_image` | IMAGE | 否 | - | 可选的起始图像，用于初始化视频序列 |
+| `camera_conditions` | WAN_CAMERA_EMBEDDING | 否 | - | 可选的相机嵌入条件，用于视频生成 |
+
+**注意：** 当提供 `start_image` 时，节点会使用它来初始化视频序列，并应用遮罩将起始帧与生成的内容混合。`camera_conditions` 和 `clip_vision_output` 参数是可选的，但当提供时，它们会修改正向和负向提示的条件。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 应用了相机条件和 CLIP 视觉输出的修改后正向条件 |
+| `negative` | CONDITIONING | 应用了相机条件和 CLIP 视觉输出的修改后负向条件 |
+| `latent` | LATENT | 生成的视频潜在表示，可用于视频模型 |
diff --git a/zh-CN/built-in-nodes/WanContextWindowsManual.mdx b/zh-CN/built-in-nodes/WanContextWindowsManual.mdx
new file mode 100644
index 000000000..2d9c6a8e5
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanContextWindowsManual.mdx
@@ -0,0 +1,30 @@
+---
+title: "WanContextWindowsManual - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanContextWindowsManual node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanContextWindowsManual"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanContextWindowsManual/zh.md)
+
+WAN 上下文窗口（手动）节点允许您为类似 WAN 的二维处理模型手动配置上下文窗口。该节点通过在采样过程中指定窗口长度、重叠量、调度方法和融合技术，应用自定义的上下文窗口设置。这使您能够精确控制模型在不同上下文区域中处理信息的方式。
+
+## 输入参数
+
+| 参数名称 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 在采样过程中要应用上下文窗口的模型。 |
+| `context_length` | INT | 是 | 1 到 1048576 | 上下文窗口的长度（默认值：81）。 |
+| `context_overlap` | INT | 是 | 0 到 1048576 | 上下文窗口的重叠量（默认值：30）。 |
+| `context_schedule` | COMBO | 是 | "static_standard"<br />"uniform_standard"<br />"uniform_looped"<br />"batched" | 上下文窗口的调度策略。 |
+| `context_stride` | INT | 是 | 1 到 1048576 | 上下文窗口的步长；仅适用于均匀调度（默认值：1）。 |
+| `closed_loop` | BOOLEAN | 是 | - | 是否闭合上下文窗口循环；仅适用于循环调度（默认值：False）。 |
+| `fuse_method` | COMBO | 是 | "pyramid" | 用于融合上下文窗口的方法（默认值："pyramid"）。 |
+
+**注意：** `context_stride` 参数仅影响均匀调度，`closed_loop` 仅适用于循环调度。上下文长度和重叠值会在处理过程中自动调整以确保最小有效值。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 应用了上下文窗口配置的模型。 |
diff --git a/zh-CN/built-in-nodes/WanFirstLastFrameToVideo.mdx b/zh-CN/built-in-nodes/WanFirstLastFrameToVideo.mdx
new file mode 100644
index 000000000..bc1711cb5
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanFirstLastFrameToVideo.mdx
@@ -0,0 +1,36 @@
+---
+title: "WanFirstLastFrameToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanFirstLastFrameToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanFirstLastFrameToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFirstLastFrameToVideo/zh.md)
+
+WanFirstLastFrameToVideo 节点通过结合起始帧和结束帧与文本提示来创建视频条件。它通过对首尾帧进行编码、应用遮罩指导生成过程，并在可用时整合 CLIP 视觉特征，为视频生成生成潜在表示。该节点为视频模型准备正向和负向条件，以在指定的起始点和结束点之间生成连贯序列。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|--------|-----------|------|----------|------|
+| `正向` | CONDITIONING | 是 | - | 用于指导视频生成的正向文本条件 |
+| `负向` | CONDITIONING | 是 | - | 用于指导视频生成的负向文本条件 |
+| `vae` | VAE | 是 | - | 用于将图像编码到潜在空间的 VAE 模型 |
+| `宽度` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频宽度（默认：832，步长：16） |
+| `高度` | INT | 否 | 16 至 MAX_RESOLUTION | 输出视频高度（默认：480，步长：16） |
+| `长度` | INT | 否 | 1 至 MAX_RESOLUTION | 视频序列中的帧数（默认：81，步长：4） |
+| `批量大小` | INT | 否 | 1 至 4096 | 同时生成的视频数量（默认：1） |
+| `clip 视觉起始图像` | CLIP_VISION_OUTPUT | 否 | - | 从起始图像提取的 CLIP 视觉特征 |
+| `clip 视觉结束图像` | CLIP_VISION_OUTPUT | 否 | - | 从结束图像提取的 CLIP 视觉特征 |
+| `起始图像` | IMAGE | 否 | - | 视频序列的起始帧图像 |
+| `结束图像` | IMAGE | 否 | - | 视频序列的结束帧图像 |
+
+**注意：** 当同时提供 `start_image` 和 `end_image` 时，节点会创建在这两个帧之间过渡的视频序列。`clip_vision_start_image` 和 `clip_vision_end_image` 参数是可选的，但若提供，它们的 CLIP 视觉特征将被拼接并应用于正向和负向条件。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `负向` | CONDITIONING | 应用了视频帧编码和 CLIP 视觉特征的正向条件 |
+| `latent` | CONDITIONING | 应用了视频帧编码和 CLIP 视觉特征的负向条件 |
+| `latent` | LATENT | 空潜在张量，其维度与指定的视频参数匹配 |
diff --git a/zh-CN/built-in-nodes/WanFunControlToVideo.mdx b/zh-CN/built-in-nodes/WanFunControlToVideo.mdx
new file mode 100644
index 000000000..66f63477d
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanFunControlToVideo.mdx
@@ -0,0 +1,39 @@
+---
+title: "WanFunControlToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanFunControlToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanFunControlToVideo"
+icon: "circle"
+mode: wide
+---
+该节点是为了支持阿里巴巴的 Wan Fun Control 模型而添加的，用于视频生成，并在 [此提交](https://github.com/comfyanonymous/ComfyUI/commit/3661c833bcc41b788a7c9f0e7bc48524f8ee5f82) 之后添加。
+
+- **目的：** 准备使用 Wan 2.1 Fun Control 模型进行视频生成所需的条件信息。
+
+WanFunControlToVideo 节点是 ComfyUI 的一个附加功能，旨在支持用于视频生成的 Wan Fun Control 模型，旨在利用 WanFun 控制进行视频创作。
+
+该节点作为准备必要条件信息的起点，并初始化潜在空间的中心点，指导后续使用 Wan 2.1 Fun 模型的视频生成过程。节点的名称清楚地表明了其功能：它接受各种输入并将其转换为适合在 WanFun 框架内控制视频生成的格式。
+
+该节点在 ComfyUI 节点层次结构中的位置表明，它在视频生成管道的早期阶段操作，专注于在实际采样或解码视频帧之前操纵条件信号。
+
+## 输入
+
+| 参数名称           | 必需 | 数据类型           | 描述                                                  | 默认值 |
+|:-------------------|:---------|:-------------------|:-------------------------------------------------------------|:-------------|
+| positive           | 是      | CONDITIONING       | 标准 ComfyUI 正条件数据，通常来自“CLIP Text Encode”节点。正提示描述用户设想的生成视频的内容、主题和艺术风格。 | N/A  |
+| negative           | 是      | CONDITIONING       | 标准 ComfyUI 负条件数据，通常由“CLIP Text Encode”节点生成。负提示指定用户希望在生成视频中避免的元素、风格或伪影。 | N/A  |
+| vae                | 是      | VAE                | 需要与 Wan 2.1 Fun 模型系列兼容的 VAE（变分自编码器）模型，用于编码和解码图像/视频数据。 | N/A  |
+| width              | 是      | INT                | 输出视频帧的期望宽度（以像素为单位），默认值为 832，最小值为 16，最大值由 nodes.MAX_RESOLUTION 决定，步长为 16。 | 832  |
+| height             | 是      | INT                | 输出视频帧的期望高度（以像素为单位），默认值为 480，最小值为 16，最大值由 nodes.MAX_RESOLUTION 决定，步长为 16。 | 480  |
+| length             | 是      | INT                | 生成视频中的总帧数，默认值为 81，最小值为 1，最大值由 nodes.MAX_RESOLUTION 决定，步长为 4。 | 81   |
+| batch_size         | 是      | INT                | 一次生成的视频数量，默认值为 1，最小值为 1，最大值为 4096。 | 1    |
+| clip_vision_output | 否       | CLIP_VISION_OUTPUT | （可选）由 CLIP 视觉模型提取的视觉特征，允许进行视觉风格和内容指导。 | 无 |
+| start_image        | 否       | IMAGE              | （可选）影响生成视频开头的初始图像。 | 无 |
+| control_video      | 否       | IMAGE              | （可选）允许用户提供经过预处理的 ControlNet 参考视频，以指导生成视频的运动和潜在结构。| 无 |
+
+## 输出
+
+| 参数名称           | 数据类型           | 描述                                                  |
+|:-------------------|:-------------------|:-------------------------------------------------------------|
+| positive           | CONDITIONING       | 提供增强的正条件数据，包括编码的 start_image 和 control_video。 |
+| negative           | CONDITIONING       | 提供同样增强的负条件数据，包含相同的 concat_latent_image。 |
+| latent             | LATENT             | 一个字典，包含一个空的潜在张量，键为“samples”。 |
diff --git a/zh-CN/built-in-nodes/WanFunInpaintToVideo.mdx b/zh-CN/built-in-nodes/WanFunInpaintToVideo.mdx
new file mode 100644
index 000000000..cff305d7f
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanFunInpaintToVideo.mdx
@@ -0,0 +1,33 @@
+---
+title: "WanFunInpaintToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanFunInpaintToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanFunInpaintToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFunInpaintToVideo/zh.md)
+
+WanFunInpaintToVideo 节点通过在起始图像和结束图像之间进行修复来创建视频序列。它接收正向和负向条件提示以及可选的帧图像，以生成视频潜在表示。该节点支持可配置尺寸和长度参数来处理视频生成。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正向` | CONDITIONING | 是 | - | 用于视频生成的正向条件提示 |
+| `负向` | CONDITIONING | 是 | - | 视频生成中需要避免的负向条件提示 |
+| `vae` | VAE | 是 | - | 用于编码/解码操作的 VAE 模型 |
+| `宽度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频宽度（像素）（默认：832，步长：16） |
+| `高度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频高度（像素）（默认：480，步长：16） |
+| `长度` | INT | 是 | 1 至 MAX_RESOLUTION | 视频序列的帧数（默认：81，步长：4） |
+| `批量大小` | INT | 是 | 1 至 4096 | 单批次生成的视频数量（默认：1） |
+| `clip_vision_output` | CLIP_VISION_OUTPUT | 否 | - | 用于附加条件提示的可选 CLIP 视觉输出 |
+| `起始图像` | IMAGE | 否 | - | 用于视频生成的可选起始帧图像 |
+| `结束图像` | IMAGE | 否 | - | 用于视频生成的可选结束帧图像 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负向` | CONDITIONING | 处理后的正向条件输出 |
+| `latent` | CONDITIONING | 处理后的负向条件输出 |
+| `latent` | LATENT | 生成的视频潜在表示 |
diff --git a/zh-CN/built-in-nodes/WanHuMoImageToVideo.mdx b/zh-CN/built-in-nodes/WanHuMoImageToVideo.mdx
new file mode 100644
index 000000000..bdb757b5b
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanHuMoImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "WanHuMoImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanHuMoImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanHuMoImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanHuMoImageToVideo/zh.md)
+
+WanHuMoImageToVideo 节点通过生成视频帧的潜在表示，将图像转换为视频序列。该节点处理条件输入，并可结合参考图像和音频嵌入来影响视频生成。节点输出适用于视频合成的修改后条件数据和潜在表示。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 正向条件输入，引导视频生成朝向期望内容 |
+| `negative` | CONDITIONING | 是 | - | 负向条件输入，使视频生成远离不需要的内容 |
+| `vae` | VAE | 是 | - | 用于将参考图像编码到潜在空间的 VAE 模型 |
+| `width` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频帧的宽度（单位：像素），默认值：832，必须能被 16 整除 |
+| `height` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频帧的高度（单位：像素），默认值：480，必须能被 16 整除 |
+| `length` | INT | 是 | 1 至 MAX_RESOLUTION | 生成视频序列的帧数，默认值：97 |
+| `batch_size` | INT | 是 | 1 至 4096 | 同时生成的视频序列数量，默认值：1 |
+| `audio_encoder_output` | AUDIOENCODEROUTPUT | 否 | - | 可选的音频编码数据，可根据音频内容影响视频生成 |
+| `ref_image` | IMAGE | 否 | - | 可选的参考图像，用于指导视频生成的风格和内容 |
+
+**注意：** 当提供参考图像时，它会被编码并添加到正向和负向条件中。当提供音频编码器输出时，它会被处理并合并到条件数据中。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 修改后的正向条件，包含参考图像和/或音频嵌入 |
+| `negative` | CONDITIONING | 修改后的负向条件，包含参考图像和/或音频嵌入 |
+| `latent` | LATENT | 生成的潜在表示，包含视频序列数据 |
diff --git a/zh-CN/built-in-nodes/WanImageToImageApi.mdx b/zh-CN/built-in-nodes/WanImageToImageApi.mdx
new file mode 100644
index 000000000..1ecfd79d5
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanImageToImageApi.mdx
@@ -0,0 +1,31 @@
+---
+title: "WanImageToImageApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanImageToImageApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanImageToImageApi"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToImageApi/zh.md)
+
+## 概述
+
+Wan Image to Image 节点能够基于一张或两张输入图像以及文本提示生成新图像。它会根据您提供的描述对输入图像进行转换，创建出保持原始输入图像宽高比的新图像。无论输入尺寸如何，输出图像都固定为160万像素。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | "wan2.5-i2i-preview" | 使用的模型（默认："wan2.5-i2i-preview"）。 |
+| `image` | IMAGE | 是 | - | 单图编辑或多图融合，最多支持2张图像。 |
+| `prompt` | STRING | 是 | - | 用于描述元素和视觉特征的提示词，支持英文/中文（默认：空）。 |
+| `negative_prompt` | STRING | 否 | - | 负面文本提示词，用于指导避免生成的内容（默认：空）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 生成时使用的随机种子（默认：0）。 |
+| `watermark` | BOOLEAN | 否 | - | 是否在结果中添加"AI生成"水印（默认：true）。 |
+
+**注意：** 此节点仅接受恰好1张或2张输入图像。如果提供超过2张图像或未提供任何图像，节点将返回错误。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 基于输入图像和文本提示生成的图像。 |
diff --git a/zh-CN/built-in-nodes/WanImageToVideo.mdx b/zh-CN/built-in-nodes/WanImageToVideo.mdx
new file mode 100644
index 000000000..ecb0ddb48
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "WanImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToVideo/zh.md)
+
+WanImageToVideo 节点为视频生成任务准备条件约束和潜在表示。它创建一个用于视频生成的空潜在空间，并可以选择性地结合起始图像和 CLIP 视觉输出来指导视频生成过程。该节点会根据提供的图像和视觉数据修改正向和负向条件约束输入。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正面` | CONDITIONING | 是 | - | 用于引导生成的正向条件约束输入 |
+| `负面` | CONDITIONING | 是 | - | 用于引导生成的负向条件约束输入 |
+| `vae` | VAE | 是 | - | 用于将图像编码到潜在空间的 VAE 模型 |
+| `宽度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的宽度（默认：832，步长：16） |
+| `高度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的高度（默认：480，步长：16） |
+| `长度` | INT | 是 | 1 至 MAX_RESOLUTION | 视频中的帧数（默认：81，步长：4） |
+| `批量大小` | INT | 是 | 1 至 4096 | 单次批量生成的视频数量（默认：1） |
+| `clip视觉输出` | CLIP_VISION_OUTPUT | 否 | - | 用于附加条件约束的可选 CLIP 视觉输出 |
+| `开始图像` | IMAGE | 否 | - | 用于初始化视频生成的可选起始图像 |
+
+**注意：** 当提供 `start_image` 时，节点会对图像序列进行编码并对条件约束输入应用掩码处理。当提供 `clip_vision_output` 参数时，会向正向和负向输入添加基于视觉的条件约束。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负面` | CONDITIONING | 融合了图像和视觉数据的修改后正向条件约束 |
+| `潜在` | CONDITIONING | 融合了图像和视觉数据的修改后负向条件约束 |
+| `latent` | LATENT | 准备用于视频生成的空潜在空间张量 |
diff --git a/zh-CN/built-in-nodes/WanImageToVideoApi.mdx b/zh-CN/built-in-nodes/WanImageToVideoApi.mdx
new file mode 100644
index 000000000..21ea77f1b
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanImageToVideoApi.mdx
@@ -0,0 +1,38 @@
+---
+title: "WanImageToVideoApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanImageToVideoApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanImageToVideoApi"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToVideoApi/zh.md)
+
+万图生视频节点从单个输入图像和文本提示开始生成视频内容。它通过根据提供的描述扩展初始帧来创建视频序列，并提供控制视频质量、时长和音频集成的选项。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | "wan2.5-i2v-preview"<br />"wan2.5-i2v-preview" | 使用的模型（默认："wan2.5-i2v-preview"） |
+| `image` | IMAGE | 是 | - | 输入图像，作为视频生成的第一帧 |
+| `prompt` | STRING | 是 | - | 用于描述元素和视觉特征的提示词，支持英文/中文（默认：空） |
+| `negative_prompt` | STRING | 否 | - | 负面文本提示词，用于指导避免生成的内容（默认：空） |
+| `resolution` | COMBO | 否 | "480P"<br />"720P"<br />"1080P" | 视频分辨率质量（默认："480P"） |
+| `duration` | INT | 否 | 5-10 | 可用时长：5秒和10秒（默认：5） |
+| `audio` | AUDIO | 否 | - | 音频必须包含清晰、响亮的人声，无杂音和背景音乐 |
+| `seed` | INT | 否 | 0-2147483647 | 生成使用的随机种子（默认：0） |
+| `generate_audio` | BOOLEAN | 否 | - | 若无音频输入，是否自动生成音频（默认：False） |
+| `prompt_extend` | BOOLEAN | 否 | - | 是否使用AI辅助增强提示词（默认：True） |
+| `watermark` | BOOLEAN | 否 | - | 是否在结果中添加"AI生成"水印（默认：True） |
+
+**约束条件：**
+
+- 视频生成需要且仅需要一个输入图像
+- 时长参数仅接受5或10秒的值
+- 当提供音频时，音频时长必须在3.0到29.0秒之间
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 基于输入图像和提示词生成的视频 |
diff --git a/zh-CN/built-in-nodes/WanInfiniteTalkToVideo.mdx b/zh-CN/built-in-nodes/WanInfiniteTalkToVideo.mdx
new file mode 100644
index 000000000..5513cb974
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanInfiniteTalkToVideo.mdx
@@ -0,0 +1,50 @@
+---
+title: "WanInfiniteTalkToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanInfiniteTalkToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanInfiniteTalkToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanInfiniteTalkToVideo/zh.md)
+
+WanInfiniteTalkToVideo 节点可从音频输入生成视频序列。它使用视频扩散模型，以从一个或两个说话者提取的音频特征为条件，生成说话人视频的潜在表示。该节点可以生成新序列，或使用先前帧作为运动上下文来扩展现有序列。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `mode` | COMBO | 是 | `"single_speaker"`<br />`"two_speakers"` | 音频输入模式。`"single_speaker"` 使用一个音频输入。`"two_speakers"` 启用第二个说话者的输入及相应的遮罩。 |
+| `model` | MODEL | 是 | - | 基础视频扩散模型。 |
+| `model_patch` | MODELPATCH | 是 | - | 包含音频投影层的模型补丁。 |
+| `positive` | CONDITIONING | 是 | - | 用于引导生成的正向条件。 |
+| `negative` | CONDITIONING | 是 | - | 用于引导生成的负向条件。 |
+| `vae` | VAE | 是 | - | 用于在图像和潜在空间之间进行编码的 VAE。 |
+| `width` | INT | 否 | 16 - MAX_RESOLUTION | 输出视频的宽度（像素）。必须能被 16 整除。（默认值：832） |
+| `height` | INT | 否 | 16 - MAX_RESOLUTION | 输出视频的高度（像素）。必须能被 16 整除。（默认值：480） |
+| `length` | INT | 否 | 1 - MAX_RESOLUTION | 要生成的帧数。（默认值：81） |
+| `clip_vision_output` | CLIPVISIONOUTPUT | 否 | - | 用于附加条件的可选 CLIP 视觉输出。 |
+| `start_image` | IMAGE | 否 | - | 用于初始化视频序列的可选起始图像。 |
+| `audio_encoder_output_1` | AUDIOENCODEROUTPUT | 是 | - | 包含第一个说话者特征的主音频编码器输出。 |
+| `motion_frame_count` | INT | 否 | 1 - 33 | 扩展现有序列时，用作运动上下文的先前帧数。（默认值：9） |
+| `audio_scale` | FLOAT | 否 | -10.0 - 10.0 | 应用于音频条件的缩放因子。（默认值：1.0） |
+| `previous_frames` | IMAGE | 否 | - | 用于扩展的可选先前视频帧。 |
+| `audio_encoder_output_2` | AUDIOENCODEROUTPUT | 否 | - | 第二个音频编码器输出。当 `mode` 设置为 `"two_speakers"` 时必须提供。 |
+| `mask_1` | MASK | 否 | - | 第一个说话者的遮罩，使用两个音频输入时必须提供。 |
+| `mask_2` | MASK | 否 | - | 第二个说话者的遮罩，使用两个音频输入时必须提供。 |
+
+**参数约束：**
+
+* 当 `mode` 设置为 `"two_speakers"` 时，参数 `audio_encoder_output_2`、`mask_1` 和 `mask_2` 变为必填项。
+* 如果提供了 `audio_encoder_output_2`，则必须同时提供 `mask_1` 和 `mask_2`。
+* 如果提供了 `mask_1` 和 `mask_2`，则必须同时提供 `audio_encoder_output_2`。
+* 如果提供了 `previous_frames`，则其包含的帧数必须至少等于 `motion_frame_count` 指定的数量。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 应用了音频条件处理的修补后模型。 |
+| `positive` | CONDITIONING | 正向条件，可能已根据附加上下文（例如起始图像、CLIP 视觉）进行了修改。 |
+| `negative` | CONDITIONING | 负向条件，可能已根据附加上下文进行了修改。 |
+| `latent` | LATENT | 潜在空间中生成的视频序列。 |
+| `trim_image` | INT | 扩展现有序列时，应从运动上下文开始处裁剪的帧数。 |
diff --git a/zh-CN/built-in-nodes/WanMoveConcatTrack.mdx b/zh-CN/built-in-nodes/WanMoveConcatTrack.mdx
new file mode 100644
index 000000000..25cfe28b4
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanMoveConcatTrack.mdx
@@ -0,0 +1,23 @@
+---
+title: "WanMoveConcatTrack - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanMoveConcatTrack node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanMoveConcatTrack"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveConcatTrack/zh.md)
+
+WanMoveConcatTrack 节点将两组运动跟踪数据合并为一个更长的序列。它通过沿各自维度连接输入轨迹的路径和可见性遮罩来实现。如果只提供了一个轨迹输入，它会直接将该数据原样传递。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `tracks_1` | TRACKS | 是 | | 要连接的第一组运动跟踪数据。 |
+| `tracks_2` | TRACKS | 否 | | 可选的第二组运动跟踪数据。如果未提供，则 `tracks_1` 将直接传递到输出。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `tracks` | TRACKS | 连接后的运动跟踪数据，包含来自输入的合并后的 `track_path` 和 `track_visibility`。 |
diff --git a/zh-CN/built-in-nodes/WanMoveTrackToVideo.mdx b/zh-CN/built-in-nodes/WanMoveTrackToVideo.mdx
new file mode 100644
index 000000000..f9c2b48a8
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanMoveTrackToVideo.mdx
@@ -0,0 +1,36 @@
+---
+title: "WanMoveTrackToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanMoveTrackToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanMoveTrackToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTrackToVideo/zh.md)
+
+WanMoveTrackToVideo 节点为视频生成准备条件数据和潜在空间数据，并可整合可选的运动跟踪信息。该节点将起始图像序列编码为潜在表示，并能融合来自对象轨迹的位置数据以引导生成视频中的运动。节点输出修改后的正向与负向条件数据，以及一个可供视频模型使用的空潜在张量。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 待修改的正向条件输入。 |
+| `negative` | CONDITIONING | 是 | - | 待修改的负向条件输入。 |
+| `vae` | VAE | 是 | - | 用于将起始图像编码到潜在空间的 VAE 模型。 |
+| `tracks` | TRACKS | 否 | - | 包含对象路径的可选运动跟踪数据。 |
+| `strength` | FLOAT | 否 | 0.0 - 100.0 | 轨迹条件化的强度。（默认值：1.0） |
+| `width` | INT | 否 | 16 - MAX_RESOLUTION | 输出视频的宽度。必须能被 16 整除。（默认值：832） |
+| `height` | INT | 否 | 16 - MAX_RESOLUTION | 输出视频的高度。必须能被 16 整除。（默认值：480） |
+| `length` | INT | 否 | 1 - MAX_RESOLUTION | 视频序列的帧数。（默认值：81） |
+| `batch_size` | INT | 否 | 1 - 4096 | 潜在输出的批次大小。（默认值：1） |
+| `start_image` | IMAGE | 是 | - | 要编码的起始图像或图像序列。 |
+| `clip_vision_output` | CLIPVISIONOUTPUT | 否 | - | 可选的 CLIP 视觉模型输出，用于添加到条件数据中。 |
+
+**注意：** `strength` 参数仅在提供了 `tracks` 时生效。如果未提供 `tracks` 或 `strength` 为 0.0，则不会应用轨迹条件化。`start_image` 用于为条件化创建潜在图像和掩码；如果未提供，节点仅会透传条件数据并输出一个空的潜在张量。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 修改后的正向条件数据，可能包含 `concat_latent_image`、`concat_mask` 和 `clip_vision_output`。 |
+| `negative` | CONDITIONING | 修改后的负向条件数据，可能包含 `concat_latent_image`、`concat_mask` 和 `clip_vision_output`。 |
+| `latent` | LATENT | 一个空的潜在张量，其维度由 `batch_size`、`length`、`height` 和 `width` 输入决定。 |
diff --git a/zh-CN/built-in-nodes/WanMoveTracksFromCoords.mdx b/zh-CN/built-in-nodes/WanMoveTracksFromCoords.mdx
new file mode 100644
index 000000000..702c32945
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanMoveTracksFromCoords.mdx
@@ -0,0 +1,26 @@
+---
+title: "WanMoveTracksFromCoords - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanMoveTracksFromCoords node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanMoveTracksFromCoords"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTracksFromCoords/zh.md)
+
+WanMoveTracksFromCoords 节点根据一系列坐标点创建一组运动轨迹。它将 JSON 格式的坐标字符串转换为可供其他视频处理节点使用的张量格式，并可选择性地应用遮罩来控制轨迹随时间的可见性。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `track_coords` | STRING | 是 | N/A | 包含轨迹坐标数据的 JSON 格式字符串。默认值为空列表 (`"[]"`)。 |
+| `track_mask` | MASK | 否 | N/A | 可选的遮罩。当提供时，节点将使用它来确定每帧中每条轨迹的可见性。 |
+
+**注意：** `track_coords` 输入需要特定的 JSON 结构。它应该是一个轨迹列表，其中每条轨迹是一个帧列表，每一帧是一个包含 `x` 和 `y` 坐标的对象。所有轨迹的帧数必须保持一致。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `tracks` | TRACKS | 生成的轨迹数据，包含每条轨迹的路径坐标和可见性信息。 |
+| `track_length` | INT | 生成轨迹的总帧数。 |
diff --git a/zh-CN/built-in-nodes/WanMoveVisualizeTracks.mdx b/zh-CN/built-in-nodes/WanMoveVisualizeTracks.mdx
new file mode 100644
index 000000000..2d8d74d60
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanMoveVisualizeTracks.mdx
@@ -0,0 +1,29 @@
+---
+title: "WanMoveVisualizeTracks - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanMoveVisualizeTracks node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanMoveVisualizeTracks"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveVisualizeTracks/zh.md)
+
+WanMoveVisualizeTracks 节点将运动跟踪数据叠加到一系列图像或视频帧上。它会绘制跟踪点的可视化表示，包括其运动路径和当前位置，使运动数据可见且更易于分析。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `images` | IMAGE | 是 | - | 用于在其上可视化轨迹的输入图像或视频帧序列。 |
+| `tracks` | TRACKS | 否 | - | 包含点路径和可见性信息的运动跟踪数据。如果未提供，则输入图像将原样传递。 |
+| `line_resolution` | INT | 是 | 1 - 1024 | 绘制每个轨迹的尾部路径线时，要使用的先前帧的数量（默认值：24）。 |
+| `circle_size` | INT | 是 | 1 - 128 | 在每个轨迹当前位置绘制的圆圈的大小（默认值：12）。 |
+| `opacity` | FLOAT | 是 | 0.0 - 1.0 | 绘制的轨迹叠加层的不透明度（默认值：0.75）。 |
+| `line_width` | INT | 是 | 1 - 128 | 用于绘制轨迹路径的线条宽度（默认值：16）。 |
+
+**注意：** 如果输入图像的数量与提供的 `tracks` 数据中的帧数不匹配，图像序列将被重复以匹配轨迹长度。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 将运动跟踪数据可视化为叠加层后的图像序列。如果未提供 `tracks`，则返回原始输入图像。 |
diff --git a/zh-CN/built-in-nodes/WanPhantomSubjectToVideo.mdx b/zh-CN/built-in-nodes/WanPhantomSubjectToVideo.mdx
new file mode 100644
index 000000000..d86300b76
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanPhantomSubjectToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "WanPhantomSubjectToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanPhantomSubjectToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanPhantomSubjectToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanPhantomSubjectToVideo/zh.md)
+
+WanPhantomSubjectToVideo 节点通过处理条件输入和可选的参考图像来生成视频内容。它创建用于视频生成的潜在表示，并在提供输入图像时能够融入视觉引导。该节点通过时间维度拼接为视频模型准备条件数据，并输出修改后的条件数据以及生成的潜在视频数据。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 用于引导视频生成的正向条件输入 |
+| `negative` | CONDITIONING | 是 | - | 用于避免某些特征的负向条件输入 |
+| `vae` | VAE | 是 | - | 用于在提供图像时进行编码的 VAE 模型 |
+| `width` | INT | 否 | 16 到 MAX_RESOLUTION | 输出视频宽度（像素）（默认：832，必须能被 16 整除） |
+| `height` | INT | 否 | 16 到 MAX_RESOLUTION | 输出视频高度（像素）（默认：480，必须能被 16 整除） |
+| `length` | INT | 否 | 1 到 MAX_RESOLUTION | 生成视频的帧数（默认：81，必须能被 4 整除） |
+| `batch_size` | INT | 否 | 1 到 4096 | 同时生成的视频数量（默认：1） |
+| `images` | IMAGE | 否 | - | 用于时间维度条件处理的可选参考图像 |
+
+**注意：** 当提供 `images` 时，它们会自动放大以匹配指定的 `width` 和 `height`，并且仅使用前 `length` 帧进行处理。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 修改后的正向条件数据，在提供图像时包含时间维度拼接 |
+| `negative_text` | CONDITIONING | 修改后的负向条件数据，在提供图像时包含时间维度拼接 |
+| `negative_img_text` | CONDITIONING | 负向条件数据，在提供图像时时间维度拼接被置零 |
+| `latent` | LATENT | 生成的潜在视频表示，具有指定的尺寸和长度 |
diff --git a/zh-CN/built-in-nodes/WanReferenceVideoApi.mdx b/zh-CN/built-in-nodes/WanReferenceVideoApi.mdx
new file mode 100644
index 000000000..588ae46f5
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanReferenceVideoApi.mdx
@@ -0,0 +1,35 @@
+---
+title: "WanReferenceVideoApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanReferenceVideoApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanReferenceVideoApi"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanReferenceVideoApi/zh.md)
+
+Wan Reference to Video 节点利用一个或多个输入参考视频的视觉外观和语音，结合文本提示词，生成新的视频内容。它在保持与参考素材中角色一致性的同时，根据您的描述创造新的内容。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | `"wan2.6-r2v"` | 用于视频生成的具体 AI 模型。 |
+| `prompt` | STRING | 是 | - | 对新视频中元素和视觉特征的描述。支持英文和中文。使用如 `character1`、`character2` 等标识符来指代参考视频中的角色。 |
+| `negative_prompt` | STRING | 否 | - | 描述希望在生成视频中避免出现的元素或特征。 |
+| `reference_videos` | AUTOGROW | 是 | - | 用作角色外观和语音参考的视频输入列表。您必须提供至少一个视频。每个视频可以分配一个名称，如 `character1`、`character2` 或 `character3`。 |
+| `size` | COMBO | 是 | `"720p: 1:1 (960x960)"`<br />`"720p: 16:9 (1280x720)"`<br />`"720p: 9:16 (720x1280)"`<br />`"720p: 4:3 (1088x832)"`<br />`"720p: 3:4 (832x1088)"`<br />`"1080p: 1:1 (1440x1440)"`<br />`"1080p: 16:9 (1920x1080)"`<br />`"1080p: 9:16 (1080x1920)"`<br />`"1080p: 4:3 (1632x1248)"`<br />`"1080p: 3:4 (1248x1632)"` | 输出视频的分辨率和宽高比。 |
+| `duration` | INT | 是 | 5 到 10 | 生成视频的长度，单位为秒。该值必须是 5 的倍数（默认值：5）。 |
+| `seed` | INT | 否 | 0 到 2147483647 | 用于获得可重现结果的随机种子值。值为 0 时将生成一个随机种子。 |
+| `shot_type` | COMBO | 是 | `"single"`<br />`"multi"` | 指定生成的视频是单个连续镜头，还是包含多个带有剪辑的镜头。 |
+| `watermark` | BOOLEAN | 否 | - | 启用后，会在最终视频上添加一个 AI 生成的水印（默认值：False）。 |
+
+**约束条件：**
+
+* `reference_videos` 中提供的每个视频时长必须在 2 到 30 秒之间。
+* `duration` 参数仅限于特定值（5 或 10 秒）。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 新生成的视频文件。 |
diff --git a/zh-CN/built-in-nodes/WanSoundImageToVideo.mdx b/zh-CN/built-in-nodes/WanSoundImageToVideo.mdx
new file mode 100644
index 000000000..a556a211f
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanSoundImageToVideo.mdx
@@ -0,0 +1,34 @@
+---
+title: "WanSoundImageToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanSoundImageToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanSoundImageToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideo/zh.md)
+
+WanSoundImageToVideo 节点能够从图像生成视频内容，并支持可选的音频条件输入。该节点通过结合正向与负向条件提示以及 VAE 模型来创建视频潜变量，并可整合参考图像、音频编码、控制视频和运动参考等多种元素来引导视频生成过程。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|--------|-----------|------|----------|------|
+| `positive` | CONDITIONING | 是 | - | 正向条件提示，指导生成视频中应出现的内容 |
+| `negative` | CONDITIONING | 是 | - | 负向条件提示，指定生成视频中应避免的内容 |
+| `vae` | VAE | 是 | - | 用于编码和解码视频潜变量表示的 VAE 模型 |
+| `width` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的宽度（像素），默认值：832，必须能被 16 整除 |
+| `height` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的高度（像素），默认值：480，必须能被 16 整除 |
+| `length` | INT | 是 | 1 至 MAX_RESOLUTION | 生成视频的帧数，默认值：77，必须能被 4 整除 |
+| `batch_size` | INT | 是 | 1 至 4096 | 同时生成的视频数量，默认值：1 |
+| `audio_encoder_output` | AUDIOENCODEROUTPUT | 否 | - | 可选的音频编码，可根据声音特征影响视频生成 |
+| `ref_image` | IMAGE | 否 | - | 可选的参考图像，为视频内容提供视觉指导 |
+| `control_video` | IMAGE | 否 | - | 可选的控制视频，指导生成视频的运动和结构 |
+| `ref_motion` | IMAGE | 否 | - | 可选的运动参考，为视频中的运动模式提供指导 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|----------|-----------|------|
+| `positive` | CONDITIONING | 经过处理的正向条件提示，已适配视频生成需求 |
+| `negative` | CONDITIONING | 经过处理的负向条件提示，已适配视频生成需求 |
+| `latent` | LATENT | 潜空间中的生成视频表示，可解码为最终视频帧 |
diff --git a/zh-CN/built-in-nodes/WanSoundImageToVideoExtend.mdx b/zh-CN/built-in-nodes/WanSoundImageToVideoExtend.mdx
new file mode 100644
index 000000000..d068952c6
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanSoundImageToVideoExtend.mdx
@@ -0,0 +1,31 @@
+---
+title: "WanSoundImageToVideoExtend - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanSoundImageToVideoExtend node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanSoundImageToVideoExtend"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideoExtend/zh.md)
+
+WanSoundImageToVideoExtend 节点通过整合音频条件处理和参考图像来扩展图像到视频的生成功能。该节点接收正向和负向条件提示、视频潜在数据以及可选的音频嵌入，以生成扩展的视频序列。节点会处理这些输入内容，创建与音频线索同步的连贯视频输出。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 正向条件提示，指导视频应包含的内容 |
+| `negative` | CONDITIONING | 是 | - | 负向条件提示，指定视频应避免的内容 |
+| `vae` | VAE | 是 | - | 用于视频帧编码和解码的变分自编码器 |
+| `length` | INT | 是 | 1 到 MAX_RESOLUTION | 为视频序列生成的帧数（默认值：77，步长：4） |
+| `video_latent` | LATENT | 是 | - | 作为扩展起点的初始视频潜在表示 |
+| `audio_encoder_output` | AUDIOENCODEROUTPUT | 否 | - | 可选的音频嵌入，可根据声音特征影响视频生成 |
+| `ref_image` | IMAGE | 否 | - | 可选的参考图像，为视频生成提供视觉指导 |
+| `control_video` | IMAGE | 否 | - | 可选的控制视频，可指导生成视频的运动和风格 |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 应用了视频上下文的已处理正向条件提示 |
+| `negative` | CONDITIONING | 应用了视频上下文的已处理负向条件提示 |
+| `latent` | LATENT | 包含扩展视频序列的生成视频潜在表示 |
diff --git a/zh-CN/built-in-nodes/WanTextToImageApi.mdx b/zh-CN/built-in-nodes/WanTextToImageApi.mdx
new file mode 100644
index 000000000..e78266787
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanTextToImageApi.mdx
@@ -0,0 +1,29 @@
+---
+title: "WanTextToImageApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanTextToImageApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanTextToImageApi"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTextToImageApi/zh.md)
+
+万文本转图像节点根据文本描述生成图像。它使用 AI 模型从书面提示创建视觉内容，支持英文和中文文本输入。该节点提供多种控制选项来调整输出图像的尺寸、质量和风格偏好。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | "wan2.5-t2i-preview" | 使用的模型（默认："wan2.5-t2i-preview"） |
+| `prompt` | STRING | 是 | - | 用于描述元素和视觉特征的提示词，支持英文/中文（默认：空） |
+| `negative_prompt` | STRING | 否 | - | 负面文本提示词，用于指导避免生成的内容（默认：空） |
+| `width` | INT | 否 | 768-1440 | 图像宽度（像素）（默认：1024，步长：32） |
+| `height` | INT | 否 | 768-1440 | 图像高度（像素）（默认：1024，步长：32） |
+| `seed` | INT | 否 | 0-2147483647 | 生成使用的随机种子（默认：0） |
+| `prompt_extend` | BOOLEAN | 否 | - | 是否通过 AI 辅助增强提示词（默认：True） |
+| `watermark` | BOOLEAN | 否 | - | 是否在结果中添加"AI 生成"水印（默认：True） |
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | IMAGE | 基于文本提示生成的图像 |
diff --git a/zh-CN/built-in-nodes/WanTextToVideoApi.mdx b/zh-CN/built-in-nodes/WanTextToVideoApi.mdx
new file mode 100644
index 000000000..a0befb512
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanTextToVideoApi.mdx
@@ -0,0 +1,35 @@
+---
+title: "WanTextToVideoApi - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanTextToVideoApi node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanTextToVideoApi"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTextToVideoApi/zh.md)
+
+## 概述
+
+Wan 文生视频节点基于文本描述生成视频内容。它使用 AI 模型根据提示词创建视频，并支持多种视频尺寸、时长和可选的音频输入。该节点可在需要时自动生成音频，并提供提示词增强和水印选项。
+
+## 输入
+
+| 参数 | 数据类型 | 必需 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | COMBO | 是 | "wan2.5-t2v-preview" | 使用的模型（默认："wan2.5-t2v-preview"） |
+| `prompt` | STRING | 是 | - | 用于描述元素和视觉特征的提示词，支持英文/中文（默认：""） |
+| `negative_prompt` | STRING | 否 | - | 负面文本提示词，用于指导应避免的内容（默认：""） |
+| `size` | COMBO | 否 | "480p: 1:1 (624x624)"<br />"480p: 16:9 (832x480)"<br />"480p: 9:16 (480x832)"<br />"720p: 1:1 (960x960)"<br />"720p: 16:9 (1280x720)"<br />"720p: 9:16 (720x1280)"<br />"720p: 4:3 (1088x832)"<br />"720p: 3:4 (832x1088)"<br />"1080p: 1:1 (1440x1440)"<br />"1080p: 16:9 (1920x1080)"<br />"1080p: 9:16 (1080x1920)"<br />"1080p: 4:3 (1632x1248)"<br />"1080p: 3:4 (1248x1632)" | 视频分辨率和宽高比（默认："480p: 1:1 (624x624)"） |
+| `duration` | INT | 否 | 5-10 | 可用时长：5 和 10 秒（默认：5） |
+| `audio` | AUDIO | 否 | - | 音频必须包含清晰、响亮的人声，无额外噪音和背景音乐 |
+| `seed` | INT | 否 | 0-2147483647 | 生成使用的随机种子（默认：0） |
+| `generate_audio` | BOOLEAN | 否 | - | 若无音频输入，是否自动生成音频（默认：False） |
+| `prompt_extend` | BOOLEAN | 否 | - | 是否使用 AI 辅助增强提示词（默认：True） |
+| `watermark` | BOOLEAN | 否 | - | 是否在结果中添加"AI 生成"水印（默认：True） |
+
+**注意：** `duration` 参数仅接受 5 或 10 秒的值，这是可用的时长选项。当提供音频输入时，音频时长必须在 3.0 到 29.0 秒之间，且包含清晰人声，无背景噪音或音乐。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 基于输入参数生成的视频 |
diff --git a/zh-CN/built-in-nodes/WanTrackToVideo.mdx b/zh-CN/built-in-nodes/WanTrackToVideo.mdx
new file mode 100644
index 000000000..9943c1d2b
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanTrackToVideo.mdx
@@ -0,0 +1,37 @@
+---
+title: "WanTrackToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanTrackToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanTrackToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTrackToVideo/zh.md)
+
+WanTrackToVideo 节点通过处理轨迹点并生成相应的视频帧，将运动跟踪数据转换为视频序列。它接收跟踪坐标作为输入，并生成可用于视频生成的视频条件信息和潜在表示。当未提供轨迹数据时，该节点将回退到标准的图像到视频转换模式。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `positive` | CONDITIONING | 是 | - | 用于视频生成的正向条件信息 |
+| `negative` | CONDITIONING | 是 | - | 用于视频生成的负向条件信息 |
+| `vae` | VAE | 是 | - | 用于编码和解码的 VAE 模型 |
+| `tracks` | STRING | 是 | - | JSON 格式的跟踪数据，作为多行字符串（默认："[]"） |
+| `width` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的宽度，单位为像素（默认：832，步长：16） |
+| `height` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频的高度，单位为像素（默认：480，步长：16） |
+| `length` | INT | 是 | 1 至 MAX_RESOLUTION | 输出视频的帧数（默认：81，步长：4） |
+| `batch_size` | INT | 是 | 1 至 4096 | 同时生成的视频数量（默认：1） |
+| `temperature` | FLOAT | 是 | 1.0 至 1000.0 | 运动修补的温度参数（默认：220.0，步长：0.1） |
+| `topk` | INT | 是 | 1 至 10 | 运动修补的 top-k 值（默认：2） |
+| `start_image` | IMAGE | 否 | - | 用于视频生成的起始图像 |
+| `clip_vision_output` | CLIPVISIONOUTPUT | 否 | - | 用于附加条件信息的 CLIP 视觉输出 |
+
+**注意：** 当 `tracks` 包含有效的跟踪数据时，节点会处理运动轨迹以生成视频。当 `tracks` 为空时，节点将切换到标准的图像到视频模式。如果提供了 `start_image`，它将初始化视频序列的第一帧。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `positive` | CONDITIONING | 应用了运动轨迹信息的正向条件信息 |
+| `negative` | CONDITIONING | 应用了运动轨迹信息的负向条件信息 |
+| `latent` | LATENT | 生成的视频潜在表示 |
diff --git a/zh-CN/built-in-nodes/WanVaceToVideo.mdx b/zh-CN/built-in-nodes/WanVaceToVideo.mdx
new file mode 100644
index 000000000..75b8d71ef
--- /dev/null
+++ b/zh-CN/built-in-nodes/WanVaceToVideo.mdx
@@ -0,0 +1,37 @@
+---
+title: "WanVaceToVideo - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WanVaceToVideo node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WanVaceToVideo"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanVaceToVideo/zh.md)
+
+WanVaceToVideo 节点为视频生成模型处理视频条件数据。它接收正向和负向条件输入以及视频控制数据，并为视频生成准备潜在表示。该节点处理视频放大、遮罩和 VAE 编码，为视频模型创建适当的结构。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必需 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `正向` | CONDITIONING | 是 | - | 用于引导生成的正向条件输入 |
+| `负向` | CONDITIONING | 是 | - | 用于引导生成的负向条件输入 |
+| `vae` | VAE | 是 | - | 用于编码图像和视频帧的 VAE 模型 |
+| `宽度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频宽度（像素）（默认：832，步长：16） |
+| `高度` | INT | 是 | 16 至 MAX_RESOLUTION | 输出视频高度（像素）（默认：480，步长：16） |
+| `长度` | INT | 是 | 1 至 MAX_RESOLUTION | 视频帧数（默认：81，步长：4） |
+| `批量大小` | INT | 是 | 1 至 4096 | 同时生成的视频数量（默认：1） |
+| `强度` | FLOAT | 是 | 0.0 至 1000.0 | 视频条件控制强度（默认：1.0，步长：0.01） |
+| `控制视频` | IMAGE | 否 | - | 用于控制条件的可选输入视频 |
+| `控制mask` | MASK | 否 | - | 用于控制视频修改区域的可选遮罩 |
+| `参考图像` | IMAGE | 否 | - | 用于附加条件的可选参考图像 |
+
+**注意：** 当提供 `control_video` 时，它将被放大以匹配指定的宽度和高度。如果提供了 `control_masks`，则必须与控制视频的尺寸匹配。当提供 `reference_image` 时，它通过 VAE 编码并预置到潜在序列中。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `负向` | CONDITIONING | 应用了视频控制数据的正向条件 |
+| `latent` | CONDITIONING | 应用了视频控制数据的负向条件 |
+| `裁剪latent` | LATENT | 准备用于视频生成的空潜在张量 |
+| `trim_latent` | INT | 使用参考图像时需要修剪的潜在帧数 |
diff --git a/zh-CN/built-in-nodes/WavespeedFlashVSRNode.mdx b/zh-CN/built-in-nodes/WavespeedFlashVSRNode.mdx
new file mode 100644
index 000000000..af51a4fb9
--- /dev/null
+++ b/zh-CN/built-in-nodes/WavespeedFlashVSRNode.mdx
@@ -0,0 +1,28 @@
+---
+title: "WavespeedFlashVSRNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WavespeedFlashVSRNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WavespeedFlashVSRNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WavespeedFlashVSRNode/zh.md)
+
+WavespeedFlashVSRNode 是一个快速、高质量的视频超分辨率节点，能够提升低分辨率或模糊素材的分辨率并恢复其清晰度。它处理输入视频，并输出用户所选更高分辨率的新视频。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `video` | VIDEO | 是 | N/A | 待进行超分辨率处理的输入视频文件。 |
+| `target_resolution` | STRING | 是 | `"720p"`<br />`"1080p"`<br />`"2K"`<br />`"4K"` | 超分辨率处理后输出视频的目标分辨率。 |
+
+**输入限制：**
+
+* 输入的 `video` 文件必须为 MP4 容器格式。
+* 输入的 `video` 时长必须在 5 秒到 10 分钟（600 秒）之间。
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `output` | VIDEO | 按所选目标分辨率生成的超分辨率视频文件。 |
diff --git a/zh-CN/built-in-nodes/WavespeedImageUpscaleNode.mdx b/zh-CN/built-in-nodes/WavespeedImageUpscaleNode.mdx
new file mode 100644
index 000000000..2ed1b2918
--- /dev/null
+++ b/zh-CN/built-in-nodes/WavespeedImageUpscaleNode.mdx
@@ -0,0 +1,26 @@
+---
+title: "WavespeedImageUpscaleNode - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WavespeedImageUpscaleNode node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WavespeedImageUpscaleNode"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WavespeedImageUpscaleNode/zh.md)
+
+WaveSpeed 图像超分辨率节点使用外部 AI 服务来提高图像的分辨率和质量。它接收一张输入照片，并将其超分辨率到更高的目标分辨率，例如 2K、4K 或 8K，从而生成更清晰、细节更丰富的结果。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | STRING | 是 | `"SeedVR2"`<br />`"Ultimate"` | 用于超分辨率的 AI 模型。"SeedVR2" 和 "Ultimate" 提供不同质量和价格层级。 |
+| `image` | IMAGE | 是 | | 待进行超分辨率的输入图像。 |
+| `target_resolution` | STRING | 是 | `"2K"`<br />`"4K"`<br />`"8K"` | 超分辨率后图像的期望输出分辨率。 |
+
+**注意：** 此节点要求恰好输入一张图像。提供一批图像将导致错误。
+
+## 输出
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `image` | IMAGE | 经过超分辨率处理的高分辨率输出图像。 |
diff --git a/zh-CN/built-in-nodes/WebcamCapture.mdx b/zh-CN/built-in-nodes/WebcamCapture.mdx
new file mode 100644
index 000000000..69e4ff384
--- /dev/null
+++ b/zh-CN/built-in-nodes/WebcamCapture.mdx
@@ -0,0 +1,27 @@
+---
+title: "WebcamCapture - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the WebcamCapture node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "WebcamCapture"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WebcamCapture/zh.md)
+
+WebcamCapture 节点可从网络摄像头设备捕获图像，并将其转换为可在 ComfyUI 工作流中使用的格式。该节点继承自 LoadImage 节点，并提供控制捕获尺寸和时机的选项。启用后，该节点可在每次处理工作流队列时捕获新图像。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `图像` | WEBCAM | 是 | - | 用于捕获图像的网络摄像头输入源 |
+| `宽度` | INT | 否 | 0 至 MAX_RESOLUTION | 捕获图像的期望宽度（默认：0，使用网络摄像头原生分辨率） |
+| `高度` | INT | 否 | 0 至 MAX_RESOLUTION | 捕获图像的期望高度（默认：0，使用网络摄像头原生分辨率） |
+| `执行时捕获` | BOOLEAN | 否 | - | 启用后，每次处理工作流队列时都会捕获新图像（默认：True） |
+
+**注意：** 当 `width` 和 `height` 均设置为 0 时，节点将使用网络摄像头的原生分辨率。将任一维度设置为非零值将相应调整捕获图像的尺寸。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `IMAGE` | IMAGE | 已转换为 ComfyUI 图像格式的捕获网络摄像头图像 |
diff --git a/zh-CN/built-in-nodes/ZImageFunControlnet.mdx b/zh-CN/built-in-nodes/ZImageFunControlnet.mdx
new file mode 100644
index 000000000..0393d732c
--- /dev/null
+++ b/zh-CN/built-in-nodes/ZImageFunControlnet.mdx
@@ -0,0 +1,32 @@
+---
+title: "ZImageFunControlnet - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the ZImageFunControlnet node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "ZImageFunControlnet"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ZImageFunControlnet/zh.md)
+
+ZImageFunControlnet 节点应用专门的控制网络来影响图像生成或编辑过程。它使用基础模型、模型补丁和VAE，允许您调整控制效果的强度。该节点可以与基础图像、修复图像和遮罩配合使用，实现更精准的编辑。
+
+## 输入参数
+
+| 参数 | 数据类型 | 必填 | 范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | - | 用于生成过程的基础模型。 |
+| `model_patch` | MODEL_PATCH | 是 | - | 应用控制网络引导的专门补丁模型。 |
+| `vae` | VAE | 是 | - | 用于编码和解码图像的变分自编码器。 |
+| `strength` | FLOAT | 是 | -10.0 到 10.0 | 控制网络影响的强度。正值应用效果，负值可能反转效果（默认值：1.0）。 |
+| `image` | IMAGE | 否 | - | 用于引导生成过程的可选基础图像。 |
+| `inpaint_image` | IMAGE | 否 | - | 专门用于修复由遮罩定义区域的可选图像。 |
+| `mask` | MASK | 否 | - | 定义图像中哪些区域应被编辑或修复的可选遮罩。 |
+
+**注意：** `inpaint_image` 参数通常与 `mask` 结合使用，以指定修复内容。节点的行为可能根据提供的可选输入而改变（例如，使用 `image` 进行引导，或使用 `image`、`mask` 和 `inpaint_image` 进行修复）。
+
+## 输出参数
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 已应用控制网络补丁的模型，准备好在采样流程中使用。 |
+| `positive` | CONDITIONING | 可能被控制网络输入修改的正向条件。 |
+| `negative` | CONDITIONING | 可能被控制网络输入修改的负向条件。 |
diff --git a/zh-CN/built-in-nodes/unCLIPCheckpointLoader.mdx b/zh-CN/built-in-nodes/unCLIPCheckpointLoader.mdx
new file mode 100644
index 000000000..d737aba62
--- /dev/null
+++ b/zh-CN/built-in-nodes/unCLIPCheckpointLoader.mdx
@@ -0,0 +1,29 @@
+---
+title: "unCLIPCheckpointLoader - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the unCLIPCheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "unCLIPCheckpointLoader"
+icon: "circle"
+mode: wide
+---
+该节点会检测位于 `ComfyUI/models/checkpoints` 文件夹下的模型，
+同时也会读取你在 extra_model_paths.yaml 文件中配置的额外路径的模型，
+有时你可能需要 **刷新 ComfyUI 界面** 才能让它读取到对应文件夹下的模型文件
+
+unCLIP检查点加载节点旨在加载专门为unCLIP模型定制的检查点。它便于检索和初始化模型、CLIP视觉模块和变分自编码器（VAE）从指定的检查点，简化了进一步操作或分析的设置过程。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `Checkpoint名称` | COMBO[STRING] | 'ckpt_name' 参数指定要加载的检查点的名称。它对于从预定义的检查点目录中识别和检索正确的检查点文件至关重要，从而决定了要初始化的模型和配置。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `model` | MODEL | 表示从检查点加载的主要模型。 |
+| `clip` | CLIP | 表示从检查点加载的CLIP模块，如果可用。 |
+| `vae` | VAE | 表示从检查点加载的VAE模块，如果可用。 |
+| `clip_vision` | CLIP_VISION | 表示从检查点加载的CLIP视觉模块，如果可用。 |
+
+---
diff --git a/zh-CN/built-in-nodes/unCLIPConditioning.mdx b/zh-CN/built-in-nodes/unCLIPConditioning.mdx
new file mode 100644
index 000000000..7a76d76a1
--- /dev/null
+++ b/zh-CN/built-in-nodes/unCLIPConditioning.mdx
@@ -0,0 +1,25 @@
+---
+title: "unCLIPConditioning - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the unCLIPConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "unCLIPConditioning"
+icon: "circle"
+mode: wide
+---
+此节点设计用于将CLIP视觉输出整合到条件过程中，根据指定的强度和噪声增强参数调整这些输出的影响。它通过视觉上下文丰富了条件，增强了生成过程。
+
+## 输入
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 基础条件数据，将向其添加CLIP视觉输出，作为进一步修改的基础。 |
+| `CLIP视觉输出` | `CLIP_VISION_OUTPUT` | 来自CLIP视觉模型的输出，提供被整合进条件的视觉上下文。 |
+| `强度` | `FLOAT` | 确定CLIP视觉输出对条件影响的强度。 |
+| `噪波增强` | `FLOAT` | 指定在将CLIP视觉输出整合进条件之前应用的噪声增强水平。 |
+
+## 输出
+
+| 参数名称 | 数据类型 | 作用 |
+| --- | --- | --- |
+| `CONDITIONING` | CONDITIONING | 丰富的条件数据，现在包含已应用强度和噪声增强的整合CLIP视觉输出。 |
+
+---
diff --git a/zh-CN/built-in-nodes/wanBlockSwap.mdx b/zh-CN/built-in-nodes/wanBlockSwap.mdx
new file mode 100644
index 000000000..4bc7d9100
--- /dev/null
+++ b/zh-CN/built-in-nodes/wanBlockSwap.mdx
@@ -0,0 +1,22 @@
+---
+title: "wanBlockSwap - ComfyUI Built-in Node Documentation"
+description: "Complete documentation for the wanBlockSwap node in ComfyUI. Learn its inputs, outputs, parameters and usage."
+sidebarTitle: "wanBlockSwap"
+icon: "circle"
+mode: wide
+---
+> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/wanBlockSwap/zh.md)
+
+此节点已弃用，不执行任何功能。它接受一个模型作为输入，并原封不动地返回相同的模型。描述中的 "NOP" 表示它不执行任何操作。
+
+## 输入参数
+
+| 参数名 | 数据类型 | 必填 | 取值范围 | 描述 |
+|-----------|-----------|----------|-------|-------------|
+| `model` | MODEL | 是 | | 要通过此节点传递的模型。 |
+
+## 输出结果
+
+| 输出名称 | 数据类型 | 描述 |
+|-------------|-----------|-------------|
+| `model` | MODEL | 与输入提供的模型相同，未作任何更改。 |
diff --git a/zh-CN/tutorials/partner-nodes/pricing.mdx b/zh-CN/tutorials/partner-nodes/pricing.mdx
index 15ec94dc1..f14c775b7 100644
--- a/zh-CN/tutorials/partner-nodes/pricing.mdx
+++ b/zh-CN/tutorials/partner-nodes/pricing.mdx
@@ -13,567 +13,598 @@ mode: wide
 
 ## BFL
 
-| 产品名称                   | 配置                       | 积分        | 类别  |
-| :------------------------- | :------------------------- | :---------- | :---- |
-| prod-v1-BFL Image Products | model: flux-dev            | 5.28 / run  | Image |
-| prod-v1-BFL Image Products | model: flux-kontext-max    | 16.88 / run | Image |
-| prod-v1-BFL Image Products | model: flux-kontext-pro    | 8.44 / run  | Image |
-| prod-v1-BFL Image Products | model: flux-pro-1.0-canny  | 10.55 / run | Image |
-| prod-v1-BFL Image Products | model: flux-pro-1.0-depth  | 10.55 / run | Image |
-| prod-v1-BFL Image Products | model: flux-pro-1.0-expand | 10.55 / run | Image |
-| prod-v1-BFL Image Products | model: flux-pro-1.0-fill   | 10.55 / run | Image |
-| prod-v1-BFL Image Products | model: flux-pro-1.1        | 8.44 / run  | Image |
-| prod-v1-BFL Image Products | model: flux-pro-1.1-ultra  | 12.66 / run | Image |
-| prod-v1-BFL Image Products | model: /v1/flux-pro        | 10.55 / run | Image |
-| BFL Cost                   | NA                         | 2.11 / run  | Image |
+| 产品名称               | 配置              | 积分     | 类别 |
+| :------------------------- | :------------------------- | :---------- | :------- |
+| prod-v1-BFL Image Products | model: flux-dev            | 5.28 / run  | Image    |
+| prod-v1-BFL Image Products | model: flux-kontext-max    | 16.88 / run | Image    |
+| prod-v1-BFL Image Products | model: flux-kontext-pro    | 8.44 / run  | Image    |
+| prod-v1-BFL Image Products | model: flux-pro-1.0-canny  | 10.55 / run | Image    |
+| prod-v1-BFL Image Products | model: flux-pro-1.0-depth  | 10.55 / run | Image    |
+| prod-v1-BFL Image Products | model: flux-pro-1.0-expand | 10.55 / run | Image    |
+| prod-v1-BFL Image Products | model: flux-pro-1.0-fill   | 10.55 / run | Image    |
+| prod-v1-BFL Image Products | model: flux-pro-1.1        | 8.44 / run  | Image    |
+| prod-v1-BFL Image Products | model: flux-pro-1.1-ultra  | 12.66 / run | Image    |
+| prod-v1-BFL Image Products | model: /v1/flux-pro        | 10.55 / run | Image    |
+| BFL Cost                   | NA                         | 2.11 / run  | Image    |
 
 ## Bria
 
-| 产品名称        | 配置                                 | 积分       | 类别  |
-| :-------------- | :----------------------------------- | :--------- | :---- |
-| Bria Image Edit | endpoint: v2/image/edit, model: fibo | 8.44 / run | Image |
+| 产品名称                 | 配置                             | 积分     | 类别 |
+| :--------------------------- | :---------------------------------------- | :---------- | :------- |
+| Bria Image Edit              | endpoint: v2/image/edit, model: fibo      | 8.44 / run  | Image    |
+| Bria Image Remove Background | endpoint: v2/image/edit/remove_background | 3.8 / run   | Image    |
+| Bria Video Remove Background | endpoint: v2/video/edit/remove_background | 29.54 / sec | Video    |
 
 ## ByteDance
 
-| 产品名称                                             | 配置                                                            | 积分              | 类别  |
-| :--------------------------------------------------- | :-------------------------------------------------------------- | :---------------- | :---- |
-| BytePlus Image Generation Product                    | model: seededit-3-0-i2i-250628                                  | 6.33 / run        | Image |
-| BytePlus Image Generation Product                    | model: seedream-3-0-t2i-250415                                  | 6.33 / run        | Image |
-| BytePlus Image Generation Product                    | model: seedream-4-0-250828                                      | 6.33 / run        | Image |
-| BytePlus Image Generation Product                    | model: seedream-4-5-251128                                      | 8.44 / run        | Image |
-| BytePlus Image Generation Product                    | model: seedream-5-0-lite                                        | 7.4 / run         | Image |
-| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-lite-i2v-250428, video_type: image-to-video | 379.8 / 1M tokens | Video |
-| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-lite-t2v-250428, video_type: text-to-video  | 379.8 / 1M tokens | Video |
-| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-250528, video_type: image-to-video      | 527.5 / 1M tokens | Video |
-| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-250528, video_type: text-to-video       | 527.5 / 1M tokens | Video |
-| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-fast-251015, video_type: image-to-video | 211 / 1M tokens   | Video |
-| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-fast-251015, video_type: text-to-video  | 211 / 1M tokens   | Video |
-| BytePlus Video Generation Product (Per 1M tokens)    | model: seedream-4-5-251128, video_type: text-to-video           | 211 / 1M tokens   | Video |
-| BytePlus Video Generation With Audio (Per 1M tokens) | generate_audio: false, model: seedance-1-5-pro-251215           | 253.2 / 1M tokens | Video |
-| BytePlus Video Generation With Audio (Per 1M tokens) | generate_audio: true, model: seedance-1-5-pro-251215            | 506.4 / 1M tokens | Video |
+| 产品名称                                         | 配置                                                   | 积分           | 类别 |
+| :--------------------------------------------------- | :-------------------------------------------------------------- | :---------------- | :------- |
+| BytePlus Image Generation Product                    | model: seededit-3-0-i2i-250628                                  | 6.33 / run        | Image    |
+| BytePlus Image Generation Product                    | model: seedream-3-0-t2i-250415                                  | 6.33 / run        | Image    |
+| BytePlus Image Generation Product                    | model: seedream-4-0-250828                                      | 6.33 / run        | Image    |
+| BytePlus Image Generation Product                    | model: seedream-4-5-251128                                      | 8.44 / run        | Image    |
+| BytePlus Image Generation Product                    | model: seedream-5-0-260128                                      | 7.39 / run        | Image    |
+| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-lite-i2v-250428, video_type: image-to-video | 379.8 / 1M tokens | Video    |
+| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-lite-t2v-250428, video_type: text-to-video  | 379.8 / 1M tokens | Video    |
+| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-250528, video_type: image-to-video      | 527.5 / 1M tokens | Video    |
+| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-250528, video_type: text-to-video       | 527.5 / 1M tokens | Video    |
+| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-fast-251015, video_type: image-to-video | 211 / 1M tokens   | Video    |
+| BytePlus Video Generation Product (Per 1M tokens)    | model: seedance-1-0-pro-fast-251015, video_type: text-to-video  | 211 / 1M tokens   | Video    |
+| BytePlus Video Generation Product (Per 1M tokens)    | model: seedream-4-5-251128, video_type: text-to-video           | 211 / 1M tokens   | Video    |
+| BytePlus Video Generation With Audio (Per 1M tokens) | generate_audio: false, model: seedance-1-5-pro-251215           | 253.2 / 1M tokens | Video    |
+| BytePlus Video Generation With Audio (Per 1M tokens) | generate_audio: true, model: seedance-1-5-pro-251215            | 506.4 / 1M tokens | Video    |
+
+## ElevenLabs
+
+| 产品名称                           | 配置                                              | 积分     | 类别 |
+| :------------------------------------- | :--------------------------------------------------------- | :---------- | :------- |
+| 11labs Text-to-Speech                  | endpoint: v1/text-to-dialogue, model: eleven_v3            | 50.64 / run | Audio    |
+| 11labs Text-to-Speech                  | endpoint: v1/text-to-speech, model: eleven_multilingual_v2 | 50.64 / run | Audio    |
+| 11labs Text-to-Speech                  | endpoint: v1/text-to-speech, model: eleven_v3              | 50.64 / run | Audio    |
+| 11labs Speech-to-Text                  | endpoint: v1/speech-to-text, model: scribe_v2              | 92.84 / run | Audio    |
+| 11labs Speech-to-Text Keyterm          | endpoint: v1/speech-to-text, model: scribe_v2              | 18.57 / run | Audio    |
+| 11labs Speech-to-Text Entity Detection | endpoint: scribe_v2, model: v1/speech-to-text              | 27.85 / run | Audio    |
+| 11labs Speech-to-Speech Per Minute     | endpoint: v1/speech-to-speech                              | 50.64 / min | Audio    |
+| 11labs Sound Generation Per Minute     | endpoint: v1/sound-generation                              | 29.54 / min | Audio    |
+| 11labs Audio Isolation Per Minute      | endpoint: v1/audio-isolation                               | 50.64 / min | Audio    |
+| 11labs Add Voice                       | endpoint: v1/voices/add                                    | 31.65 / run | Audio    |
 
 ## Freepik
 
-| 产品名称                     | 配置                              | 积分        | 类别  |
-| :--------------------------- | :-------------------------------- | :---------- | :---- |
-| Freepik Image Per Generation | endpoint: magnific-relight        | 23.21 / run | Image |
-| Freepik Image Per Generation | endpoint: magnific-style-transfer | 23.21 / run | Image |
-| Freepik Image Per Generation | endpoint: skin-enhancer-creative  | 61.19 / run | Image |
-| Freepik Image Per Generation | endpoint: skin-enhancer-faithful  | 78.07 / run | Image |
-| Freepik Image Per Generation | endpoint: skin-enhancer-flexible  | 94.95 / run | Image |
+| 产品名称                 | 配置                     | 积分     | 类别 |
+| :--------------------------- | :-------------------------------- | :---------- | :------- |
+| Freepik Image Per Generation | endpoint: magnific-relight        | 23.21 / run | Image    |
+| Freepik Image Per Generation | endpoint: magnific-style-transfer | 23.21 / run | Image    |
+| Freepik Image Per Generation | endpoint: skin-enhancer-creative  | 61.19 / run | Image    |
+| Freepik Image Per Generation | endpoint: skin-enhancer-faithful  | 78.07 / run | Image    |
+| Freepik Image Per Generation | endpoint: skin-enhancer-flexible  | 94.95 / run | Image    |
+| Freepik Image Cost           | NA                                | 211 / run   | Image    |
 
 ## Google
 
-| 产品名称                                    | 配置                                                       | 积分               | 类别  |
-| :------------------------------------------ | :--------------------------------------------------------- | :----------------- | :---- |
-| prod-v1-Veo 2 Product                       | model: veo-2.0-generate-001                                | 105.5 / run        | Image |
-| prod-v1-Veo 2 Product                       | model: veo-3.0-generate-preview                            | 158.25 / run       | Image |
-| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash-image                              | 63.3 / 1M tokens   | Text  |
-| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash-image-preview                      | 63.3 / 1M tokens   | Text  |
-| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash                                    | 63.3 / 1M tokens   | Text  |
-| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Text  |
-| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Text  |
-| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Text  |
-| Gemini Input Text Tokens (per 1M) Product   | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Text  |
-| Gemini Input Text Tokens (per 1M) Product   | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Text  |
-| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 527.5 / 1M tokens  | Text  |
-| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 527.5 / 1M tokens  | Text  |
-| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash                                    | 527.5 / 1M tokens  | Text  |
-| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 527.5 / 1M tokens  | Text  |
-| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 2110 / 1M tokens   | Text  |
-| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 2110 / 1M tokens   | Text  |
-| Gemini Output Text Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 2532 / 1M tokens   | Text  |
-| Gemini Output Text Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 2532 / 1M tokens   | Text  |
-| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 63.3 / 1M tokens   | Image |
-| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 63.3 / 1M tokens   | Image |
-| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash                                    | 63.3 / 1M tokens   | Image |
-| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Image |
-| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Image |
-| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Image |
-| Gemini Input Image Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Image |
-| Gemini Input Image Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Image |
-| Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-image                              | 6330 / 1M tokens   | Image |
-| Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-image-preview                      | 6330 / 1M tokens   | Image |
-| Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 3165 / 1M tokens   | Image |
-| Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-pro-preview-05-06                        | 7385 / 1M tokens   | Image |
-| Gemini Output Image Tokens (per 1M) Product | model: gemini-3-pro-image-preview                          | 25320 / 1M tokens  | Image |
-| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 63.3 / 1M tokens   | Video |
-| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 63.3 / 1M tokens   | Video |
-| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash                                    | 63.3 / 1M tokens   | Video |
-| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Video |
-| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Video |
-| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Video |
-| Gemini Input Video Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Video |
-| Gemini Input Video Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Video |
-| Gemini Output Video Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 4220 / 1M tokens   | Video |
-| Gemini Output Video Tokens (per 1M) Product | model: gemini-2.5-pro-preview-05-06                        | 8440 / 1M tokens   | Video |
-| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 211 / 1M tokens    | Audio |
-| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 211 / 1M tokens    | Audio |
-| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash                                    | 211 / 1M tokens    | Audio |
-| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 211 / 1M tokens    | Audio |
-| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Audio |
-| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Audio |
-| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Audio |
-| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Audio |
-| Gemini Output Audio Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 3165 / 1M tokens   | Audio |
-| Gemini Output Audio Tokens (per 1M) Product | model: gemini-2.5-pro-preview-05-06                        | 7385 / 1M tokens   | Audio |
-| Google Veo3/Veo3 Fast Video Generation      | generateAudio: false, model: veo-3.0-fast-generate-001     | 168.8 / run        | Video |
-| Google Veo3/Veo3 Fast Video Generation      | generateAudio: false, model: veo-3.0-generate-001          | 337.6 / run        | Video |
-| Google Veo3/Veo3 Fast Video Generation      | generateAudio: true, model: veo-3.0-fast-generate-001      | 253.2 / run        | Video |
-| Google Veo3/Veo3 Fast Video Generation      | generateAudio: true, model: veo-3.0-generate-001           | 675.2 / run        | Video |
-| Google Veo2 Video Generation                | NA                                                         | 105.5 / run        | Video |
-| Google Veo3                                 | generateAudio: false, model: veo-3.0-fast-generate-001     | 21.1 / run         | Image |
-| Google Veo3                                 | generateAudio: false, model: veo-3.0-generate-001          | 42.2 / run         | Image |
-| Google Veo3                                 | generateAudio: false, model: veo-3.1-fast-generate-preview | 21.1 / run         | Image |
-| Google Veo3                                 | generateAudio: false, model: veo-3.1-generate-preview      | 42.2 / run         | Image |
-| Google Veo3                                 | generateAudio: true, model: veo-3.0-fast-generate-001      | 31.65 / run        | Image |
-| Google Veo3                                 | generateAudio: true, model: veo-3.0-generate-001           | 84.4 / run         | Image |
-| Google Veo3                                 | generateAudio: true, model: veo-3.1-fast-generate-preview  | 31.65 / run        | Image |
-| Google Veo3                                 | generateAudio: true, model: veo-3.1-generate-preview       | 84.4 / run         | Image |
-| Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3-pro-image-preview                          | 2532 / 1M tokens   | Text  |
-| Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3-pro-preview                                | 2532 / 1M tokens   | Text  |
+| 产品名称                                | 配置                                              | 积分            | 类别 |
+| :------------------------------------------ | :--------------------------------------------------------- | :----------------- | :------- |
+| prod-v1-Veo 2 Product                       | model: veo-2.0-generate-001                                | 105.5 / run        | Image    |
+| prod-v1-Veo 2 Product                       | model: veo-3.0-generate-preview                            | 158.25 / run       | Image    |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash-image                              | 63.3 / 1M tokens   | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash-image-preview                      | 63.3 / 1M tokens   | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash                                    | 63.3 / 1M tokens   | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-3.1-flash-image-preview                      | 105.5 / 1M tokens  | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-3.1-pro-preview                              | 422 / 1M tokens    | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Text     |
+| Gemini Input Text Tokens (per 1M) Product   | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 527.5 / 1M tokens  | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 527.5 / 1M tokens  | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash                                    | 527.5 / 1M tokens  | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 527.5 / 1M tokens  | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 2110 / 1M tokens   | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 2110 / 1M tokens   | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-3.1-flash-image-preview                      | 633 / 1M tokens    | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-3.1-pro-preview                              | 2532 / 1M tokens   | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 2532 / 1M tokens   | Text     |
+| Gemini Output Text Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 2532 / 1M tokens   | Text     |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 63.3 / 1M tokens   | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 63.3 / 1M tokens   | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash                                    | 63.3 / 1M tokens   | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-3.1-flash-image-preview                      | 105.5 / 1M tokens  | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-3.1-pro-preview                              | 422 / 1M tokens    | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Image    |
+| Gemini Input Image Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-image                              | 6330 / 1M tokens   | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-image-preview                      | 6330 / 1M tokens   | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 3165 / 1M tokens   | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-2.5-pro-preview-05-06                        | 7385 / 1M tokens   | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-3.1-flash-image-preview                      | 12660 / 1M tokens  | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-3.1-pro-preview                              | 25320 / 1M tokens  | Image    |
+| Gemini Output Image Tokens (per 1M) Product | model: gemini-3-pro-image-preview                          | 25320 / 1M tokens  | Image    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 63.3 / 1M tokens   | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 63.3 / 1M tokens   | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash                                    | 63.3 / 1M tokens   | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 63.3 / 1M tokens   | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-3.1-pro-preview                              | 422 / 1M tokens    | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Video    |
+| Gemini Input Video Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Video    |
+| Gemini Output Video Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 4220 / 1M tokens   | Video    |
+| Gemini Output Video Tokens (per 1M) Product | model: gemini-2.5-pro-preview-05-06                        | 8440 / 1M tokens   | Video    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash-image                              | 211 / 1M tokens    | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash-image-preview                      | 211 / 1M tokens    | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash                                    | 211 / 1M tokens    | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-flash-preview-04-17                      | 211 / 1M tokens    | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-pro                                      | 263.75 / 1M tokens | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-2.5-pro-preview-05-06                        | 263.75 / 1M tokens | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-3.1-pro-preview                              | 422 / 1M tokens    | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-3-pro-image-preview                          | 422 / 1M tokens    | Audio    |
+| Gemini Input Audio Tokens (per 1M) Product  | model: gemini-3-pro-preview                                | 422 / 1M tokens    | Audio    |
+| Gemini Output Audio Tokens (per 1M) Product | model: gemini-2.5-flash-preview-04-17                      | 3165 / 1M tokens   | Audio    |
+| Gemini Output Audio Tokens (per 1M) Product | model: gemini-2.5-pro-preview-05-06                        | 7385 / 1M tokens   | Audio    |
+| Google Veo3/Veo3 Fast Video Generation      | generateAudio: false, model: veo-3.0-fast-generate-001     | 168.8 / run        | Video    |
+| Google Veo3/Veo3 Fast Video Generation      | generateAudio: false, model: veo-3.0-generate-001          | 337.6 / run        | Video    |
+| Google Veo3/Veo3 Fast Video Generation      | generateAudio: true, model: veo-3.0-fast-generate-001      | 253.2 / run        | Video    |
+| Google Veo3/Veo3 Fast Video Generation      | generateAudio: true, model: veo-3.0-generate-001           | 675.2 / run        | Video    |
+| Google Veo2 Video Generation                | NA                                                         | 105.5 / run        | Video    |
+| Google Veo3                                 | generateAudio: false, model: veo-3.0-fast-generate-001     | 21.1 / run         | Image    |
+| Google Veo3                                 | generateAudio: false, model: veo-3.0-generate-001          | 42.2 / run         | Image    |
+| Google Veo3                                 | generateAudio: false, model: veo-3.1-fast-generate-preview | 21.1 / run         | Image    |
+| Google Veo3                                 | generateAudio: false, model: veo-3.1-generate-preview      | 42.2 / run         | Image    |
+| Google Veo3                                 | generateAudio: true, model: veo-3.0-fast-generate-001      | 31.65 / run        | Image    |
+| Google Veo3                                 | generateAudio: true, model: veo-3.0-generate-001           | 84.4 / run         | Image    |
+| Google Veo3                                 | generateAudio: true, model: veo-3.1-fast-generate-preview  | 31.65 / run        | Image    |
+| Google Veo3                                 | generateAudio: true, model: veo-3.1-generate-preview       | 84.4 / run         | Image    |
+| Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3.1-flash-image-preview                      | 633 / 1M tokens    | Text     |
+| Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3.1-pro-preview                              | 2532 / 1M tokens   | Text     |
+| Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3-pro-image-preview                          | 2532 / 1M tokens   | Text     |
+| Gemini Thoughts Tokens (per 1M) Product     | model: gemini-3-pro-preview                                | 2532 / 1M tokens   | Text     |
+
+## Hitpaw
+
+| 产品名称   | 配置 | 积分    | 类别 |
+| :------------- | :------------ | :--------- | :------- |
+| Hitpaw Credits | NA            | 0.21 / run | Image    |
 
 ## Ideogram
 
-| 产品名称                                  | 配置                                                                   | 积分        | 类别  |
-| :---------------------------------------- | :--------------------------------------------------------------------- | :---------- | :---- |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit-character-ref, rendering_speed: DEFAULT     | 45.26 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit-character-ref, rendering_speed: QUALITY     | 60.35 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit-character-ref, rendering_speed: TURBO       | 30.17 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit, rendering_speed: BALANCED                  | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit, rendering_speed: DEFAULT                   | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit, rendering_speed: QUALITY                   | 27.16 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit, rendering_speed: TURBO                     | 9.05 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate-character-ref, rendering_speed: DEFAULT | 45.26 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate-character-ref, rendering_speed: QUALITY | 60.35 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate-character-ref, rendering_speed: TURBO   | 30.17 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate, rendering_speed: BALANCED              | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate, rendering_speed: DEFAULT               | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate, rendering_speed: QUALITY               | 27.16 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate, rendering_speed: TURBO                 | 9.05 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/reframe, rendering_speed: DEFAULT                | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/reframe, rendering_speed: QUALITY                | 27.16 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/reframe, rendering_speed: TURBO                  | 9.05 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/remix, rendering_speed: BALANCED                 | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/remix, rendering_speed: DEFAULT                  | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/remix, rendering_speed: QUALITY                  | 27.16 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/remix, rendering_speed: TURBO                    | 9.05 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/replace-background, rendering_speed: BALANCED    | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/replace-background, rendering_speed: DEFAULT     | 18.1 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/replace-background, rendering_speed: QUALITY     | 27.16 / run | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/replace-background, rendering_speed: TURBO       | 9.05 / run  | Image |
-| prod-v1-Ideogram V3 Image Generation      | endpoint: remix, rendering_speed: TURBO                                | 9.05 / run  | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: edit, model: v_2                                             | 24.14 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: edit, model: v_2_turbo                                       | 15.09 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_1                                         | 18.1 / run  | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_1_turbo                                   | 6.03 / run  | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_2a                                        | 12.07 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_2a_turbo                                  | 7.54 / run  | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_2                                         | 24.14 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_2_turbo                                   | 15.09 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: reframe, model: v_2                                          | 24.14 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: reframe, model: v_2_turbo                                    | 15.09 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_1                                            | 18.1 / run  | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_1_turbo                                      | 6.03 / run  | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_2a                                           | 12.07 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_2a_turbo                                     | 7.54 / run  | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_2                                            | 24.14 / run | Image |
-| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_2_turbo                                      | 15.09 / run | Image |
+| 产品名称                              | 配置                                                          | 积分     | 类别 |
+| :---------------------------------------- | :--------------------------------------------------------------------- | :---------- | :------- |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit-character-ref, rendering_speed: DEFAULT     | 45.26 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit-character-ref, rendering_speed: QUALITY     | 60.35 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit-character-ref, rendering_speed: TURBO       | 30.17 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit, rendering_speed: BALANCED                  | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit, rendering_speed: DEFAULT                   | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit, rendering_speed: QUALITY                   | 27.16 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/edit, rendering_speed: TURBO                     | 9.05 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate-character-ref, rendering_speed: DEFAULT | 45.26 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate-character-ref, rendering_speed: QUALITY | 60.35 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate-character-ref, rendering_speed: TURBO   | 30.17 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate, rendering_speed: BALANCED              | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate, rendering_speed: DEFAULT               | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate, rendering_speed: QUALITY               | 27.16 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/generate, rendering_speed: TURBO                 | 9.05 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/reframe, rendering_speed: DEFAULT                | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/reframe, rendering_speed: QUALITY                | 27.16 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/reframe, rendering_speed: TURBO                  | 9.05 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/remix, rendering_speed: BALANCED                 | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/remix, rendering_speed: DEFAULT                  | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/remix, rendering_speed: QUALITY                  | 27.16 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/remix, rendering_speed: TURBO                    | 9.05 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/replace-background, rendering_speed: BALANCED    | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/replace-background, rendering_speed: DEFAULT     | 18.1 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/replace-background, rendering_speed: QUALITY     | 27.16 / run | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: ideogram-v3/replace-background, rendering_speed: TURBO       | 9.05 / run  | Image    |
+| prod-v1-Ideogram V3 Image Generation      | endpoint: remix, rendering_speed: TURBO                                | 9.05 / run  | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: edit, model: v_2                                             | 24.14 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: edit, model: v_2_turbo                                       | 15.09 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_1                                         | 18.1 / run  | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_1_turbo                                   | 6.03 / run  | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_2a                                        | 12.07 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_2a_turbo                                  | 7.54 / run  | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_2                                         | 24.14 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: generate, model: v_2_turbo                                   | 15.09 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: reframe, model: v_2                                          | 24.14 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: reframe, model: v_2_turbo                                    | 15.09 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_1                                            | 18.1 / run  | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_1_turbo                                      | 6.03 / run  | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_2a                                           | 12.07 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_2a_turbo                                     | 7.54 / run  | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_2                                            | 24.14 / run | Image    |
+| prod-v1-Ideogram Image Generation Product | endpoint: remix, model: v_2_turbo                                      | 15.09 / run | Image    |
 
 ## Kling
 
-| 产品名称                                  | 配置                                                         | 积分         | 类别  |
-| :---------------------------------------- | :----------------------------------------------------------- | :----------- | :---- |
-| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v1-5                                 | 103.39 / run | Video |
-| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v1-6                                 | 103.39 / run | Video |
-| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v1                                   | 103.39 / run | Video |
-| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v2-1-master                          | 295.4 / run  | Video |
-| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v2-1                                 | 103.39 / run | Video |
-| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v2-5-turbo                           | 73.85 / run  | Video |
-| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v2-master                            | 295.4 / run  | Video |
-| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v1-5                                 | 59.08 / run  | Video |
-| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v1-6                                 | 59.08 / run  | Video |
-| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v1                                   | 29.54 / sec  | Video |
-| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v2-1-master                          | 295.4 / run  | Video |
-| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v2-1                                 | 59.08 / run  | Video |
-| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v2-master                            | 295.4 / run  | Video |
-| Kling Virtual Try On                      | model: kolors-virtual-try-on-v1-5                            | 14.77 / run  | Image |
-| Kling Virtual Try On                      | model: kolors-virtual-try-on-v1                              | 14.77 / run  | Image |
-| Kling Image Generation Product            | model: kling-v1-5, operation: image_to_image                 | 5.91 / run   | Image |
-| Kling Image Generation Product            | model: kling-v1-5, operation: text_to_image                  | 2.95 / run   | Image |
-| Kling Image Generation Product            | model: kling-v1, operation: image_to_image                   | 0.74 / run   | Image |
-| Kling Image Generation Product            | model: kling-v1, operation: text_to_image                    | 0.74 / run   | Image |
-| Kling Image Generation Product            | model: kling-v2, operation: text_to_image                    | 2.95 / run   | Image |
-| Kling Video Extension Product             | NA                                                           | 59.08 / run  | Video |
-| Kling Lip Sync Product                    | NA                                                           | 14.77 / run  | Image |
-| Kling Image Generation w/ N               | model: kling-v1-5, operation: image_to_image                 | 5.91 / run   | Image |
-| Kling Image Generation w/ N               | model: kling-v1-5, operation: text_to_image                  | 2.95 / run   | Image |
-| Kling Image Generation w/ N               | model: kling-v1, operation: image_to_image                   | 0.74 / run   | Image |
-| Kling Image Generation w/ N               | model: kling-v1, operation: text_to_image                    | 0.74 / run   | Image |
-| Kling Image Generation w/ N               | model: kling-v2, operation: text_to_image                    | 2.95 / run   | Image |
-| Kling Omni Video Product                  | generate_with_video: false, mode: pro, model: kling-video-o1 | 23.63 / sec  | Video |
-| Kling Omni Video Product                  | generate_with_video: false, mode: std, model: kling-video-o1 | 17.72 / sec  | Video |
-| Kling Omni Video Product                  | generate_with_video: true, mode: pro, model: kling-video-o1  | 35.45 / sec  | Video |
-| Kling Omni Video Product                  | generate_with_video: true, mode: std, model: kling-video-o1  | 26.59 / sec  | Video |
-| Kling Omni Image Product                  | model: kling-image-o1                                        | 5.91 / run   | Image |
-| Kling Video Generation with Sound Product | mode: pro, model: kling-v2-6, sound: off                     | 14.77 / sec  | Video |
-| Kling Video Generation with Sound Product | mode: pro, model: kling-v2-6, sound: on                      | 29.54 / sec  | Video |
-| Kling Motion Control Product              | mode: pro, model: kling-v2-6                                 | 23.63 / run  | Image |
-| Kling Motion Control Product              | mode: std, model: kling-v2-6                                 | 14.77 / run  | Image |
+| 产品名称                              | 配置                                                | 积分      | 类别 |
+| :---------------------------------------- | :----------------------------------------------------------- | :----------- | :------- |
+| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v1-5                                 | 103.39 / run | Video    |
+| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v1-6                                 | 103.39 / run | Video    |
+| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v1                                   | 103.39 / run | Video    |
+| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v2-1-master                          | 295.4 / run  | Video    |
+| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v2-1                                 | 103.39 / run | Video    |
+| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v2-5-turbo                           | 73.85 / run  | Video    |
+| prod-v1-Kling Video Generation Product    | mode: pro, model: kling-v2-master                            | 295.4 / run  | Video    |
+| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v1-5                                 | 59.08 / run  | Video    |
+| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v1-6                                 | 59.08 / run  | Video    |
+| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v1                                   | 29.54 / sec  | Video    |
+| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v2-1-master                          | 295.4 / run  | Video    |
+| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v2-1                                 | 59.08 / run  | Video    |
+| prod-v1-Kling Video Generation Product    | mode: std, model: kling-v2-master                            | 295.4 / run  | Video    |
+| Kling Virtual Try On                      | model: kolors-virtual-try-on-v1-5                            | 14.77 / run  | Image    |
+| Kling Virtual Try On                      | model: kolors-virtual-try-on-v1                              | 14.77 / run  | Image    |
+| Kling Image Generation Product            | model: kling-v1-5, operation: image_to_image                 | 5.91 / run   | Image    |
+| Kling Image Generation Product            | model: kling-v1-5, operation: text_to_image                  | 2.95 / run   | Image    |
+| Kling Image Generation Product            | model: kling-v1, operation: image_to_image                   | 0.74 / run   | Image    |
+| Kling Image Generation Product            | model: kling-v1, operation: text_to_image                    | 0.74 / run   | Image    |
+| Kling Image Generation Product            | model: kling-v2, operation: text_to_image                    | 2.95 / run   | Image    |
+| Kling Video Extension Product             | NA                                                           | 59.08 / run  | Video    |
+| Kling Lip Sync Product                    | NA                                                           | 14.77 / run  | Image    |
+| Kling Image Generation w/ N               | model: kling-v1-5, operation: image_to_image                 | 5.91 / run   | Image    |
+| Kling Image Generation w/ N               | model: kling-v1-5, operation: text_to_image                  | 2.95 / run   | Image    |
+| Kling Image Generation w/ N               | model: kling-v1, operation: image_to_image                   | 0.74 / run   | Image    |
+| Kling Image Generation w/ N               | model: kling-v1, operation: text_to_image                    | 0.74 / run   | Image    |
+| Kling Image Generation w/ N               | model: kling-v2, operation: text_to_image                    | 2.95 / run   | Image    |
+| Kling Omni Video Product                  | generate_with_video: false, mode: pro, model: kling-video-o1 | 23.63 / sec  | Video    |
+| Kling Omni Video Product                  | generate_with_video: false, mode: std, model: kling-video-o1 | 17.72 / sec  | Video    |
+| Kling Omni Video Product                  | generate_with_video: true, mode: pro, model: kling-video-o1  | 35.45 / sec  | Video    |
+| Kling Omni Video Product                  | generate_with_video: true, mode: std, model: kling-video-o1  | 26.59 / sec  | Video    |
+| Kling Omni Image Product                  | model: kling-image-o1                                        | 5.91 / run   | Image    |
+| Kling Video Generation with Sound Product | mode: pro, model: kling-v2-6, sound: off                     | 14.77 / sec  | Video    |
+| Kling Video Generation with Sound Product | mode: pro, model: kling-v2-6, sound: on                      | 29.54 / sec  | Video    |
+| Kling Motion Control Product              | mode: pro, model: kling-v2-6                                 | 23.63 / run  | Image    |
+| Kling Motion Control Product              | mode: std, model: kling-v2-6                                 | 14.77 / run  | Image    |
+| Kling Credits                             | type: image                                                  | 0.74 / run   | Image    |
+| Kling Credits                             | type: video                                                  | 29.54 / run  | Image    |
 
 ## Lightricks
 
-| 产品名称                     | 配置                                                               | 积分        | 类别  |
-| :--------------------------- | :----------------------------------------------------------------- | :---------- | :---- |
-| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-fast, resolution: 1920x1080 | 8.44 / sec  | Video |
-| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-fast, resolution: 2560x1440 | 16.88 / sec | Video |
-| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-fast, resolution: 3840x2160 | 33.76 / sec | Video |
-| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-pro, resolution: 1920x1080  | 12.66 / sec | Video |
-| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-pro, resolution: 2560x1440  | 25.32 / sec | Video |
-| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-pro, resolution: 3840x2160  | 50.64 / run | Video |
-| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-fast, resolution: 1920x1080  | 8.44 / sec  | Video |
-| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-fast, resolution: 2560x1440  | 16.88 / sec | Video |
-| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-fast, resolution: 3840x2160  | 33.76 / sec | Video |
-| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-pro, resolution: 1920x1080   | 12.66 / sec | Video |
-| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-pro, resolution: 2560x1440   | 25.32 / sec | Video |
-| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-pro, resolution: 3840x2160   | 50.64 / run | Video |
+| 产品名称                 | 配置                                                      | 积分     | 类别 |
+| :--------------------------- | :----------------------------------------------------------------- | :---------- | :------- |
+| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-fast, resolution: 1920x1080 | 8.44 / sec  | Video    |
+| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-fast, resolution: 2560x1440 | 16.88 / sec | Video    |
+| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-fast, resolution: 3840x2160 | 33.76 / sec | Video    |
+| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-pro, resolution: 1920x1080  | 12.66 / sec | Video    |
+| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-pro, resolution: 2560x1440  | 25.32 / sec | Video    |
+| Ltx Video generation product | endpoint: image-to-video, model: ltx-2-pro, resolution: 3840x2160  | 50.64 / run | Video    |
+| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-fast, resolution: 1920x1080  | 8.44 / sec  | Video    |
+| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-fast, resolution: 2560x1440  | 16.88 / sec | Video    |
+| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-fast, resolution: 3840x2160  | 33.76 / sec | Video    |
+| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-pro, resolution: 1920x1080   | 12.66 / sec | Video    |
+| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-pro, resolution: 2560x1440   | 25.32 / sec | Video    |
+| Ltx Video generation product | endpoint: text-to-video, model: ltx-2-pro, resolution: 3840x2160   | 50.64 / run | Video    |
 
 ## Luma
 
-| 产品名称                                            | 配置                  | 积分       | 类别  |
-| :-------------------------------------------------- | :-------------------- | :--------- | :---- |
-| prod-v1-Luma Video Generation Product               | model: ray-1-6        | 0.97 / sec | Video |
-| prod-v1-Luma Video Generation Product               | model: ray-2          | 1.93 / sec | Video |
-| prod-v1-Luma Video Generation Product               | model: ray-flash-2    | 0.66 / sec | Video |
-| Luma Image Generations (millions of pixels) Product | model: photon-1       | 2.2 / run  | Image |
-| Luma Image Generations (millions of pixels) Product | model: photon-flash-1 | 0.57 / run | Image |
+| 产品名称                                        | 配置         | 积分    | 类别 |
+| :-------------------------------------------------- | :-------------------- | :--------- | :------- |
+| prod-v1-Luma Video Generation Product               | model: ray-1-6        | 0.97 / sec | Video    |
+| prod-v1-Luma Video Generation Product               | model: ray-2          | 1.93 / sec | Video    |
+| prod-v1-Luma Video Generation Product               | model: ray-flash-2    | 0.66 / sec | Video    |
+| Luma Image Generations (millions of pixels) Product | model: photon-1       | 2.2 / run  | Image    |
+| Luma Image Generations (millions of pixels) Product | model: photon-flash-1 | 0.57 / run | Image    |
 
 ## Meshy
 
-| 产品名称                | 配置                                                        | 积分        | 类别  |
-| :---------------------- | :---------------------------------------------------------- | :---------- | :---- |
-| Meshy Retexture         | NA                                                          | 84.4 / run  | 3D    |
-| Meshy Rigging           | NA                                                          | 42.2 / run  | 3D    |
-| Meshy Remesh            | NA                                                          | 42.2 / run  | 3D    |
-| Meshy Animation         | NA                                                          | 25.32 / run | 3D    |
-| Meshy Multi Image to 3D | should_texture: false                                       | 42.2 / run  | Image |
-| Meshy Multi Image to 3D | should_texture: true                                        | 126.6 / run | Image |
-| Meshy Text to 3D        | mode: preview, model: latest                                | 168.8 / run | 3D    |
-| Meshy Text to 3D        | mode: preview, model: meshy-5                               | 42.2 / run  | 3D    |
-| Meshy Text to 3D        | mode: refine, model: latest                                 | 84.4 / run  | 3D    |
-| Meshy Image to 3D       | model: latest, model_type: lowpoly, should_texture: false   | 168.8 / run | Image |
-| Meshy Image to 3D       | model: latest, model_type: lowpoly, should_texture: true    | 253.2 / run | Image |
-| Meshy Image to 3D       | model: latest, model_type: standard, should_texture: false  | 168.8 / run | Image |
-| Meshy Image to 3D       | model: latest, model_type: standard, should_texture: true   | 253.2 / run | Image |
-| Meshy Image to 3D       | model: meshy-5, model_type: lowpoly, should_texture: false  | 168.8 / run | Image |
-| Meshy Image to 3D       | model: meshy-5, model_type: lowpoly, should_texture: true   | 253.2 / run | Image |
-| Meshy Image to 3D       | model: meshy-5, model_type: standard, should_texture: false | 42.2 / run  | Image |
-| Meshy Image to 3D       | model: meshy-5, model_type: standard, should_texture: true  | 126.6 / run | Image |
+| 产品名称            | 配置                                               | 积分     | 类别 |
+| :---------------------- | :---------------------------------------------------------- | :---------- | :------- |
+| Meshy Retexture         | NA                                                          | 84.4 / run  | 3D       |
+| Meshy Rigging           | NA                                                          | 42.2 / run  | 3D       |
+| Meshy Remesh            | NA                                                          | 42.2 / run  | 3D       |
+| Meshy Animation         | NA                                                          | 25.32 / run | 3D       |
+| Meshy Multi Image to 3D | should_texture: false                                       | 42.2 / run  | Image    |
+| Meshy Multi Image to 3D | should_texture: true                                        | 126.6 / run | Image    |
+| Meshy Text to 3D        | mode: preview, model: latest                                | 168.8 / run | 3D       |
+| Meshy Text to 3D        | mode: preview, model: meshy-5                               | 42.2 / run  | 3D       |
+| Meshy Text to 3D        | mode: refine, model: latest                                 | 84.4 / run  | 3D       |
+| Meshy Image to 3D       | model: latest, model_type: lowpoly, should_texture: false   | 168.8 / run | Image    |
+| Meshy Image to 3D       | model: latest, model_type: lowpoly, should_texture: true    | 253.2 / run | Image    |
+| Meshy Image to 3D       | model: latest, model_type: standard, should_texture: false  | 168.8 / run | Image    |
+| Meshy Image to 3D       | model: latest, model_type: standard, should_texture: true   | 253.2 / run | Image    |
+| Meshy Image to 3D       | model: meshy-5, model_type: lowpoly, should_texture: false  | 168.8 / run | Image    |
+| Meshy Image to 3D       | model: meshy-5, model_type: lowpoly, should_texture: true   | 253.2 / run | Image    |
+| Meshy Image to 3D       | model: meshy-5, model_type: standard, should_texture: false | 42.2 / run  | Image    |
+| Meshy Image to 3D       | model: meshy-5, model_type: standard, should_texture: true  | 126.6 / run | Image    |
 
 ## Minimax
 
-| 产品名称                                        | 配置                                                     | 积分         | 类别  |
-| :---------------------------------------------- | :------------------------------------------------------- | :----------- | :---- |
-| prod-v1-Minimax Video Product                   | model: i2v-01-director                                   | 90.73 / run  | Video |
-| prod-v1-Minimax Video Product                   | model: i2v-01-live                                       | 90.73 / run  | Video |
-| prod-v1-Minimax Video Product                   | model: i2v-01                                            | 90.73 / run  | Video |
-| prod-v1-Minimax Video Product                   | model: s2v-01                                            | 137.15 / run | Video |
-| prod-v1-Minimax Video Product                   | model: t2v-01-director                                   | 90.73 / run  | Video |
-| prod-v1-Minimax Video Product                   | model: t2v-01                                            | 90.73 / run  | Video |
-| Minimax Video Generation_models after Hailuo-02 | duration: 10, model: minimax-hailuo-02, resolution: 768P | 118.16 / run | Video |
-| Minimax Video Generation_models after Hailuo-02 | duration: 6, model: minimax-hailuo-02, resolution: 1080P | 103.39 / run | Video |
-| Minimax Video Generation_models after Hailuo-02 | duration: 6, model: minimax-hailuo-02, resolution: 768P  | 59.08 / run  | Video |
+| 产品名称                                    | 配置                                            | 积分      | 类别 |
+| :---------------------------------------------- | :------------------------------------------------------- | :----------- | :------- |
+| prod-v1-Minimax Video Product                   | model: i2v-01-director                                   | 90.73 / run  | Video    |
+| prod-v1-Minimax Video Product                   | model: i2v-01-live                                       | 90.73 / run  | Video    |
+| prod-v1-Minimax Video Product                   | model: i2v-01                                            | 90.73 / run  | Video    |
+| prod-v1-Minimax Video Product                   | model: s2v-01                                            | 137.15 / run | Video    |
+| prod-v1-Minimax Video Product                   | model: t2v-01-director                                   | 90.73 / run  | Video    |
+| prod-v1-Minimax Video Product                   | model: t2v-01                                            | 90.73 / run  | Video    |
+| Minimax Video Generation_models after Hailuo-02 | duration: 10, model: minimax-hailuo-02, resolution: 768P | 118.16 / run | Video    |
+| Minimax Video Generation_models after Hailuo-02 | duration: 6, model: minimax-hailuo-02, resolution: 1080P | 103.39 / run | Video    |
+| Minimax Video Generation_models after Hailuo-02 | duration: 6, model: minimax-hailuo-02, resolution: 768P  | 59.08 / run  | Video    |
 
 ## Moonvalley
 
-| 产品名称                      | 配置 | 积分         | 类别  |
-| :---------------------------- | :--- | :----------- | :---- |
-| Moonvalley Image-to-Video 5s  | NA   | 316.5 / run  | Video |
-| Moonvalley Image-to-Video 10s | NA   | 633 / run    | Video |
-| Moonvalley Text-to-Video 5s   | NA   | 316.5 / run  | Video |
-| Moonvalley Text-to-Video 10s  | NA   | 633 / run    | Video |
-| Moonvalley Video-to-Video 5s  | NA   | 474.75 / run | Video |
-| Moonvalley Video-to-Video 10s | NA   | 844 / run    | Video |
+| 产品名称                  | 配置 | 积分      | 类别 |
+| :---------------------------- | :------------ | :----------- | :------- |
+| Moonvalley Image-to-Video 5s  | NA            | 316.5 / run  | Video    |
+| Moonvalley Image-to-Video 10s | NA            | 633 / run    | Video    |
+| Moonvalley Text-to-Video 5s   | NA            | 316.5 / run  | Video    |
+| Moonvalley Text-to-Video 10s  | NA            | 633 / run    | Video    |
+| Moonvalley Video-to-Video 5s  | NA            | 474.75 / run | Video    |
+| Moonvalley Video-to-Video 10s | NA            | 844 / run    | Video    |
 
 ## OpenAI
 
-| 产品名称                                                  | 配置                                                | 积分               | 类别  |
-| :-------------------------------------------------------- | :-------------------------------------------------- | :----------------- | :---- |
-| OpenAI Images dall-e-2 Product                            | size: 1024x1024                                     | 4.22 / run         | Image |
-| OpenAI Images dall-e-2 Product                            | size: 256x256                                       | 3.38 / run         | Image |
-| OpenAI Images dall-e-2 Product                            | size: 512x512                                       | 3.8 / run          | Image |
-| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: hd, size: 1024x1024       | 16.88 / run        | Image |
-| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: hd, size: 1024x1792       | 25.32 / run        | Image |
-| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: hd, size: 1792x1024       | 25.32 / run        | Image |
-| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: standard, size: 1024x1024 | 8.44 / run         | Image |
-| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: standard, size: 1024x1792 | 16.88 / run        | Image |
-| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: standard, size: 1792x1024 | 16.88 / run        | Image |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: computer-use-preview                         | 633 / 1M tokens    | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4.1-mini                                 | 84.4 / 1M tokens   | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4.1-nano                                 | 21.1 / 1M tokens   | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4.1                                      | 422 / 1M tokens    | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4.5-preview                              | 15825 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-audio-preview                         | 527.5 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-mini-audio-preview                    | 31.65 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-mini                                  | 31.65 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-mini-realtime-preview                 | 126.6 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-mini-search-preview                   | 31.65 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o                                       | 527.5 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-realtime-preview                      | 1055 / 1M tokens   | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-search-preview                        | 527.5 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-5-mini                                   | 52.75 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-5-nano                                   | 10.55 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-5                                        | 263.75 / 1M tokens | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-image-1.5                                | 1055 / 1M tokens   | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-image-1                                  | 1055 / 1M tokens   | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: o1-mini                                      | 232.1 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: o1                                           | 3165 / 1M tokens   | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: o1-pro                                       | 31650 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: o3-mini                                      | 232.1 / 1M tokens  | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: o3                                           | 422 / 1M tokens    | Text  |
-| OpenAI Input Text Tokens (per 1M) Product                 | model: o4-mini                                      | 232.1 / 1M tokens  | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4.1-mini                                 | 21.1 / 1M tokens   | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4.1-nano                                 | 5.28 / 1M tokens   | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4.1                                      | 105.5 / 1M tokens  | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4.5-preview                              | 7912.5 / 1M tokens | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4o-mini                                  | 15.82 / 1M tokens  | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4o-mini-realtime-preview                 | 63.3 / 1M tokens   | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4o                                       | 263.75 / 1M tokens | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4o-realtime-preview                      | 527.5 / 1M tokens  | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-5-mini                                   | 5.28 / 1M tokens   | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-5-nano                                   | 1.05 / 1M tokens   | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-5                                        | 26.38 / 1M tokens  | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o1-mini                                      | 116.05 / 1M tokens | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o1                                           | 1582.5 / 1M tokens | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o3-mini                                      | 116.05 / 1M tokens | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o3                                           | 105.5 / 1M tokens  | Text  |
-| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o4-mini                                      | 58.03 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: computer-use-preview                         | 2532 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4.1-mini                                 | 337.6 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4.1-nano                                 | 84.4 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4.1                                      | 1688 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4.5-preview                              | 31650 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-audio-preview                         | 2110 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-mini-audio-preview                    | 126.6 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-mini                                  | 126.6 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-mini-realtime-preview                 | 506.4 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-mini-search-preview                   | 126.6 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o                                       | 2110 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-realtime-preview                      | 4220 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-search-preview                        | 2110 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-5-mini                                   | 422 / 1M tokens    | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-5-nano                                   | 84.4 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-5                                        | 2110 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: o1-mini                                      | 928.4 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: o1                                           | 12660 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: o1-pro                                       | 126600 / 1M tokens | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: o3-mini                                      | 928.4 / 1M tokens  | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: o3                                           | 1688 / 1M tokens   | Text  |
-| OpenAI Output Text Tokens (per 1M) Product                | model: o4-mini                                      | 928.4 / 1M tokens  | Text  |
-| OpenAI Responses Output Image Tokens (per 1M) Product     | model: gpt-image-1                                  | 8440 / 1M tokens   | Image |
-| OpenAI Responses Input Image Tokens (per 1M) Product      | model: gpt-image-1                                  | 2110 / 1M tokens   | Image |
-| OpenAI Chat Completion Image Output Tokens (1M)           | model: gpt-image-1.5                                | 6752 / 1M tokens   | Image |
-| OpenAI Chat Completion Image Output Tokens (1M)           | model: gpt-image-1                                  | 8440 / 1M tokens   | Image |
-| OpenAI Input Image Tokens (1M tokens)                     | model: gpt-image-1.5                                | 1688 / 1M tokens   | Image |
-| OpenAI Input Image Tokens (1M tokens)                     | model: gpt-image-1                                  | 2110 / 1M tokens   | Image |
-| OpenAI Video Generation Product                           | model: sora-2-pro, size: 1024x1792                  | 105.5 / run        | Video |
-| OpenAI Video Generation Product                           | model: sora-2-pro, size: 1280x720                   | 63.3 / run         | Video |
-| OpenAI Video Generation Product                           | model: sora-2-pro, size: 1792x1024                  | 105.5 / run        | Video |
-| OpenAI Video Generation Product                           | model: sora-2-pro, size: 720x1280                   | 63.3 / run         | Video |
-| OpenAI Video Generation Product                           | model: sora-2, size: 1280x720                       | 21.1 / sec         | Video |
-| OpenAI Video Generation Product                           | model: sora-2, size: 720x1280                       | 21.1 / sec         | Video |
-| OpenAI Output Text Tokens (per 1M) Product (non-response) | model: gpt-image-1.5                                | 2110 / 1M tokens   | Text  |
+| 产品名称                                              | 配置                                       | 积分            | 类别 |
+| :-------------------------------------------------------- | :-------------------------------------------------- | :----------------- | :------- |
+| OpenAI Images dall-e-2 Product                            | size: 1024x1024                                     | 4.22 / run         | Image    |
+| OpenAI Images dall-e-2 Product                            | size: 256x256                                       | 3.38 / run         | Image    |
+| OpenAI Images dall-e-2 Product                            | size: 512x512                                       | 3.8 / run          | Image    |
+| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: hd, size: 1024x1024       | 16.88 / run        | Image    |
+| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: hd, size: 1024x1792       | 25.32 / run        | Image    |
+| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: hd, size: 1792x1024       | 25.32 / run        | Image    |
+| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: standard, size: 1024x1024 | 8.44 / run         | Image    |
+| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: standard, size: 1024x1792 | 16.88 / run        | Image    |
+| OpenAI dall-e-3 Product                                   | model: dall-e-3, quality: standard, size: 1792x1024 | 16.88 / run        | Image    |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: computer-use-preview                         | 633 / 1M tokens    | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4.1-mini                                 | 84.4 / 1M tokens   | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4.1-nano                                 | 21.1 / 1M tokens   | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4.1                                      | 422 / 1M tokens    | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4.5-preview                              | 15825 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-audio-preview                         | 527.5 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-mini-audio-preview                    | 31.65 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-mini                                  | 31.65 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-mini-realtime-preview                 | 126.6 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-mini-search-preview                   | 31.65 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o                                       | 527.5 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-realtime-preview                      | 1055 / 1M tokens   | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-4o-search-preview                        | 527.5 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-5-mini                                   | 52.75 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-5-nano                                   | 10.55 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-5                                        | 263.75 / 1M tokens | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-image-1.5                                | 1055 / 1M tokens   | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: gpt-image-1                                  | 1055 / 1M tokens   | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: o1-mini                                      | 232.1 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: o1                                           | 3165 / 1M tokens   | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: o1-pro                                       | 31650 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: o3-mini                                      | 232.1 / 1M tokens  | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: o3                                           | 422 / 1M tokens    | Text     |
+| OpenAI Input Text Tokens (per 1M) Product                 | model: o4-mini                                      | 232.1 / 1M tokens  | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4.1-mini                                 | 21.1 / 1M tokens   | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4.1-nano                                 | 5.28 / 1M tokens   | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4.1                                      | 105.5 / 1M tokens  | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4.5-preview                              | 7912.5 / 1M tokens | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4o-mini                                  | 15.82 / 1M tokens  | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4o-mini-realtime-preview                 | 63.3 / 1M tokens   | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4o                                       | 263.75 / 1M tokens | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-4o-realtime-preview                      | 527.5 / 1M tokens  | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-5-mini                                   | 5.28 / 1M tokens   | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-5-nano                                   | 1.05 / 1M tokens   | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: gpt-5                                        | 26.38 / 1M tokens  | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o1-mini                                      | 116.05 / 1M tokens | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o1                                           | 1582.5 / 1M tokens | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o3-mini                                      | 116.05 / 1M tokens | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o3                                           | 105.5 / 1M tokens  | Text     |
+| OpenAI Cached Input Text Tokens (per 1M) Product          | model: o4-mini                                      | 58.03 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: computer-use-preview                         | 2532 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4.1-mini                                 | 337.6 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4.1-nano                                 | 84.4 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4.1                                      | 1688 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4.5-preview                              | 31650 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-audio-preview                         | 2110 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-mini-audio-preview                    | 126.6 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-mini                                  | 126.6 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-mini-realtime-preview                 | 506.4 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-mini-search-preview                   | 126.6 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o                                       | 2110 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-realtime-preview                      | 4220 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-4o-search-preview                        | 2110 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-5-mini                                   | 422 / 1M tokens    | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-5-nano                                   | 84.4 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: gpt-5                                        | 2110 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: o1-mini                                      | 928.4 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: o1                                           | 12660 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: o1-pro                                       | 126600 / 1M tokens | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: o3-mini                                      | 928.4 / 1M tokens  | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: o3                                           | 1688 / 1M tokens   | Text     |
+| OpenAI Output Text Tokens (per 1M) Product                | model: o4-mini                                      | 928.4 / 1M tokens  | Text     |
+| OpenAI Responses Output Image Tokens (per 1M) Product     | model: gpt-image-1                                  | 8440 / 1M tokens   | Image    |
+| OpenAI Responses Input Image Tokens (per 1M) Product      | model: gpt-image-1                                  | 2110 / 1M tokens   | Image    |
+| OpenAI Chat Completion Image Output Tokens (1M)           | model: gpt-image-1.5                                | 6752 / 1M tokens   | Image    |
+| OpenAI Chat Completion Image Output Tokens (1M)           | model: gpt-image-1                                  | 8440 / 1M tokens   | Image    |
+| OpenAI Input Image Tokens (1M tokens)                     | model: gpt-image-1.5                                | 1688 / 1M tokens   | Image    |
+| OpenAI Input Image Tokens (1M tokens)                     | model: gpt-image-1                                  | 2110 / 1M tokens   | Image    |
+| OpenAI Video Generation Product                           | model: sora-2-pro, size: 1024x1792                  | 105.5 / run        | Video    |
+| OpenAI Video Generation Product                           | model: sora-2-pro, size: 1280x720                   | 63.3 / run         | Video    |
+| OpenAI Video Generation Product                           | model: sora-2-pro, size: 1792x1024                  | 105.5 / run        | Video    |
+| OpenAI Video Generation Product                           | model: sora-2-pro, size: 720x1280                   | 63.3 / run         | Video    |
+| OpenAI Video Generation Product                           | model: sora-2, size: 1280x720                       | 21.1 / sec         | Video    |
+| OpenAI Video Generation Product                           | model: sora-2, size: 720x1280                       | 21.1 / sec         | Video    |
+| OpenAI Output Text Tokens (per 1M) Product (non-response) | model: gpt-image-1.5                                | 2110 / 1M tokens   | Text     |
 
 ## Pika
 
-| 产品名称                                           | 配置                                                 | 积分        | 类别  |
-| :------------------------------------------------- | :--------------------------------------------------- | :---------- | :---- |
-| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/i2v, resolution: 1080p        | 211 / run   | Video |
-| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/i2v, resolution: 720p         | 126.6 / run | Video |
-| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/pikaframes, resolution: 1080p | 211 / run   | Video |
-| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/pikaframes, resolution: 720p  | 52.75 / run | Video |
-| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/pikascenes, resolution: 1080p | 316.5 / run | Video |
-| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/pikascenes, resolution: 720p  | 84.4 / run  | Video |
-| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/t2v, resolution: 1080p        | 211 / run   | Video |
-| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/t2v, resolution: 720p         | 126.6 / run | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/i2v, resolution: 1080p        | 94.95 / run | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/i2v, resolution: 720p         | 42.2 / run  | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/pikaframes, resolution: 1080p | 63.3 / run  | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/pikaframes, resolution: 720p  | 42.2 / run  | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/pikascenes, resolution: 1080p | 105.5 / run | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/pikascenes, resolution: 720p  | 63.3 / run  | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/t2v, resolution: 1080p        | 94.95 / run | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/t2v, resolution: 720p         | 42.2 / run  | Video |
-| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/pikaffects, resolution: 720p      | 94.95 / run | Video |
-| Pika Basic Video Product                           | endpoint: generate/pikadditions                      | 63.3 / run  | Video |
-| Pika Basic Video Product                           | endpoint: generate/pikaffects                        | 94.95 / run | Video |
-| Pika Basic Video Product                           | endpoint: generate/pikaswaps                         | 63.3 / run  | Video |
+| 产品名称                                       | 配置                                        | 积分     | 类别 |
+| :------------------------------------------------- | :--------------------------------------------------- | :---------- | :------- |
+| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/i2v, resolution: 1080p        | 211 / run   | Video    |
+| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/i2v, resolution: 720p         | 126.6 / run | Video    |
+| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/pikaframes, resolution: 1080p | 211 / run   | Video    |
+| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/pikaframes, resolution: 720p  | 52.75 / run | Video    |
+| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/pikascenes, resolution: 1080p | 316.5 / run | Video    |
+| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/pikascenes, resolution: 720p  | 84.4 / run  | Video    |
+| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/t2v, resolution: 1080p        | 211 / run   | Video    |
+| prod-v1-Pika Video Generation Product (10 seconds) | endpoint: generate/2.2/t2v, resolution: 720p         | 126.6 / run | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/i2v, resolution: 1080p        | 94.95 / run | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/i2v, resolution: 720p         | 42.2 / run  | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/pikaframes, resolution: 1080p | 63.3 / run  | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/pikaframes, resolution: 720p  | 42.2 / run  | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/pikascenes, resolution: 1080p | 105.5 / run | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/pikascenes, resolution: 720p  | 63.3 / run  | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/t2v, resolution: 1080p        | 94.95 / run | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/2.2/t2v, resolution: 720p         | 42.2 / run  | Video    |
+| prod-v1-Pika Video Generation (5 seconds)          | endpoint: generate/pikaffects, resolution: 720p      | 94.95 / run | Video    |
+| Pika Basic Video Product                           | endpoint: generate/pikadditions                      | 63.3 / run  | Video    |
+| Pika Basic Video Product                           | endpoint: generate/pikaffects                        | 94.95 / run | Video    |
+| Pika Basic Video Product                           | endpoint: generate/pikaswaps                         | 63.3 / run  | Video    |
 
 ## Pixverse
 
-| 产品名称                         | 配置                                             | 积分        | 类别  |
-| :------------------------------- | :----------------------------------------------- | :---------- | :---- |
-| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: fast, quality: 360p    | 189.9 / run | Video |
-| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: fast, quality: 540p    | 189.9 / run | Video |
-| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: fast, quality: 720p    | 253.2 / run | Video |
-| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: normal, quality: 1080p | 253.2 / run | Video |
-| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: normal, quality: 360p  | 94.95 / run | Video |
-| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: normal, quality: 540p  | 94.95 / run | Video |
-| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: normal, quality: 720p  | 126.6 / run | Video |
-| Pixverse 8 seconds Video Product | model: v3.5, motion_mode: normal, quality: 360p  | 189.9 / run | Video |
-| Pixverse 8 seconds Video Product | model: v3.5, motion_mode: normal, quality: 540p  | 189.9 / run | Video |
-| Pixverse 8 seconds Video Product | model: v3.5, motion_mode: normal, quality: 720p  | 253.2 / run | Video |
-
-## Recraft
-
-| 产品名称             | 配置 | 积分       | 类别  |
-| :------------------- | :--- | :--------- | :---- |
-| Recraft All Products | NA   | 0.21 / run | Image |
+| 产品名称                     | 配置                                    | 积分     | 类别 |
+| :------------------------------- | :----------------------------------------------- | :---------- | :------- |
+| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: fast, quality: 360p    | 189.9 / run | Video    |
+| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: fast, quality: 540p    | 189.9 / run | Video    |
+| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: fast, quality: 720p    | 253.2 / run | Video    |
+| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: normal, quality: 1080p | 253.2 / run | Video    |
+| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: normal, quality: 360p  | 94.95 / run | Video    |
+| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: normal, quality: 540p  | 94.95 / run | Video    |
+| Pixverse 5 seconds Video Product | model: v3.5, motion_mode: normal, quality: 720p  | 126.6 / run | Video    |
+| Pixverse 8 seconds Video Product | model: v3.5, motion_mode: normal, quality: 360p  | 189.9 / run | Video    |
+| Pixverse 8 seconds Video Product | model: v3.5, motion_mode: normal, quality: 540p  | 189.9 / run | Video    |
+| Pixverse 8 seconds Video Product | model: v3.5, motion_mode: normal, quality: 720p  | 253.2 / run | Video    |
 
 ## Rodin
 
-| 产品名称                          | 配置 | 积分        | 类别 |
-| :-------------------------------- | :--- | :---------- | :--- |
-| Rodin 3D Generation (no addons)   | NA   | 84.4 / run  | 3D   |
-| Rodin 3D Generation (with AddOns) | NA   | 253.2 / run | 3D   |
+| 产品名称                      | 配置 | 积分     | 类别 |
+| :-------------------------------- | :------------ | :---------- | :------- |
+| Rodin 3D Generation (no addons)   | NA            | 84.4 / run  | 3D       |
+| Rodin 3D Generation (with AddOns) | NA            | 253.2 / run | 3D       |
 
 ## Runway
 
-| 产品名称                                | 配置               | 积分        | 类别  |
-| :-------------------------------------- | :----------------- | :---------- | :---- |
-| prod-v1-Runway Video Generation Product | model: gen3a_turbo | 15.09 / sec | Video |
-| prod-v1-Runway Video Generation Product | model: gen4_turbo  | 15.09 / sec | Video |
-| prod-v1-Runway Video Generation Product | model: gen4_turbo  | 10.55 / sec | Video |
-| RunwayML Image Generation Product       | model: gen4_image  | 24.14 / run | Image |
+| 产品名称                            | 配置      | 积分     | 类别 |
+| :-------------------------------------- | :----------------- | :---------- | :------- |
+| prod-v1-Runway Video Generation Product | model: gen3a_turbo | 15.09 / sec | Video    |
+| prod-v1-Runway Video Generation Product | model: gen4_turbo  | 15.09 / sec | Video    |
+| prod-v1-Runway Video Generation Product | model: gen4_turbo  | 10.55 / sec | Video    |
+| RunwayML Image Generation Product       | model: gen4_image  | 24.14 / run | Image    |
 
 ## Stability AI
 
-| 产品名称                                   | 配置                                                                          | 积分        | 类别  |
-| :----------------------------------------- | :---------------------------------------------------------------------------- | :---------- | :---- |
-| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/generate/core                                   | 6.33 / run  | Image |
-| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/generate/ultra                                  | 16.88 / run | Image |
-| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/upscale/conservative                            | 84.4 / run  | Image |
-| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/upscale/creative                                | 126.6 / run | Image |
-| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/upscale/fast                                    | 4.22 / run  | Image |
-| Stability AI SD3 Image Products            | model: sd3.5-large                                                            | 13.71 / run | Image |
-| Stability AI SD3 Image Products            | model: sd3.5-large-turbo                                                      | 8.44 / run  | Image |
-| Stability AI SD3 Image Products            | model: sd3.5-medium                                                           | 7.39 / run  | Image |
-| Stability Audio Generation Product         | endpoint: v2beta/audio/stable-audio-2/audio-to-audio, model: stable-audio-2.5 | 42.2 / run  | Audio |
-| Stability Audio Generation Product         | endpoint: v2beta/audio/stable-audio-2/inpaint, model: stable-audio-2.5        | 42.2 / run  | Audio |
-| Stability Audio Generation Product         | endpoint: v2beta/audio/stable-audio-2/text-to-audio, model: stable-audio-2.5  | 42.2 / run  | Audio |
+| 产品名称                               | 配置                                                                 | 积分     | 类别 |
+| :----------------------------------------- | :---------------------------------------------------------------------------- | :---------- | :------- |
+| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/generate/core                                   | 6.33 / run  | Image    |
+| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/generate/ultra                                  | 16.88 / run | Image    |
+| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/upscale/conservative                            | 84.4 / run  | Image    |
+| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/upscale/creative                                | 126.6 / run | Image    |
+| prod-v1-Stability Image Generation Product | endpoint: v2beta/stable-image/upscale/fast                                    | 4.22 / run  | Image    |
+| Stability AI SD3 Image Products            | model: sd3.5-large                                                            | 13.71 / run | Image    |
+| Stability AI SD3 Image Products            | model: sd3.5-large-turbo                                                      | 8.44 / run  | Image    |
+| Stability AI SD3 Image Products            | model: sd3.5-medium                                                           | 7.39 / run  | Image    |
+| Stability Audio Generation Product         | endpoint: v2beta/audio/stable-audio-2/audio-to-audio, model: stable-audio-2.5 | 42.2 / run  | Audio    |
+| Stability Audio Generation Product         | endpoint: v2beta/audio/stable-audio-2/inpaint, model: stable-audio-2.5        | 42.2 / run  | Audio    |
+| Stability Audio Generation Product         | endpoint: v2beta/audio/stable-audio-2/text-to-audio, model: stable-audio-2.5  | 42.2 / run  | Audio    |
 
 ## Tencent
 
-| 产品名称                    | 配置                                              | 积分        | 类别  |
-| :-------------------------- | :------------------------------------------------ | :---------- | :---- |
-| Tencent 3D Generate Type    | endpoint: hunyuan/3d-pro, generate_type: Geometry | 63.3 / run  | 3D    |
-| Tencent 3D Generate Type    | endpoint: hunyuan/3d-pro, generate_type: LowPoly  | 126.6 / run | 3D    |
-| Tencent 3D Generate Type    | endpoint: hunyuan/3d-pro, generate_type: Normal   | 105.5 / run | 3D    |
-| Tencent 3D Generate Type    | endpoint: hunyuan/3d-pro, generate_type: Sketch   | 105.5 / run | 3D    |
-| Tencent 3D Face Count       | custom_face_count: true, endpoint: hunyuan/3d-pro | 42.2 / run  | 3D    |
-| Tencent 3D PBR              | enable_pbr: true, endpoint: hunyuan/3d-pro        | 42.2 / run  | 3D    |
-| Tencent 3D Multiview Images | endpoint: hunyuan/3d-pro, multi_view: true        | 42.2 / run  | Image |
+| 产品名称                | 配置                                     | 积分     | 类别 |
+| :-------------------------- | :------------------------------------------------ | :---------- | :------- |
+| Tencent 3D Generate Type    | endpoint: hunyuan/3d-pro, generate_type: Geometry | 63.3 / run  | 3D       |
+| Tencent 3D Generate Type    | endpoint: hunyuan/3d-pro, generate_type: LowPoly  | 126.6 / run | 3D       |
+| Tencent 3D Generate Type    | endpoint: hunyuan/3d-pro, generate_type: Normal   | 105.5 / run | 3D       |
+| Tencent 3D Generate Type    | endpoint: hunyuan/3d-pro, generate_type: Sketch   | 105.5 / run | 3D       |
+| Tencent 3D Face Count       | custom_face_count: true, endpoint: hunyuan/3d-pro | 42.2 / run  | 3D       |
+| Tencent 3D PBR              | enable_pbr: true, endpoint: hunyuan/3d-pro        | 42.2 / run  | 3D       |
+| Tencent 3D Multiview Images | endpoint: hunyuan/3d-pro, multi_view: true        | 42.2 / run  | Image    |
+| Tencent 3D                  | endpoint: hunyuan/3d-part                         | 126.6 / run | 3D       |
+| Tencent 3D                  | endpoint: hunyuan/3d-texture-edit                 | 126.6 / run | 3D       |
+| Tencent 3D                  | endpoint: hunyuan/3d-uv                           | 42.2 / run  | 3D       |
 
 ## Topaz
 
-| 产品名称 | 配置 | 积分        | 类别  |
-| :------- | :--- | :---------- | :---- |
-| Topaz    | NA   | 16.88 / run | Image |
+| 产品名称 | 配置 | 积分     | 类别 |
+| :----------- | :------------ | :---------- | :------- |
+| Topaz        | NA            | 16.88 / run | Image    |
 
 ## Tripo
 
-| 产品名称                                 | 配置                                                                      | 积分        | 类别 |
-| :--------------------------------------- | :------------------------------------------------------------------------ | :---------- | :--- |
-| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: detailed, type: image_to_model     | 84.4 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: detailed, type: multiview_to_model | 84.4 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: detailed, type: text_to_model      | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: standard, type: image_to_model     | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: standard, type: multiview_to_model | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: standard, type: text_to_model      | 42.2 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: detailed, type: image_to_model     | 84.4 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: detailed, type: multiview_to_model | 84.4 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: detailed, type: text_to_model      | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: standard, type: image_to_model     | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: standard, type: multiview_to_model | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: standard, type: text_to_model      | 42.2 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: detailed, type: image_to_model     | 84.4 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: detailed, type: multiview_to_model | 84.4 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: detailed, type: text_to_model      | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: standard, type: image_to_model     | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: standard, type: multiview_to_model | 63.3 / run  | 3D   |
-| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: standard, type: text_to_model      | 42.2 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v2.0-20240919, type: image_to_model                                | 42.2 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v2.0-20240919, type: multiview_to_model                            | 42.2 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v2.0-20240919, type: text_to_model                                 | 21.1 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v2.5-20250123, type: image_to_model                                | 42.2 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v2.5-20250123, type: multiview_to_model                            | 42.2 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v2.5-20250123, type: text_to_model                                 | 21.1 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v3.0-20250812, type: image_to_model                                | 42.2 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v3.0-20250812, type: multiview_to_model                            | 42.2 / run  | 3D   |
-| Tripo Generation (no textures) Product   | model: v3.0-20250812, type: text_to_model                                 | 21.1 / run  | 3D   |
-| Tripo Style Product                      | NA                                                                        | 10.55 / run | 3D   |
-| Tripo Quadrangular Product               | NA                                                                        | 10.55 / run | 3D   |
-| Tripo Add Texture Product                | texture_quality: detailed                                                 | 42.2 / run  | 3D   |
-| Tripo Add Texture Product                | texture_quality: standard                                                 | 21.1 / run  | 3D   |
-| Tripo Post-Processing Product            | type: animate_retarget                                                    | 21.1 / run  | 3D   |
-| Tripo Post-Processing Product            | type: animate_rig                                                         | 52.75 / run | 3D   |
-| Tripo Post-Processing Product            | type: stylize_model                                                       | 42.2 / run  | 3D   |
-| Tripo Convert Product                    | convert_format: advanced                                                  | 21.1 / run  | 3D   |
-| Tripo Convert Product                    | convert_format: basic                                                     | 10.55 / run | 3D   |
-| Tripo V1-4 Generation Product            | type: image_to_model                                                      | 63.3 / run  | 3D   |
-| Tripo V1-4 Generation Product            | type: refine_model                                                        | 63.3 / run  | 3D   |
-| Tripo V1-4 Generation Product            | type: text_to_model                                                       | 42.2 / run  | 3D   |
-| Tripo Geometry Quality Product           | geometry_quality: detailed                                                | 42.2 / run  | 3D   |
+| 产品名称                             | 配置                                                             | 积分     | 类别 |
+| :--------------------------------------- | :------------------------------------------------------------------------ | :---------- | :------- |
+| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: detailed, type: image_to_model     | 84.4 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: detailed, type: multiview_to_model | 84.4 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: detailed, type: text_to_model      | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: standard, type: image_to_model     | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: standard, type: multiview_to_model | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.0-20240919, texture_quality: standard, type: text_to_model      | 42.2 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: detailed, type: image_to_model     | 84.4 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: detailed, type: multiview_to_model | 84.4 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: detailed, type: text_to_model      | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: standard, type: image_to_model     | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: standard, type: multiview_to_model | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v2.5-20250123, texture_quality: standard, type: text_to_model      | 42.2 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: detailed, type: image_to_model     | 84.4 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: detailed, type: multiview_to_model | 84.4 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: detailed, type: text_to_model      | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: standard, type: image_to_model     | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: standard, type: multiview_to_model | 63.3 / run  | 3D       |
+| Tripo Generation (with Textures) Product | model: v3.0-20250812, texture_quality: standard, type: text_to_model      | 42.2 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v2.0-20240919, type: image_to_model                                | 42.2 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v2.0-20240919, type: multiview_to_model                            | 42.2 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v2.0-20240919, type: text_to_model                                 | 21.1 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v2.5-20250123, type: image_to_model                                | 42.2 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v2.5-20250123, type: multiview_to_model                            | 42.2 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v2.5-20250123, type: text_to_model                                 | 21.1 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v3.0-20250812, type: image_to_model                                | 42.2 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v3.0-20250812, type: multiview_to_model                            | 42.2 / run  | 3D       |
+| Tripo Generation (no textures) Product   | model: v3.0-20250812, type: text_to_model                                 | 21.1 / run  | 3D       |
+| Tripo Style Product                      | NA                                                                        | 10.55 / run | 3D       |
+| Tripo Quadrangular Product               | NA                                                                        | 10.55 / run | 3D       |
+| Tripo Add Texture Product                | texture_quality: detailed                                                 | 42.2 / run  | 3D       |
+| Tripo Add Texture Product                | texture_quality: standard                                                 | 21.1 / run  | 3D       |
+| Tripo Post-Processing Product            | type: animate_retarget                                                    | 21.1 / run  | 3D       |
+| Tripo Post-Processing Product            | type: animate_rig                                                         | 52.75 / run | 3D       |
+| Tripo Post-Processing Product            | type: stylize_model                                                       | 42.2 / run  | 3D       |
+| Tripo Convert Product                    | convert_format: advanced                                                  | 21.1 / run  | 3D       |
+| Tripo Convert Product                    | convert_format: basic                                                     | 10.55 / run | 3D       |
+| Tripo V1-4 Generation Product            | type: image_to_model                                                      | 63.3 / run  | 3D       |
+| Tripo V1-4 Generation Product            | type: refine_model                                                        | 63.3 / run  | 3D       |
+| Tripo V1-4 Generation Product            | type: text_to_model                                                       | 42.2 / run  | 3D       |
+| Tripo Geometry Quality Product           | geometry_quality: detailed                                                | 42.2 / run  | 3D       |
 
 ## Vidu
 
-| Model(Node name)        | 类别  | Parameters that affect price | Parameter combo | Price (积分) |
-| ----------------------- | ----- | ---------------------------- | --------------- | ------------ |
-| ViduImageToVideoNode    | Video | NA                           | NA              | 84.4         |
-| ViduReferenceVideoNode  | Video | NA                           | NA              | 84.4         |
-| ViduStartEndToVideoNode | Video | NA                           | NA              | 84.4         |
-| ViduTextToVideoNode     | Video | NA                           | NA              | 84.4         |
+| 产品名称                  | 配置 | 积分    | 类别 |
+| :---------------------------- | :------------ | :--------- | :------- |
+| Vidu Video Generation Product | NA            | 1.05 / sec | Video    |
 
 ## WAN
 
-| 产品名称                     | 配置                                         | 积分        | 类别  |
-| :--------------------------- | :------------------------------------------- | :---------- | :---- |
-| Wan Image Generation Product | model: wan2.5-i2i-preview                    | 6.33 / run  | Image |
-| Wan Image Generation Product | model: wan2.5-t2i-preview                    | 6.33 / run  | Image |
-| Wan Image Generation Product | model: wan2.6-t2i                            | 6.33 / run  | Image |
-| Wan Video Generation Product | model: wan2.5-i2v-preview, resolution: 1080P | 31.65 / sec | Video |
-| Wan Video Generation Product | model: wan2.5-i2v-preview, resolution: 480P  | 10.55 / sec | Video |
-| Wan Video Generation Product | model: wan2.5-i2v-preview, resolution: 720P  | 21.1 / sec  | Video |
-| Wan Video Generation Product | model: wan2.5-t2v-preview, resolution: 1080P | 31.65 / sec | Video |
-| Wan Video Generation Product | model: wan2.5-t2v-preview, resolution: 480P  | 10.55 / sec | Video |
-| Wan Video Generation Product | model: wan2.5-t2v-preview, resolution: 720P  | 21.1 / sec  | Video |
-| Wan Video Generation Product | model: wan2.6-i2v, resolution: 1080P         | 31.65 / sec | Video |
-| Wan Video Generation Product | model: wan2.6-i2v, resolution: 720P          | 21.1 / sec  | Video |
-| Wan Video Generation Product | model: wan2.6-r2v, resolution: 1080P         | 31.65 / sec | Video |
-| Wan Video Generation Product | model: wan2.6-r2v, resolution: 720P          | 21.1 / sec  | Video |
-| Wan Video Generation Product | model: wan2.6-t2v, resolution: 1080P         | 31.65 / sec | Video |
-| Wan Video Generation Product | model: wan2.6-t2v, resolution: 720P          | 21.1 / sec  | Video |
-| Wavespeed Flashvsr           | resolution: 1080p                            | 18.99 / run | Image |
-| Wavespeed Flashvsr           | resolution: 2k                               | 25.32 / run | Image |
-| Wavespeed Flashvsr           | resolution: 4k                               | 33.76 / run | Image |
-| Wavespeed Flashvsr           | resolution: 720p                             | 12.66 / run | Image |
-| Wavespeed Image              | endpoint: seedvr2                            | 2.11 / run  | Image |
-| Wavespeed Image              | endpoint: ultimate-image-upscaler            | 12.66 / run | Image |
+| 产品名称                 | 配置                                | 积分     | 类别 |
+| :--------------------------- | :------------------------------------------- | :---------- | :------- |
+| Wan Image Generation Product | model: wan2.5-i2i-preview                    | 6.33 / run  | Image    |
+| Wan Image Generation Product | model: wan2.5-t2i-preview                    | 6.33 / run  | Image    |
+| Wan Image Generation Product | model: wan2.6-t2i                            | 6.33 / run  | Image    |
+| Wan Video Generation Product | model: wan2.5-i2v-preview, resolution: 1080P | 31.65 / sec | Video    |
+| Wan Video Generation Product | model: wan2.5-i2v-preview, resolution: 480P  | 10.55 / sec | Video    |
+| Wan Video Generation Product | model: wan2.5-i2v-preview, resolution: 720P  | 21.1 / sec  | Video    |
+| Wan Video Generation Product | model: wan2.5-t2v-preview, resolution: 1080P | 31.65 / sec | Video    |
+| Wan Video Generation Product | model: wan2.5-t2v-preview, resolution: 480P  | 10.55 / sec | Video    |
+| Wan Video Generation Product | model: wan2.5-t2v-preview, resolution: 720P  | 21.1 / sec  | Video    |
+| Wan Video Generation Product | model: wan2.6-i2v, resolution: 1080P         | 31.65 / sec | Video    |
+| Wan Video Generation Product | model: wan2.6-i2v, resolution: 720P          | 21.1 / sec  | Video    |
+| Wan Video Generation Product | model: wan2.6-r2v, resolution: 1080P         | 31.65 / sec | Video    |
+| Wan Video Generation Product | model: wan2.6-r2v, resolution: 720P          | 21.1 / sec  | Video    |
+| Wan Video Generation Product | model: wan2.6-t2v, resolution: 1080P         | 31.65 / sec | Video    |
+| Wan Video Generation Product | model: wan2.6-t2v, resolution: 720P          | 21.1 / sec  | Video    |
+| Wavespeed Flashvsr           | resolution: 1080p                            | 18.99 / run | Image    |
+| Wavespeed Flashvsr           | resolution: 2k                               | 25.32 / run | Image    |
+| Wavespeed Flashvsr           | resolution: 4k                               | 33.76 / run | Image    |
+| Wavespeed Flashvsr           | resolution: 720p                             | 12.66 / run | Image    |
+| Wavespeed Image              | endpoint: seedvr2                            | 2.11 / run  | Image    |
+| Wavespeed Image              | endpoint: ultimate-image-upscaler            | 12.66 / run | Image    |
 
 ## xAI
 
 <Note>
-Video endpoints charge for moderated content.
+视频对经过审核的内容收费。
 </Note>
 
-| 产品名称                                     | 配置                                                                                                    | 积分        | 类别  |
-| :------------------------------------------- | :------------------------------------------------------------------------------------------------------ | :---------- | :---- |
-| xAI Image Generation                         | endpoint: v1/images/generations, model: grok-imagine-image-beta, resolution: 1k                         | 6.96 / run  | Image |
-| xAI Image Edit Output                        | endpoint: v1/images/edits, model: grok-imagine-image-beta, resolution: 1k                               | 6.96 / run  | Image |
-| xAI Image Edit Input                         | endpoint: v1/images/edits, model: grok-imagine-image-beta, resolution: 1k                               | 0.42 / run  | Image |
-| xAI Video Generation Output Video Per Second | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 480p                       | 38.19 / sec | Video |
-| xAI Video Generation Output Video Per Second | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 720p                       | 38.19 / sec | Video |
-| xAI Video Generation Input Image             | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 480p, type: image-to-video | 0.42 / sec  | Video |
-| xAI Video Generation Input Image             | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 720p, type: image-to-video | 0.42 / sec  | Video |
-| xAI Video Edit Input+Output Video Per Second | endpoint: v1/videos/edits, model: grok-imagine-video-beta, resolution: 480p                             | 40.3 / sec  | Video |
-
+| 产品名称                                 | 配置                                                                                           | 积分     | 类别 |
+| :------------------------------------------- | :------------------------------------------------------------------------------------------------------ | :---------- | :------- |
+| xAI Image Generation                         | endpoint: v1/images/generations, model: grok-imagine-image-beta, resolution: 1k                         | 6.96 / run  | Image    |
+| xAI Image Edit Output                        | endpoint: v1/images/edits, model: grok-imagine-image-beta, resolution: 1k                               | 6.96 / run  | Image    |
+| xAI Image Edit Input                         | endpoint: v1/images/edits, model: grok-imagine-image-beta, resolution: 1k                               | 0.42 / run  | Image    |
+| xAI Video Generation Output Video Per Second | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 480p                       | 38.19 / sec | Video    |
+| xAI Video Generation Output Video Per Second | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 720p                       | 38.19 / sec | Video    |
+| xAI Video Generation Input Image             | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 480p, type: image-to-video | 0.42 / sec  | Video    |
+| xAI Video Generation Input Image             | endpoint: v1/videos/generations, model: grok-imagine-video-beta, resolution: 720p, type: image-to-video | 0.42 / sec  | Video    |
+| xAI Video Edit Input+Output Video Per Second | endpoint: v1/videos/edits, model: grok-imagine-video-beta, resolution: 480p                             | 40.3 / sec  | Video    |
\ No newline at end of file