Add LTX-2.3 documentation

docs.json

@@ -201,7 +201,8 @@
                         "group": "LTX",
                         "pages": [
                           "tutorials/video/ltxv",
-                          "tutorials/video/ltx/ltx-2"
+                          "tutorials/video/ltx/ltx-2",
+                          "tutorials/video/ltx/ltx-2-3"
                         ]
                       },
                       {
@@ -943,7 +944,8 @@
                         "group": "LTX",
                         "pages": [
                           "zh-CN/tutorials/video/ltxv",
-                          "zh-CN/tutorials/video/ltx/ltx-2"
+                          "zh-CN/tutorials/video/ltx/ltx-2",
+                          "zh-CN/tutorials/video/ltx/ltx-2-3"
                         ]
                       },
                       {

tutorials/video/ltx/ltx-2-3.mdx

@@ -0,0 +1,104 @@
+---
+title: "LTX-2.3"
+description: "Latest evolution of Lightricks' open-source audio-video generation model with major quality improvements"
+---
+
+import UpdateReminder from "/snippets/tutorials/update-reminder.mdx";
+
+[LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3) is the latest evolution of Lightricks' open-source audio-video generation model, now natively supported in ComfyUI. Building on LTX-2, this release delivers major quality improvements across fine details, portrait video, audio, image-to-video, prompt understanding, and text rendering.
+
+<UpdateReminder/>
+
+## Key features
+
+- **Finer details**: New latent space & updated VAE for sharper textures, cleaner edges, and more precise visuals
+- **9:16 Portrait support**: Greatly improved quality for vertical portrait videos, perfect for social media & mobile
+- **Better audio**: Cleaner sound with reduced noise, enhanced dialogue, music, and ambient audio
+- **Improved image-to-video**: More consistent motion and fewer glitches, such as frozen frames, for smoother, more natural animations
+- **Smarter prompt understanding**: Improved text encoder for more accurate interpretation of complex prompts
+- **Clearer text rendering**: More accurate text and letter rendering in videos
+
+## Getting started
+
+LTX-2.3 is natively supported in ComfyUI. To get started:
+
+1. Update ComfyUI to the latest version
+2. Go to **Template Library** > **Video** > choose any LTX-2.3 workflow
+3. Follow the pop-up to download models and run the workflow
+
+## Workflows
+
+### Image-to-video
+
+Generate videos from an input image with more consistent motion and smoother animations.
+
+<CardGroup cols={2}>
+  <Card title="Image-to-Video" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_3_i2v.json">
+    Download workflow
+  </Card>
+  <Card title="Run on Comfy Cloud" icon="cloud" href="https://links.comfy.org/4skdlDQ">
+    Open in cloud
+  </Card>
+</CardGroup>
+
+### Text-to-video
+
+Generate videos from text prompts with improved prompt understanding and text rendering.
+
+<CardGroup cols={2}>
+  <Card title="Text-to-Video" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_3_t2v.json">
+    Download workflow
+  </Card>
+  <Card title="Run on Comfy Cloud" icon="cloud" href="https://links.comfy.org/4rZ1DyY">
+    Open in cloud
+  </Card>
+</CardGroup>
+
+## Model downloads
+
+### Checkpoints
+
+| Name | Description | Download |
+|------|-------------|----------|
+| ltx-2.3-22b-dev | BF16 full model | [Download](https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-22b-dev.safetensors) |
+| ltx-2.3-22b-dev-fp8 | FP8 quantized model | [Download](https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors) |
+
+### LoRAs
+
+| Name | Download |
+|------|----------|
+| ltx-2.3-22b-distilled-lora-384 | [Download](https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-22b-distilled-lora-384.safetensors) |
+
+### Latent upscale models
+
+| Name | Download |
+|------|----------|
+| ltx-2.3-spatial-upscaler-x2-1.0 | [Download](https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-spatial-upscaler-x2-1.0.safetensors) |
+
+### Text encoders
+
+| Name | Download |
+|------|----------|
+| gemma_3_12B_it_fp4_mixed | [Download](https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors) |
+
+## Model storage location
+
+```
+ComfyUI/
+├── models/
+│   ├── latent_upscale_models/
+│   │   └── ltx-2.3-spatial-upscaler-x2-1.0.safetensors
+│   ├── checkpoints/
+│   │   ├── ltx-2.3-22b-dev-fp8.safetensors
+│   │   └── ltx-2.3-22b-dev.safetensors
+│   ├── loras/
+│   │   └── ltx-2.3-22b-distilled-lora-384.safetensors
+│   └── text_encoders/
+│       └── gemma_3_12B_it_fp4_mixed.safetensors
+```
+
+## Resources
+
+- [Hugging Face Model](https://huggingface.co/Lightricks/LTX-2.3)
+- [GitHub Repository](https://github.com/Lightricks/LTX-2)
+- [ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo/)

zh-CN/tutorials/video/ltx/ltx-2-3.mdx

@@ -0,0 +1,104 @@
+---
+title: "LTX-2.3"
+description: "Lightricks 开源音视频生成模型的最新版本，在细节、画质、音频等方面有重大改进"
+---
+
+import UpdateReminder from "/snippets/zh/tutorials/update-reminder.mdx";
+
+[LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3) 是 Lightricks 开源音视频生成模型的最新版本，现已原生支持 ComfyUI。在 LTX-2 的基础上，该版本在细节、竖屏视频、音频、图生视频、提示词理解和文字渲染方面都有重大改进。
+
+<UpdateReminder/>
+
+## 主要特性
+
+- **更精细的细节**：新的潜空间和更新的 VAE，带来更锐利的纹理、更干净的边缘和更精确的视觉效果
+- **9:16 竖屏支持**：竖屏视频质量大幅提升，非常适合社交媒体和移动端
+- **更好的音频**：更干净的声音，减少噪音，增强对话、音乐和环境音效
+- **改进的图生视频**：更一致的运动效果，减少卡顿等问题，动画更流畅自然
+- **更智能的提示词理解**：改进的文本编码器，更准确地理解复杂提示词
+- **更清晰的文字渲染**：视频中的文字和字母渲染更准确
+
+## 快速入门
+
+LTX-2.3 已原生支持 ComfyUI。开始使用：
+
+1. 将 ComfyUI 更新到最新版本
+2. 进入 **模板库** > **视频** > 选择任意 LTX-2.3 工作流
+3. 按照弹窗提示下载模型并运行工作流
+
+## 工作流
+
+### 图生视频
+
+从输入图像生成视频，运动更一致，动画更流畅。
+
+<CardGroup cols={2}>
+  <Card title="图生视频" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_3_i2v.json">
+    下载工作流
+  </Card>
+  <Card title="在 Comfy Cloud 运行" icon="cloud" href="https://links.comfy.org/4skdlDQ">
+    在云端打开
+  </Card>
+</CardGroup>
+
+### 文生视频
+
+从文本提示词生成视频，提示词理解和文字渲染更出色。
+
+<CardGroup cols={2}>
+  <Card title="文生视频" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_3_t2v.json">
+    下载工作流
+  </Card>
+  <Card title="在 Comfy Cloud 运行" icon="cloud" href="https://links.comfy.org/4rZ1DyY">
+    在云端打开
+  </Card>
+</CardGroup>
+
+## 模型下载
+
+### 检查点
+
+| 名称 | 描述 | 下载 |
+|------|------|------|
+| ltx-2.3-22b-dev | BF16 完整模型 | [下载](https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-22b-dev.safetensors) |
+| ltx-2.3-22b-dev-fp8 | FP8 量化模型 | [下载](https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors) |
+
+### LoRAs
+
+| 名称 | 下载 |
+|------|------|
+| ltx-2.3-22b-distilled-lora-384 | [下载](https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-22b-distilled-lora-384.safetensors) |
+
+### 潜空间放大模型
+
+| 名称 | 下载 |
+|------|------|
+| ltx-2.3-spatial-upscaler-x2-1.0 | [下载](https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-spatial-upscaler-x2-1.0.safetensors) |
+
+### 文本编码器
+
+| 名称 | 下载 |
+|------|------|
+| gemma_3_12B_it_fp4_mixed | [下载](https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors) |
+
+## 模型存储位置
+
+```
+ComfyUI/
+├── models/
+│   ├── latent_upscale_models/
+│   │   └── ltx-2.3-spatial-upscaler-x2-1.0.safetensors
+│   ├── checkpoints/
+│   │   ├── ltx-2.3-22b-dev-fp8.safetensors
+│   │   └── ltx-2.3-22b-dev.safetensors
+│   ├── loras/
+│   │   └── ltx-2.3-22b-distilled-lora-384.safetensors
+│   └── text_encoders/
+│       └── gemma_3_12B_it_fp4_mixed.safetensors
+```
+
+## 资源
+
+- [Hugging Face 模型](https://huggingface.co/Lightricks/LTX-2.3)
+- [GitHub 仓库](https://github.com/Lightricks/LTX-2)
+- [ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo/)