Add KVAE 1.0

docs/source/en/_toctree.yml

@@ -446,6 +446,10 @@
         title: AutoencoderKLHunyuanVideo
       - local: api/models/autoencoder_kl_hunyuan_video15
         title: AutoencoderKLHunyuanVideo15
+      - local: api/models/autoencoder_kl_kvae
+        title: AutoencoderKLKVAE
+      - local: api/models/autoencoder_kl_kvae_video
+        title: AutoencoderKLKVAEVideo
       - local: api/models/autoencoderkl_audio_ltx_2
         title: AutoencoderKLLTX2Audio
       - local: api/models/autoencoderkl_ltx_2

docs/source/en/api/models/autoencoder_kl_kvae.md

@@ -0,0 +1,32 @@
+<!-- Copyright 2025 The Kandinsky Team and The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License. -->
+
+# AutoencoderKLKVAE
+
+The 2D variational autoencoder (VAE) model with KL loss.
+
+The model can be loaded with the following code snippet.
+
+```python
+import torch
+from diffusers import AutoencoderKLKVAE
+
+vae = AutoencoderKLKVAE.from_pretrained("kandinskylab/KVAE-2D-1.0", subfolder="diffusers", torch_dtype=torch.bfloat16)
+```
+
+## AutoencoderKLKVAE
+
+[[autodoc]] AutoencoderKLKVAE
+  - decode
+  - all

docs/source/en/api/models/autoencoder_kl_kvae_video.md

@@ -0,0 +1,33 @@
+<!-- Copyright 2025 The Kandinsky Team and The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License. -->
+
+# AutoencoderKLKVAEVideo
+
+The 3D variational autoencoder (VAE) model with KL loss.
+
+The model can be loaded with the following code snippet.
+
+```python
+import torch
+from diffusers import AutoencoderKLKVAEVideo
+
+vae = AutoencoderKLKVAEVideo.from_pretrained("kandinskylab/KVAE-3D-1.0", subfolder="diffusers", torch_dtype=torch.float16)
+```
+
+## AutoencoderKLKVAEVideo
+
+[[autodoc]] AutoencoderKLKVAEVideo
+  - decode
+  - all
+

src/diffusers/__init__.py

@@ -193,6 +193,8 @@
             "AutoencoderKLHunyuanImageRefiner",
             "AutoencoderKLHunyuanVideo",
             "AutoencoderKLHunyuanVideo15",
+            "AutoencoderKLKVAE",
+            "AutoencoderKLKVAEVideo",
             "AutoencoderKLLTX2Audio",
             "AutoencoderKLLTX2Video",
             "AutoencoderKLLTXVideo",
@@ -974,6 +976,8 @@
             AutoencoderKLHunyuanImageRefiner,
             AutoencoderKLHunyuanVideo,
             AutoencoderKLHunyuanVideo15,
+            AutoencoderKLKVAE,
+            AutoencoderKLKVAEVideo,
             AutoencoderKLLTX2Audio,
             AutoencoderKLLTX2Video,
             AutoencoderKLLTXVideo,

src/diffusers/models/__init__.py

@@ -40,6 +40,8 @@
     _import_structure["autoencoders.autoencoder_kl_hunyuanimage"] = ["AutoencoderKLHunyuanImage"]
     _import_structure["autoencoders.autoencoder_kl_hunyuanimage_refiner"] = ["AutoencoderKLHunyuanImageRefiner"]
     _import_structure["autoencoders.autoencoder_kl_hunyuanvideo15"] = ["AutoencoderKLHunyuanVideo15"]
+    _import_structure["autoencoders.autoencoder_kl_kvae"] = ["AutoencoderKLKVAE"]
+    _import_structure["autoencoders.autoencoder_kl_kvae_video"] = ["AutoencoderKLKVAEVideo"]
     _import_structure["autoencoders.autoencoder_kl_ltx"] = ["AutoencoderKLLTXVideo"]
     _import_structure["autoencoders.autoencoder_kl_ltx2"] = ["AutoencoderKLLTX2Video"]
     _import_structure["autoencoders.autoencoder_kl_ltx2_audio"] = ["AutoencoderKLLTX2Audio"]
@@ -161,6 +163,8 @@
             AutoencoderKLHunyuanImageRefiner,
             AutoencoderKLHunyuanVideo,
             AutoencoderKLHunyuanVideo15,
+            AutoencoderKLKVAE,
+            AutoencoderKLKVAEVideo,
             AutoencoderKLLTX2Audio,
             AutoencoderKLLTX2Video,
             AutoencoderKLLTXVideo,

src/diffusers/models/autoencoders/__init__.py

@@ -9,6 +9,8 @@
 from .autoencoder_kl_hunyuanimage import AutoencoderKLHunyuanImage
 from .autoencoder_kl_hunyuanimage_refiner import AutoencoderKLHunyuanImageRefiner
 from .autoencoder_kl_hunyuanvideo15 import AutoencoderKLHunyuanVideo15
+from .autoencoder_kl_kvae import AutoencoderKLKVAE
+from .autoencoder_kl_kvae_video import AutoencoderKLKVAEVideo
 from .autoencoder_kl_ltx import AutoencoderKLLTXVideo
 from .autoencoder_kl_ltx2 import AutoencoderKLLTX2Video
 from .autoencoder_kl_ltx2_audio import AutoencoderKLLTX2Audio