Merge branch 'main' into main

Author: lawrence-cj

docs/source/en/_toctree.yml

@@ -295,6 +295,8 @@
         title: CogView4Transformer2DModel
       - local: api/models/consisid_transformer3d
         title: ConsisIDTransformer3DModel
+      - local: api/models/cosmos_transformer3d
+        title: CosmosTransformer3DModel
       - local: api/models/dit_transformer2d
         title: DiTTransformer2DModel
       - local: api/models/easyanimate_transformer3d
@@ -363,6 +365,8 @@
         title: AutoencoderKLAllegro
       - local: api/models/autoencoderkl_cogvideox
         title: AutoencoderKLCogVideoX
+      - local: api/models/autoencoderkl_cosmos
+        title: AutoencoderKLCosmos
       - local: api/models/autoencoder_kl_hunyuan_video
         title: AutoencoderKLHunyuanVideo
       - local: api/models/autoencoderkl_ltx_video
@@ -433,6 +437,8 @@
       title: ControlNet-XS with Stable Diffusion XL
     - local: api/pipelines/controlnet_union
       title: ControlNetUnion
+    - local: api/pipelines/cosmos
+      title: Cosmos
     - local: api/pipelines/dance_diffusion
       title: Dance Diffusion
     - local: api/pipelines/ddim

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

@@ -0,0 +1,40 @@
+<!-- Copyright 2024 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. -->
+
+# AutoencoderKLCosmos
+
+[Cosmos Tokenizers](https://github.com/NVIDIA/Cosmos-Tokenizer).
+
+Supported models:
+- [nvidia/Cosmos-1.0-Tokenizer-CV8x8x8](https://huggingface.co/nvidia/Cosmos-1.0-Tokenizer-CV8x8x8)
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLCosmos
+
+vae = AutoencoderKLCosmos.from_pretrained("nvidia/Cosmos-1.0-Tokenizer-CV8x8x8", subfolder="vae")
+```
+
+## AutoencoderKLCosmos
+
+[[autodoc]] AutoencoderKLCosmos
+    - decode
+    - encode
+    - all
+
+## AutoencoderKLOutput
+
+[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/cosmos_transformer3d.md

@@ -0,0 +1,30 @@
+<!-- Copyright 2024 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. -->
+
+# CosmosTransformer3DModel
+
+A Diffusion Transformer model for 3D video-like data was introduced in [Cosmos World Foundation Model Platform for Physical AI](https://huggingface.co/papers/2501.03575) by NVIDIA.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import CosmosTransformer3DModel
+
+transformer = CosmosTransformer3DModel.from_pretrained("nvidia/Cosmos-1.0-Diffusion-7B-Text2World", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## CosmosTransformer3DModel
+
+[[autodoc]] CosmosTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/pipelines/cosmos.md

@@ -0,0 +1,41 @@
+<!-- Copyright 2024 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. -->
+
+# Cosmos
+
+[Cosmos World Foundation Model Platform for Physical AI](https://huggingface.co/papers/2501.03575) by NVIDIA.
+
+*Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make our platform open-source and our models open-weight with permissive licenses available via https://github.com/NVIDIA/Cosmos.*
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+## CosmosTextToWorldPipeline
+
+[[autodoc]] CosmosTextToWorldPipeline
+  - all
+  - __call__
+
+## CosmosVideoToWorldPipeline
+
+[[autodoc]] CosmosVideoToWorldPipeline
+  - all
+  - __call__
+
+## CosmosPipelineOutput
+
+[[autodoc]] pipelines.cosmos.pipeline_output.CosmosPipelineOutput