Merge branch 'main' into feature/group-offload-pinning

Author: sayakpaul

.github/workflows/codeql.yml

@@ -0,0 +1,22 @@
+---
+name: CodeQL Security Analysis For Github Actions
+
+on:
+  push:
+    branches: ["main"]
+  workflow_dispatch:
+  # pull_request:
+
+jobs:
+  codeql:
+    name: CodeQL Analysis
+    uses: huggingface/security-workflows/.github/workflows/codeql-reusable.yml@v1
+    permissions:
+      security-events: write
+      packages: read
+      actions: read
+      contents: read
+    with:
+      languages: '["actions","python"]'
+      queries: 'security-extended,security-and-quality'
+      runner: 'ubuntu-latest' #optional if need custom runner

.github/workflows/mirror_community_pipeline.yml

@@ -24,7 +24,6 @@ jobs:
   mirror_community_pipeline:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_COMMUNITY_MIRROR }}
-
     runs-on: ubuntu-22.04
     steps:
       # Checkout to correct ref
@@ -39,25 +38,29 @@ jobs:
       #     If ref is 'refs/heads/main' => set 'main'
       #     Else it must be a tag => set {tag}
       - name: Set checkout_ref and path_in_repo
+        env:
+          EVENT_NAME: ${{ github.event_name }}
+          EVENT_INPUT_REF: ${{ github.event.inputs.ref }}
+          GITHUB_REF: ${{ github.ref }}
         run: |
-          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
-            if [ -z "${{ github.event.inputs.ref }}" ]; then
+          if [ "$EVENT_NAME" == "workflow_dispatch" ]; then
+            if [ -z "$EVENT_INPUT_REF" ]; then
               echo "Error: Missing ref input"
               exit 1
-            elif [ "${{ github.event.inputs.ref }}" == "main" ]; then
+            elif [ "$EVENT_INPUT_REF" == "main" ]; then
               echo "CHECKOUT_REF=refs/heads/main" >> $GITHUB_ENV
               echo "PATH_IN_REPO=main" >> $GITHUB_ENV
             else
-              echo "CHECKOUT_REF=refs/tags/${{ github.event.inputs.ref }}" >> $GITHUB_ENV
-              echo "PATH_IN_REPO=${{ github.event.inputs.ref }}" >> $GITHUB_ENV
+              echo "CHECKOUT_REF=refs/tags/$EVENT_INPUT_REF" >> $GITHUB_ENV
+              echo "PATH_IN_REPO=$EVENT_INPUT_REF" >> $GITHUB_ENV
             fi
-          elif [ "${{ github.ref }}" == "refs/heads/main" ]; then
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
+          elif [ "$GITHUB_REF" == "refs/heads/main" ]; then
+            echo "CHECKOUT_REF=$GITHUB_REF" >> $GITHUB_ENV
             echo "PATH_IN_REPO=main" >> $GITHUB_ENV
           else
             # e.g. refs/tags/v0.28.1 -> v0.28.1
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-            echo "PATH_IN_REPO=$(echo ${{ github.ref }} | sed 's/^refs\/tags\///')" >> $GITHUB_ENV
+            echo "CHECKOUT_REF=$GITHUB_REF" >> $GITHUB_ENV
+            echo "PATH_IN_REPO=$(echo $GITHUB_REF | sed 's/^refs\/tags\///')" >> $GITHUB_ENV
           fi
       - name: Print env vars
         run: |
@@ -99,4 +102,4 @@ jobs:
       - name: Report failure status
         if: ${{ failure() }}
         run: |
-          pip install requests && python utils/notify_community_pipelines_mirror.py --status=failure
+          pip install requests && python utils/notify_community_pipelines_mirror.py --status=failure

docs/source/en/_toctree.yml

@@ -367,6 +367,8 @@
         title: LatteTransformer3DModel
       - local: api/models/longcat_image_transformer2d
         title: LongCatImageTransformer2DModel
+      - local: api/models/ltx2_video_transformer3d
+        title: LTX2VideoTransformer3DModel
       - local: api/models/ltx_video_transformer3d
         title: LTXVideoTransformer3DModel
       - local: api/models/lumina2_transformer2d
@@ -443,6 +445,10 @@
         title: AutoencoderKLHunyuanVideo
       - local: api/models/autoencoder_kl_hunyuan_video15
         title: AutoencoderKLHunyuanVideo15
+      - local: api/models/autoencoderkl_audio_ltx_2
+        title: AutoencoderKLLTX2Audio
+      - local: api/models/autoencoderkl_ltx_2
+        title: AutoencoderKLLTX2Video
       - local: api/models/autoencoderkl_ltx_video
         title: AutoencoderKLLTXVideo
       - local: api/models/autoencoderkl_magvit
@@ -678,6 +684,8 @@
         title: Kandinsky 5.0 Video
       - local: api/pipelines/latte
         title: Latte
+      - local: api/pipelines/ltx2
+        title: LTX-2
       - local: api/pipelines/ltx_video
         title: LTXVideo
       - local: api/pipelines/mochi

docs/source/en/api/models/autoencoderkl_audio_ltx_2.md

@@ -0,0 +1,29 @@
+<!-- Copyright 2025 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. -->
+
+# AutoencoderKLLTX2Audio
+
+The 3D variational autoencoder (VAE) model with KL loss used in [LTX-2](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks. This is for encoding and decoding audio latent representations.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLLTX2Audio
+
+vae = AutoencoderKLLTX2Audio.from_pretrained("Lightricks/LTX-2", subfolder="vae", torch_dtype=torch.float32).to("cuda")
+```
+
+## AutoencoderKLLTX2Audio
+
+[[autodoc]] AutoencoderKLLTX2Audio
+    - encode
+    - decode
+    - all

docs/source/en/api/models/autoencoderkl_ltx_2.md

@@ -0,0 +1,29 @@
+<!-- Copyright 2025 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. -->
+
+# AutoencoderKLLTX2Video
+
+The 3D variational autoencoder (VAE) model with KL loss used in [LTX-2](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLLTX2Video
+
+vae = AutoencoderKLLTX2Video.from_pretrained("Lightricks/LTX-2", subfolder="vae", torch_dtype=torch.float32).to("cuda")
+```
+
+## AutoencoderKLLTX2Video
+
+[[autodoc]] AutoencoderKLLTX2Video
+    - decode
+    - encode
+    - all

docs/source/en/api/models/ltx2_video_transformer3d.md

@@ -0,0 +1,26 @@
+<!-- Copyright 2025 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. -->
+
+# LTX2VideoTransformer3DModel
+
+A Diffusion Transformer model for 3D data from [LTX](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import LTX2VideoTransformer3DModel
+
+transformer = LTX2VideoTransformer3DModel.from_pretrained("Lightricks/LTX-2", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+```
+
+## LTX2VideoTransformer3DModel
+
+[[autodoc]] LTX2VideoTransformer3DModel

docs/source/en/api/pipelines/ltx2.md

@@ -0,0 +1,43 @@
+<!-- Copyright 2025 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. -->
+
+# LTX-2
+
+LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution.
+
+You can find all the original LTX-Video checkpoints under the [Lightricks](https://huggingface.co/Lightricks) organization.
+
+The original codebase for LTX-2 can be found [here](https://github.com/Lightricks/LTX-2).
+
+## LTX2Pipeline
+
+[[autodoc]] LTX2Pipeline
+  - all
+  - __call__
+
+## LTX2ImageToVideoPipeline
+
+[[autodoc]] LTX2ImageToVideoPipeline
+  - all
+  - __call__
+
+## LTX2LatentUpsamplePipeline
+
+[[autodoc]] LTX2LatentUpsamplePipeline
+  - all
+  - __call__
+
+## LTX2PipelineOutput
+
+[[autodoc]] pipelines.ltx2.pipeline_output.LTX2PipelineOutput

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

@@ -136,7 +136,7 @@ export_to_video(video, "output.mp4", fps=24)
   - The recommended dtype for the transformer, VAE, and text encoder is `torch.bfloat16`. The VAE and text encoder can also be `torch.float32` or `torch.float16`.
   - For guidance-distilled variants of LTX-Video, set `guidance_scale` to `1.0`. The `guidance_scale` for any other model should be set higher, like `5.0`, for good generation quality.
   - For timestep-aware VAE variants (LTX-Video 0.9.1 and above), set `decode_timestep` to `0.05` and `image_cond_noise_scale` to `0.025`.
-  - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitionts in the generated video.
+  - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitions in the generated video.
 
 - LTX-Video 0.9.7 includes a spatial latent upscaler and a 13B parameter transformer. During inference, a low resolution video is quickly generated first and then upscaled and refined.
 
@@ -329,7 +329,7 @@ export_to_video(video, "output.mp4", fps=24)
 
   <details>
   <summary>Show example code</summary>
-  
+
   ```python
   import torch
   from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
@@ -474,6 +474,12 @@ export_to_video(video, "output.mp4", fps=24)
 
   </details>
 
+## LTXI2VLongMultiPromptPipeline
+
+[[autodoc]] LTXI2VLongMultiPromptPipeline
+  - all
+  - __call__
+
 ## LTXPipeline
 
 [[autodoc]] LTXPipeline

docs/source/en/api/pipelines/skyreels_v2.md

@@ -37,7 +37,8 @@ The following SkyReels-V2 models are supported in Diffusers:
 - [SkyReels-V2 I2V 1.3B - 540P](https://huggingface.co/Skywork/SkyReels-V2-I2V-1.3B-540P-Diffusers)
 - [SkyReels-V2 I2V 14B - 540P](https://huggingface.co/Skywork/SkyReels-V2-I2V-14B-540P-Diffusers)
 - [SkyReels-V2 I2V 14B - 720P](https://huggingface.co/Skywork/SkyReels-V2-I2V-14B-720P-Diffusers)
-- [SkyReels-V2 FLF2V 1.3B - 540P](https://huggingface.co/Skywork/SkyReels-V2-FLF2V-1.3B-540P-Diffusers)
+
+This model was contributed by [M. Tolga Cangöz](https://github.com/tolgacangoz).
 
 > [!TIP]
 > Click on the SkyReels-V2 models in the right sidebar for more examples of video generation.

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

@@ -250,9 +250,6 @@ The code snippets available in [this](https://github.com/huggingface/diffusers/p
 
 The general rule of thumb to keep in mind when preparing inputs for the VACE pipeline is that the input images, or frames of a video that you want to use for conditioning, should have a corresponding mask that is black in color. The black mask signifies that the model will not generate new content for that area, and only use those parts for conditioning the generation process. For parts/frames that should be generated by the model, the mask should be white in color.
 
-</hfoption>
-</hfoptions>
-
 ### Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
 
 [Wan-Animate](https://huggingface.co/papers/2509.14055) by the Wan Team.