Add transfer support to the Cosmos3 modular pipeline

.github/workflows/build_documentation.yml

@@ -17,14 +17,13 @@ permissions:
 
 jobs:
   build:
-    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@2430c1ec91d04667414e2fa31ecfc36c153ea391  # main
+    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@e60a538eea9817ab312196d0d233604b01697265  # main
     with:
       commit_sha: ${{ github.sha }}
       install_libgl1: true
       package: diffusers
       notebook_folder: diffusers_doc
       languages: en ko zh ja pt
-      custom_container: diffusers/diffusers-doc-builder
       pre_command: uv pip uninstall transformers huggingface_hub && UV_PRERELEASE=allow uv pip install -U transformers@git+https://github.com/huggingface/transformers.git
     secrets:
       token: ${{ secrets.HUGGINGFACE_PUSH }}

.github/workflows/build_pr_documentation.yml

@@ -42,12 +42,11 @@ jobs:
 
   build:
     needs: check-links
-    uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3  # main
+    uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@e60a538eea9817ab312196d0d233604b01697265  # main
     with:
       commit_sha: ${{ github.event.pull_request.head.sha }}
       pr_number: ${{ github.event.number }}
       install_libgl1: true
       package: diffusers
       languages: en ko zh ja pt
-      custom_container: diffusers/diffusers-doc-builder
       pre_command: uv pip uninstall transformers huggingface_hub && UV_PRERELEASE=allow uv pip install -U transformers@git+https://github.com/huggingface/transformers.git

docker/diffusers-pytorch-cuda/Dockerfile

@@ -40,11 +40,6 @@ RUN uv pip install --no-cache-dir \
     torchaudio==2.10.0 \
     --index-url https://download.pytorch.org/whl/cu129
 
-# Install compatible versions of numba/llvmlite for Python 3.10+
-RUN uv pip install --no-cache-dir \
-    "llvmlite>=0.40.0" \
-    "numba>=0.57.0"
-
 RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
 
 # Extra dependencies

docs/source/en/_toctree.yml

@@ -353,6 +353,8 @@
         title: HunyuanVideoTransformer3DModel
       - local: api/models/ideogram4_transformer2d
         title: Ideogram4Transformer2DModel
+      - local: api/models/transformer_joyimage_edit_plus
+        title: JoyImageEditPlusTransformer3DModel
       - local: api/models/transformer_joyimage
         title: JoyImageEditTransformer3DModel
       - local: api/models/krea2_transformer2d
@@ -555,6 +557,8 @@
         title: InstructPix2Pix
       - local: api/pipelines/joyimage_edit
         title: JoyImage Edit
+      - local: api/pipelines/joyimage_edit_plus
+        title: JoyImage Edit Plus
       - local: api/pipelines/kandinsky
         title: Kandinsky 2.1
       - local: api/pipelines/kandinsky_v22

docs/source/en/api/models/transformer_joyimage_edit_plus.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.
+-->
+
+# JoyImageEditPlusTransformer3DModel
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import JoyImageEditPlusTransformer3DModel
+
+transformer = JoyImageEditPlusTransformer3DModel.from_pretrained("jdopensource/JoyAI-Image-Edit-Plus-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## JoyImageEditPlusTransformer3DModel
+
+[[autodoc]] JoyImageEditPlusTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -68,7 +68,7 @@ scheduler = DDIMScheduler.from_pretrained(
 pipe.scheduler = scheduler
 
 # enable memory savings
-pipe.enable_vae_slicing()
+pipe.vae.enable_slicing()
 pipe.enable_model_cpu_offload()
 
 output = pipe(
@@ -395,8 +395,8 @@ pipe = AnimateDiffSDXLPipeline.from_pretrained(
 ).to("cuda")
 
 # enable memory savings
-pipe.enable_vae_slicing()
-pipe.enable_vae_tiling()
+pipe.vae.enable_slicing()
+pipe.vae.enable_tiling()
 
 output = pipe(
     prompt="a panda surfing in the ocean, realistic, high quality",
@@ -441,7 +441,7 @@ scheduler = DDIMScheduler.from_pretrained(
 pipe.scheduler = scheduler
 
 # enable memory savings
-pipe.enable_vae_slicing()
+pipe.vae.enable_slicing()
 pipe.enable_model_cpu_offload()
 
 # helper function to load videos
@@ -640,7 +640,7 @@ scheduler = DDIMScheduler.from_pretrained(
 pipe.scheduler = scheduler
 
 # enable memory savings
-pipe.enable_vae_slicing()
+pipe.vae.enable_slicing()
 pipe.enable_model_cpu_offload()
 
 output = pipe(
@@ -714,7 +714,7 @@ scheduler = DDIMScheduler.from_pretrained(
 pipe.scheduler = scheduler
 
 # enable memory savings
-pipe.enable_vae_slicing()
+pipe.vae.enable_slicing()
 pipe.enable_model_cpu_offload()
 
 output = pipe(
@@ -772,8 +772,8 @@ pipe.scheduler = DDIMScheduler.from_pretrained(
 )
 
 # enable memory savings
-pipe.enable_vae_slicing()
-pipe.enable_vae_tiling()
+pipe.vae.enable_slicing()
+pipe.vae.enable_tiling()
 
 # enable FreeInit
 # Refer to the enable_free_init documentation for a full list of configurable parameters
@@ -840,7 +840,7 @@ pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="
 
 pipe.load_lora_weights("wangfuyun/AnimateLCM", weight_name="sd15_lora_beta.safetensors", adapter_name="lcm-lora")
 
-pipe.enable_vae_slicing()
+pipe.vae.enable_slicing()
 pipe.enable_model_cpu_offload()
 
 output = pipe(
@@ -882,7 +882,7 @@ pipe.load_lora_weights("wangfuyun/AnimateLCM", weight_name="sd15_lora_beta.safet
 pipe.load_lora_weights("guoyww/animatediff-motion-lora-tilt-up", adapter_name="tilt-up")
 
 pipe.set_adapters(["lcm-lora", "tilt-up"], [1.0, 0.8])
-pipe.enable_vae_slicing()
+pipe.vae.enable_slicing()
 pipe.enable_model_cpu_offload()
 
 output = pipe(

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

@@ -37,8 +37,6 @@ The original codebase can be found at [lllyasviel/ControlNet](https://github.com
 	- __call__
 	- enable_attention_slicing
 	- disable_attention_slicing
-	- enable_vae_slicing
-	- disable_vae_slicing
 	- enable_xformers_memory_efficient_attention
 	- disable_xformers_memory_efficient_attention
 	- load_textual_inversion
@@ -49,8 +47,6 @@ The original codebase can be found at [lllyasviel/ControlNet](https://github.com
 	- __call__
 	- enable_attention_slicing
 	- disable_attention_slicing
-	- enable_vae_slicing
-	- disable_vae_slicing
 	- enable_xformers_memory_efficient_attention
 	- disable_xformers_memory_efficient_attention
 	- load_textual_inversion
@@ -61,8 +57,6 @@ The original codebase can be found at [lllyasviel/ControlNet](https://github.com
 	- __call__
 	- enable_attention_slicing
 	- disable_attention_slicing
-	- enable_vae_slicing
-	- disable_vae_slicing
 	- enable_xformers_memory_efficient_attention
 	- disable_xformers_memory_efficient_attention
 	- load_textual_inversion