Merge branch 'main' into integrations/skyreels-v1

Author: a-r-r-o-w

.github/workflows/pr_tests.yml

@@ -64,6 +64,7 @@ jobs:
         run: |
           python utils/check_copies.py
           python utils/check_dummies.py
+          python utils/check_support_list.py
           make deps_table_check_updated
       - name: Check if failure
         if: ${{ failure() }}
@@ -120,7 +121,8 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment
       run: |

.github/workflows/push_tests.yml

@@ -1,6 +1,13 @@
 name: Fast GPU Tests on main
 
 on:
+  pull_request:
+    branches: main
+    paths:
+      - "src/diffusers/models/modeling_utils.py"
+      - "src/diffusers/models/model_loading_utils.py"
+      - "src/diffusers/pipelines/pipeline_utils.py"
+      - "src/diffusers/pipeline_loading_utils.py"
   workflow_dispatch:
   push:
     branches:
@@ -160,6 +167,7 @@ jobs:
         path: reports
 
   flax_tpu_tests:
+    if: ${{ github.event_name != 'pull_request' }}
     name: Flax TPU Tests
     runs-on:
       group: gcp-ct5lp-hightpu-8t
@@ -208,6 +216,7 @@ jobs:
         path: reports
 
   onnx_cuda_tests:
+    if: ${{ github.event_name != 'pull_request' }}
     name: ONNX CUDA Tests
     runs-on:
       group: aws-g4dn-2xlarge
@@ -256,6 +265,7 @@ jobs:
         path: reports
 
   run_torch_compile_tests:
+    if: ${{ github.event_name != 'pull_request' }}
     name: PyTorch Compile CUDA tests
 
     runs-on:
@@ -299,6 +309,7 @@ jobs:
         path: reports
 
   run_xformers_tests:
+    if: ${{ github.event_name != 'pull_request' }}
     name: PyTorch xformers CUDA tests
 
     runs-on:
@@ -349,7 +360,6 @@ jobs:
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host
-
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -359,7 +369,6 @@ jobs:
     - name: NVIDIA-SMI
       run: |
         nvidia-smi
-
     - name: Install dependencies
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"

docs/source/en/api/activations.md

@@ -25,3 +25,16 @@ Customized activation functions for supporting various models in 🤗 Diffusers.
 ## ApproximateGELU
 
 [[autodoc]] models.activations.ApproximateGELU
+
+
+## SwiGLU
+
+[[autodoc]] models.activations.SwiGLU
+
+## FP32SiLU
+
+[[autodoc]] models.activations.FP32SiLU
+
+## LinearActivation
+
+[[autodoc]] models.activations.LinearActivation

docs/source/en/api/attnprocessor.md

@@ -147,3 +147,20 @@ An attention processor is a class for applying different types of attention mech
 ## XLAFlashAttnProcessor2_0
 
 [[autodoc]] models.attention_processor.XLAFlashAttnProcessor2_0
+
+## XFormersJointAttnProcessor
+
+[[autodoc]] models.attention_processor.XFormersJointAttnProcessor
+
+## IPAdapterXFormersAttnProcessor
+
+[[autodoc]] models.attention_processor.IPAdapterXFormersAttnProcessor
+
+## FluxIPAdapterJointAttnProcessor2_0
+
+[[autodoc]] models.attention_processor.FluxIPAdapterJointAttnProcessor2_0
+
+
+## XLAFluxFlashAttnProcessor2_0
+
+[[autodoc]] models.attention_processor.XLAFluxFlashAttnProcessor2_0

docs/source/en/api/loaders/lora.md

@@ -23,6 +23,7 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`LTXVideoLoraLoaderMixin`] provides similar functions for [LTX-Video](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video).
 - [`SanaLoraLoaderMixin`] provides similar functions for [Sana](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana).
 - [`HunyuanVideoLoraLoaderMixin`] provides similar functions for [HunyuanVideo](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hunyuan_video).
+- [`Lumina2LoraLoaderMixin`] provides similar functions for [Lumina2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/lumina2).
 - [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
@@ -68,6 +69,10 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 [[autodoc]] loaders.lora_pipeline.HunyuanVideoLoraLoaderMixin
 
+## Lumina2LoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.Lumina2LoraLoaderMixin
+
 ## AmusedLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin

docs/source/en/api/normalization.md

@@ -29,3 +29,43 @@ Customized normalization layers for supporting various models in 🤗 Diffusers.
 ## AdaGroupNorm
 
 [[autodoc]] models.normalization.AdaGroupNorm
+
+## AdaLayerNormContinuous
+
+[[autodoc]] models.normalization.AdaLayerNormContinuous
+
+## RMSNorm
+
+[[autodoc]] models.normalization.RMSNorm
+
+## GlobalResponseNorm
+
+[[autodoc]] models.normalization.GlobalResponseNorm
+
+
+## LuminaLayerNormContinuous
+[[autodoc]] models.normalization.LuminaLayerNormContinuous
+
+## SD35AdaLayerNormZeroX
+[[autodoc]] models.normalization.SD35AdaLayerNormZeroX
+
+## AdaLayerNormZeroSingle
+[[autodoc]] models.normalization.AdaLayerNormZeroSingle
+
+## LuminaRMSNormZero
+[[autodoc]] models.normalization.LuminaRMSNormZero
+
+## LpNorm
+[[autodoc]] models.normalization.LpNorm
+
+## CogView3PlusAdaLayerNormZeroTextImage
+[[autodoc]] models.normalization.CogView3PlusAdaLayerNormZeroTextImage
+
+## CogVideoXLayerNormZero
+[[autodoc]] models.normalization.CogVideoXLayerNormZero
+
+## MochiRMSNormZero
+[[autodoc]] models.transformers.transformer_mochi.MochiRMSNormZero
+
+## MochiRMSNorm
+[[autodoc]] models.normalization.MochiRMSNorm

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

@@ -77,7 +77,7 @@ from diffusers import StableDiffusion3Pipeline
 from transformers import SiglipVisionModel, SiglipImageProcessor
 
 image_encoder_id = "google/siglip-so400m-patch14-384"
-ip_adapter_id = "guiyrt/InstantX-SD3.5-Large-IP-Adapter-diffusers"
+ip_adapter_id = "InstantX/SD3.5-Large-IP-Adapter"
 
 feature_extractor = SiglipImageProcessor.from_pretrained(
     image_encoder_id,

examples/README.md

@@ -40,9 +40,9 @@ Training examples show how to pretrain or fine-tune diffusion models for a varie
 | [**Text-to-Image fine-tuning**](./text_to_image) | ✅ | ✅ |
 | [**Textual Inversion**](./textual_inversion) | ✅ | - | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb)
 | [**Dreambooth**](./dreambooth) | ✅ | - | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb)
-| [**ControlNet**](./controlnet) | ✅ | ✅ | -
-| [**InstructPix2Pix**](./instruct_pix2pix) | ✅ | ✅ | -
-| [**Reinforcement Learning for Control**](./reinforcement_learning)                    | - | - | coming soon.
+| [**ControlNet**](./controlnet) | ✅ | ✅ | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
+| [**InstructPix2Pix**](./instruct_pix2pix) | ✅ | ✅ | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/InstructPix2Pix_using_diffusers.ipynb)
+| [**Reinforcement Learning for Control**](./reinforcement_learning)                    | - | - | [Notebook1](https://github.com/huggingface/notebooks/blob/main/diffusers/reinforcement_learning_for_control.ipynb),  [Notebook2](https://github.com/huggingface/notebooks/blob/main/diffusers/reinforcement_learning_with_diffusers.ipynb)
 
 ## Community