Merge branch 'main' into flux-quantized-w-lora

Author: sayakpaul

.github/workflows/pr_style_bot.yml

@@ -13,39 +13,5 @@ jobs:
     uses: huggingface/huggingface_hub/.github/workflows/style-bot-action.yml@main
     with:
       python_quality_dependencies: "[quality]"
-      pre_commit_script_name: "Download and Compare files from the main branch"
-      pre_commit_script: |
-        echo "Downloading the files from the main branch"
-
-        curl -o main_Makefile https://raw.githubusercontent.com/huggingface/diffusers/main/Makefile
-        curl -o main_setup.py https://raw.githubusercontent.com/huggingface/diffusers/refs/heads/main/setup.py
-        curl -o main_check_doc_toc.py https://raw.githubusercontent.com/huggingface/diffusers/refs/heads/main/utils/check_doc_toc.py
-
-        echo "Compare the files and raise error if needed"
-
-        diff_failed=0
-        if ! diff -q main_Makefile Makefile; then
-          echo "Error: The Makefile has changed. Please ensure it matches the main branch."
-          diff_failed=1
-        fi
-
-        if ! diff -q main_setup.py setup.py; then
-          echo "Error: The setup.py has changed. Please ensure it matches the main branch."
-          diff_failed=1
-        fi
-
-        if ! diff -q main_check_doc_toc.py utils/check_doc_toc.py; then
-          echo "Error: The utils/check_doc_toc.py has changed. Please ensure it matches the main branch."
-          diff_failed=1
-        fi
-
-        if [ $diff_failed -eq 1 ]; then
-          echo "❌ Error happened as we detected changes in the files that should not be changed ❌"
-          exit 1
-        fi
-
-        echo "No changes in the files. Proceeding..."
-        rm -rf main_Makefile main_setup.py main_check_doc_toc.py
-      style_command: "make style && make quality"
     secrets:
       bot_token: ${{ secrets.GITHUB_TOKEN }}

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

@@ -14,6 +14,7 @@ specific language governing permissions and limitations under the License.
 
 <div class="flex flex-wrap space-x-1">
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
 </div>
 
 ## Overview

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

@@ -14,6 +14,7 @@ specific language governing permissions and limitations under the License.
 
 <div class="flex flex-wrap space-x-1">
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
 </div>
 
 Flux is a series of text-to-image generation models based on diffusion transformers. To know more about Flux, check out the original [blog post](https://blackforestlabs.ai/announcing-black-forest-labs/) by the creators of Flux, Black Forest Labs.

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

@@ -14,6 +14,7 @@ specific language governing permissions and limitations under the License.
 
 <div class="flex flex-wrap space-x-1">
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
 </div>
 
 ![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/kolors/kolors_header_collage.png)

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

@@ -16,6 +16,7 @@
 
 <div class="flex flex-wrap space-x-1">
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
 </div>
 
 [LTX Video](https://huggingface.co/Lightricks/LTX-Video) is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content. We provide a model for both text-to-video as well as image + text-to-video usecases.
@@ -32,6 +33,7 @@ Available models:
 |:-------------:|:-----------------:|
 | [`LTX Video 0.9.0`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.safetensors) | `torch.bfloat16` |
 | [`LTX Video 0.9.1`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.1.safetensors) | `torch.bfloat16` |
+| [`LTX Video 0.9.5`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.5.safetensors) | `torch.bfloat16` |
 
 Note: The recommended dtype is for the transformer component. The VAE and text encoders can be either `torch.float32`, `torch.bfloat16` or `torch.float16` but the recommended dtype is `torch.bfloat16` as used in the original repository.
 

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

@@ -16,6 +16,7 @@
 
 <div class="flex flex-wrap space-x-1">
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
 </div>
 
 [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://huggingface.co/papers/2410.10629) from NVIDIA and MIT HAN Lab, by Enze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao Lu, Song Han.

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

@@ -14,6 +14,7 @@ specific language governing permissions and limitations under the License.
 
 <div class="flex flex-wrap space-x-1">
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
 </div>
 
 Stable Diffusion 3 (SD3) was proposed in [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://arxiv.org/pdf/2403.03206.pdf) by Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Muller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, Kyle Lacey, Alex Goodwin, Yannik Marek, and Robin Rombach.

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

@@ -14,6 +14,7 @@ specific language governing permissions and limitations under the License.
 
 <div class="flex flex-wrap space-x-1">
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
 </div>
 
 Stable Diffusion XL (SDXL) was proposed in [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://huggingface.co/papers/2307.01952) by Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, and Robin Rombach.

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

@@ -133,6 +133,46 @@ output = pipe(
 export_to_video(output, "wan-i2v.mp4", fps=16)
 ```
 
+### Video to Video Generation
+
+```python
+import torch
+from diffusers.utils import load_video, export_to_video
+from diffusers import AutoencoderKLWan, WanVideoToVideoPipeline, UniPCMultistepScheduler
+
+# Available models: Wan-AI/Wan2.1-T2V-14B-Diffusers, Wan-AI/Wan2.1-T2V-1.3B-Diffusers
+model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(
+    model_id, subfolder="vae", torch_dtype=torch.float32
+)
+pipe = WanVideoToVideoPipeline.from_pretrained(
+    model_id, vae=vae, torch_dtype=torch.bfloat16
+)
+flow_shift = 3.0  # 5.0 for 720P, 3.0 for 480P
+pipe.scheduler = UniPCMultistepScheduler.from_config(
+    pipe.scheduler.config, flow_shift=flow_shift
+)
+# change to pipe.to("cuda") if you have sufficient VRAM
+pipe.enable_model_cpu_offload()
+
+prompt = "A robot standing on a mountain top. The sun is setting in the background"
+negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
+video = load_video(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hiker.mp4"
+)
+output = pipe(
+    video=video,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=512,
+    guidance_scale=7.0,
+    strength=0.7,
+).frames[0]
+
+export_to_video(output, "wan-v2v.mp4", fps=16)
+```
+
 ## Memory Optimizations for Wan 2.1
 
 Base inference with the large 14B Wan 2.1 models can take up to 35GB of VRAM when generating videos at 720p resolution. We'll outline a few memory optimizations we can apply to reduce the VRAM required to run the model.
@@ -323,7 +363,7 @@ import numpy as np
 from diffusers import AutoencoderKLWan, WanTransformer3DModel, WanImageToVideoPipeline
 from diffusers.hooks.group_offloading import apply_group_offloading
 from diffusers.utils import export_to_video, load_image
-from transformers import UMT5EncoderModel, CLIPVisionMode
+from transformers import UMT5EncoderModel, CLIPVisionModel
 
 model_id = "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers"
 image_encoder = CLIPVisionModel.from_pretrained(
@@ -356,7 +396,7 @@ prompt = (
     "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in "
     "the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
 )
-negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
+negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
 num_frames = 33
 
 output = pipe(
@@ -372,7 +412,7 @@ output = pipe(
 export_to_video(output, "wan-i2v.mp4", fps=16)
 ```
 
-### Using a Custom Scheduler
+## Using a Custom Scheduler
 
 Wan can be used with many different schedulers, each with their own benefits regarding speed and generation quality. By default, Wan uses the `UniPCMultistepScheduler(prediction_type="flow_prediction", use_flow_sigmas=True, flow_shift=3.0)` scheduler. You can use a different scheduler as follows:
 
@@ -403,7 +443,7 @@ transformer = WanTransformer3DModel.from_single_file(ckpt_path, torch_dtype=torc
 pipe = WanPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", transformer=transformer)
 ```
 
-## Recommendations for Inference:
+## Recommendations for Inference
 - Keep `AutencoderKLWan` in `torch.float32` for better decoding quality.
 - `num_frames` should satisfy the following constraint: `(num_frames - 1) % 4 == 0`
 - For smaller resolution videos, try lower values of `shift` (between `2.0` to `5.0`) in the [Scheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler.shift). For larger resolution videos, try higher values (between `7.0` and `12.0`). The default value is `3.0` for Wan.

docs/source/en/installation.md

@@ -161,10 +161,10 @@ Your Python environment will find the `main` version of 🤗 Diffusers on the ne
 
 Model weights and files are downloaded from the Hub to a cache which is usually your home directory. You can change the cache location by specifying the `HF_HOME` or `HUGGINFACE_HUB_CACHE` environment variables or configuring the `cache_dir` parameter in methods like [`~DiffusionPipeline.from_pretrained`].
 
-Cached files allow you to run 🤗 Diffusers offline. To prevent 🤗 Diffusers from connecting to the internet, set the `HF_HUB_OFFLINE` environment variable to `True` and 🤗 Diffusers will only load previously downloaded files in the cache.
+Cached files allow you to run 🤗 Diffusers offline. To prevent 🤗 Diffusers from connecting to the internet, set the `HF_HUB_OFFLINE` environment variable to `1` and 🤗 Diffusers will only load previously downloaded files in the cache.
 
 ```shell
-export HF_HUB_OFFLINE=True
+export HF_HUB_OFFLINE=1
 ```
 
 For more details about managing and cleaning the cache, take a look at the [caching](https://huggingface.co/docs/huggingface_hub/guides/manage-cache) guide.
@@ -179,14 +179,16 @@ Telemetry is only sent when loading models and pipelines from the Hub,
 and it is not collected if you're loading local files.
 
 We understand that not everyone wants to share additional information,and we respect your privacy.
-You can disable telemetry collection by setting the `DISABLE_TELEMETRY` environment variable from your terminal:
+You can disable telemetry collection by setting the `HF_HUB_DISABLE_TELEMETRY` environment variable from your terminal:
 
 On Linux/MacOS:
+
 ```bash
-export DISABLE_TELEMETRY=YES
+export HF_HUB_DISABLE_TELEMETRY=1
 ```
 
 On Windows:
+
 ```bash
-set DISABLE_TELEMETRY=YES
+set HF_HUB_DISABLE_TELEMETRY=1
 ```