only resume download

run the documentation workflow in a custom container.

.github/workflows/build_docker_images.yml

@@ -69,6 +69,7 @@ jobs:
           - diffusers-flax-tpu
           - diffusers-onnxruntime-cpu
           - diffusers-onnxruntime-cuda
+          - diffusers-doc-builder
 
     steps:
       - name: Checkout repository

.github/workflows/build_documentation.yml

@@ -21,7 +21,7 @@ jobs:
       package: diffusers
       notebook_folder: diffusers_doc
       languages: en ko zh ja pt
-
+      custom_container: diffusers/diffusers-doc-builder
     secrets:
       token: ${{ secrets.HUGGINGFACE_PUSH }}
       hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}

.github/workflows/build_pr_documentation.yml

@@ -20,3 +20,4 @@ jobs:
       install_libgl1: true
       package: diffusers
       languages: en ko zh ja pt
+      custom_container: diffusers/diffusers-doc-builder

docker/diffusers-doc-builder/Dockerfile

@@ -0,0 +1,50 @@
+FROM ubuntu:20.04
+LABEL maintainer="Hugging Face"
+LABEL repository="diffusers"
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get -y update \
+    && apt-get install -y software-properties-common \
+    && add-apt-repository ppa:deadsnakes/ppa
+
+RUN apt install -y bash \
+                   build-essential \
+                   git \
+                   git-lfs \
+                   curl \
+                   ca-certificates \
+                   libsndfile1-dev \
+                   python3.10 \
+                   python3-pip \
+                   libgl1 \
+                   python3.10-venv && \
+    rm -rf /var/lib/apt/lists
+
+# make sure to use venv
+RUN python3.10 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
+RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3.10 -m uv pip install --no-cache-dir \
+        torch \
+        torchvision \
+        torchaudio \
+        invisible_watermark \
+        --extra-index-url https://download.pytorch.org/whl/cpu && \
+    python3.10 -m uv pip install --no-cache-dir \
+        accelerate \
+        datasets \
+        hf-doc-builder \
+        huggingface-hub \
+        Jinja2 \
+        librosa \
+        numpy \
+        scipy \
+        tensorboard \
+        transformers \
+        matplotlib \
+        setuptools==69.5.1
+
+CMD ["/bin/bash"]

examples/community/README.md

@@ -69,6 +69,7 @@ Please also check out our [Community Scripts](https://github.com/huggingface/dif
 |   UFOGen Scheduler                                                                                               | Scheduler for UFOGen Model (compatible with Stable Diffusion pipelines)                                                                                                                                                                                                                                                                                                                                                 |  [UFOGen Scheduler](#ufogen-scheduler) | - | [dg845](https://github.com/dg845) |
 | Stable Diffusion XL IPEX Pipeline | Accelerate Stable Diffusion XL inference pipeline with BF16/FP32 precision on Intel Xeon CPUs with [IPEX](https://github.com/intel/intel-extension-for-pytorch) | [Stable Diffusion XL on IPEX](#stable-diffusion-xl-on-ipex) | - | [Dan Li](https://github.com/ustcuna/) |
 | Stable Diffusion BoxDiff Pipeline | Training-free controlled generation with bounding boxes using [BoxDiff](https://github.com/showlab/BoxDiff) | [Stable Diffusion BoxDiff Pipeline](#stable-diffusion-boxdiff) | - | [Jingyang Zhang](https://github.com/zjysteven/) |
+|   FRESCO V2V Pipeline                                                                                                    | Implementation of [[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation](https://arxiv.org/abs/2403.12962)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [FRESCO V2V Pipeline](#fresco)      | - |              [Yifan Zhou](https://github.com/SingleZombie) |
 
 To load a custom pipeline you just need to pass the `custom_pipeline` argument to `DiffusionPipeline`, as one of the files in `diffusers/examples/community`. Feel free to send a PR with your own pipelines, we will merge them quickly.
 
@@ -4035,6 +4036,93 @@ onestep_image = pipe(prompt, num_inference_steps=1).images[0]
 multistep_image = pipe(prompt, num_inference_steps=4).images[0]
 ```
 
+### FRESCO
+
+This is the Diffusers implementation of zero-shot video-to-video translation pipeline [FRESCO](https://github.com/williamyang1991/FRESCO) (without Ebsynth postprocessing and background smooth). To run the code, please install gmflow. Then modify the path in `gmflow_dir`. After that, you can run the pipeline with:
+
+```py
+from PIL import Image
+import cv2
+import torch
+import numpy as np
+
+from diffusers import ControlNetModel,DDIMScheduler, DiffusionPipeline
+import sys
+gmflow_dir = "/path/to/gmflow"
+sys.path.insert(0, gmflow_dir)
+
+def video_to_frame(video_path: str, interval: int):
+    vidcap = cv2.VideoCapture(video_path)
+    success = True
+
+    count = 0
+    res = []
+    while success:
+        count += 1
+        success, image = vidcap.read()
+        if count % interval != 1:
+            continue
+        if image is not None:
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+            res.append(image)
+            if len(res) >= 8:
+                break
+
+    vidcap.release()
+    return res
+
+
+input_video_path = 'https://github.com/williamyang1991/FRESCO/raw/main/data/car-turn.mp4'
+output_video_path = 'car.gif'
+
+# You can use any fintuned SD here
+model_path = 'SG161222/Realistic_Vision_V2.0'
+
+prompt = 'a red car turns in the winter'
+a_prompt = ', RAW photo, subject, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, '
+n_prompt = '(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation'
+
+input_interval = 5
+frames = video_to_frame(
+    input_video_path, input_interval)
+
+control_frames = []
+# get canny image
+for frame in frames:
+    image = cv2.Canny(frame, 50, 100)
+    np_image = np.array(image)
+    np_image = np_image[:, :, None]
+    np_image = np.concatenate([np_image, np_image, np_image], axis=2)
+    canny_image = Image.fromarray(np_image)
+    control_frames.append(canny_image)
+
+# You can use any ControlNet here
+controlnet = ControlNetModel.from_pretrained(
+    "lllyasviel/sd-controlnet-canny").to('cuda')
+
+pipe = DiffusionPipeline.from_pretrained(
+    model_path, controlnet=controlnet, custom_pipeline='fresco_v2v').to('cuda')
+pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+
+generator = torch.manual_seed(0)
+frames = [Image.fromarray(frame) for frame in frames]
+
+output_frames = pipe(
+    prompt + a_prompt,
+    frames,
+    control_frames,
+    num_inference_steps=20,
+    strength=0.75,
+    controlnet_conditioning_scale=0.7,
+    generator=generator,
+    negative_prompt=n_prompt
+).images
+
+output_frames[0].save(output_video_path, save_all=True,
+                 append_images=output_frames[1:], duration=100, loop=0)
+
+```
+
 # Perturbed-Attention Guidance
 
 [Project](https://ku-cvlab.github.io/Perturbed-Attention-Guidance/) / [arXiv](https://arxiv.org/abs/2403.17377) / [GitHub](https://github.com/KU-CVLAB/Perturbed-Attention-Guidance)

src/diffusers/commands/env.py

@@ -31,6 +31,7 @@ from ..utils import (
     is_transformers_available,
     is_xformers_available,
 )
+from ..utils.testing_utils import get_python_version
 from . import BaseDiffusersCLICommand
 
 
@@ -105,6 +106,11 @@ class EnvironmentCommand(BaseDiffusersCLICommand):
 
             xformers_version = xformers.__version__
 
+        if get_python_version() >= (3, 10):
+            platform_info = f"{platform.freedesktop_os_release().get('PRETTY_NAME', None)} - {platform.platform()}"
+        else:
+            platform_info = platform.platform()
+
         is_notebook_str = "Yes" if is_notebook() else "No"
 
         is_google_colab_str = "Yes" if is_google_colab() else "No"
@@ -152,7 +158,7 @@ class EnvironmentCommand(BaseDiffusersCLICommand):
 
         info = {
             "🤗 Diffusers version": version,
-            "Platform": f"{platform.freedesktop_os_release().get('PRETTY_NAME', None)} - {platform.platform()}",
+            "Platform": platform_info,
             "Running on a notebook?": is_notebook_str,
             "Running on Google Colab?": is_google_colab_str,
             "Python version": platform.python_version(),

src/diffusers/loaders/single_file.py

@@ -340,7 +340,7 @@ class FromSingleFileMixin:
             deprecate("original_config_file", "1.0.0", deprecation_message)
             original_config = original_config_file
 
-        resume_download = kwargs.pop("resume_download", False)
+        resume_download = kwargs.pop("resume_download", None)
         force_download = kwargs.pop("force_download", False)
         proxies = kwargs.pop("proxies", None)
         token = kwargs.pop("token", None)

src/diffusers/loaders/single_file_model.py

@@ -166,7 +166,7 @@ class FromOriginalModelMixin:
                 "`from_single_file` cannot accept both `config` and `original_config` arguments. Please provide only one of these arguments"
             )
 
-        resume_download = kwargs.pop("resume_download", False)
+        resume_download = kwargs.pop("resume_download", None)
         force_download = kwargs.pop("force_download", False)
         proxies = kwargs.pop("proxies", None)
         token = kwargs.pop("token", None)