update

.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

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

examples/community/README.md

@@ -69,7 +69,6 @@ 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.
 
@@ -4036,93 +4035,6 @@ 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

@@ -31,7 +31,6 @@ from ..utils import (
     is_transformers_available,
     is_xformers_available,
 )
-from ..utils.testing_utils import get_python_version
 from . import BaseDiffusersCLICommand
 
 
@@ -106,11 +105,6 @@ 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"
@@ -158,7 +152,7 @@ class EnvironmentCommand(BaseDiffusersCLICommand):
 
         info = {
             "🤗 Diffusers version": version,
-            "Platform": platform_info,
+            "Platform": f"{platform.freedesktop_os_release().get('PRETTY_NAME', None)} - {platform.platform()}",
             "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", None)
+        resume_download = kwargs.pop("resume_download", False)
         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", None)
+        resume_download = kwargs.pop("resume_download", False)
         force_download = kwargs.pop("force_download", False)
         proxies = kwargs.pop("proxies", None)
         token = kwargs.pop("token", None)