Jizhongpeng / onediff

OneDiff: An out-of-the-box acceleration library for diffusion models.

---

About OneDiff

OneDiff is an out-of-the-box acceleration library for diffusion models, it provides:

• PyTorch Module compilation tools and strong optimized GPU Kernels for diffusion models
• Out-of-the-box acceleration for popular UIs/libs
  • OneDiff for HF diffusers 🤗
  • OneDiff for ComfyUI
  • OneDiff for Stable Diffusion web UI

OneDiff News

OneDiff is the abbreviation of "one line of code to accelerate diffusion models". Here is the latest news:

• 🚀Accelerating Stable Video Diffusion 3x faster with OneDiff DeepCache + Int8
• 🚀Accelerating SDXL 3x faster with DeepCache and OneDiff
• 🚀InstantID can run 1.8x Faster with OneDiff

Community and Support

Here is the introduction of OneDiff Community.

• Create an issue
• Chat in Discord:
• Email for Enterprise Edition or other business inquiries: [e-mail]

---

The Full Introduction of OneDiff:

• More About OneDiff
  • State-of-the-art performance
  • Acceleration for production environment
  • Acceleration for State-of-the-art models
  • OneDiff Enterprise Edition
• Installation
• Release

More About OneDiff

State-of-the-art performance

SDXL E2E time

• Model stabilityai/stable-diffusion-xl-base-1.0;
• Image size 1024*1024, batch size 1, steps 30;
• NVIDIA A100 80G SXM4;

SVD E2E time

• Model stabilityai/stable-video-diffusion-img2vid-xt;
• Image size 576*1024, batch size 1, steps 25, decoder chunk size 5;
• NVIDIA A100 80G SXM4;

Acceleration for State-of-the-art models

OneDiff supports the acceleration for SOTA models.

• stable: release for public usage, and has long-term support;
• beta: release for professional usage, and has long-term support;
• alpha: early release for expert usage, and is under active development;

AIGC Type	Models	HF diffusers		ComfyUI		SD web UI
		Community	Enterprise	Community	Enterprise	Community	Enterprise
Image	SD 1.5	stable	stable	stable	stable	beta	beta
	SD 2.1	stable	stable	stable	stable	beta	beta
	SDXL	stable	stable	stable	stable	beta	beta
	LoRA	stable		stable		beta
	ControlNet	stable		stable
	SDXL Turbo	stable		stable
	LCM	stable		stable
	SDXL DeepCache	stable	beta	stable	beta
	InstantID	stable		stable
Video	SVD(stable Video Diffusion)	stable	beta	stable	beta
	SVD DeepCache	stable	beta	stable	beta

Note: Enterprise Edition contains all the functionality in Community Edition.

Acceleration for production environment

PyTorch Module compilation

• compilation with oneflow_compile

Avoid compilation time for new input shape

• Support Multi-resolution input

Avoid compilation time for online serving

Compile and save the compiled result offline, then load it online for serving

• Save and Load the compiled graph
• Change device of the compiled graph to do multi-process serving
  • Compile at one device(such as device 0), then use the compiled result to other device(such as device 1~7).
  • This is for special scene and is in the Enterprise Edition.

OneDiff Enterprise Edition

If you need Enterprise-level Support for your system or business, you can

• subscribe to Enterprise Edition online and get all support after the order: https://siliconflow.com/onediff.html
• or send an email to [e-mail] and tell us about your user case, deployment scale, and requirements.

OneDiff Enterprise Edition can be subscripted for one month and one GPU and the cost is low.

	OneDiff Enterprise Edition	OneDiff Community Edition
Multiple Resolutions	Yes(No time cost for most of the cases)	Yes(No time cost for most of the cases)
More Extreme and Dedicated optimization(usually another 20~100% performance gain) for the most used model	Yes
Tools for specific(very large scale) server side deployment	Yes
Technical Support for deployment	High priority support	Community
Get the experimental features	Yes

Installation

OS and GPU support

• Linux
  • If you want to use OneDiff on Windows, please use it under WSL.
• NVIDIA GPUs

OneDiff Installation

1. Install OneFlow

NOTE: We have updated OneFlow frequently for OneDiff, so please install OneFlow by the links below.

• CUDA 11.8

  # For NA/EU users
  python3 -m pip install -U --pre oneflow -f https://github.com/siliconflow/oneflow_releases/releases/expanded_assets/community_cu118

  # For CN users
  python3 -m pip install -U --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu118

Click to get OneFlow packages for other CUDA versions.

• CUDA 12.1

  # For NA/EU users
  python3 -m pip install -U --pre oneflow -f https://github.com/siliconflow/oneflow_releases/releases/expanded_assets/community_cu121

  # For CN users
  python3 -m pip install -U --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu121

• CUDA 12.2

  # For NA/EU users
  python3 -m pip install -U --pre oneflow -f https://github.com/siliconflow/oneflow_releases/releases/expanded_assets/community_cu122

  # For CN users
  python3 -m pip install -U --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu122

2. Install torch and diffusers

Note: You can choose the latest versions you want for diffusers or transformers.

python3 -m pip install "torch" "transformers==4.27.1" "diffusers[torch]==0.19.3"

3. Install OneDiff

• From PyPI

python3 -m pip install --pre onediff

• From source

git clone https://github.com/siliconflow/onediff.git
cd onediff && python3 -m pip install -e .

NOTE: If you intend to utilize plugins for ComfyUI/StableDiffusion-WebUI, we highly recommend installing OneDiff from the source rather than PyPI. This is necessary as you'll need to manually copy (or create a soft link) for the relevant code into the extension folder of these UIs/Libs.

4. (Optional)Login huggingface-cli

python3 -m pip install huggingface_hub
 ~/.local/bin/huggingface-cli login

Release

• run examples to check it works

  cd onediff_diffusers_extensions
  python3 examples/text_to_image.py

• bump version in these files:

  .github/workflows/pub.yml
  src/onediff/__init__.py
  

• install build package

  python3 -m pip install build

• build wheel

  rm -rf dist
  python3 -m build

• upload to pypi

  twine upload dist/*