# siliconflow/onediff

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

Repository: https://github.com/siliconflow/onediff
Canonical: https://ross.abutalabs.com/products/onediff
Homepage: https://github.com/siliconflow/onediff/wiki
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: comfyui, diffusers, pytorch, sdxl, stable-diffusion, aigc-serving, comfyui-workflow, cuda, inference-engine, lcm, lcm-lora, performance-optimization, sd-webui, stable-video-diffusion, diffusion-models, lora, sdxl-turbo
Last push: 2025-12-04T01:30:48+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 55, release rhythm 8, longevity 100
- inputs: {"age_days": 1442, "days_push": 273, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1964, forks 128 (observed 2026-08-28T04:05:59.797715+00:00)

## What it is
OneDiff is an out-of-the-box acceleration library for diffusion models, providing PyTorch compilation tools and optimized GPU kernels. It integrates with popular frameworks and UIs such as Hugging Face diffusers and ComfyUI to speed up image and video generation.

## Use cases
- speed up stable diffusion image generation
- accelerate sdxl inference in comfyui
- compile pytorch diffusion models for faster gpu inference
- run flux or sd3 models faster
- quantize diffusion models to reduce memory usage
- accelerate stable video diffusion
- serve stable diffusion models with lower latency

## When to choose
- you use ComfyUI or HF diffusers and want faster diffusion inference
- you need GPU kernel optimization and compilation for SDXL, FLUX, or DiT models
- you want quantization to cut memory and boost throughput

## When to avoid
- you need the latest diffusers versions beyond the supported maximums
- you work on CPU-only or non-CUDA hardware
- you need a general-purpose inference engine beyond diffusion models

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-inference, gpu-computing, compiler
- domain: deep-learning, image-processing, gpu-computing, machine-learning
- platform: python, windows
- tags: diffusion-models, stable-diffusion, sdxl, comfyui, diffusers, inference-acceleration, pytorch, lora, quantization, aigc, gpu, linux

## Member repositories
- siliconflow/onediff (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:59.797715+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:05:30.820751+00:00, confidence not recorded.
  - readme: https://github.com/siliconflow/onediff (fetched 2026-08-28T04:05:59.797715+00:00, sha 63bceb31b646)
  - homepage: https://github.com/siliconflow/onediff/wiki (fetched 2026-08-29T10:45:11.455849+00:00, sha aa0b369918a6)
  - registry_pypi: https://pypi.org/pypi/onediff/json (fetched 2026-08-29T10:45:11.465290+00:00, sha fc10bd92377e)
- Data as of 2026-08-30T08:39:29.467469+00:00.