chengzeyi/stable-fast
https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
This project helps AI practitioners generate images and videos much faster using HuggingFace Diffusers models on NVIDIA GPUs. You input an existing Stable Diffusion or Stable Video Diffusion model, and it outputs an optimized version that significantly speeds up the creative process. It's ideal for anyone involved in AI art, video generation, or research who needs to quickly iterate on visual content.
1,305 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer, AI artist, or researcher working with Stable Diffusion or Stable Video Diffusion models and need to drastically reduce image and video generation times on NVIDIA GPUs.
Not ideal if you are not working with HuggingFace Diffusers models, do not have an NVIDIA GPU, or need to optimize models other than image/video generation (though future versions may support LLMs).
Stars
1,305
Forks
91
Language
Python
License
MIT
Category
Last pushed
Mar 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/chengzeyi/stable-fast"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
siliconflow/onediff
OneDiff: An out-of-the-box acceleration library for diffusion models.
wooyeolbaek/attention-map-diffusers
🚀 Cross attention map tools for huggingface/diffusers
jina-ai/discoart
🪩 Create Disco Diffusion artworks in one line
hkproj/pytorch-stable-diffusion
Stable Diffusion implemented from scratch in PyTorch
explainingai-code/StableDiffusion-PyTorch
This repo implements a Stable Diffusion model in PyTorch with all the essential components.