sayakpaul/diffusers-torchao
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
This project helps machine learning engineers and researchers accelerate the process of generating images and videos using diffusion models. By applying advanced optimization techniques, it significantly speeds up model inference and allows for more efficient training. You input a pre-trained diffusion model and receive an optimized version that produces the same high-quality visual outputs faster.
397 stars.
Use this if you are working with large diffusion models for image or video generation and need to improve their performance, especially inference speed and memory footprint, on modern NVIDIA GPUs.
Not ideal if you are using older GPU hardware or are not working with diffusion models, as its specific optimizations are tailored for these modern architectures and model types.
Stars
397
Forks
16
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sayakpaul/diffusers-torchao"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PrunaAI/pruna
Pruna is a model optimization framework built for developers, enabling you to deliver faster,...
bytedance/LatentSync
Taming Stable Diffusion for Lip Sync!
haoheliu/AudioLDM-training-finetuning
AudioLDM training, finetuning, evaluation and inference.
Text-to-Audio/Make-An-Audio
PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model
teticio/audio-diffusion
Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead...