huggingface / huggingface/diffusers

Is there any plan to support TeaCache for training-free acceleration?

Open
#10,374 4 comments 0 reactions 1 assignee Claimed by @a-r-r-o-w View on GitHub
wip
Dominant language
Python
Stars
34.5k
Forks
7.3k
Avg merge
3d 3h
Merged PRs (30d)
91

Description

TeaCache is a training-free inference acceleration method for visual generation. TeaCache currently supports HunyuanVideo, CogVideoX, Open-Sora, Open-Sora-Plan and Latte. TeaCache can speedup HunyuanVideo 2x without much visual quality degradation. For example, the inference for a 720p, 129-frame video takes around 50 minutes on a single A800 GPU while TeaCache can sppeedup to 23 minutes. Thanks for your efforts!
https://github.com/LiewFeng/TeaCache.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.