huggingface / huggingface/diffusers
Is there any plan to support TeaCache for training-free acceleration?
Open
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
Assessment
This issue has not been assessed yet.