Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Is there any plan to support TeaCache for training-free acceleration? #6235

Open
LiewFeng opened this issue Dec 27, 2024 · 1 comment
Open

Is there any plan to support TeaCache for training-free acceleration? #6235

LiewFeng opened this issue Dec 27, 2024 · 1 comment
Labels
Feature A new feature to add to ComfyUI.

Comments

@LiewFeng
Copy link

Feature Idea

TeaCache is a training-free inference acceleration method for visual generation. 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. Teacache4FLUX will also be released in a few days. Thanks for your efforts!
https://github.com/LiewFeng/TeaCache.

Existing Solutions

No response

Other

No response
@LiewFeng LiewFeng added the Feature A new feature to add to ComfyUI. label Dec 27, 2024
@LiewFeng
Copy link
Author

TeaCache supports FLUX now. TeaCache can speedup FLUX 2x without much visual quality degradation.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Feature A new feature to add to ComfyUI.
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@LiewFeng