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.

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

Face Enhancer is too slow on CUDA #857

Open
monish567 opened this issue Dec 29, 2024 · 0 comments
Open

Face Enhancer is too slow on CUDA #857

monish567 opened this issue Dec 29, 2024 · 0 comments

Comments

@monish567
Copy link

Started the app using "python run.py --execution-provider cuda" command
Options I enabled in UI: Face Enhancer, Map Faces, Keep FPS, Keep Audio.
Target video used was 720p, 30fps and 10 seconds length.

I don't get how come Face Swapper ran fast but face enhancer is too slow. Face enhancer was faster even when I was using only CPU, on avg it took only around 3 to 4 seconds/frame with CPU. But here with GPU its taking 16 seconds/frame!!!

How to solve this problem? Am I missing something? Any workarounds?

Attached screenshots.

Nvidia Driver Details

image

Console Log

image

GPU Usage - While Face Enhancer was running

image

GPU Usage - After all the video processing is complete, but app is still running.

image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant