-
Notifications
You must be signed in to change notification settings - Fork 6.4k
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
Comments
Experiencing the same, on an RTX 3050...Any fix? |
Uncheck face enhancer. Ig this App ist for graphic cards that begin with 40 |
Install either of the Supported versions of CUDA tookit |
Same issue with 4090 and 4060, getting low fps (2 to 3 fps) |
install onnxruntime-gpu latest version |
latest version of oonnxruntime-gpu creates black square and fps dropping to 1 |
Hi, I'm trying to run the Deep-Live-Cam project, but I'm encountering a problem. The ui.py file is missing from the modules directory. I've tried the following:
In all cases, the ui.py file is not present. I've also checked the repository on GitHub.com directly in my browser, and the file is missing there as well. The modules directory contains the following files: [List the files you see]. Could you please let me know how to obtain the ui.py file? Is it intentionally missing, or is there a separate download/generation step required? Thanks for your help! |
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
Console Log
GPU Usage - While Face Enhancer was running
GPU Usage - After all the video processing is complete, but app is still running.
The text was updated successfully, but these errors were encountered: