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

better performance with model offloading #86

Closed

noskill opened this issue Nov 8, 2024 · 1 comment

Assignees

Collaborator

noskill commented Nov 8, 2024

The issue is that with cpu offloading turned on performance is kind of slow, especially for flux.1-dev

1048 x 1344 image takes 55 seconds on 3090

we can try
https://huggingface.co/docs/diffusers/en/optimization/memory#model-offloading

or try to split different components to different gpus..

noskill self-assigned this

Collaborator Author

noskill commented Jan 9, 2025

resolved by #89 and #87

noskill closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment