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

Optimize performance #30

Closed
2 tasks done
seruva19 opened this issue May 4, 2023 · 0 comments
Closed
2 tasks done

Optimize performance #30

seruva19 opened this issue May 4, 2023 · 0 comments
Labels
needs research Requires further research

Comments

@seruva19
Copy link
Owner

seruva19 commented May 4, 2023 •
edited
Loading

Inference might not work with 8 Gb: #2 (but: #14)
Textual inversion training requires > 21-22 Gb source source 2
Dreambooth training requires >= 32 Gb source

edit. but training prior/unclip separately fits into 16 Gb VRAM #74

Integrating K2 into diffusers might open up opportunities for optimization huggingface/diffusers#2985
@seruva19 seruva19 added the needs research Requires further research label May 4, 2023
@seruva19 seruva19 mentioned this issue May 11, 2023
Closed
@seruva19 seruva19 changed the title VRAM limitations Optimize performance May 15, 2023
This was referenced May 15, 2023
Closed
Closed
@seruva19 seruva19 pinned this issue May 15, 2023
@seruva19 seruva19 mentioned this issue May 15, 2023
Closed
@seruva19 seruva19 unpinned this issue May 23, 2023
@seruva19 seruva19 mentioned this issue Jun 1, 2023
Open
@seruva19 seruva19 closed this as completed Jul 1, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
needs research Requires further research
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@seruva19