-
Notifications
You must be signed in to change notification settings - Fork 17
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
feat: Adds hires fix on layer diffusion #278
Conversation
This reverts commit 61aaa9b.
This should help identify issues when analyzing logs that have to do with poor system RAM/VRAM conditions.
@tazlin I added a change which sets the upscale steps to 30% of the normal steps. From what I see, this doesn't change the results by any significant amount so that could be a good workaround and later we can expose the hires_steps as well. Can you validate as well? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Everything looks reasonable as of now. Assuming tests pass, I'm OK with a rebase onto main
and publishing for a (at least brief) beta testing window with workers.
I just wanted to emphasize that the images are visually identical to my eye and did not require updating/changing for the cosine image similarity/histogram checks. |
All tox passes on my end