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

SDXL model caching not working with Perturbed Attention Guidance #90

Closed
ikarsokolov opened this issue Jan 19, 2025 · 5 comments
Closed

SDXL model caching not working with Perturbed Attention Guidance #90

ikarsokolov opened this issue Jan 19, 2025 · 5 comments

Comments

@ikarsokolov
Copy link

ikarsokolov commented Jan 19, 2025 •
edited
Loading

It seems that SDXL model caching not working with Perturbed Attention Guidance (PAG). As soon as I connect PAG node in ComfyUI first block caching stops working. At least I don't see any speed difference with or without cache.

Maybe related to #62.
@blepping
Copy link
Contributor

#83 should fix that. Any testing would be very welcome.

@ikarsokolov
Copy link
Author

#83 should fix that. Any testing would be very welcome.

It works! Can't say much about quality yet but I can definitely see the effect of caching now.

@blepping
Copy link
Contributor

It works! Can't say much about quality yet but I can definitely see the effect of caching now.

Good to hear, thank you for taking the time to try it out!

@blepping
Copy link
Contributor

The fix was merged. If your problem was resolved, can probably close this issue now.

@ikarsokolov
Copy link
Author

The issue is resolved.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@ikarsokolov @blepping