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.

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

Odd behaviour (with IPAdapter?) #2

Open
Xyem opened this issue Nov 22, 2023 · 0 comments
Open

Odd behaviour (with IPAdapter?) #2

Xyem opened this issue Nov 22, 2023 · 0 comments

Comments

@Xyem
Copy link

Xyem commented Nov 22, 2023

I was doing some generations with a similar workflow in #1 (just with an IPAdapter added after the OpenPose) and I found an extremely odd behaviour. It appears that IPAdapter is getting applied to the model it outputs, repeatedly, so the generations get progressively worse.

2023-11-22-010242_1684x187_scrot

This doesn't happen if I replace all of the custom EZ pipes nodes with my original implementation, nor if I replace the one at the start of the IPAdapter group with mine.

EDIT: To be clear, I was forcing the generations (they all have the same seed) by alternating the OpenPose strength between 0.80 and 0.79.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant