Replies: 1 comment
-
|
post on the issues tab as a feature request |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
If I see it right in the workflow, currently, if you use for example IP Adpater FaceID and Refiner/Upscale in one step (hiresfix), the hires-step is done without the IP Adapter Input. So the Output image will begin to differ more from the input image(s) while upscaling.
Most people if not all who use an IP Adapter want it to be active in the whole process. So this could be either default or at least an option in the refiner/upscale area.
Beta Was this translation helpful? Give feedback.
All reactions