stablediffusion icon indicating copy to clipboard operation
stablediffusion copied to clipboard

Published 20 hours ago • verified publisher icon Stability-AI

Bad image quality with v-prediction model on 512x512 resolution

Open meatybobby opened this issue 1 year ago • 0 comments

In the README, it shows v2.0-v getting better clip score than v2.0-base. t2i However, I got very bad image quality when I use v2.0-v on 512x512 resolution. t2i With same config and 768x768 resolution, it works well. Is this an expected result for v-prediction model? Does FID CLIP score in README actually testing with 768x768 for v2.0-v model?

meatybobby avatar Jul 05 '23 21:07 meatybobby