In the README, it shows v2.0-v getting better clip score than v2.0-base.
However, I got very bad image quality when I use v2.0-v on 512x512 resolution.
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?
In the README, it shows v2.0-v getting better clip score than v2.0-base.
However, I got very bad image quality when I use v2.0-v on 512x512 resolution.
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?