Comment on VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control

p03locke@lemmy.dbzer0.com ⁨4⁩ ⁨weeks⁩ ago

It almost seems like it’s forcing a certain kind of lighting without prompting. I wonder how well it performs when specifically given something that isn’t “natural light”.

source
Sort:hotnewtop