News for hackers. Stuff that matters.
Re:Stable Diffusion 3 by Workaccount2 on Thursday February 22, 2024 @09:48AM (#39467867)
Not bad, I'm curious of the output if you ask for a mirrored sphere instead.
Re:Stable Diffusion 3 by svenmakes on Thursday February 22, 2024 @01:13PM (#39470892)
This is actually the approach of one paper to estimate lighting conditions. Their strategy is to paint a mirrored sphere onto an existing image: https://diffusionlight.github.io/