News for hackers. Stuff that matters.
Re:Reflected Diffusion Models by ttul on Monday May 08, 2023 @12:59PM (#35864014)
As is so often the case in neural network design, preventing numbers from blowing up is the cause of so many necessary, but poorly understood math hacks. It seems these researchers have found a potentially better way to control the sampling process so that diffusion models can generate outputs that are more correct.

I often wonder if Midjourney, behind the scenes, has already discovered something like this in their v5 release, which is substantially better at modelling things like hands.

There are no comments on this comment yet.