News for hackers. Stuff that matters.

A comment on Diffusion Models Beat GANs on Image Synthesis. Parent comment

Re:Diffusion Models Beat GANs on Image Synthesis by ericjang on Wednesday May 12, 2021 @09:27PM (#27137418)
Ah, thanks. I had mistakenly assumed the diffusion process here was comparable / drop-in replacement to Langevin dynamics used with energy models.
[ Parent | on HN ]
Re:Diffusion Models Beat GANs on Image Synthesis by ericjang on Monday May 17, 2021 @12:57AM (#27180185)
I went and read the paper in more detail. Yeah, my original comment was way off-base, except if you draw a parallel with normalizing flows as iterated refinement (similar to iterated de-noising), and see that the DDPM is a more unconstrained form.

But at a surface level, there isn't a clear connection between DDPM and energy-based models.

[ Parent | on HN ]