Rethinking How to Train Diffusion Models

Originally published at: https://developer.nvidia.com/blog/rethinking-how-to-train-diffusion-models/

After exploring the fundamentals of diffusion model sampling, parameterization, and training as explained in Generative AI Research Spotlight: Demystifying Diffusion-Based Models, our team began investigating the internals of these network architectures. This turned out to be a frustrating exercise. Any direct attempt to improve these models tended to worsen the results. They seemed to be…