flâneur

Learning the integral of a diffusion model – Sander Dieleman

sander.ai · 17,454 words · saved by 4 readers

A deep dive on flow maps.

Sampling from a diffusion model is an iterative process: at each step, the denoiser estimates the tangent direction to a path through input space. We move along this path by repeatedly taking small steps in this direction, effectively calculating an integral across noise levels . This gradually transforms samples from a simple noise distribution into samples from a target distribution, and traces out the path that connects them. Can we train neural networks to directly predict this integral instead, in order to speed up sampling? Yes we can – welcome to the world of flow maps ! Ever since the

saved by

related reading