Diffusion Models and Gaussian Flow Matching: Two Sides of the Same Coin

Ruiqi Gao, Emiel Hoogeboom, Jonathan Heek, Valentin De Bortoli, Kevin Patrick Murphy, Tim Salimans

Published: 23 Jan 2025, Last Modified: 26 Feb 2025ICLR 2025 Blogpost TrackEveryoneRevisionsBibTeXCC BY 4.0
Blogpost Url: https://d2jud02ci9yv69.cloudfront.net/2025-04-28-diffusion-flow-173/blog/diffusion-flow/
Abstract: Flow matching and diffusion models are two popular frameworks in generative modeling. Despite seeming similar, there is some confusion in the community about their exact connection. In this post we aim to clear up this confusion and show that diffusion models and Gaussian flow matching are the same -- Different model specifications lead to different noise schedules and loss weightings but correspond to the same generative model. That's great news, it means that you can use the two frameworks interchangeably.
Conflict Of Interest: I have no conflicts of interest with any of the papers listed in the referenced section.
Submission Number: 93