Diffusion models are a key innovation with far-reaching impacts on multiple fields, from image generation to robotics. Despite its pivotal role in modern AI, I have never found an explanation for how they work that helps me really understand them.

In this video I present a different view of diffusion models as a gradient descent-like algorithm that stochastically optimizes for some notion of image quality, which is based on the "score matching" view of diffusion models (https://arxiv.org/pdf/1907.05600)

This video is designed to ease AI practitioners who are familiar with more common machine learning paradigms into the world of probabilistic models, while allowing non-technical people to get a glimpse into the key computational techniques that has driven the recent advances in image generation quality. As such, I have kept it light on the math, while still imparting the key intuitions and assumptions behind what makes diffusion models work so well.