An Introduction to Flow Matching and Diffusion Models
It provides a foundational resource for machine learning researchers to understand and apply generative AI methods, but it is incremental as it synthesizes existing knowledge into a tutorial format.
This tutorial introduces diffusion and flow-based generative models, which are state-of-the-art for generative AI across various data modalities, by systematically developing mathematical background and deriving core algorithms for building image and video generators.
Diffusion and flow-based models have become the state of the art for generative AI across a wide range of data modalities, including images, videos, shapes, molecules, music, and more. This tutorial provides a self-contained introduction to diffusion and flow-based generative models from first principles. We systematically develop the necessary mathematical background in ordinary and stochastic differential equations and derive the core algorithms of flow matching and denoising diffusion models. We then provide a step-by-step guide to building image and video generators, including training methods, guidance, and architectural design. This tutorial is ideal for machine learning researchers who want to develop a principled understanding of the theory and practice of generative AI.