10-799 Special Topics: Diffusion Models & Flow Matching

6 units, Carnegie Mellon University

Want to understand how Stable Diffusion, DALL-E, and Sora actually work - and how to build something even better? This course takes you from mathematical foundations to hands-on research frontiers in diffusion models and flow matching, the generative AI frameworks reshaping computer vision and beyond. In this class, you will explore topics from foundational probabilistic modeling through modern advances: denoising diffusion models, score-based SDEs, flow matching, fast sampling algorithms, controllable generation, distillation methods, and discrete variants. Choose your path to level up - fidelity (photorealistic quality), controllability (precise user control), or speed (real-time generation) - and build from scratch towards a complete working system through cumulative homework and both your theoretical understanding and practical implementation skills by the end of this course.

Prerequisites: 21-259 (min C) and 21-341 (min C) and 21-260 (min C) and 15-112 (min C) and (15-359 (min C) or 21-325 (min C) or 36-219 (min C) or 36-217 (min C) or 15-259 (min C) or 36-218 (min C) or 36-225 (min C))

Offered: Spring 2026

Courseweave needs JavaScript to show sections, workloads and planning tools.