Phase 04: Computer Vision
AI From Scratch/Lesson 23/~75 minutes

Diffusion Transformers & Rectified Flow

The U-Net is not the secret of diffusion. Replace it with a transformer, swap the noise schedule for a straight-line flow, and suddenly you have SD3, FLUX, and every 2026 text-to-image model.

Learn + BuildPythonNo prerequisites
Loading lesson page...