AI Engineering/Phase 04/Lesson 23

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 + Build 1.3 hr Python

Prerequisites: Phase 4 Lesson 10 (Diffusion DDPM), Phase 4 Lesson 14 (ViT), Phase 7 Lesson 02 (Self-Attention)

#Learning Objectives

Trace the evolution from U-Net DDPM (Lesson 10) to Diffusion Transformer (DiT), MMDiT (SD3), and single+double-stream DiT (FLUX)
Explain rectified flow: why a straight-line trajectory between noise and data lets models sample in 20 steps instead of 1000
Implement a tiny DiT block and a rectified-flow training loop, both under 100 lines
Distinguish model variants (SD3, FLUX.1-dev, FLUX.1-schnell, Z-Image, Qwen-Image) by architecture, parameter count, and licensing

Full Access lesson

Keep going. The rest of this lesson is one step away.

Unlock all 503 lessons, video, code, quizzes and every future update. Pay in your own currency with Paystack.

See plans Sign in

The text and code of this lesson are based on AI Engineering from Scratch by Rohit Ghumare, MIT licensed.