Phase 4: Vision Transformers · ~75 minutes · Python

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.

What you will learn

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

Introduction

Type: Learn + Build
Languages: Python
Prerequisites: the Transformers & LLMs from Scratch course
Time: ~75 minutes

Objective

Learning objectives

Trace the evolution from U-Net DDPM (Image Generation — Diffusion Models) 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

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card.

Key terms in this lesson

Transformer