Phase 1: Convolutional Neural Networks · ~75 minutes · Python

Image Generation — Diffusion Models

A diffusion model learns to denoise. Train it to remove a tiny bit of noise from a noisy image, repeat that backwards a thousand times, and you have an image generator.

What you will learn

Derive the forward noising process `x_0 -> x_1 -> ... -> x_T` and explain why the closed-form `q(x_t | x_0)` holds for any t
Implement a DDPM-style training objective that regresses the noise added at each step, and a sampler that walks back from pure noise to an image
Build a time-conditioned U-Net (small enough to train on CPU) that predicts the noise for any timestep
Explain the difference between DDPM and DDIM sampling, and when each is appropriate (Lesson 23 covers flow matching and rectified flow in depth)

Introduction

Type: Build
Languages: Python
Prerequisites: the Math for AI & ML course, the Deep Learning from Scratch course, Optimizers
Time: ~75 minutes

Objective

Learning objectives

Derive the forward noising process x_0 -> x_1 -> ... -> x_T and explain why the closed-form q(x_t | x_0) holds for any t
Implement a DDPM-style training objective that regresses the noise added at each step, and a sampler that walks back from pure noise to an image
Build a time-conditioned U-Net (small enough to train on CPU) that predicts the noise for any timestep
Explain the difference between DDPM and DDIM sampling, and when each is appropriate (Diffusion Transformers & Rectified Flow covers flow matching and rectified flow in depth)

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.