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.

Hiring signal: Understanding of image generation — diffusion models internals

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: Phase 4 Lesson 07 (U-Net), Phase 1 Lesson 06 (Probability), Phase 3 Lesson 06 (Optimizers) Time: ~75 minutes

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 (Lesson 23 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 It, Use It, Ship It, Exercises, Key Terms, Further Reading — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.