Phase 1: Generative Adversarial Networks · ~75 minutes · Python

Diffusion Models — DDPM from Scratch

Ho, Jain, Abbeel (2020) gave the field a recipe it could not quit. Destroy the data with noise over a thousand small steps. Train one neural net to predict the noise. Reverse the process at inference. Today every mainstream image, video, 3D, and music model runs on this loop, possibly with flow matching or consistency tricks on top.

What you will learn

Implement diffusion models — ddpm from scratch from scratch
Understand the math and intuition behind the algorithm
Use production libraries for the same task
Ship a reusable artifact

Introduction

Type: Build
Languages: Python
Prerequisites: Multi-Layer Networks and Forward Pass (Deep Learning from Scratch), Autoencoders & Variational Autoencoders (VAE)
Time: ~75 minutes

The Problem

You want a sampler for p_data(x). GANs play a minimax game that often diverges. VAEs produce blurry samples from a Gaussian decoder. What you really want is a training objective that is (a) a single stable loss (no saddle point, no minimax), (b) a lower bound on log p(x) (so you have likelihoods), and (c) samples that match SOTA quality.

Sohl-Dickstein et al. (2015) had a theoretical answer: define a Markov chain q(x_t | x_{t-1}) that gradually adds Gaussian noise, and train a reverse chain p_θ(x_{t-1} | x_t) to denoise. Ho, Jain, Abbeel (2020) showed the loss could be simplified to one line — predict the noise — and cleaned up the math. In 2020 this was a curiosity. In 2021 it produced state-of-the-art samples. In 2022 it became Stable Diffusion. In 2026 it is the substrate.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Concept, Build, Check Yourself, 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.