---
title: "Diffusion Models: Learning to Undo Noise"
description: "Training adds noise to a sample in small steps and asks the network to predict the noise that was added. Generation runs that chain backwards from pure noise, so one hard sampling problem becomes a lo"
canonical: https://lightmysky.com/learn/computing/diffusion-models-learning-to-undo-noise-mt_kZdQJ96iZ3
source: https://lightmysky.com/learn/computing/diffusion-models-learning-to-undo-noise-mt_kZdQJ96iZ3.md
retrieved: 2026-09-12
---

> **Agent view.** This is the Markdown twin of the page, for tools and assistants.
> When to use this site, and the call that answers each job: https://lightmysky.com/agent-instructions.md
> API description (OpenAPI 3.1): https://lightmysky.com/openapi.json · Authentication: https://lightmysky.com/auth.md
> Pricing: https://lightmysky.com/pricing.md · Catalog: https://lightmysky.com/llms.txt · Full catalog: https://lightmysky.com/llms-full.txt
> Every machine-readable file on this domain: https://lightmysky.com/.well-known/ai-catalog.json
> Ask for Markdown with `Accept: text/markdown`, a `.md` address, or `?mode=agent`.

# Diffusion Models: Learning to Undo Noise

Training adds noise to a sample in small steps and asks the network to predict the noise that was added. Generation runs that chain backwards from pure noise, so one hard sampling problem becomes a long series of easy denoising ones.

Subject: Computing · Area: Machine Learning · Ages 22 to 24
Page: https://lightmysky.com/learn/computing/diffusion-models-learning-to-undo-noise-mt_kZdQJ96iZ3

## Ready when they can

- Describe the forward corruption process and say why it needs no training
- State what the network predicts at each step and how repeating it yields a sample
- Say what more sampling steps buy and what they cost

## Lesson: Pictures from unmaking noise

Training starts by wrecking a sample on purpose. Noise is added in small steps until nothing but static remains. This forward corruption is a fixed recipe, so it needs no training at all.

**Example.** At each noise level the network predicts the noise that was just added. Generation runs the chain backwards: start from pure noise, subtract the predicted noise, and repeat until a clean sample stands. One hard sampling problem becomes a long series of easy denoising ones.

More sampling steps buy a cleaner sample and cost more waiting. Fewer steps run fast but leave rough edges and odd textures.

**Tip.** When results look noisy, add steps before touching anything else. When results look fine but slow, trim steps first.

**Recap.** Learn each denoising step, then walk backwards from noise to sample.

## Practice

8 questions on this page, each with its working shown.

## Needs first

- [Generative Models: Learning a Distribution You Can Sample](https://lightmysky.com/learn/computing/generative-models-learning-a-distribution-you-can-sample-mt_3CHsmpWVX5)
- [Brownian Motion and Its Defining Properties](https://lightmysky.com/learn/mathematics/brownian-motion-and-its-defining-properties-mt_T5KtWIk07Z)