← All lessons
Week 2 · LLM Deep Dive
MAM5020F — Generative AI for Research

How AI Image Generation Works

Contents
← All lessons
Week 2 · LLM Deep Dive
Key terms
Diffusion model
A generative AI that learns to create images by reversing a process of gradually adding noise: starting from random static, it progressively refines an image guided by a text prompt. Stable Diffusion works this way.

This video provides a clear explanation of how AI image generation systems like DALL-E, Midjourney, and Stable Diffusion actually work. It demystifies the technology behind text-to-image generation, showing how these systems transform random noise into coherent images guided by text descriptions.

← PreviousFine-Tuning, RLHF and Alignment

Drafted with Claude (Anthropic) and reviewed by Jonathan Shock before publication. AI-generated errors are possible — if you spot one, please email jonathan.shock@uct.ac.za. Full detail: AI Content Disclaimer.

© 2026 Jonathan Shock · MAM5020F: Generative AI for Research · CC BY 4.0

Week 2
Lesson 4
1 min read
Key terms
Diffusion model
A generative AI that learns to create images by reversing a process of gradually adding noise: starting from random static, it progressively refines an image guided by a text prompt. Stable Diffusion works this way.