← Back to the AI Glossary 📖 Models & Architecture

Diffusion Model

A type of generative AI model that creates images (or video/audio) by starting from random noise and gradually refining it into a coherent result.

Most modern AI image generators — Midjourney, Stable Diffusion, DALL·E — are built on this technique, which is where 'Diffusion' in Stable Diffusion's name comes from.
One of 60 free AI glossary terms
Plain-language definitions for the AI jargon you'll actually run into — no email needed, ever, for this section.
Browse the Full Glossary →
More in Models & Architecture
Multimodal Model
An AI model that can understand and/or generate more than one type of content — for exampl...
Reasoning Model
An AI model specifically trained to spend extra computation "thinking" through a problem s...
Encoder-Decoder Architecture
A model design split into two parts — one that reads and understands an input, and a secon...
Model Card
A short published document describing an AI model's capabilities, limitations, training da...