Skip to main content
All terms
Architectures

Diffusion Model

A generator that starts from random noise and denoises step by step into an image or video.

Definition

A diffusion model generates content by learning to reverse a process that gradually adds noise to data. At training time it learns to predict and remove noise at each step; at generation time it starts from random noise and denoises step by step into a coherent image, audio clip, or video — usually guided by a text prompt. Diffusion is the dominant approach behind modern text-to-image and text-to-video systems.