Term · Advanced

Diffusion Model

The AI architecture behind most image and video generators, it denoises randomness into a picture.

A diffusion model generates images by starting from pure noise and gradually removing it, step by step, until a coherent picture matching your prompt emerges. It's the engine under Stable Diffusion, Midjourney, and most modern image and video tools, which is why understanding it helps you predict how settings like steps and guidance behave. Knowing the mechanism makes prompt and parameter tuning far less like guesswork.

Also called Diffusion, Latent Diffusion

Related

More in Editing & Post