Diffusion model
A diffusion model is the kind of AI behind most image and video generators. It learns to turn random visual noise, step by step, into a picture that matches a text description.
In one line, for a 12-year-old
A diffusion model starts with TV static and cleans it up, bit by bit, until a picture appears.
An example
Typing "a moose wearing a toque, children's book style" into an image tool and getting four versions in seconds.
Why it matters to people
Image generators were trained on millions of artists' works, often without consent, and can produce realistic fakes. Label generated images and never pass them off as real photos.