Glossary · Term

diffusion model

← all terms

Definition

Plain language

An AI that creates an image by starting from noise and cleaning it up step by step.

As stated in the literature

A generative model that learns to reverse a gradual noising process, producing images or other data through iterative denoising; distinct from autoregressive token generation and central to image-generation stacks like Show-o2.

Also called: diffusion models, diffusion

Why it matters: It's the approach behind much of today's AI image generation, producing detailed pictures from nothing but noise and a prompt.

For example, to make a picture of a cat, the system starts with random static and removes the noise bit by bit until a cat appears.

Heard on the show

“The dreamer, the five-billion-parameter diffusion model that predicts the next summary from the recent past plus everyone's buttons.”
Episode 206 — How Four-Second Clips Become Hours of Playable AI Soccer

Mentioned in 5 episodes

  1. 206
    How Four-Second Clips Become Hours of Playable AI Soccer
  2. 127
    What Diffusion Language Models Were Missing: A Map, Not an Algorithm
  3. 106
    Giving Agents a Notebook Instead of New Weights: How ExpGraph Lets Frozen Models Learn
  4. 042
    An Agentic Scientific Computing System That Actually Remembers What It Learns
  5. 027
    When AI Agents Build the Serving Stack: A Bet on Bespoke Infrastructure

Related concepts

Related terms