Skip to content
BENIBIX Learn

Stable Diffusion

Also known as Stable Diffusion 3.5, SDXL

An open model that draws pictures from words. You can run it at home.

Think of it like

It is like a painter. She starts with a blur and makes it sharp, bit by bit.

Example

Emma types 'a red fox in the snow, in watercolour'. Stable Diffusion runs on her own graphics card and gives her four pictures to pick from.

Why it matters

It was the open art model that let anyone make AI art at home. A huge set of add-ons grew around it.

Definition

Stable Diffusion is a model that draws pictures from words, made by Stability AI. You type what you want, and it turns random noise into a picture, step by step. That way of working is called diffusion. Its weights are open, so people run it on their own computers and train it on their own style. The newest family is Stable Diffusion 3.5.
Stable Diffusion takes words in and gives a picture out.

Common mistake

Thinking any app that uses diffusion is Stable Diffusion. Lots of models work that way. This is one named family.

Key takeaways

  1. 1
    Words to picture. Type it, and get it.
  2. 2
    Open weights. It runs on your own machine.
  3. 3
    Noise to image. It cleans noise step by step.

Compare

Learn it properly