# Stable Diffusion

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

**Field:** Artificial Intelligence  
**Category:** Models & Providers  
**Also known as:** Stable Diffusion 3.5, SDXL

## Think of it like

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

## 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.

## 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.

## Common mistake

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

## Three principles

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

## Related terms

- [Stability AI](https://learn.benibix.com/term/ai/stability-ai)
- [Diffusion Model](https://learn.benibix.com/term/ai/diffusion-model)
- [Text-to-Image](https://learn.benibix.com/term/ai/text-to-image)
- [Open-Weight Model](https://learn.benibix.com/term/ai/open-weight-model)
- [FLUX](https://learn.benibix.com/term/ai/flux)
- [Negative Prompt](https://learn.benibix.com/term/ai/negative-prompt)
- [ComfyUI](https://learn.benibix.com/term/ai/comfyui)

## Told apart from

- [ComfyUI vs Stable Diffusion](https://learn.benibix.com/compare/comfyui-vs-stable-diffusion): People think ComfyUI is an AI model, and it is not. ComfyUI is the app, and Stable Diffusion is one of the models it runs. The model makes the picture. ComfyUI lets you wire up the steps around it, like the prompt and the size. You download the two parts on their own.

## Taught in

- [AI Image Generation Models](https://learn.benibix.com/learn/ai-models-providers/ai-image-generation-models): AI Models and Providers, 9/13
- [Midjourney and AI Image Tools](https://learn.benibix.com/learn/ai-ai-tools/midjourney-and-ai-image-tools): AI Apps and Tools, 9/10

![Four rows, each reading input, model, output. Words go into Stable Diffusion or FLUX and a picture comes out. Words go into Veo and a video with sound comes out. Speech goes into Whisper and written text comes out. A picture and some captions go into CLIP and the best match comes out.](https://learn.benibix.com/diagrams/ai2-media-models.svg)

---

Source: https://learn.benibix.com/term/ai/stable-diffusion
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-19
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
