Skip to content

Stable Diffusion

← All terms · Image, video, audio AI

Also called SDXL, Stable Diffusion 3.5

A foundational, open-weight text-to-image model by Stability AI that made it possible for anyone to generate and fine-tune AI imagery locally.

What it is

Stable Diffusion is the backbone of the open-source AI image ecosystem. By open-sourcing the model weights, it spawned a massive community of developers building custom fine-tunes, UI tools (like ComfyUI), and extensions (like ControlNet) that allow for granular, director-level control over image generation on consumer hardware.

When you would use it

You use Stable Diffusion when you need total ownership, extreme customization, and the ability to run image generation workflows locally without API restrictions.

Common operations

  • Running private image generation locally on consumer GPUs.
  • Fine-tuning a custom model specifically on a company's brand assets.

Related terms

Where this is taught

Going deeper