Plain-AyI
← All projects
Images & video

stable-diffusion.cpp

A lightweight program for making AI images and videos on your own computer, using many popular models.

New this week

What it does

stable-diffusion.cpp runs image-generation models, the kind of AI that makes pictures from a text description, directly on your own computer. It is written in plain C and C++ with no extra software needed, in the same style as the popular llama.cpp project.

It supports a long list of image models, including Stable Diffusion, FLUX, Qwen Image and Z-Image, plus several video models. It can also edit existing images and has a built-in web interface.

It works on Windows, Mac and Linux with many kinds of graphics cards, and has settings to reduce memory use.

Who it's for

Hobbyists and developers who want to generate AI images locally without heavy software.

Can I use it without coding?

With some setup. Ready-made programs are offered, but you download model files separately and run it from a command window. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Windows, Mac, Linux
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Download the ready-made program for your computer from the project's releases page.
  2. Download an image model file, such as Stable Diffusion.
  3. Run the program with a text prompt to create your first image.
Official download page

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it