leejet/stable-diffusion.cpp

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

69
/ 100
Established

This project helps artists, designers, and content creators generate images and videos from text descriptions using popular diffusion models like Stable Diffusion, FLUX, and Wan. You provide a text prompt describing your desired image or video, and it outputs the corresponding visual content. This tool is for anyone who wants to create digital art or media efficiently on their own computer, without relying on cloud services.

5,579 stars. Actively maintained with 41 commits in the last 30 days.

Use this if you want to generate high-quality images or short videos from text prompts using various advanced models directly on your personal computer, even without a powerful GPU.

Not ideal if you prefer a simple, ready-to-use web interface for image generation without any setup or command-line interaction.

generative-art digital-design content-creation video-production visual-media
No Package No Dependents
Maintenance 23 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

5,579

Forks

551

Language

C++

License

MIT

Last pushed

Mar 16, 2026

Commits (30d)

41

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/leejet/stable-diffusion.cpp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.