stable-diffusion.cpp

Pure C/C++ inference for SD, Flux, and Qwen-Image weights — CPU included.

Install Repository Compare

Fit.

Catalog snapshot

Platforms: Linux, Macos, Windows
Operating systems: Linux, macOS, Windows
Ram floor: 4 GB
Gpu: Optional · 4 GB VRAM helps
Docker: No
Setup: Advanced
Deploy as: Local
Commercial use: Allowed

CPU generation works but is measured in minutes, not seconds.

Project.

Fetched Sep 12, 2026¹

License: MIT
Stars: 7k¹
Forks: 781¹
Open issues: 238¹
Language: C++¹
Last commit: Sep 11, 2026¹
Tags: cppquantizationcpu

About.

stable-diffusion.cpp is the llama.cpp move for images: one C/C++ runtime that runs SD, Flux, and Qwen-Image weights on CPU or modest GPUs with quantization. No UI. It is the engine you embed, not the studio you open.

pure C/C++ · CPU inference · SD, Flux, and Qwen-Image weights · quantization

Alternatives.

Nearby.

All Image AI

SDStable Diffusion web UIThe AUTOMATIC1111 Gradio UI that made local SD mainstream.Compare
IInvokeAIPolished local creative tool around diffusion, with a studio UI.Compare
FFooocusMidjourney-like simplicity on top of local diffusion.Compare
KAKrita AI DiffusionKrita plugin that generates, inpaints, and outpaints as native layers via ComfyUI.Compare
SDStable Diffusion WebUI ForgeLeaner Stable Diffusion WebUI rework tuned for SDXL and Flux on modest GPUs.Compare