# leejet/stable-diffusion.cpp

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

Repository: https://github.com/leejet/stable-diffusion.cpp
Canonical: https://ross.abutalabs.com/products/stable-diffusioncpp
Language: C++
License: MIT
License Family: permissive
Topics: ai, cplusplus, diffusion, ggml, image-generation, latent-diffusion, stable-diffusion, text2image, txt2img, image2image, img2img, flux, flux-dev, videogeneration, wan, qwen-image, z-image, z-image-turbo, ltx-video
Last push: 2026-08-26T15:45:37+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 79
- inputs: {"age_days": 1116, "days_push": 7, "days_rel": 8, "gap_med": 0, "n_releases_24m": 530}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6846, forks 753 (observed 2026-08-28T04:09:50.809987+00:00)

## What it is
A pure C/C++ inference engine for diffusion models (Stable Diffusion, FLUX, Wan, Qwen Image, Z-Image, and more) built on ggml in the style of llama.cpp. It ships as a lightweight dependency-free library plus CLI with text-to-image, image-to-image, image editing, and video generation support.

## Use cases
- generate images from text prompts without python
- run stable diffusion inference in pure C++
- run FLUX or Qwen Image models locally on CPU or GPU
- embed diffusion model inference into a C++ application
- convert text to image from the command line
- run image editing models like FLUX Kontext locally
- generate videos with Wan or LTX models

## When to choose
- you need lightweight, dependency-free diffusion inference in C/C++
- you want llama.cpp-style local inference without Python or PyTorch
- you need to embed image generation into a native application
- you want broad model support including SD, SDXL, SD3, FLUX, and Wan

## When to avoid
- you need the full Python ecosystem of diffusers pipelines and extensions
- you want a polished GUI-first image generation tool
- you need a frozen, stable API - the project is under active development and interfaces change frequently

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, image-processing, cli, machine-learning, stable-diffusion
- domain: artificial-intelligence, image-processing, machine-learning, deep-learning, gpu-computing
- platform: cpp, c, cross-platform, cli, windows
- tags: ggml, text-to-image, image-to-image, diffusion-models, flux, stable-diffusion, video-generation, llama.cpp-style, lightweight-inference, gpu, linux, macos

## Member repositories
- leejet/stable-diffusion.cpp (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:50.809987+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:41:50.670800+00:00, confidence not recorded.
  - readme: https://github.com/leejet/stable-diffusion.cpp (fetched 2026-08-28T04:09:50.809987+00:00, sha 2f266719ae51)
- Data as of 2026-08-30T08:39:29.467469+00:00.