stable-diffusion.cpp
A lightweight C/C++ program for running Stable Diffusion, FLUX and other diffusion models locally.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About stable-diffusion.cpp
stable-diffusion.cpp runs diffusion models in plain C/C++ on top of ggml, working in the same way as llama.cpp and without external dependencies. It supports image models such as SD1.x, SD2.x, SDXL, FLUX, Qwen-Image and Z-Image, and video models such as Wan and LTX.
It is used from the command line, and since April 2026 it also includes an embedded web UI. The project is under active development, and the README warns that the API and command-line options change often.
Strengths
- No external dependencies and a small footprint
- Quick support for new image and video models
- Embedded web UI in addition to the command line
Limitations
- Command-line options change frequently
- More technical to set up than graphical image generators
Details
- Pricing
- FreeFree and open source under the MIT licence.
- License
- MIT
- Developer
- leejet
- Platforms
- Command line
- How it runs
- Downloadable app
- Account
- Not required
- Works offline
- Yes
- Best suited for
- Running image and video diffusion models locally with minimal dependencies
- Categories
- Local AI tools, AI image generators
- Last verified
- Added
Alternatives to stable-diffusion.cpp
Compare allSoftware that can replace stable-diffusion.cpp for an important use case, and what changes if you switch.
MFLUX
A command-line tool that runs FLUX and other image generation models natively on Apple Silicon Macs.
MFLUX is also a free MIT-licensed command-line tool running FLUX and other models, but only on Apple Silicon Macs using a native MLX implementation.
ComfyUI
Construct AI generation workflows with a visual node graph.
ComfyUI replaces the command line with a visual node graph on Windows, macOS and Linux under GPL-3.0, with separate model downloads.
Stable Diffusion web UI
Generate and edit images using a local Stable Diffusion interface.
Stable Diffusion web UI offers a full graphical interface with inpainting and outpainting under AGPL-3.0, but requires Python and its dependencies.
SD.Next
Generate and refine images through a locally hosted AI interface.
SD.Next provides a locally hosted Apache-2.0 web interface supporting multiple model families, with heavier setup than a dependency-free binary.
Stable Diffusion WebUI Forge
Generate images with a Stable Diffusion web interface.
Stable Diffusion WebUI Forge adds a web interface with resource-management options under AGPL-3.0, on Windows, macOS and Linux.
InvokeAI
A professional web interface for Stable Diffusion models, with a node-based workflow editor and a unified canvas.
InvokeAI adds a unified canvas and node workflow editor with a launcher-based install under Apache-2.0, but needs a capable GPU.
SwarmUI
Manage AI image-generation workflows through a modular web interface.
SwarmUI offers a modular MIT-licensed web interface with extensible backends, but it is listed for Windows only.
Fooocus
Offline image generator that asks for a prompt and handles the tuning itself.
Fooocus is a GPL-3.0 prompt-first graphical app that handles tuning itself, though upstream development has largely stopped.
Similar software
Related functionality, not necessarily a direct replacement.
Wan2GP
A local AI video generator built to run open video and image models on low-memory GPUs.
Stability Matrix
Install and manage AI image-generation interfaces from one application.
Kohya's GUI
A local graphical interface for training LoRA models and fine-tuning Stable Diffusion image models.
Civitai
A community site for sharing Stable Diffusion and Flux models, with online AI image generation.
Draw Things
Image generator that runs Stable Diffusion models locally on Apple hardware.
