Diffusion model(SD,Flux,Wan,...) inference in pure C/C++
Note that this project is under active development.
API and command-line option may change frequently.
- 2026/11/11 🚀 stable-diffusion.cpp adds Day-0 support for MiniMax-H3-Image
- 2026/10/16 🚀 stable-diffusion.cpp adds Day-0 support for MOSS-Image-Base / MOSS-Image-SFT
- 2026/10/16 🚀 stable-diffusion.cpp adds Day-0 support for FLUX.3 Image Klein / Klein Base
- 2026/09/20 🚀 stable-diffusion.cpp adds Day-0 support for Qwen-Image-2.1
- 2026/08/20 🚀 stable-diffusion.cpp now supports LTX-2.5
- 2026/08/04 🚀 stable-diffusion.cpp adds Day-1 support for MiniMax-H3
- 2026/06/25 🚀 stable-diffusion.cpp now supports Krea2
- 2026/06/04 🚀 stable-diffusion.cpp now supports Ideogram4
- 2026/05/31 🚀 stable-diffusion.cpp now supports PiD
- 2026/05/27 🚀 stable-diffusion.cpp now supports Lens
- 2026/05/17 🚀 stable-diffusion.cpp now supports LTX-2.3
- 2026/04/11 🚀 stable-diffusion.cpp now uses a brand-new embedded web UI.
- 2026/01/18 🚀 stable-diffusion.cpp now supports FLUX.2-klein
- 2025/12/01 🚀 stable-diffusion.cpp now supports Z-Image
- 2025/11/30 🚀 stable-diffusion.cpp now supports FLUX.2-dev
- 2025/10/13 🚀 stable-diffusion.cpp now supports Qwen-Image-Edit / Qwen-Image-Edit 2509
- 2025/10/12 🚀 stable-diffusion.cpp now supports Qwen-Image
- 2025/09/14 🚀 stable-diffusion.cpp now supports Wan2.1 Vace
- 2025/09/06 🚀 stable-diffusion.cpp now supports Wan2.1 / Wan2.2
- Plain C/C++ implementation based on ggml, working in the same way as llama.cpp
- Super lightweight and without external dependencies
- Built-in Web UI for image and video generation
- Supported models
- Image Models
- SD1.x, SD2.x, SD-Turbo
- SDXL, SDXL-Turbo
- Some SD1.x and SDXL distilled models
- SD3/SD3.5
- FLUX.1-dev/FLUX.1-schnell
- FLUX.2-dev/FLUX.2-klein
- FLUX.3 Image Klein / Klein Base
- MOSS-Image-Base / MOSS-Image-SFT
- Fibo 2.0 Dev
- Lens
- Chroma
- Chroma1-Radiance
- Qwen Image
- Qwen Image 2.1
- PiD
- LongCat Image
- Z-Image
- Z-Image L2P
- MiniT2I
- P-H3-Image
- MiniMax-H3-Image
- SenseNova U1.5
- Ovis-Image
- Anima
- ERNIE-Image
- Boogu Image
- Krea2
- Mage-Flow
- SeFi-Image
- HiDream-O1-Image
- Ideogram4
- LLaDA-Image
- Ming-Image Design
- PixArt
- Iris-3B
- Image Edit Models
- Video Models
- Video Upscale Models
- PhotoMaker support.
- IP-Adapter support (SD 1.5 and SDXL, including Plus)
- Control Net support with SD 1.5
- ADetailer
- LoRA support, same as stable-diffusion-webui
- Latent Consistency Models support (LCM/LCM-LoRA)
- Faster and memory efficient latent decoding with TAESD
- Upscale images generated with ESRGAN
- Image Models
- Supported backends
- CPU (AVX, AVX2 and AVX512 support for x86 architectures)
- CUDA
- Vulkan
- Metal
- OpenCL
- SYCL
- Supported weight formats
- Pytorch checkpoint (
.ckptor.pthor.pt) - Safetensors (
.safetensors) - GGUF (
.gguf)
- Pytorch checkpoint (
- Convert mode supports converting model weights to
.ggufor.safetensors - Supported platforms
- Linux
- Mac OS
- Windows
- Android (via Termux, Local Diffusion)
- Flash Attention for memory usage optimization
- Negative prompt
- stable-diffusion-webui style tokenizer (not all the features, only token weighting for now)
- VAE tiling processing for reduce memory usage
- Support for a wide range of sampling methods and schedulers
- Cross-platform reproducibility
--rng cuda, default, consistent with thestable-diffusion-webui GPU RNG--rng cpu, consistent with thecomfyui RNG
- Embedds generation parameters into png output as webui-compatible text string
- Download and extract pre-built binaries from the releases page
- Or build from source by following the build guide
The executable examples below run from the build directory (cd build from
the repository root). Windows examples use the Visual Studio Release path;
adjust the executable path for other build configurations or extracted archives.
Model files stay under the repository's models/ directory.
Choose a model from the model guides and download its
weights and required components. For a simple example, save Stable Diffusion 1.5
under models/checkpoints/:
Windows (PowerShell)
New-Item -ItemType Directory -Force ..\models\checkpoints | Out-Null
curl.exe -L -o ..\models\checkpoints\v1-5-pruned-emaonly.safetensors https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensorsLinux/macOS
mkdir -p ../models/checkpoints
curl -L -o ../models/checkpoints/v1-5-pruned-emaonly.safetensors https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensorsStart the server:
Windows (PowerShell)
.\bin\Release\sd-server.exe --model-dir ..\modelsLinux/macOS
./bin/sd-server --model-dir ../modelsOpen http://127.0.0.1:1234/, choose SD 1.x in Recipe, select the checkpoint, and click Load models. Enter a prompt and click Generate. See the Web UI guide for the full workflow.
Generate an image with one command:
Windows (PowerShell)
.\bin\Release\sd-cli.exe -m ..\models\checkpoints\v1-5-pruned-emaonly.safetensors -p "a lovely cat"Linux/macOS
./bin/sd-cli -m ../models/checkpoints/v1-5-pruned-emaonly.safetensors -p "a lovely cat"Run .\bin\Release\sd-cli.exe --help on Windows or ./bin/sd-cli --help on
Linux/macOS for all command-line options. See the
CLI guide for additional usage notes.
If you want to improve performance or reduce VRAM/RAM usage, please refer to performance guide. For runtime and parameter backend placement, see the backend selection guide.
Browse the documentation index or jump to a topic:
- Getting started: build, Docker, CLI, and server
- Models and components
- Generation and inputs
- Devices and performance
- Weights and quantization
- Troubleshooting
- Development and contributing
Thank you to all the people who have already contributed to stable-diffusion.cpp!
