stable-diffusion.cpp

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.

🔥Important News

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

Features

Plain C/C++ implementation based on ggml, working in the same way as llama.cpp
Super lightweight and without external dependencies
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
  - Lens
  - Chroma
  - Chroma1-Radiance
  - Qwen Image
  - LongCat Image
  - Z-Image
  - Ovis-Image
  - Anima
  - ERNIE-Image
  - HiDream-O1-Image
- Image Edit Models
- Video Models
  - Wan2.1/Wan2.2
  - LTX-2.3
- PhotoMaker support.
- Control Net support with SD 1.5
- 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
Supported backends
- CPU (AVX, AVX2 and AVX512 support for x86 architectures)
- CUDA
- Vulkan
- Metal
- OpenCL
- SYCL
Supported weight formats
- Pytorch checkpoint (.ckpt or .pth or .pt)
- Safetensors (.safetensors)
- GGUF (.gguf)
Convert mode supports converting model weights to .gguf or .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
Sampling method
- Euler A
- Euler
- Heun
- DPM2
- DPM++ 2M
- DPM++ 2M v2
- DPM++ 2S a
- ER-SDE
- LCM
Cross-platform reproducibility
- --rng cuda, default, consistent with the stable-diffusion-webui GPU RNG
- --rng cpu, consistent with the comfyui RNG
Embedds generation parameters into png output as webui-compatible text string

Quick Start

Get the sd executable

Download pre-built binaries from the releases page
Or build from source by following the build guide

Download model weights

download weights(.ckpt or .safetensors or .gguf). For example
- Stable Diffusion v1.5 from https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5
```
sh
curl -L -O https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors
```

Generate an image with just one command

sh
./bin/sd-cli -m ../models/v1-5-pruned-emaonly.safetensors -p "a lovely cat"

For detailed command-line arguments, check out cli doc.

Performance

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.