mirror of https://github.com/leejet/stable-diffusion.cpp synced 2026-04-20 22:06:07 +02:00

Go to file

leejet 09b12d5f6d feat(cli): add metadata inspection mode (#1381 )		2026-04-01 00:52:03 +08:00
.github	feat(cli): add metadata inspection mode (#1381 )	2026-04-01 00:52:03 +08:00
assets	docs: add anima docs	2026-03-01 15:32:25 +08:00
docs	docs: update Spectrum info about DiT models (#1360 )	2026-03-30 00:12:57 +08:00
examples	feat(cli): add metadata inspection mode (#1381 )	2026-04-01 00:52:03 +08:00
ggml@404fcb9d7c	sync: update ggml	2026-03-30 23:00:53 +08:00
include	sync: update ggml	2026-03-30 23:00:53 +08:00
script	refactor: reorganize the file structure (#1266 )	2026-02-10 23:13:35 +08:00
src	feat: show tensor loading progress in MB/s or GB/s (#1380 )	2026-03-31 23:06:44 +08:00
thirdparty	chore: eliminate compilation warnings under MSVC (#1170 )	2026-01-04 22:26:57 +08:00
.clang-format	style: format code	2024-01-29 23:05:18 +08:00
.clang-tidy	chore: add .clang-tidy configuration and apply modernize checks (#902 )	2025-10-18 23:23:40 +08:00
.dockerignore	chore: add Linux Vulkan build and Docker image workflows (#1164 )	2026-01-05 23:42:12 +08:00
.gitignore	feat: add image preview support (#522 )	2025-11-10 00:12:02 +08:00
.gitmodules	feat: add embedded WebUI (#1207 )	2026-03-16 00:26:57 +08:00
CMakeLists.txt	chore: remove SD_FAST_SOFTMAX build flag (#1338 )	2026-03-15 16:42:47 +08:00
Dockerfile	chore: add Linux Vulkan build and Docker image workflows (#1164 )	2026-01-05 23:42:12 +08:00
Dockerfile.cuda	ci: avoid cuda docker build timeout by using -j16	2026-03-15 18:39:29 +08:00
Dockerfile.musa	chore: downgrade ubuntu base image in musa container image (#1176 )	2026-01-05 23:56:34 +08:00
Dockerfile.sycl	chore: add Linux Vulkan build and Docker image workflows (#1164 )	2026-01-05 23:42:12 +08:00
Dockerfile.vulkan	chore: add Linux Vulkan build and Docker image workflows (#1164 )	2026-01-05 23:42:12 +08:00
format-code.sh	refactor: reorganize the vocab file structure (#1271 )	2026-02-11 00:44:17 +08:00
LICENSE	Initial commit	2023-08-13 16:00:22 +08:00
README.md	docs: add anima docs	2026-03-01 15:32:25 +08:00

README.md

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

2026/01/18 🚀 stable-diffusion.cpp now supports FLUX.2-klein
👉 Details: PR #1193
2025/12/01 🚀 stable-diffusion.cpp now supports Z-Image
👉 Details: PR #1020
2025/11/30 🚀 stable-diffusion.cpp now supports FLUX.2-dev
👉 Details: PR #1016
2025/10/13 🚀 stable-diffusion.cpp now supports Qwen-Image-Edit / Qwen-Image-Edit 2509
👉 Details: PR #877
2025/10/12 🚀 stable-diffusion.cpp now supports Qwen-Image
👉 Details: PR #851
2025/09/14 🚀 stable-diffusion.cpp now supports Wan2.1 Vace
👉 Details: PR #819
2025/09/06 🚀 stable-diffusion.cpp now supports Wan2.1 / Wan2.2
👉 Details: PR #778

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
  - Chroma
  - Chroma1-Radiance
  - Qwen Image
  - Z-Image
  - Ovis-Image
  - Anima
- Image Edit Models
  - FLUX.1-Kontext-dev
  - Qwen Image Edit series
- Video Models
  - Wan2.1/Wan2.2
- 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)
- Safetensors (.safetensors)
- GGUF (.gguf)
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
- 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
```
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

./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.

More Guides

Bindings

These projects wrap stable-diffusion.cpp for easier use in other languages/frameworks.

Golang (non-cgo): seasonjs/stable-diffusion
Golang (cgo): Binozo/GoStableDiffusion
C#: DarthAffe/StableDiffusion.NET
Python: william-murray1204/stable-diffusion-cpp-python
Rust: newfla/diffusion-rs
Flutter/Dart: rmatif/Local-Diffusion

UIs

These projects use stable-diffusion.cpp as a backend for their image generation.

Contributors

Thank you to all the people who have already contributed to stable-diffusion.cpp!