mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2025-12-12 13:28:37 +00:00

Go to file

chrore: enable Windows ROCm(HIP) build release (#956 )

* build: fix missing commit sha in macOS and Ubuntu build zip name

The build workflows for macOS and Ubuntu incorrectly check for the
"main" branch instead of "master" when retrieving the commit hash for
naming the build artifacts.

* build: correct Vulkan SDK installation condition in build workflow

* build: Enable Windows ROCm(HIP) build release

Refer to the build workflow of llama.cpp to add a Windows ROCm (HIP)
build release to the workflow.
Since there are many differences between the HIP build and other
builds, this commit add a separate "windows-latest-cmake-hip" job,
instead of enabling the ROCm matrix entry in the existing Windows
build job.

Main differences include:

- Install ROCm SDK from AMD official installer.
- Add a cache step for ROCm installation and a ccache step for build
  processing, since the HIP build takes much longer time than other
  builds.
- Include the ROCm/HIP artifact in the release assets.

2025-11-12 00:28:55 +08:00

.github

chrore: enable Windows ROCm(HIP) build release (#956 )

2025-11-12 00:28:55 +08:00

assets

feat: add chroma radiance support (#910 )

2025-10-25 23:56:14 +08:00

docs

feat: add support for SD2.x with TINY U-Nets (#939 )

2025-11-09 22:47:37 +08:00

examples

feat: add image preview support (#522 )

2025-11-10 00:12:02 +08:00

ggml @ 2d3876d554

sync: update ggml

2025-10-24 00:32:45 +08:00

thirdparty

feat: add wan2.1/2.2 support (#778 )

2025-09-06 18:08:03 +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 sd Dockerfile

2023-08-22 22:14:20 +08:00

.gitignore

feat: add image preview support (#522 )

2025-11-10 00:12:02 +08:00

.gitmodules

feat: add wan2.1/2.2 support (#778 )

2025-09-06 18:08:03 +08:00

clip.hpp

refactor: simplify the model loading logic (#933 )

2025-11-03 21:21:34 +08:00

CMakeLists.txt

chore: allow building ggml as a separate shared lib (#468 )

2025-10-15 22:10:26 +08:00

common.hpp

fix: compatibility for models with modified tensor shapes (#951 )

2025-11-07 23:04:41 +08:00

conditioner.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

control.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

denoiser.hpp

refactor: unify the naming style of ggml extension functions (#921 )

2025-10-28 23:26:48 +08:00

diffusion_model.hpp

refactor: simplify the model loading logic (#933 )

2025-11-03 21:21:34 +08:00

Dockerfile

chore: fix dockerfile libgomp1 dependency + improvements (#852 )

2025-10-11 00:17:45 +08:00

Dockerfile.musa

feat: upgrade musa sdk to rc4.2.0 (#732 )

2025-07-28 21:51:11 +08:00

Dockerfile.sycl

feat: Add SYCL Dockerfile (#651 )

2025-09-14 13:02:59 +08:00

esrgan.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

face_detect.py

feat: add PhotoMaker Version 2 support (#358 )

2024-11-23 11:50:14 +08:00

flux.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

format-code.sh

chore: add .clang-tidy configuration and apply modernize checks (#902 )

2025-10-18 23:23:40 +08:00

ggml_extend.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

gguf_reader.hpp

feat: add wan2.1/2.2 support (#778 )

2025-09-06 18:08:03 +08:00

gits_noise.inl

fix: clang complains about needless braces (#618 )

2025-03-09 12:26:41 +08:00

latent-preview.h

feat: add image preview support (#522 )

2025-11-10 00:12:02 +08:00

LICENSE

Initial commit

2023-08-13 16:00:22 +08:00

lora.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

ltxv.hpp

refactor: introduce GGMLRunnerContext (#928 )

2025-11-02 02:11:04 +08:00

mmdit.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

model.cpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

model.h

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

name_conversion.cpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

name_conversion.h

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

ordered_map.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

pmid.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

preprocessing.hpp

refactor: unify the naming style of ggml extension functions (#921 )

2025-10-28 23:26:48 +08:00

qwen_image.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

qwenvl.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

README.md

docs: add Koboldcpp as an available UI (#930 )

2025-11-02 02:03:01 +08:00

rng_philox.hpp

chore: add .clang-tidy configuration and apply modernize checks (#902 )

2025-10-18 23:23:40 +08:00

rng.hpp

chore: add .clang-tidy configuration and apply modernize checks (#902 )

2025-10-18 23:23:40 +08:00

rope.hpp

refactor: introduce GGMLRunnerContext (#928 )

2025-11-02 02:11:04 +08:00

stable-diffusion.cpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

stable-diffusion.h

fix: specify enum modifier in sd_set_preview_callback signature (#959 )

2025-11-12 00:27:23 +08:00

t5.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

tae.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

tokenize_util.cpp

feat: add Qwen Image support (#851 )

2025-10-12 23:23:19 +08:00

tokenize_util.h

feat: add Qwen Image support (#851 )

2025-10-12 23:23:19 +08:00

unet.hpp

feat: add support for SD2.x with TINY U-Nets (#939 )

2025-11-09 22:47:37 +08:00

upscaler.cpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +08:00

util.cpp

feat: add image preview support (#522 )

2025-11-10 00:12:02 +08:00

util.h

feat: add image preview support (#522 )

2025-11-10 00:12:02 +08:00

vae.hpp

fix: compatibility for models with modified tensor shapes (#951 )

2025-11-07 23:04:41 +08:00

vocab_qwen.hpp

feat: add Qwen Image support (#851 )

2025-10-12 23:23:19 +08:00

vocab_umt5.hpp

feat: add wan2.1/2.2 support (#778 )

2025-09-06 18:08:03 +08:00

vocab.hpp

feat: add sd3 support (#298 )

2024-07-28 15:44:08 +08:00

wan.hpp

refactor: optimize the logic for name conversion and the processing of the LoRA model (#955 )

2025-11-10 00:12:20 +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

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-dev/Flux-schnell
  - Chroma
  - Chroma1-Radiance
  - Qwen Image
- Image Edit Models
  - FLUX.1-Kontext-dev
  - Qwen Image Edit/Qwen Image Edit 2509
- 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, consistent with the stable-diffusion-webui GPU 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/runwayml/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 -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!

README.md

stable-diffusion.cpp

🔥Important News

Features

Quick Start

Get the sd executable

Download model weights

Generate an image with just one command

Performance

More Guides

Bindings

UIs

Contributors

Star History

References