leejet/stable-diffusion.cpp

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

What it solves

它提供一种轻量且高性能的方式，在本地运行扩散模型（用于图像和视频生成），无需庞大的外部依赖或复杂的 Python 环境。

How it works

使用纯 C/C++ 编写，基于 ggml 库，实现对多种扩散模型的推理。支持多种硬件后端（CPU、CUDA、Vulkan、Metal、OpenCL、SYCL）以及 GGUF、Safetensors、PyTorch checkpoint 等权重格式。通过 Flash Attention、VAE tiling 等技术优化内存使用。

Who it’s for

开发者和用户，想在各种平台（Linux、macOS、Windows、Android）上以最小的开销和最高的硬件兼容性运行图像和视频生成模型。

Highlights

  • Broad Model Support: Compatible with SD1.x, SD2.x, SDXL, SD3/3.5, FLUX.1/2, Wan2.1/2.2, LTX-2.3, and many others.
  • Multi-Modal Capabilities: Supports image generation, image editing, and video generation.
  • Hardware Flexibility: Runs on CPU (with AVX/AVX2/AVX512), NVIDIA GPUs (CUDA), Apple Silicon (Metal), and other accelerators via Vulkan, OpenCL, and SYCL.
  • Advanced Features: Includes LoRA support, ControlNet (SD 1.5), ADetailer, and various sampling methods (Euler, DPM++, LCM).
  • Efficient Formats: Supports GGUF quantization and weight conversion.