leejet/stable-diffusion.cpp
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
What it solves
它提供一種輕量且高效能的方式，在本機執行擴散模型（用於影像與影片生成），不需要龐大的外部依賴或複雜的 Python 環境。
How it works
以純 C/C++ 撰寫，並以 ggml 函式庫為基礎，實作各種擴散模型的推論。支援多種硬體後端（CPU、CUDA、Vulkan、Metal、OpenCL、SYCL）以及 GGUF、Safetensors、PyTorch checkpoint 等權重格式。透過 Flash Attention、VAE tiling 等技術優化記憶體使用。
Who it’s for
開發者與使用者，想在各種平台（Linux、macOS、Windows、Android）上以最小的開銷與最高的硬體相容性執行影像與影片生成模型。
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.