README.md

AIGC	ContentProducer ContentPropagator Label ProduceID PropagateID ReservedCode1 ReservedCode2 001191110102MAD55U9H0F10002 001191110102MAD55U9H0F10002 1 2cdeb6ee-14ee-430a-83e1-74638ca084d0 2cdeb6ee-14ee-430a-83e1-74638ca084d0 46b9dfd6-63bb-4d88-b995-0f54b87f4438 46b9dfd6-63bb-4d88-b995-0f54b87f4438

stable-diffusion.cpp

Diffusion model(SD,Flux,Wan,...) inference in pure C/C++

Important

这是 CreatorCpp 定制版 fork — 引擎服务于 CreatorCpp 本地生图工作台（8GB 显存优化实践）。上游全部功能保留，可跟随上游更新。

相对上游的定制（详见下方说明）：

1. fp8_scaled per-tensor scale 修复 — 修复 nlohmann::json 字母序迭代导致 scale 恒为 1.0，以及 F8 原地覆盖产生 NaN 的两个连锁 bug
2. Krea2 参考图 v3 API — sd_encode_image_prompt_v3（视觉塔 + 多参考图 + FA）、ref_images_strength per-image 强度、encode-only version 预设
3. 显存管理 — ComfyUI 风格 host-offload 架构 + ggml 子模块定制（CreatorCpp-ggml，pinned memory cudaMemAdvise 零拷贝），8GB 显存跑 20B 级模型
4. Krea2 flow_shift、diffusion-model-only TE/VAE 校验跳过

定制提交作者为 DoGeMisu（git log --author=DoGeMisu），完整上游历史保留便于合并。

Note that this project is under active development.
API and command-line option may change frequently.

🔥Important News

• 2026/08/04 🚀 stable-diffusion.cpp adds Day-1 support for MiniMax-H3
• 2026/06/25 🚀 stable-diffusion.cpp now supports Krea2
• 2026/06/04 🚀 stable-diffusion.cpp now supports Ideogram4
• 2026/05/31 🚀 stable-diffusion.cpp now supports PiD
• 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
    • PiD
    • LongCat Image
    • Z-Image
    • MiniT2I
    • Ovis-Image
    • Anima
    • ERNIE-Image
    • Boogu Image
    • Krea2
    • Mage-Flow
    • SeFi-Image
    • HiDream-O1-Image
    • Ideogram4
  • Image Edit Models
    • FLUX.1-Kontext-dev
    • Qwen Image Edit series
    • LongCat Image Edit
    • Boogu Image Edit
    • Mage-Flow-Edit
  • Video Models
    • Wan2.1/Wan2.2
    • MiniMax-H3
    • LTX-2.3
    • HunyuanVideo 1.5
    • LingBot-Video
  • PhotoMaker support.
  • IP-Adapter support (SD 1.5 and SDXL, including Plus)
  • Control Net support with SD 1.5
  • ADetailer
  • 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

  curl -L -O https://huggingface.co/stable-diffusion-v1-5/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. For runtime and parameter backend placement, see the backend selection guide.

More Guides

• Backend selection
• RPC
• LoRA
• LCM/LCM-LoRA
• Docker
• Quantization and GGUF
• INT8 convrot safetensors
• Inference acceleration via caching

Bindings

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

• Golang (non-cgo): seasonjs/stable-diffusion
• Golang (cgo): Binozo/GoStableDiffusion
• Golang (non-cgo): l8bloom/gosd
• 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.

• GIMP Plugins
• Jellybox
• Stable Diffusion GUI
• Stable Diffusion CLI-GUI
• Local Diffusion
• sd.cpp-webui
• LocalAI
• Neural-Pixel
• KoboldCpp

Contributors

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