stable-diffusion.cpp

stable-diffusion.cpp is a lightweight software library for running diffusion model inference in pure C and C++.

Stable-diffusion.cpp is a software library that performs diffusion model inference in pure C and C++ without external dependencies. It works similarly to llama.cpp and supports various image, video, and image edit models including Stable Diffusion, FLUX, Wan, and Qwen Image series. The library runs on backends like CPU, CUDA, Vulkan, Metal, OpenCL, and SYCL, and handles PyTorch checkpoints, Safetensors, and GGUF weight formats. It includes features like LoRA support, ControlNet, Flash Attention, VAE tiling, and an embedded web UI. Designed for developers and users wanting local diffusion inference, it operates across Linux, macOS, Windows, and Android.

stable-diffusion.cpp at a glance

Best for: Software engineer, Designer
Runs on: Linux, macOS, Windows, Android, CLI, self-hosted, open source
Pricing: Free
Released: August 2023
Category: AI image tool
Website: github.com/leejet/stable-diffusion.cpp

Key features

Pure C and C++ implementation based on ggml
Support for numerous image and video models
Multiple backend options including CPU, CUDA, and Metal
Model weight conversion to GGUF or Safetensors
LoRA and ControlNet support
Flash Attention and VAE tiling for memory optimization
Embedded web UI and command-line interface

Use it for

Run local diffusion model inference
Generate images from text prompts
Convert model weights to GGUF format
Process video generation models

Alternatives to stable-diffusion.cpp

Easy Diffusion — Hassle-free 1-click installation with no technical knowledge required.
audio.cpp — Runs modern audio models locally with high-performance, native C++ execution.
LyCORIS — It provides diverse algorithms like LoHa, LoKr, and DyLoRA for Stable Diffusion fine-tuning.
Mochi Diffusion — Runs Stable Diffusion and FLUX models natively on Mac hardware with full offline privacy.
TurboDiffusion — Accelerates video diffusion generation by up to 200 times on single GPUs.
Diffusers — A modular toolbox for inference and training of diffusion models.
Dsh Sd Bridge Guard — Connects DeepSeek directly to local Stable Diffusion without manual setup.
DiffusionBee — Runs generative artificial intelligence locally without cloud uploads.
SimpleTuner — It supports dozens of model families with advanced memory and enterprise features.
Krita AI Diffusion — Enables precise control and efficient AI workflows inside Krita.
Stability Matrix — Manages multiple AI user interfaces and a shared model repository.
SwarmUI — It offers modular powertools and high performance for managing multiple AI models.

All stable-diffusion.cpp alternatives