How to use Stable Diffusion CPP: what you can do with it

3 use cases

• Generate images locally with a single command

  Download the sd binary and a model, then make images from a text prompt with no Python setup.

  • REPO leejet/stable-diffusion.cpp
  • Claude Code
  • Codex
  • Cursor
  • Content
  • Beginner
  View prompt

  Download the latest leejet/stable-diffusion.cpp release for my OS, fetch Stable Diffusion v1.5 weights and generate 4 images of <prompt> with sd-cli, each with a different seed. Save them to <folder> and list the exact commands you ran.

  Share Email me this

• Run FLUX or Qwen Image on modest hardware with GGUF

  Use GGUF quantized weights and the right backend so newer image models fit in limited memory.

  • REPO leejet/stable-diffusion.cpp
  • Claude Code
  • Codex
  • Cursor
  • Content
  • Intermediate
  View prompt

  Help me run <FLUX or Qwen Image> with leejet/stable-diffusion.cpp on my <hardware>. Follow the model's docs page and the Quantization and GGUF guide to choose weights that fit in <memory>, then generate one test image of <prompt> and tell me the time and memory used.

  Share Email me this

• Add local image generation to your own app

  Use a Stable Diffusion CPP binding for Python, Go, Rust, C# or Flutter to generate images inside your program.

  • REPO leejet/stable-diffusion.cpp
  • Claude Code
  • Codex
  • Cursor
  • Content
  • Advanced
  View prompt

  Add local image generation to my <language> app using the stable-diffusion.cpp binding listed for it in the leejet/stable-diffusion.cpp README. Load <model weights>, expose a generate(prompt) function, and pin the library version.

  Share Email me this

Quick start with Stable Diffusion CPP

1. Check you have what it needs: The sd executable from the releases page, or a build from source following the build guide; Model weights in .ckpt, .safetensors or .gguf format; Linux, macOS or Windows; Android works through Termux.
2. Open leejet/stable-diffusion.cpp on GitHub and read the README and license.
3. Download a pre-built sd binary from the releases page, or build it from source with the build guide
4. Download weights, for example curl -L -O https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors
5. Generate an image: ./bin/sd-cli -m ../models/v1-5-pruned-emaonly.safetensors -p "a lovely cat"
6. Check the cli doc for options such as negative prompt, sampling method and seed

These steps come from our top use case, Generate images locally with a single command, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for leejet/stable-diffusion.cpp

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Content

About this repo

• Who it is forDevelopers and tinkerers who want local image and video generation without a Python stack or a heavy web UI.
• Why it is hot7.8k stars, talked about in 2 AI sources we track
• LanguageC++
• Sourcegithub.com/leejet/stable-diffusion.cpp · Back to Hot repos

Requirements

• The sd executable from the releases page, or a build from source following the build guide
• Model weights in .ckpt, .safetensors or .gguf format
• Linux, macOS or Windows; Android works through Termux
• Enough RAM or VRAM for the model; the performance guide covers reducing it

Related repos

• Trended earlier REPO worldbench/DiffusionOPSD DiffusionOPSD DiffusionOPSD is an external Python implementation of an on-policy self-distillation method for reward-guided post-training of diffusion models such as SD3.5-M and Z-Image-Turbo.
• Trended earlier REPO ggml-org/llama.cpp llama.cpp llama.cpp is a dependency-free C/C++ engine for running LLMs and vision language models locally or in the cloud, with quantization, many GPU backends, a CLI and an OpenAI-compatible server.
• Trended earlier REPO huggingface/diffusers Diffusers Diffusers is Hugging Face's Python library for pretrained diffusion models that generate images, audio and even 3D molecule structures. It offers ready pipelines that run in a few lines of code, interchangeable noise schedulers that trade speed for quality, and pretrained model building blocks for your own diffusion systems, with access to more than 30,000 checkpoints on the Hub and guides for optimization and training.