# leejet/stable-diffusion.cpp

> Diffusion model inference (Stable Diffusion, FLUX, Wan, Qwen Image, etc.) implemented in pure C/C++ on top of ggml — like llama.cpp but for image and video generation. Runs without external dependencies on CPU, CUDA, Vulkan, Metal and other backends.

- Magnitude: 2.3 out of 10 — Steady
- Stars: 7,090 total · +4 stars today, ≈ 12 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: C++ · License: MIT · Created: 2023-08-13 · Last push: 2026-09-21
- GitHub: https://github.com/leejet/stable-diffusion.cpp · Page: https://gitnova.dev/en/r/leejet/stable-diffusion.cpp

## Useful for

- Generate an image from a text prompt with a single sd-cli command locally
- Run Stable Diffusion or FLUX on CPU without a GPU or Python environment
- Convert model weights to GGUF format to reduce memory usage

## Why it’s here

- 4 stars so far today, about 12 expected by the end of the day.
- Over the last two days the pace is 2.5× that of the previous week and a half.
- The spike has held for 2 days in a row — not a one-off blip.
- GitHub Trending C++ today: #5, +29 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 799
- Issues and pull requests: 1,838
- Watchers: 77
- Average over the last week: 16 per day
- Usual pace: 8 per day
- Stars in the last hour (measured): 0
- Latest release: master-890-74988b2 (2026-09-21)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-08-24 … 2026-09-22: 8, 6, 11, 8, 6, 6, 12, 14, 9, 5, 6, 9, 7, 8, 3, 11, 10, 11, 3, 5, 8, 7, 9, 7, 11, 9, 11, 29, 29, 4

## Spotted in now

- GitHub Trending C++ today: #5, +29 stars

## Similar by description

1. **0xShug0/audio.cpp** — 1.9 · Cooling · Generative media · C++ · +8 stars today, ≈ 17 by evening
   A native C++ inference engine for audio models built on ggml: TTS, speech recognition, VAD, voice cloning, music generation. Runs without Python on CPU, CUDA, ROCm, Vulkan and Metal.
   Full card: https://gitnova.dev/en/r/0xShug0/audio.cpp.md
2. **localai-org/kimodo.cpp** — 1.1 · Steady · Generative media · C++ · +2 stars today, ≈ 5 by evening
   A C++/GGML port of NVIDIA's Kimodo text-to-motion model that generates skeleton motion from a text prompt on CPU or Vulkan. Supports SMPL-X, SOMA and Unitree G1 checkpoints, and ships a C API, safetensors-to-GGUF conversion and a demo…
   Full card: https://gitnova.dev/en/r/localai-org/kimodo.cpp.md
3. **ggml-org/llama.cpp** — 3.3 · Steady · Language models · C++ · +38 stars today, ≈ 89 by evening
   LLM and VLM inference implemented in C/C++ with no dependencies, running on CPUs and GPUs across many hardware backends. Enables local model execution with minimal setup and quantization.
   Full card: https://gitnova.dev/en/r/ggml-org/llama.cpp.md
4. **techjarves/Portable-Local-Studio** — 0.9 · Steady · Apps · JavaScript · +0 stars today, ≈ 1 by evening
   Offline local AI studio for Windows, Linux and macOS with a zero-setup GUI: image generation (Stable Diffusion), GGUF LLM chat, speech-to-text (Whisper) and text-to-speech (Kokoro TTS).
   Full card: https://gitnova.dev/en/r/techjarves/Portable-Local-Studio.md
5. **unslothai/unsloth** — 2.4 · Steady · Language models · Python · +17 stars today, ≈ 34 by evening
   Desktop app and web UI for locally running, fine-tuning and serving LLMs, diffusion, embedding and audio models, with OpenAI-compatible API and integrations for Claude Code, Codex and MCP agents.
   Full card: https://gitnova.dev/en/r/unslothai/unsloth.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-22 12:33 UTC, updated every 30 minutes.