# rupeshs/fastsdcpu

Fast stable diffusion on CPU and AI PC

Repository: https://github.com/rupeshs/fastsdcpu
Canonical: https://ross.abutalabs.com/products/fastsdcpu
Language: Python
License: MIT
License Family: permissive
Topics: cpu, diffusion, stablediffusion, lcmdiffusion, latentconsistencymodels, fastsdcpu, cli, gradio, qt, webui, desktopgui, openvino, sdxlturbo, diffusers, sdupcale, torch, sdxs, api, flux, aipc
Last push: 2026-07-24T16:08:22+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 60, longevity 74
- inputs: {"age_days": 1049, "days_push": 40, "days_rel": 59, "gap_med": 23.0, "n_releases_24m": 17}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2143, forks 214 (observed 2026-08-28T04:06:18.567568+00:00)

## What it is
FastSD CPU is a Python application that runs Stable Diffusion image generation quickly on CPUs and Intel AI PCs using Latent Consistency Models, Adversarial Diffusion Distillation, and OpenVINO. It ships with a Qt desktop GUI, a Gradio WebUI, a CLI, an API, and an MCP server, supporting models like SDXS, SDXL Turbo, and Flux.

## Use cases
- generate stable diffusion images on a CPU without a GPU
- run fast text-to-image generation on an Intel AI PC with NPU support
- create 512x512 images in under a second with OpenVINO
- use stable diffusion from the command line or a local web UI
- serve text-to-image generation through an API or MCP server
- run image editing, photo restoration, and colorization locally
- run stable diffusion on a Raspberry Pi or Android via Termux

## When to choose
- you have no GPU or want fast diffusion inference on CPU or Intel NPU/GPU
- you need a self-contained local text-to-image tool with GUI, CLI, and API options
- you want to use distilled fast models like LCM, SDXS, SDXL Turbo, or Flux GGUF

## When to avoid
- you need the full quality and ecosystem of a GPU-based Stable Diffusion UI like ComfyUI or Automatic1111
- you require large-scale batch image generation in a datacenter setting
- you need fine-grained node-based workflow control for complex pipelines

## Facets
- artifact type: application
- maturity: active
- function: image-processing, machine-learning, llm-inference, cli, gui, mcp
- domain: image-processing, artificial-intelligence, machine-learning, cross-platform
- platform: windows, python, cross-platform, cli
- tags: stable-diffusion, openvino, latent-consistency-models, sdxl-turbo, flux, cpu-inference, text-to-image, gradio, webui, npu, gguf, linux, macos, docker

## Member repositories
- rupeshs/fastsdcpu (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:18.567568+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:51:15.890177+00:00, confidence not recorded.
  - readme: https://github.com/rupeshs/fastsdcpu (fetched 2026-08-28T04:06:18.567568+00:00, sha a9b9144120b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.