# ahrm/UnstableFusion

A Stable Diffusion desktop frontend with inpainting, img2img and more!

Repository: https://github.com/ahrm/UnstableFusion
Canonical: https://ross.abutalabs.com/products/unstablefusion
Language: Jupyter Notebook
License: GPL-3.0
License Family: copyleft
Last push: 2023-03-21T09:56:42+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1441, "days_push": 1261, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1273, forks 90 (observed 2026-08-28T04:04:12.317321+00:00)

## What it is
UnstableFusion is a PyQt5 desktop frontend for Stable Diffusion that supports text-to-image generation, inpainting, img2img, and outpainting-style canvas editing. It can run models locally on a GPU or connect to a remote backend such as a Google Colab notebook.

## Use cases
- generate images from text prompts with stable diffusion on desktop
- inpaint parts of an image with a diffusion model
- img2img image-to-image generation
- outpaint to extend an image canvas with more detail
- run stable diffusion via colab without a local gpu
- interactive canvas editor for ai image generation

## When to avoid
- you want a web-based UI or the latest diffusion features and active development
- you need a maintained tool - the project has not seen releases since early 2023
- you prefer modern alternatives like AUTOMATIC1111 or ComfyUI with larger ecosystems

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, gui, machine-learning, llm-inference
- domain: image-processing, artificial-intelligence, desktop-applications
- platform: windows, python, cross-platform
- tags: stable-diffusion, inpainting, img2img, pyqt5, text-to-image, diffusion-models, colab, linux, macos, desktop

## Member repositories
- ahrm/UnstableFusion (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:12.317321+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 2026-08-30T05:03:12.029092+00:00, confidence not recorded.
  - readme: https://github.com/ahrm/UnstableFusion (fetched 2026-08-28T04:04:12.317321+00:00, sha 27903f929d32)
- Data as of 2026-08-30T08:39:29.467469+00:00.