# theamusing/perfectPixel

Refine and quantize messy AI pixel art into clean, perfect pixels.

Repository: https://github.com/theamusing/perfectPixel
Canonical: https://ross.abutalabs.com/products/perfectpixel
Language: Python
License Family: other
Last push: 2026-02-01T06:31:44+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 65, release rhythm 35, longevity 17
- inputs: {"age_days": 238, "days_push": 213, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1971, forks 127 (observed 2026-08-28T04:06:00.892566+00:00)

## What it is
A Python library that automatically detects the optimal grid size in AI-generated pixel art images and refines them into clean, perfectly aligned pixel grids. It offers OpenCV and lightweight NumPy backends, plus a ComfyUI custom node for workflow integration.

## Use cases
- clean up messy AI-generated pixel art into perfect grids
- detect the grid size of a pixel-style image automatically
- convert Stable Diffusion pixel-style outputs into true pixel art
- prepare pixel art sprites for perler bead crafting
- integrate pixel art refinement into ComfyUI workflows
- quantize non-square pixel grids into aligned pixels

## When to avoid
- you need to create pixel art from scratch rather than refine existing images
- you work with hand-drawn pixel art that is already grid-perfect
- you need a GUI desktop application rather than a library or web demo

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning
- domain: image-processing, artificial-intelligence, graphics
- platform: python, cross-platform
- tags: pixel-art, ai-generated-images, image-refinement, quantization, comfyui, stable-diffusion

## Member repositories
- theamusing/perfectPixel (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:00.892566+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 2026-08-30T03:05:06.023934+00:00, confidence not recorded.
  - readme: https://github.com/theamusing/perfectPixel (fetched 2026-08-28T04:06:00.892566+00:00, sha 738c358c19c6)
- Data as of 2026-08-30T08:39:29.467469+00:00.