# lllyasviel/style2paints

sketch + style = paints :art: (TOG2018/SIGGRAPH2018ASIA)

Repository: https://github.com/lllyasviel/style2paints
Canonical: https://ross.abutalabs.com/products/style2paints
Language: JavaScript
License: Apache-2.0
License Family: permissive
Last push: 2023-08-01T02:02:00+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3377, "days_push": 1129, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18179, forks 2058 (observed 2026-08-28T04:11:26.415995+00:00)

## What it is
Style2Paints is an AI-driven tool that colorizes lineart sketches, optionally guided by human hints, style reference images, and lighting. It outputs layered results (PSD-style layers) that fit into real digital painting workflows.

## Use cases
- colorize manga or anime lineart automatically
- apply a color style from a reference image to a sketch
- add lighting and shading to flat lineart
- get separated flat-color and rendering layers for Photoshop
- colorize illustrations with minimal manual painting

## When to choose
- you need high-quality AI colorization of lineart with layered output
- you want a downloadable desktop app without installing CUDA or Python
- you work in a digital illustration pipeline and want editable layers

## When to avoid
- you need an actively developed tool with recent updates
- you are not on Windows x64
- you need V5 features, which are not yet released

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, graphics
- platform: windows, python
- tags: lineart-colorization, ai-painting, digital-art, style-transfer, psd-layers, gpu

## Member repositories
- lllyasviel/style2paints (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.415995+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 2026-08-29T17:02:07.802023+00:00, confidence not recorded.
  - readme: https://github.com/lllyasviel/style2paints (fetched 2026-08-28T04:11:26.415995+00:00, sha 3e55b962881e)
- Data as of 2026-08-30T08:39:29.467469+00:00.