# pfnet/PaintsChainer

line drawing colorization using chainer

Repository: https://github.com/pfnet/PaintsChainer
Canonical: https://ross.abutalabs.com/products/paintschainer
Homepage: https://paintschainer.preferred.tech/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2019-01-06T02:35:33+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3505, "days_push": 2797, "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 3762, forks 543 (observed 2026-08-28T04:08:17.951844+00:00)

## What it is
Paints Chainer is a semi-automatic line drawing colorizer that uses convolutional neural networks built on the Chainer deep learning framework to colorize sketches. It includes a web-based UI for uploading line drawings and a Python server, along with training scripts and pre-trained models.

## Use cases
- colorize line drawings and sketches semi-automatically
- add color hints to black-and-white manga or anime-style line art
- run a local web server to colorize sketches through a browser UI
- train custom colorization models on your own line art dataset
- experiment with CNN-based image colorization using Chainer

## When to choose
- you want to automatically colorize anime or manga style line drawings with minimal manual effort
- you need a self-hosted sketch colorization tool with a browser-based interface
- you want to study or modify a CNN-based colorization pipeline with training scripts included

## When to avoid
- you need actively maintained software or support for modern deep learning frameworks
- you require a production-ready colorization service with commercial licensing for the models
- you work without an NVIDIA GPU or CUDA environment, since GPU support is central to its performance

## Facets
- artifact type: application
- maturity: abandoned
- function: machine-learning, image-processing, web-framework, gpu-computing
- domain: machine-learning, image-processing, artificial-intelligence, web-development
- platform: windows, python
- tags: colorization, line-drawing, sketch-colorization, cnn, chainer, deep-learning, semi-automatic-colorization, web-ui, pre-trained-models, anime-art, linux, web-server, gpu

## Member repositories
- pfnet/PaintsChainer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:17.951844+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 2026-08-29T18:28:52.709222+00:00, confidence not recorded.
  - readme: https://github.com/pfnet/PaintsChainer (fetched 2026-08-28T04:08:17.951844+00:00, sha 7e36031ad236)
  - homepage: https://paintschainer.preferred.tech/ (fetched 2026-08-29T09:22:51.889310+00:00, sha f1b84ed85a8e)
- Data as of 2026-08-30T08:39:29.467469+00:00.