# youyuge34/Anime-InPainting

An application tool of edge-connect, which can do anime inpainting and drawing.   动漫人物图片自动修复，去马赛克，填补，去瑕疵

Repository: https://github.com/youyuge34/Anime-InPainting
Canonical: https://ross.abutalabs.com/products/anime-inpainting
Language: Python
License: NOASSERTION
License Family: other
Topics: deep-learning, neural-network, gan, generative-adversarial-network, inpainting, mosaic, cv, opencv, python, pytorch, computer-vision, anime
Last push: 2019-03-27T15:07:00+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2795, "days_push": 2716, "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 1127, forks 151 (observed 2026-08-28T04:03:41.377803+00:00)

## What it is
An application tool built on Edge-Connect that performs anime image inpainting, allowing users to repair, fill, and remove blemishes or mosaics from anime character images. It provides an OpenCV-based frontend with an optimized training pipeline and pretrained model weights for anime faces.

## Use cases
- repair damaged or incomplete anime character images
- remove mosaics from anime pictures
- fill in missing regions of anime artwork
- remove blemishes from anime faces
- train a custom inpainting model on my own anime dataset
- apply GAN-based inpainting to anime images

## When to choose
- you need a ready-to-use anime inpainting tool with pretrained weights
- you want a convenient GUI-like application mode on top of Edge-Connect
- you want to train your own anime inpainting model with auto-save and simplified training phases

## When to avoid
- you need inpainting for full anime characters rather than faces (pretrained weights are face-focused)
- you need a non-commercial license (CC BY-NC 4.0)
- you want an actively maintained project - the authors recommend PI-REC instead
- you need CPU-only inference with good performance

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing
- platform: windows, python
- tags: anime-inpainting, gan, edge-connect, opencv, pytorch, mosaic-removal, image-restoration, anime, linux, gpu

## Member repositories
- youyuge34/Anime-InPainting (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:41.377803+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 2026-08-30T06:39:00.864620+00:00, confidence not recorded.
  - readme: https://github.com/youyuge34/Anime-InPainting (fetched 2026-08-28T04:03:41.377803+00:00, sha 055008f4cfc1)
- Data as of 2026-08-30T08:39:29.467469+00:00.