# zyddnys/manga-image-translator

Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)

Repository: https://github.com/zyddnys/manga-image-translator
Canonical: https://ross.abutalabs.com/products/manga-image-translator
Homepage: https://cotrans.touhou.ai/
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: manga, anime, ocr, deep-learning, image-processing, auto-translation, machine-translation, pytorch-implementation, text-detection, text-detection-recognition, chinese-translation, japanese-translations, neural-network, inpainting, transformer
Last push: 2026-07-20T07:17:48+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 8, longevity 100
- inputs: {"age_days": 2022, "days_push": 44, "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 10345, forks 1053 (observed 2026-08-28T04:10:41.721398+00:00)

## What it is
A Python tool that automatically detects, OCRs, translates, inpaints, and re-typesets text in images, primarily for manga and comics. It runs as a CLI, batch processor, web UI, or API server and supports Japanese, Chinese, English, and 20+ other languages.

## Use cases
- translate manga pages automatically
- remove text from images and inpaint
- translate text inside screenshots
- batch translate webtoon chapters
- self-host an image translation API
- translate Japanese comics without knowing Japanese

## When to choose
- you need automated translation of text embedded in images, especially manga
- you want both text removal/inpainting and re-typesetting in one pipeline
- you need CLI, batch, web, or API deployment modes

## When to avoid
- you need professional-quality human translation
- you only need document OCR without translation
- you cannot run GPU/CPU-heavy deep learning models locally

## Facets
- artifact type: application
- maturity: active
- function: ocr, image-processing, machine-learning, deep-learning, nlp, cli, http-server
- domain: image-processing, computer-vision, media, deep-learning
- platform: python, cross-platform, cli
- tags: manga-translation, image-translation, text-detection, inpainting, machine-translation, comic-typesetting, webtoon, natural-language-processing, localization, docker, web-server, gpu

## Member repositories
- zyddnys/manga-image-translator (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:41.721398+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 2026-08-29T17:19:08.284120+00:00, confidence not recorded.
  - readme: https://github.com/zyddnys/manga-image-translator (fetched 2026-08-28T04:10:41.721398+00:00, sha e802f8012c14)
  - homepage: https://cotrans.touhou.ai/ (fetched 2026-08-29T08:18:27.920703+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.