# hgmzhn/manga-translator-ui

基于manga-image-translator 实现的开源漫画AI翻译桌面工具。支持日、韩、英文漫画自动处理，集成OpenAl、Gemini等多翻译引擎；实现OCR文字检测、原文擦除、AI翻译、图像修复、译文排版完整链路，自带可视化编辑器，支持自定义文本样式，一键部署开箱即用。

Repository: https://github.com/hgmzhn/manga-translator-ui
Canonical: https://ross.abutalabs.com/products/manga-translator-ui
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: automated-translation, comic-translation, gemini, image-translator, machine-translation, ocr, openai, python, scanlation, manga-translato
Last push: 2026-08-26T20:06:18+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 26
- inputs: {"age_days": 368, "days_push": 7, "days_rel": 14, "gap_med": 1.0, "n_releases_24m": 75}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2651, forks 127 (observed 2026-08-28T04:07:07.048189+00:00)

## What it is
A desktop GUI application built on manga-image-translator that automatically translates text in manga/comic images across Japanese, Korean, and English. It provides a full pipeline of text detection, OCR, AI translation (OpenAI, Gemini, and more), text erasure, image inpainting, and typesetting, with a built-in rich-text visual editor.

## Use cases
- translate manga pages from japanese to chinese automatically
- erase original text from comic images and re-typeset translations
- batch translate korean webtoons with AI
- edit translated text styles in a visual editor
- scanlation tooling for fan translations
- ocr japanese text from manga bubbles

## When to choose
- you want a one-click, out-of-the-box desktop manga translation tool with a GUI
- you need the full detect-OCR-translate-erase-typeset pipeline in one app
- you want to fine-tune translated text placement and styling visually
- you prefer multiple translation engines including OpenAI and Gemini

## When to avoid
- you need a headless CLI or server-side batch API rather than a desktop app
- you only need raw OCR without translation or typesetting
- you require languages outside Japanese, Korean, and English
- you cannot run local ML models or lack API keys for cloud translation engines

## Facets
- artifact type: application
- maturity: active
- function: ocr, machine-learning, image-processing, gui, nlp
- domain: image-processing, media, developer-tools
- platform: cross-platform, python
- tags: manga-translation, scanlation, comic-translation, image-inpainting, text-eraser, typesetting, visual-editor, openai, gemini, paddleocr, manga-ocr, natural-language-processing, desktop

## Member repositories
- hgmzhn/manga-translator-ui (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:07.048189+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 2026-08-30T02:18:42.053337+00:00, confidence not recorded.
  - readme: https://github.com/hgmzhn/manga-translator-ui (fetched 2026-08-28T04:07:07.048189+00:00, sha 78225658d9f3)
- Data as of 2026-08-30T08:39:29.467469+00:00.