# dmMaze/BallonsTranslator

深度学习辅助漫画翻译工具, 支持一键机翻和简单的图像/文本编辑 | Yet another computer-aided comic/manga translation tool powered by deeplearning

Repository: https://github.com/dmMaze/BallonsTranslator
Canonical: https://ross.abutalabs.com/products/ballonstranslator
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: comics, computer-aided-translation, deep-learning, manga, ocr, scene-text-detection, inpainting, pytorch, computer-vision, auto-translation, chinese-translation, qt, qt6, pyqt, pyqt6
Last push: 2026-08-26T16:51:05+00:00

## Health v2 (maintenance only)
Score: 99/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 100
- inputs: {"age_days": 1607, "days_push": 7, "days_rel": 13, "gap_med": 5.0, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5065, forks 346 (observed 2026-08-28T04:09:09.262364+00:00)

## What it is
A desktop GUI application that uses deep learning to automatically translate comics and manga, combining text detection, OCR, inpainting, and machine translation with one-click operation. It includes image and rich-text editing tools for refining translations, plus LLM-based translation with context history and glossaries.

## Use cases
- translate manga pages automatically with one click
- erase original text from comic speech bubbles and inpaint the background
- machine translate Japanese or English comics into Chinese
- edit translated text with rich text formatting and font presets
- translate webtoons with consistent character names using an LLM glossary
- export translated comics to Word documents

## When to choose
- you need to translate manga/comics with automatic text detection, OCR, and text removal in one tool
- you want a GUI with image inpainting and rich-text editing to polish machine translations
- you want LLM translation with translation history and reusable glossaries for consistent terminology

## When to avoid
- you need production-grade professional translation without human review
- you only need plain document or subtitle translation rather than image-based comics
- you cannot run GPU-accelerated deep learning models locally or lack the required resources

## Facets
- artifact type: application
- maturity: active
- function: ocr, image-processing, machine-learning, computer-vision, llm-inference, gui
- domain: image-processing, computer-vision
- platform: windows, python
- tags: manga-translation, comic-translation, text-inpainting, scene-text-detection, machine-translation, pyqt6, webtoon, natural-language-processing, localization, macos, linux, desktop, gpu

## Member repositories
- dmMaze/BallonsTranslator (main) score 99

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:09.262364+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 2026-08-29T18:17:18.110313+00:00, confidence not recorded.
  - readme: https://github.com/dmMaze/BallonsTranslator (fetched 2026-08-28T04:09:09.262364+00:00, sha 3f30623cdb1c)
- Data as of 2026-08-30T08:39:29.467469+00:00.