Comic Translate
English | 한국어 | Français | 简体中文
Intro
Many Automatic Manga Translators exist. Very few properly support comics of other kinds in other languages.
This project was created to utilize the ability of State of the Art (SOTA) Large Language Models (LLMs) like GPT and translate comics from all over the world.
Currently, it supports translating comics from the following languages: English, Korean, Japanese, French, Simplified Chinese, Traditional Chinese, Russian, German, Dutch, Spanish and Italian. It can translate to the above mentioned and more.
The State of Machine Translation
For a couple dozen languages, the best Machine Translator is not Google Translate, Papago or even DeepL, but a SOTA LLM like GPT-4, and by far.
This is very apparent for distant language pairs (Korean<->English, Japanese<->English etc) where other translators still often devolve into gibberish.
Excerpt from “The Walking Practice”(보행 연습) by Dolki Min(돌기민)
Comic Samples
GPT-4 as Translator.
Note: Some of these also have Official English Translations
The Wretched of the High Seas
Journey to the West
The Wormworld Saga
Frieren: Beyond Journey’s End
Days of Sand
Player (OH Hyeon-Jun)
Carbon & Silicon
Installation
Download
-
Desktop App: Download and install Comic Translate for Windows and macOS from here.
Ignore Smart Screen for Windows (Click More info > Run anyway).
For macOS, after trying to open, go to Settings > Privacy and Security > Scroll down and click Open Anyway.
Note: GPU acceleration is currently only available when running from source.
-
Browser Extension: Install the Comic Translate extension for Chromium-based browsers (Chrome, Edge, Brave, etc.) here to read directly on websites.
From Source
Alternatively, if you’d like to run the source code directly.
Install Python 3.12. Tick “Add python.exe to PATH” during the setup.
https://www.python.org/downloads/
Install git
https://git-scm.com/
Install uv
https://docs.astral.sh/uv/getting-started/installation/
Then, in the command line
git clone https://github.com/ogkalu2/comic-translate
cd comic-translate
uv init --python 3.12
and install the requirements
uv add -r requirements.txt --compile-bytecode
To Update, run this in the comic-translate folder
git pull
uv init --python 3.12 (Note: only run this line if you did not use uv for the first time installation)
uv add -r requirements.txt --compile-bytecode
If you have an NVIDIA GPU, then it is recommended to run
uv pip install onnxruntime-gpu
Usage
In the comic-translate directory, run
uv run comic.py
This will launch the GUI
Tips
- CBR/RAR extraction requires a supported helper such as UnRAR, Unar, or 7-Zip. On Windows, install WinRAR or 7-Zip and add its folder (for example,
C:\Program Files\WinRAR) to PATH. On macOS, the desktop app automatically checks standard Homebrew and MacPorts locations when launched from Finder. If no supported extraction tool is available, you may get the error:
raise RarCannotExec("Cannot find working tool")
In that case, Instructions for Windows, Linux, Mac
- Make sure the selected Font supports characters of the target language
- v2.0 introduces a Manual Mode. When you run into issues with Automatic Mode (No text detected, Incorrect OCR, Insufficient Cleaning etc), you are now able to make corrections. Simply Undo the Image and toggle Manual Mode.
- In Automatic Mode, Once an Image has been processed, it is loaded in the Viewer or stored to be loaded on switch so you can keep reading in the app as the other Images are being translated.
- Ctrl + Mouse Wheel to Zoom otherwise Vertical Scrolling
- The Usual Trackpad Gestures work for viewing the Image
- Right, Left Keys to Navigate Between Images
How it works
Speech Bubble Detection and Text Segmentation
bubble-and-text-detector. RT-DETR-v2 model trained on 11k images of comics (Manga, Webtoons, Western).
Algorithmic segmentation based on the boxes provided from the detection model.
OCR
By Default:
Optional:
These can be used for any of the supported languages.
- Gemini 2.0 Flash
- Microsoft Azure Vision
Inpainting
To remove the segmented text
Translation
Currently, this supports using GPT-4.1, Claude-4.5,
Gemini-2.5.
All LLMs are fed the entire page text to aid translations.
There is also the Option to provide the Image itself for further context.
Text Rendering
Wrapped text in bounding boxes obtained from bubbles and text.
Acknowledgements
评论