Languages (MTL)
🇺🇸 English |
🇨🇳 简体中文 |
🇰🇷 한국어
Warning
Do not run this for production unless you know what you are doing (If you do not know what that is do not portforward this for other people)
Caution
This is in alpha testing bugs are to be expected if you have a problem make a Report including data from your console http://localhost:8000/console
- Download C++ Buildtools: https://visualstudio.microsoft.com/visual-cpp-build-tools/ (Make sure to select c++ buildtools)
- Download Latest Release: Latest Version
- 3: Cd inside
cd MangaAMTL - 4: Install dependencies
pip install -r requirements.txtor for cudapip install -r cudarequirements.txt - 5: Run the development server
python app.py
The application will start on: http://localhost:8000
- https://huggingface.co/Qwen/Qwen3.5-0.8B
- https://huggingface.co/sharky172/manga-light-colorizer/
- https://huggingface.co/Kirogii/Yolo-Manga_Textbox-Region_Detect/
- https://huggingface.co/zai-org/GLM-OCR
- https://www.soundjay.com/page-flip-sounds-1.html (Sound: Page Flip Sound Effect 2)
- Run
apt install wget - Run
wget https://raw.githubusercontent.com/Kirogii/MangaAMTL/refs/heads/main/Ubuntu.sh - Run
chmod +x Ubuntu.sh - Run
./Ubuntu.sh
- Multi language translation from source support (Chinese,Korean,Japanese,Russian,Indonesian,English)
- Model selection (You can install/add new models without much effort GGUF ONLY)
- Colorizing Support
- Llama-Cpp-Python erroring (ON Cuda version): Install: https://developer.nvidia.com/cuda-downloads (Then rerun the install command from above)
- Cuda not being set on ocr/ai:
pip install torch==2.9.1 torchvision==0.24.1 torchaudio==2.9.1 --index-url https://download.pytorch.org/whl/cu126

