koharu-models
| Crates.io | koharu-models |
| lib.rs | koharu-models |
| version | 0.10.1 |
| created_at | 2025-11-22 00:54:40.315741+00 |
| updated_at | 2025-11-25 10:59:45.958184+00 |
| description | Manga translation tools |
| homepage | https://koharu.rs |
| repository | https://github.com/mayocream/koharu |
| max_upload_size | |
| id | 1944568 |
| size | 154,443 |
Mayo Takanashi (mayocream)
documentation
README
Koharu
AI-powered manga translator, written in Rust.
Koharu introduces a new workflow for manga translation, utilizing the power of AI to automate the process. It combines the capabilities of object detection, OCR, inpainting, and LLMs to create a seamless translation experience.
Under the hood, Koharu uses ort and candle for high-performance inference, and uses Tauri for the GUI. All components are written in Rust, ensuring safety and speed.
[!NOTE] For help and support, please join our Discord server.
Features
- Automatic speech bubble detection and segmentation
- OCR for manga text recognition
- Inpainting to remove original text from images
- LLM-powered translation
- Vertical text layout for CJK languages
GPU acceleration
CUDA
Koharu is built with CUDA support, allowing it to leverage the power of NVIDIA GPUs for faster processing.
Koharu bundles CUDA toolkit 12 and cuDNN 9, so you don't need to install them separately. Just make sure you have the appropriate NVIDIA drivers installed on your system.
Metal
Koharu also supports Metal for GPU acceleration on macOS with Apple Silicon (M1, M2, etc.). This allows Koharu to run efficiently on a wide range of Apple devices.
Models
Koharu relies on a mixin of ONNX models and LLM models to perform various tasks.
ONNX models
Koharu uses several pre-trained models for different tasks:
The models will be automatically downloaded when you run Koharu for the first time.
We convert the original models to ONNX format for better performance and compatibility with Rust. The converted models are hosted on Hugging Face.
LLMs
Koharu supports various quantized LLMs in GGUF format via candle. Currently supported models include:
Installation
You can download the latest release of Koharu from the releases page.
We provide pre-built binaries for Windows and macOS, for other platforms, you may need to build from source, see the Development section below.
Development
Prerequisites
Install dependencies
bun install
Build
bun run build
The built binaries will be located in the target/release directory.
Sponsorship
If you find Koharu useful, consider sponsoring the project to support its development!
License
Koharu application is licensed under the GNU General Public License v3.0.
The sub-crates of Koharu are licensed under the Apache License 2.0.