Koharu
ML-powered manga translator, written in Rust.
Getting Started · Docs · Bug reports · Discord
日本語 | 简体中文
Koharu introduces a local-first workflow for manga translation, utilizing the power of ML to automate the process. It combines the capabilities of object detection, OCR, inpainting, and LLMs to create a seamless translation experience.
Koharu runs its vision models and LLMs locally on your machine to keep your data private and secure.

Features
- Multi-format project management for raster images, archives, and PDFs with page sequencing
- Selective pipeline for detection, OCR, translation, and inpainting at page or project scope
- Detection and segmentation for panels, speech bubbles, text, and sound effects
- OCR for Japanese, Chinese, Korean, and English manga text
- Local GGUF inference and hosted providers for LLM translation, including ChatGPT and Grok sign-in
- Generative inpainting for source-text removal and artwork reconstruction
- Proofreading for correcting OCR and translation output
- GPU-based canvas for manual cleanup, text placement, and page composition
- Multilingual text shaping and layout with automatic fitting, font fallback, vertical CJK, and right-to-left text
- PNG, CBZ, and layered PSD export for flattened delivery and layered editing
- Agent-driven workflow with an MCP server for AI agents
Hardware Acceleration
Koharu supports CUDA on Windows and Linux, ROCm / HIP on x86-64 Windows and Linux, Metal on Apple silicon, and Vulkan on Windows and Linux out of the box. See Runtime and hardware requirements for model-specific guidance.
CUDA
CUDA 13.3 requires an NVIDIA Turing-class or newer GPU and an R610 or newer driver. Check NVIDIA’s official CUDA toolkit, driver, and architecture matrix and install the latest NVIDIA driver.
ROCm / HIP
ROCm 10.1 support depends on the exact AMD GPU, operating system, and driver combination. Check AMD’s official ROCm 10.1.0 compatibility matrix and install a compatible AMD driver.
Metal is available on Apple silicon Macs.
Vulkan
Vulkan is available on Windows and Linux as an alternative to CUDA and ROCm / HIP. With Vulkan, some models still fall back to the CPU, which is slower.
Machine Learning Models
Koharu uses separate models for detection, OCR, inpainting, and translation. Vision and inpainting and translation have separate model settings.
Computer Vision Models
Detection, OCR, and inpainting models are selected separately.
Detection and Layout
The detection model finds panels, speech bubbles, text, and sound effects, with a mask over each text’s glyphs.
OCR
OCR reads source text from detected regions.
Inpainting
Inpainting reconstructs the image behind source text before the translation is rendered.
Large Language Models
Translation can use a local language model or a remote API.
Translation Models
General-Purpose Local Models
- LFM3: lfm3-1.7b
- Gemma 4: gemma4-e2b-it, gemma4-e4b-it, gemma4-12b-it, gemma4-26b-a4b-it, gemma4-31b-it
- Qwen 3.5: qwen3.5-0.8b, qwen3.5-2b, qwen3.5-4b, qwen3.5-9b, qwen3.5-27b, qwen3.5-35b-a3b
- Qwen 3.6: qwen3.6-27b, qwen3.6-35b-a3b
- Qwen 3.8: qwen3.8-27b
Uncensored Local Models
Cloud Providers (BYOK)
Hosted LLM providers with an API key: OpenAI, Anthropic, Google Gemini, xAI, DeepSeek, MiniMax, and OpenRouter.
Subscriptions with sign-in: ChatGPT, and Grok with a SuperGrok or X Premium plan.
Self-Hosted Providers
Ollama and LM Studio, at their local addresses or a base URL you set, and one OpenAI-compatible endpoint at its base URL.
Installation
Download release builds from the releases page. Installation requirements and first launch vary by operating system.
Builds are available for Windows (x64), macOS (Apple silicon), and Linux (x86-64 and ARM64).
WinGet
Install on Windows with winget:
winget install koharu
Homebrew
Install on macOS with Homebrew:
brew install --cask koharu
Troubleshooting
Startup, runtime, model, and provider errors are covered in Troubleshooting. Koharu writes a log file of its INFO messages and above; its location is listed in Formats and data. Set RUST_LOG to debug or trace for verbose logs in a terminal:
# macOS / Linux
RUST_LOG=debug koharu
# Windows (PowerShell)
$env:RUST_LOG="debug"; koharu.exe
Development
Platform dependencies and validation commands for local builds are listed in Development Setup.
Prerequisites
- Rust 1.97.1 or later (Rust 2024 edition)
- Bun 1.3.14 or later
- LLVM 22.1.8 or later
Install dependencies
bun install
Development
bun dev
Build
bun run build
The executable is written to target/release.
If Koharu is useful in your workflow, consider sponsoring the project.

Contributors ❤️
Thanks to all the contributors who have helped make Koharu better!
License
Copyright 2025-2026 Mayo Takanashi and Koharu contributors.
Koharu is dual-licensed under the MIT License or the
Apache License, Version 2.0, at your option.
评论