mayocream/koharu
ML-powered manga translator, written in Rust. observed · 2026-08-28
Health v2 · maintenance only
82/100
- Activity 99
- Release rhythm 87
- Longevity 36
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 0.0
- age_days: 511
- days_rel: 7
- days_push: 7
- n_releases_24m: 219
Adoption not part of the score
5410 stars · 363 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
Koharu is a local-first desktop application that automates manga translation using machine learning, combining text/bubble detection, OCR, LLM-based translation, and generative inpainting in one pipeline. It is written in Rust with a Tauri/WebGPU editor for manual cleanup, typesetting, review, and PNG or layered PSD export.
Use cases
- translate manga pages from japanese to other languages
- remove original lettering from comic artwork with inpainting
- run ocr on manga speech bubbles locally
- typeset translated text with vertical cjk and rtl support
- export translated manga as png or layered psd
- batch translate a whole manga chapter or archive
- proofread and correct ocr and translation output
When to choose
- you want a fully local, privacy-preserving manga translation workflow with gpu acceleration
- you need an end-to-end pipeline from detection to typesetting and export in one app
- you want editable, reviewable output rather than an opaque one-shot conversion
- you need layered PSD export for further editing
When to avoid
- you need a headless server-side batch translation service
- you have no gpu and need fast inference (cpu fallback is slow)
- you only need plain text translation without image editing
- you require platforms beyond windows, linux, or apple-silicon macos
Facets
application · maturity active
machine-learning computer-vision ocr image-processing llm-inference gui internationalization machine-learning computer-vision image-processing desktop-applications windows rust manga-translation inpainting webgpu tauri local-first typesetting psd-export gguf natural-language-processing linux macos desktop gpu
10 sources
- readme: https://github.com/mayocream/koharu · fetched 2026-08-28 · adeea60b3423
- homepage: https://koharu.rs · fetched 2026-08-29 · 6ee3314b9db3
- site_page: https://koharu.rs/ja-JP/getting-started/first-project · fetched 2026-08-29 · e23221807ca1
- site_page: https://koharu.rs/getting-started/install · fetched 2026-08-29 · 67c58d439261
- site_page: https://koharu.rs/getting-started/first-project · fetched 2026-08-29 · f335439a0346
- site_page: https://koharu.rs/getting-started/runtime-models-and-hardware · fetched 2026-08-29 · 4490ca8d7f6c
- site_page: https://koharu.rs/ja-JP/getting-started/install · fetched 2026-08-29 · b8a7ad411fe5
- site_page: https://koharu.rs/ja-JP/getting-started/runtime-models-and-hardware · fetched 2026-08-29 · 37d35437c9d7
- site_page: https://koharu.rs/zh-CN/getting-started/install · fetched 2026-08-29 · e2cad0436d1b
- site_page: https://koharu.rs/zh-CN/getting-started/first-project · fetched 2026-08-29 · 0ef412ed437e
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| mayocream/koharu | main | 82 |
For agents
markdown · JSON · MCP: product_card(name="mayocream/koharu")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem