Key Features

What you can do

One-Click Multimodal Translation

Uses multimodal AI to translate image-based comics by recognizing visual content and context for improved accuracy.

Per-Bubble Editing and Image Repair

Allows precise adjustments of text, styles, and background repairs on individual speech bubbles with manual annotation and brush tools, featuring real-time previews.

Bookshelf Management

Organizes books and chapters with features like progress saving, tagging, classification, and batch operations.

AI-Driven Comic Analysis

Provides story summaries, timelines, and intelligent Q&A on plots using a retrieval-augmented generation knowledge base.

Complete Translation Workflow

Supports the entire process from importing images or PDFs, text detection, translation, editing, to viewing and downloading results.