---
title: AI Manga Translator
emoji: 🈂️
colorFrom: gray
colorTo: pink
sdk: gradio
sdk_version: 6.0.1
app_file: app.py
pinned: false
license: apache-2.0
short_description: Translate Manga Images with PaddleOCR-VL-1.5
models:
  - PaddlePaddle/PaddleOCR-VL-1.5
---

# 📚 AI Manga Translator

**Powered by [PaddleOCR-VL-1.5](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5)** — a state-of-the-art 0.9B Vision-Language Model for text spotting and document parsing.

An intelligent tool that detects, recognizes, and translates text in manga/comic images end-to-end.

## Key Capabilities

- 🔍 **High-Precision OCR**: [PaddleOCR-VL-1.5](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5) accurately spots and recognizes text with bounding box coordinates, even in complex manga layouts.
- 🖌️ **Smart Text Replacement**: Automatically detects text bubbles, wipes them clean, and overlays translated text.
- 📖 **Manga-Optimized**: Handles vertical text and right-to-left reading order correctly.
- 🌏 **Multi-Language Translation**: Translates detected text into your preferred language (Chinese, English, French, etc.).

## Technologies

- **OCR Engine**: [PaddleOCR-VL-1.5](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5) — a 0.9B multi-task VLM achieving SOTA on OmniDocBench v1.5, with text spotting (localization + recognition) capabilities.
- **Translation**: ERNIE 4.5 (via OpenAI-compatible API)

## Setup

To run locally:
1. Install dependencies: `pip install -r requirements.txt`
2. Configure `.env` with your translation API credentials
3. Run `python app.py`