zf-kbot/manga-translator

An advanced, automated pipeline for translating manga and comics. This project integrates state-of-the-art Computer Vision and NLP models to perform detection, recognition, translation, and typesetting in a single seamless process.

Public

79 runs

Playground API Examples README Versions

Run zf-kbot/manga-translator with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
source_lan	None	ja	Source language (Auto-selects the best OCR engine: MangaOCR for JA, Paddle for ZH/KO, EasyOCR for others)
target_lan	None	zh-CN	Target language for translation
translator	None	google	Translation Engine: 'google' (Free/Fast) or 'llm' (High Quality, requires API Key)
image	string		Input image file
openai_model	string	gpt-4o	LLM Model Name. (e.g., 'gpt-4o', 'deepseek-chat', 'moonshot-v1-8k')
openai_api_key	string		LLM API Key. Required if 'translator' is set to 'llm'. Supports OpenAI, DeepSeek, Moonshot, etc.
openai_base_url	string	https://api.openai.com/v1	LLM Base URL. Optional. Change this if using non-OpenAI models (e.g., 'https://api.deepseek.com')

{
  "type": "object",
  "title": "Input",
  "required": [
    "image"
  ],
  "properties": {
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "description": "Input image file"
    },
    "source_lan": {
      "enum": [
        "ja",
        "zh",
        "ko",
        "en",
        "fr",
        "de"
      ],
      "type": "string",
      "title": "source_lan",
      "description": "Source language (Auto-selects the best OCR engine: MangaOCR for JA, Paddle for ZH/KO, EasyOCR for others)",
      "default": "ja",
      "x-order": 1
    },
    "target_lan": {
      "enum": [
        "zh-CN",
        "zh-TW",
        "en",
        "ja",
        "ko",
        "fr",
        "de",
        "es",
        "it"
      ],
      "type": "string",
      "title": "target_lan",
      "description": "Target language for translation",
      "default": "zh-CN",
      "x-order": 2
    },
    "translator": {
      "enum": [
        "google",
        "llm"
      ],
      "type": "string",
      "title": "translator",
      "description": "Translation Engine: 'google' (Free/Fast) or 'llm' (High Quality, requires API Key)",
      "default": "google",
      "x-order": 3
    },
    "openai_model": {
      "type": "string",
      "title": "Openai Model",
      "default": "gpt-4o",
      "description": "LLM Model Name. (e.g., 'gpt-4o', 'deepseek-chat', 'moonshot-v1-8k')"
    },
    "openai_api_key": {
      "type": "string",
      "title": "Openai Api Key",
      "format": "password",
      "nullable": true,
      "writeOnly": true,
      "description": "LLM API Key. Required if 'translator' is set to 'llm'. Supports OpenAI, DeepSeek, Moonshot, etc.",
      "x-cog-secret": true
    },
    "openai_base_url": {
      "type": "string",
      "title": "Openai Base Url",
      "default": "https://api.openai.com/v1",
      "description": "LLM Base URL. Optional. Change this if using non-OpenAI models (e.g., 'https://api.deepseek.com')"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}