ihmily/doubao-nomark

What it solves

This project provides a way to extract images and videos from Doubao (and similar platforms like Dola and Qianwen) without watermarks. It solves the problem of needing to save media assets from chat conversations while avoiding the platform's default branding or watermarks.

How it works

The project functions as both a backend API service and a set of browser extensions. Users can provide a link to a Doubao conversation, and the service parses the content to return direct, clean URLs for the media files. It supports local deployment via Docker, Python, or as a library, and offers browser-based tools like Chrome extensions, Edge add-ons, and Tampermonkey scripts for direct interaction within the chat interface.

Who it’s for

It is for users who want to save high-quality, watermark-free images and videos from AI chat platforms for personal use or archiving. It is also useful for developers who want to integrate these extraction capabilities into their own Python applications.

Highlights

• Supports extraction of both images and videos from Doubao, Dola, and Qianwen.
• Offers multiple deployment options: Docker, local Python environment, or as a Python library.
• Includes user-friendly browser extensions for Chrome, Edge, and Tampermonkey for one-click extraction.
• Provides an interactive API documentation page for testing and integration.
• Automatically parses media from conversation links provided by the user.