Tag: computer-vision
Screenshot to Structured Data Extraction
Extracts text, UI layouts, tables, and charts from screenshots into structured JSON format. The service supports multiple extraction modes and is payable via x402 on the Base network.
AI image super-resolution upscaling tool
This tool provides AI-powered super-resolution upscaling (2x, 3x, or 4x) for images using Real-ESRGAN. It accepts image URLs or base64 data and returns the enhanced image via a dedicated API endpoint.
Unity Camera Screenshot Tool
Captures a screenshot from a specified Unity camera and returns the image directly. It supports custom dimensions and targeting specific GameObjects via hierarchy paths or instance IDs.
AI-powered browser automation and extraction
An AI-driven engine that uses LLMs and computer vision to automate web workflows, extract structured data, and manage browser sessions. It integrates via Python and TypeScript SDKs, a REST API, and an MCP server.