Florence2
Createdjkawamoto
Processes images using Florence-2 to extract text via OCR or generate descriptive captions.
About
Florence2 is an MCP server designed to process images and PDF files, whether stored locally or on a web server. It leverages Florence-2 to extract text from images using Optical Character Recognition (OCR) and generate descriptive captions summarizing the image content, offering powerful image understanding capabilities for various applications.
Key Features
- Generates descriptive captions for images
- Can process files from local storage or web servers
- Extracts text from images using OCR
- Supports processing images and PDF files
- 1 GitHub stars
Use Cases
- Automated text extraction from scanned documents
- Integrating image processing capabilities into other applications via MCP
- Image captioning for accessibility and content understanding
