This MCP server implementation provides a bridge to Florence-2, a powerful image processing model. Developed by Junpei Kawamoto, it enables AI assistants to perform advanced image analysis and manipulation tasks. The server utilizes PyTorch and Hugging Face's Transformers library to leverage Florence-2's capabilities. It's designed for seamless integration into existing AI workflows, making it particularly useful for applications requiring sophisticated image understanding, such as visual question answering, image captioning, or content-based image retrieval. The implementation focuses on efficient processing and easy deployment, with support for various Python environments and package management systems.
まだレビューはありません. 最初のレビューを投稿しましょう！
会話に参加するにはサインインしてください
Extracts all visible text from images or multi-page PDF documents. Parameters: src (string) - Local file path or HTTP/HTTPS URL of an image or PDF file.
Generates comprehensive, detailed captions describing what is depicted in the image. Parameters: src (string) - Local file path or HTTP/HTTPS URL of an image or PDF file.
Executes custom Florence-2 task prompts directly against the input image or PDF for advanced computer vision workflows. Parameters: src (string) - Local file path or HTTP/HTTPS URL of an image or PDF file; prompt (string) - Task prompt specifying the operation to perform.
