Florence 2 DocVQA is a Hugging Face Space that demonstrates Microsoft's Florence-2 vision-language model. Users upload document images and provide text prompts to receive detailed answers about the content. The interface showcases document visual question answering capabilities through an easy-to-use web demo.
Florence 2 is an AI & ML project. It focuses on extracting information and answering questions from document images without manual data entry. It is built as a consumer product for developers and researchers. Florence 2 is free to use. It runs on the web.
andito builds and maintains Florence 2, and it first shipped in 2024. Key capabilities include Image Upload, Document Q&A, and Visual Question Answering.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do