15
UGround
📱
Extract text from images using various OCR modes
Track points in a video
Upload an image and ask questions about it
Generate responses to video or image inputs
Tool to detect personality traits and automate HR-processes
Convert PDFs or images to Markdown with OCR
Visual Retrieval with ColPali and Vespa
Generate clickable coordinates on a screenshot
Demo for https://github.com/Byaidu/PDFMathTranslate
Controlling Computers with Small Models