UGround
📱
16
Extract text and formatted data from images with OCR
Track points in a video
Describe image contents with prompts
Answer questions about uploaded videos or images
Embedded MinerU document extraction demo
Visual Retrieval with ColPali and Vespa
Generate clickable coordinates on a screenshot
Demo for https://github.com/Byaidu/PDFMathTranslate
Controlling Computers with Small Models
Generate code snippets from plain text