nvidia/LocateAnything-3B
Image-Text-to-Text • 4B • Updated • 14 • 96
Generate realistic person images with new clothes or poses
Answer math questions from uploaded images or sketches
Easily expand image boundaries
Generate depth maps from images
Generate normal maps from images
Generate customized images from text and reference photos
Convert text to natural-sounding speech audio
Generate normal maps from images and videos
Create HD cutouts from any image with just a prompt
Segment body parts in images
Generate responses from text and images