95
Describe Anything
⚡
Describe parts of images using text prompts
Describe Anything
Multimodal Large Language Models for Detailed Localized Image and Video Captioning
-
-
nvidia/DAM-3B
Image-Text-to-Text • Updated • 925 • 66 -
nvidia/DAM-3B-Video
Image-Text-to-Text • Updated • 280 • 37 -
nvidia/DAM-3B-Self-Contained
Image-Text-to-Text • Updated • 488 • 16 -
nvidia/describe-anything-dataset
Viewer • Updated • 916k • 2.73k • 18 -
nvidia/DLC-Bench
Viewer • Updated • 77 • 100 • 5 -
Describe Anything: Detailed Localized Image and Video Captioning
Paper • 2504.16072 • Published • 49