Describe Anything
⚡
341
Describe masked parts of images
Describe Anything
Multimodal Large Language Models for Detailed Localized Image and Video Captioning
-
-
nvidia/DAM-3B
Image-Text-to-Text • Updated • 30.9k • 128 -
nvidia/DAM-3B-Video
Image-Text-to-Text • Updated • 3.19k • 57 -
nvidia/DAM-3B-Self-Contained
Image-Text-to-Text • Updated • 304 • 24 -
nvidia/describe-anything-dataset
Viewer • Updated • 916k • 7.8k • 55 -
nvidia/DLC-Bench
Viewer • Updated • 77 • 96 • 6 -
Describe Anything: Detailed Localized Image and Video Captioning
Paper • 2504.16072 • Published • 63