Salesforce/blip-image-captioning-large
Image-to-Text • 0.5B • Updated • 1.4M • 1.47k
Vision-Language Collections
Some of the popular models for image-text domain
-
-
Salesforce/blip-image-captioning-base
Image-to-Text • Updated • 2.15M • 849 -
Salesforce/instructblip-vicuna-7b
Image-Text-to-Text • 8B • Updated • 11.3k • 99 -
microsoft/git-large-coco
Image-to-Text • 0.4B • Updated • 5.03k • 105 -
Salesforce/blip2-opt-2.7b
Image-Text-to-Text • 4B • Updated • 428k • 438 -
Salesforce/blip2-flan-t5-xxl
Image-Text-to-Text • 12B • Updated • 1.28k • 94 -
Salesforce/instructblip-flan-t5-xxl
Image-Text-to-Text • 12B • Updated • 635 • 21 -
Salesforce/instructblip-flan-t5-xl
Image-Text-to-Text • Updated • 10.5k • 30 -
microsoft/trocr-base-handwritten
Image-to-Text • 0.3B • Updated • 151k • 490 -
microsoft/trocr-base-printed
Image-to-Text • 0.3B • Updated • 780k • 205 -
microsoft/trocr-large-printed
Image-to-Text • 0.6B • Updated • 311k • 179 -
microsoft/trocr-small-printed
Image-to-Text • 61.4M • Updated • 26.9k • 48 -
microsoft/trocr-large-handwritten
Image-to-Text • Updated • 254k • 158 -
google/pix2struct-large
Image-to-Text • 1B • Updated • 1.18k • 34