unum-cloud/uform-gen

Image-to-Text • 1B • Updated Dec 31, 2023 • 34 • 45

Note Popular Transformer for Caption Gen and Visual Question Answering. Trained on sbu_captions

BridgeTower/bridgetower-base

Updated Jan 27, 2023 • 4.21k • 9

Note Seems to be multi-modal

BridgeTower/bridgetower-large-itm-mlm-itc

Updated Mar 8, 2023 • 54.9k • 12

Note Maybe what we want too?

Salesforce/instructblip-vicuna-7b

Image-Text-to-Text • 8B • Updated Feb 3, 2025 • 10.2k • 102

Note This one looks promising for visual question answering