These are the models that we have used with our first version.
-
google/owlv2-base-patch16-ensemble
Zero-Shot Object Detection • Updated • 608k • 97 -
Qwen/Qwen1.5-0.5B-Chat
Text Generation • Updated • 474k • • 79 -
Salesforce/blip-image-captioning-base
Image-to-Text • Updated • 4.5M • • 668 -
facebook/sam-vit-base
Mask Generation • Updated • 695k • 135