These are the models that we have used with our first version.
-
google/owlv2-base-patch16-ensemble
Zero-Shot Object Detection • Updated • 517k • 98 -
Qwen/Qwen1.5-0.5B-Chat
Text Generation • Updated • 440k • 79 -
Salesforce/blip-image-captioning-base
Image-to-Text • Updated • 2.61M • 683 -
facebook/sam-vit-base
Mask Generation • Updated • 619k • 136