🤖 Model 🖼️
adirik/owlvit-base-patch32
Detect objects in an image using free-form text queries (zero-shot, open-vocabulary). Accepts an image and a comma-separ...
← Back to search
open-vocabulary AI Models
Found 4 models (showing 1-4)
🤖 Model 🖼️
zsxkib/yolo-world
Detect objects from arbitrary, user-defined categories in images and videos in real time. Takes an image or video plus a...
🤖 Model 🖼️
adirik/grounding-dino
Detect objects in images using natural language queries. Accepts an image and comma-separated text queries (category nam...
🤖 Model 🖼️
cudanexus/detic
Detect objects in images with open-vocabulary, zero-shot labels and return an annotated image and JSON detections. Accep...