google/vit-base-patch16-224
Image Classification β’ 86.6M β’ Updated β’ 5.78M β’ β’ 980
Segment images using texts, points, or everything mode
Compare two faces to verify identity
Detect objects in images or videos
Segment and identify objects in images
State-of-the-art open-vocabulary image segmentation β‘οΈ
Segment images with prompts or automatic masks
Maskless try-on directly in pixel space