google/vit-base-patch16-224
Image Classification β’ 86.6M β’ Updated
β’ 4.22M β’ β’ 940
Segment images using texts, points, or everything mode
Compare two faces and analyze facial attributes
Detect objects in images or videos
Segment and identify objects in images
State-of-the-art open-vocabulary image segmentation β‘οΈ
Generate object masks on images with SAM2
Maskless try-on directly in pixel space