795
Florence 2
📉
Generate captions and analyze images with various tasks
Foundational Models
-
-
517
Florence2 + SAM2
🔥Segment and caption objects in images and videos
-
99
SAM2 Video Predictor
🔥Segment and track objects in a video
-
21
SAM2 Video Predictor
🔥Generate masks for objects in a video and propagate them across frames
-
Zigeng/SlimSAM-uniform-77
Mask Generation • 0.0B • Updated • 4.95k • 29 -
61
LFM2 WebGPU – In-browser tool calling
🛠In-browser tool calling, powered by Transformers.js