Florence 2
📉
829
Perform image captioning, detection, OCR and more with Florence‑2
Foundational Models
-
-
Florence2 + SAM2
🔥515Segment and caption objects in images and videos
-
SAM2 Video Predictor
🔥110Segment objects in a video with click‑based masks
-
SAM2 Video Predictor
🔥22Segment and track objects in videos
-
Zigeng/SlimSAM-uniform-77
Mask Generation • 9.72M • Updated • 4.1k • 32 -
LFM2 WebGPU – In-browser tool calling
🛠80In-browser tool calling, powered by Transformers.js