facebook/dinov3-vitl16-pretrain-lvd1689m Image Feature Extraction âĒ 0.3B âĒ Updated Aug 19, 2025 âĒ 228k âĒ 118
Running on Zero 36 EmbodiedGen Image To 3D ðž 36 Generate physically plausible 3D model from single image.
Running on Zero Featured 160 VibeVoice-Realtime-0.5B ðĻ 160 Generate natural-sounding speech from text
Running on Zero Featured 99 SAM3 Video Segmentation ð 99 Track and label objects in videos using text prompts or clicks