TV2TV: A Unified Framework for Interleaved Language and Video Generation Paper • 2512.05103 • Published 13 days ago • 16
facebook/metaclip-2-worldwide-s16-384 Zero-Shot Image Classification • 0.4B • Updated 23 days ago • 153 • 2
facebook/metaclip-2-worldwide-b16-384 Zero-Shot Image Classification • 0.6B • Updated 23 days ago • 84 • 3
facebook/metaclip-2-worldwide-b32-384 Zero-Shot Image Classification • 0.6B • Updated 23 days ago • 108 • 3
facebook/metaclip-2-mt5-worldwide-s16 Zero-Shot Image Classification • 0.1B • Updated Nov 12 • 177 • 3
facebook/metaclip-2-mt5-worldwide-m16 Zero-Shot Image Classification • 0.2B • Updated Nov 12 • 55 • 3
facebook/metaclip-2-mt5-worldwide-b32 Zero-Shot Image Classification • 0.3B • Updated Nov 12 • 168 • 6
Meta CLIP Collection Scaling CLIP data with transparent training distribution from an end-to-end pipeline. • 7 items • Updated Jul 21 • 1
timm/vit_huge_patch14_clip_quickgelu_224.metaclip2_worldwide Image Classification • Updated Aug 1 • 46 • 1
timm/vit_gigantic_patch14_clip_224.metaclip2_worldwide Zero-Shot Image Classification • Updated Aug 1 • 259 • 1
facebook/metaclip-2-worldwide-huge-quickgelu Zero-Shot Image Classification • 2B • Updated Aug 18 • 11.6k • 14
facebook/metaclip-2-worldwide-giant-378 Zero-Shot Image Classification • 4B • Updated Aug 18 • 866 • 11