Any-to-Any
•
0.4B
•
Updated
•
21
•
17
EPFL-VILAB/4M_tokenizers_rgb_16k_224-448
0.3B
•
Updated
•
257
•
4
EPFL-VILAB/4M_tokenizers_depth_8k_224-448
0.3B
•
Updated
•
1.43k
•
1
EPFL-VILAB/4M_tokenizers_normal_8k_224-448
0.3B
•
Updated
•
145
•
1
EPFL-VILAB/4M_tokenizers_semseg_4k_224-448
0.2B
•
Updated
•
74
•
1
EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448
0.2B
•
Updated
•
64
•
2
EPFL-VILAB/4M_tokenizers_edge_8k_224-512
0.2B
•
Updated
•
112
EPFL-VILAB/4M_tokenizers_sam-instance_1k_64
0.2B
•
Updated
•
66
•
1
EPFL-VILAB/4M_tokenizers_human-poses_1k_8
0.1B
•
Updated
•
12.1k
•
1
EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448
0.2B
•
Updated
•
72
•
1
EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448
0.2B
•
Updated
•
70
•
3
EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224
0.1B
•
Updated
•
20
•
1
EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224
0.1B
•
Updated
•
6
•
1