Vidi model collection for multimodal video understanding and creation
AI & ML interests
None defined yet.
Recent Activity
spaces
7
pinned
Running
9
Web Bench Leaderboard
🥇
Duplicate this leaderboard to initialize your own!
Running
on
Zero
Featured
55
UMO OmniGen2
⚡
UMO based on OmniGen2
Running
on
Zero
24
UMO UNO
⚡
UMO based on UNO
Running
on
Zero
Featured
297
USO FLUX
⚡
Generate styled images from prompts and references
Runtime error
9
RealCustom
💥
General IP Customized Generation by ByteDance
Running
on
Zero
Featured
780
UNO FLUX
⚡
Generate customized images using text and multiple images
models
25
bytedance-research/Vidi1.5-9B
10B
•
Updated
•
9
•
5
bytedance-research/OneReward
Image-to-Image
•
Updated
•
56
bytedance-research/MammothModa2-Dev
15B
•
Updated
•
24
•
3
bytedance-research/ChatTS-8B
Text Generation
•
Updated
•
216
•
6
bytedance-research/Vidi-7B
9B
•
Updated
•
105
•
14
bytedance-research/Valley2.5
9B
•
Updated
•
21
•
5
bytedance-research/Valley-Eagle-7B
9B
•
Updated
•
19
•
41
bytedance-research/Valley2-DPO
9B
•
Updated
•
35
•
3
bytedance-research/RealCustom
Text-to-Image
•
Updated
•
10
bytedance-research/MammothModa2-Preview
14B
•
Updated
•
17
•
17
datasets
6
bytedance-research/veAgentBench
Viewer
•
Updated
•
145
•
64
•
3
bytedance-research/KIE-HVQA
Updated
•
123
•
5
bytedance-research/ToolHop
Updated
•
445
•
18
bytedance-research/UNO-1M
Updated
•
1.17k
•
24
bytedance-research/Web-Bench
Viewer
•
Updated
•
1k
•
267
•
8
bytedance-research/DeepHall-data
Updated
•
53
•
1