Huggingace Model Zoo For Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos By Bytedance Seed CV Research
ByteDance
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs
MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation
spaces
12
pinned
Running
on
Zero
1.09k
InfiniteYou-FLUX
📸
Flexible Photo Recrafting While Preserving Your Identity
pinned
Runtime error
26
ID-Patch
📸
Robust ID Association for Group Photo Personalization.
pinned
Running
on
Zero
92
MegaTTS3 Demo
👋
Running
on
Zero
24
XVerse
🖼
Online demo for XVerse
Running
on
Zero
596
DreamO
🐨
A Unified Framework for Image Customization
Running
on
Zero
76
Dolphin
🦀
Dolphin Demo
models
39
ByteDance/Sa2VA-Qwen3-VL-4B
Image-Text-to-Text
•
5B
•
Updated
•
13
•
4
ByteDance/Dolphin-1.5
Image-Text-to-Text
•
0.4B
•
Updated
•
53
•
7
ByteDance/FaceCLIP
Text-to-Image
•
Updated
•
73
ByteDance/Sa2VA-InternVL3-14B
Image-Text-to-Text
•
15B
•
Updated
•
50
•
8
ByteDance/Sa2VA-Qwen2_5-VL-7B
Image-Text-to-Text
•
9B
•
Updated
•
25
•
1
ByteDance/Sa2VA-InternVL3-8B
Image-Text-to-Text
•
8B
•
Updated
•
52
•
3
ByteDance/Sa2VA-Qwen2_5-VL-3B
Image-Text-to-Text
•
4B
•
Updated
•
60
•
1
ByteDance/Sa2VA-InternVL3-2B
Image-Text-to-Text
•
2B
•
Updated
•
175
•
1
ByteDance/lynx
Image-to-Video
•
Updated
•
•
134
ByteDance/Sa2VA-26B
Image-Text-to-Text
•
26B
•
Updated
•
36
•
31
datasets
8
ByteDance/veAgentBench
Updated
•
48
•
1
ByteDance/AncientDoc
Viewer
•
Updated
•
3.44k
•
305
•
2
ByteDance/Attention2Probability
Preview
•
Updated
•
44
ByteDance/WildDoc
Viewer
•
Updated
•
35.8k
•
204
•
22
ByteDance/CloudTimeSeriesData
Viewer
•
Updated
•
11.5M
•
23
ByteDance/FullStackBench
Viewer
•
Updated
•
3.37k
•
100
•
20
ByteDance/ComTQA
Viewer
•
Updated
•
9.07k
•
25
•
19
ByteDance/MTVQA
Viewer
•
Updated
•
8.79k
•
330
•
38