ByteDance/Sa2VA-4B
Image-Text-to-Text
•
4B
•
Updated
•
176k
•
•
84
Sa2VA Model Zoo
Huggingace Model Zoo For Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos By Bytedance Seed CV Research
-
-
ByteDance/Sa2VA-8B
Image-Text-to-Text • 8B • Updated • 798 • 63 -
ByteDance/Sa2VA-1B
Image-Text-to-Text • 1B • Updated • 402 • 27 -
ByteDance/Sa2VA-26B
Image-Text-to-Text • 26B • Updated • 63 • 31 -
ByteDance/Sa2VA-InternVL3-2B
Image-Text-to-Text • 2B • Updated • 209 • 1 -
ByteDance/Sa2VA-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 95 • 3 -
ByteDance/Sa2VA-InternVL3-14B
Image-Text-to-Text • 15B • Updated • 111 • 9 -
ByteDance/Sa2VA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 457 • 1 -
ByteDance/Sa2VA-Qwen2_5-VL-7B
Image-Text-to-Text • 9B • Updated • 264 • 2 -
ByteDance/Sa2VA-Qwen3-VL-4B
Image-Text-to-Text • 5B • Updated • 99 • 6
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Paper • 2501.04001 • Published • 47Note Techinical Report For Sa2VA.