ByteDance/Sa2VA-4B
Image-Text-to-Text • Updated
• 98.6k • 96
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 • Updated • 1.27k • 65 -
ByteDance/Sa2VA-1B
Image-Text-to-Text • 1B • Updated • 862 • 29 -
ByteDance/Sa2VA-26B
Image-Text-to-Text • 26B • Updated • 81 • 31 -
ByteDance/Sa2VA-InternVL3-2B
Image-Text-to-Text • 2B • Updated • 267 • 1 -
ByteDance/Sa2VA-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 153 • 4 -
ByteDance/Sa2VA-InternVL3-14B
Image-Text-to-Text • 15B • Updated • 300 • 9 -
ByteDance/Sa2VA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 123 • 2 -
ByteDance/Sa2VA-Qwen2_5-VL-7B
Image-Text-to-Text • 9B • Updated • 147 • 4 -
ByteDance/Sa2VA-Qwen3-VL-4B
Image-Text-to-Text • 5B • Updated • 2.08k • 14
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Paper • 2501.04001 • Published • 47Note Techinical Report For Sa2VA.
-
ByteDance/Sa2VA-Qwen3-VL-2B
Image-Text-to-Text • 3B • Updated • 410 • 16