🤖 Model 🎥
bytedance/sa2va-8b-video
Segment objects in videos from natural-language instructions. Takes a video and a text instruction (referring expression...
Found 2 models (showing 1-2)
Segment objects in videos from natural-language instructions. Takes a video and a text instruction (referring expression...
Segment objects in an image from text prompts and output masks. Accepts an image plus positive and negative mask prompts...