BAAI/seggpt-vit-large
0.4B • Updated
• 22.4k • 5
Vision Tasks
-
-
q-future/one-align
Zero-Shot Image Classification • Updated • 195k • 43 -
Qwen-VL Object-Detection
✨16Compare Qwen-VL models for object detection.
-
Joycaption Watermark Detection
🔥37Watermark detection
-
SAM3 VLM-FO1
👁39Complex text label dection using SAM3 with VLM-FO1
-
SnJake/Ref2Font
Text-to-Image • Updated • 105 • 33 -
facebook/DepthLM
Image-Text-to-Text • Updated • 108 • 36 -
DA-2
⚽47Official demo of DA^2: Depth Anything in Any Direction
-
DepthLM: Metric Depth From Vision Language Models
Paper • 2509.25413 • Published • 7