Open Pose is a Large Vision Model (LVM) designed for real-time multi-person human pose detection in images and videos. It excels in detecting and mapping human body, hand, face, and foot keypoints—even in crowded scenes—without requiring special markers or suits.

Some other noteworthy features of Open Pose include robust multi-person tracking, support for 2D and 3D pose estimation, and the ability to process standard images or video streams from common cameras.

Metric	Value
Parameter Count	Unknown
Mixture of Experts	No
Context Length	Unknown
Multilingual	No
Quantized*	Yes
Precision*	FP8

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.