Human Pose Estimation runs with either a single-pose or multi-pose detection algorithm. The single person pose detector is faster and more accurate but requires only one subject present in the image.
Its ideal use case is, when there is only one person centered in an input image or video. The disadvantage is that if there are multiple persons in an image, keypoints from both persons will get conflated by the algorithm.
The output stride and input resolution have the largest effects on accuracy/speed. A higher output stride results in lower accuracy but higher speed. A higher image scale factor results in higher accuracy but lower speed.