The middle video was a post made by me n ü recorded near where I was living in Canada.

The other two videos show the outputs of a comfyUI workflow that extracted the poses of the source video with open pose and then used that as the driving material for the final outputs.

The final videos were generated using Wan2.1

It was interesting to see how many errors there was in the pose extraction (Limbs appearing and disappearing) to then see how flawless the final poses were.

From a single driving video, unlimited final videos could be created and synchronised with BPM