I don't understand how you went from video 1 to video 2
Using the tracking from the first video I'm going to place lip sync faces, like in the second video, on the blockhead's face. In the second video the characters are only able to stand still without lots of different frames and stuff, but with tracking I can have the faces change and the characters move at the same time.
You're going to make loads of videos using this right
At least a few. Just gotta think of what to make.