Is this really generating anything new or is it essentially just morphing between existing photos that it's been trained on? It would be interesting to take some of these GAN demos and write a utility where for each output, have it find the closest-matching training input, and see how similar it is.
Typically these animations that look like morphings are generated by auto-encoders. Contrary to automatically generated morphings, you'll notice that all intermediate person is realistic. I don't think GAN work that way (I haven't followed it last year though). My understanding is that a GAN simply tries to determine if an image is generated or authentic. I suppose they used one there. One way to do what you propose…
The intermediates are not realistic. There are many artifacts and they are obscured by the small, lossy video.