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 would be to plot all the training pictures in the kernel space of the autoencoder and match the closest one to the generated picture.