I think "generated" may be too strong a word for what this system seems to be doing. It feels more like it has found a bunch of averages among a large enough set of similar pictures of some fairly homogenous celebrities. When enough of those averages are put on a gradient along a particular axis you get transformations that seem magically smooth. In the example you gave I think it didn't have enough source photos along that axis. I'll further guess that this works best for celebrities that are generally considered attractive because attractive faces are already averages.

[1] https://www.ncbi.nlm.nih.gov/pubmed/15376799 "Images of faces manipulated to make their shapes closer to the average are perceived as more attractive."