Cranking up the "legibility" I see plenty of perfectly respectable "x"s. Are you sure this is "not enough training data" rather than "actually, people writing quickly write pretty bad 'x's"?
[EDITED to add:] Ah, oops, I see. You were talking specifically about _capital_ X. You are right and I was wrong: the model produces disastrous capital Xs even at high legibility settings.
[EDITED to add:] Ah, oops, I see. You were talking specifically about _capital_ X. You are right and I was wrong: the model produces disastrous capital Xs even at high legibility settings.