Something like mixup augmentation might work here as well for training - blend two SDFs and say "this is 20% A and 80% B".
Someone could also train a model that given some glyphs of a font predicts the rest of the glyphs. Then we can do weird things like give it glyphs from multiple fonts as input to make a hybrid font.
Someone could also train a model that given some glyphs of a font predicts the rest of the glyphs. Then we can do weird things like give it glyphs from multiple fonts as input to make a hybrid font.