No way this can be done in real time... at least in the near future and using the same technique :-)

Probably not for real-time, but not impossible as a filter. I would imagine it'll be more like Prisma, take your snap and let it chug for a few seconds to give you a pretty picture.

Prisma uses neural networks to learn the features, so it requires very hard training, but it leads to fast generation

I believe prisma uses Neural Style for most of its images, and that generally doesn't take too long to train IIRC

I'm just testing it and it takes ~1 minute per photo on a quad-core i7.

Yep, I later read the technique used by the OP, and is quite different compared to programs similar to this one, including mine, where a fixed set of shapes is evolved in order to find an optimal arrangement. This is a complex optimization problem that takes a lot of time. In the OP implementation old shapes are never re-arranged, just new ones are added in order to decrease the error. While the visual effect is still very interesting, you need more shapes this way to approximate the same level of details, and is in some way less interesting IMHO, at least conceptually, compared to "arrange N items to get the best result" which looks like a quasi-human task.