Hacker News Reader

They could just ask a designer to do a few bespoke illustrations, then generate synthetic data from that, right? Have an image model generate a set of variations, then convert them to SVG.

But looking at these images, Google clearly hasn’t done that yet.

View on HN

Yeah, the dedicated image generators can produce really good pelicans riding bicycles now, and you could trace one of those into a vector SVG as training data.

I don't think it would be worth it though, it would be pretty obvious you had cheated on my benchmark when it drew a perfect pelican riding a bicycle and then failed at a flamingo on a unicycle.

Reply on news.ycombinator.com