It could also be interesting to define multiple subsets of sneakers - "2021 avant garde sneakers", "skate-inspired shoes", "2010s most popular shoes in the NBA" (based on https://ballershoesdb.com/ or a similar database). It could be cool to start with a model trained on a subset of sneakers, and tweak/combine things from there.
Not only do you both get muddy, but the pig wins with the benefit of experience