I've Hunted several of those "X Does Not Exist" AI creations in the past that use GAN. This is NOT One of Those. This Hunt is more about creativity. I'm generally a very creative person and I see a lot of people struggling with creativity by being too "in the box". This is a potential remedy for that:

This project tries to find ways to score the plausibility of different types of associations. This specific dataset deals with various types of computer generated snacks of different kinds. We built a simple crawler to find interesting snack ingredients, and run our algorithm on them to see if they can work as snacks based (in part) on marketability, human preference, similarity to other snacks, linguistics and some other factors.

Few Examples

Plausibility Score