Use a GAN to generate images based on a set of paintings

Status: Closed
Prize: €140
Entries Received: 11
Winner: bsse1009

Winner

Contest Brief

I am an art collector. I want to use generative adversarial network or similar process to generate images based on my existing paintings. There would be a data set of approximately 250 representational paintings.
If possible I want the network to generate a digital twin (or sibling) for each artwork which is similar to the original but processed based on all teh other artworks in the collection.
I want to use these digital twins for building NFTs. Thus the twins should all have a similar style.
And I want to be able to add more artworks (images of them) to the network later on.
I want to run teh application in the cloud (google, amazon, Azur...).