[CSactuary]

To the creator: since most (all?) of the beetles are symmetrical, couldn’t you generate left halves and then reflect it to create the right half? This could help you prevent asymmetric generations

[dan-robertson]

Most of the images have lighting which isn’t symmetrical and I think that makes it pretty obvious when an image is made by mirroring half a beetle.

But maybe there’s some way to deal with that.

[erikpukinskis]

Naively, you could train another network to correct the lighting on a mirrored beetle.

Although I’m sure there’s a smarter way.

[lopmotr]

The network should just learn that they all have symmetry and only encode the unique information. Once you start hand-coding priors like this, where do you stop? Maybe also constrain the range of colors? Size? Other geometric features? Eventually you're just doing old fashioned programming, not ML. And since generating beetle images isn't really the important goal anyway, why would you use dirty tricks to achieve it?