The progress in this field is astonishing. It wasn't even a few years ago that the typical demonstration in a paper on GAN would have been an array of very small images. I recall often seeing numbers between 64x64 and 256x256. At the time, the argument was raised that the resolution can hardly be increased because it is our brain that tries to identify objects and faces in the photos to figure out what they are representing.

Then here we are, with indistinguishable 1024x1024 recreations and trippy latent space interpolations. I know not every researcher or entrepreneur has the resources of NVIDIA to train for this many days, but let's not forget, that part needs to occur only once. It makes me wonder about the day that a GAN manages to bankrupt stock photography services.