How Generative AI Works to Produce Images

In a raw image presented in terms of pixels, there's a lot of redundancy. But with neural nets, it's possible to do much greater compression and preserve the meaning of an image without worrying about its precise details. As part of training a neural net not to associate images with captions, we can derive a kind of latent representation of images or an effective feature vector that captures the important features of the image. And then we can do everything we've discussed so far directly on this latent representation, decoding it only at the end into the actual pixel representation of the picture. That's basically the story of how the generative AI works to produce images.