Anything we can provide is just a drop in the ocean of data they already have. Plus, this was how image generation worked before we got diffusion models (see “generative adversarial networks”) and they never reached the level of image quality that diffusion models did.
Huh? GANs, even ones like thispersondoesnotexist are way better than SDXL, they’re just hyper-narrow in focus usually, whereas SD can do just about anything
Devil’s advocate: Why would we want to give AI image generators free hueristics to help them make themselves less detectable?
Anything we can provide is just a drop in the ocean of data they already have. Plus, this was how image generation worked before we got diffusion models (see “generative adversarial networks”) and they never reached the level of image quality that diffusion models did.
Huh? GANs, even ones like thispersondoesnotexist are way better than SDXL, they’re just hyper-narrow in focus usually, whereas SD can do just about anything
If only it were that simple to train something into an AI.