Hacker News Reader

https://nonint.com/2023/06/10/the-it-in-ai-models-is-the-dat...

That's an incredibly interesting observation. Thanks for sharing.

It's because the only thing these models can do is rip off existing images, and the prompt is very specific.

"Generative AI" is a learned, lossy compression codec. You should not be surprised that the range of outputs for a given input seems limited.

That makes sense - but in Google's case, I'd expect them to have access to private datasets that would give it something different than public models like SD.

https://news.ycombinator.com/item?id=38633910

I think you might be misunderstanding. The GP did three runs using one model, each with the same prompt that was used for the Imagen demo image. The outputs are images 1, 3 and 4. Hence the similarity.

Because imgur scrambled the order during upload. /facepalm

Because the central limit theorem applies to web-trained image models.