zlacker

The prompt "A shot of a 32-year-old female, up and coming conservationist in a jungle; athletic with short, curly hair and a warm smile" produced an impressive image. But I ran the same prompt 3 times on my laptop in just a few minutes, and got 3 almost-equally impressive images. (using stable diffusion and a free model called devlishphotorealism_sdxl15)

https://imgur.com/a/4otrN17

>>knodi1+(OP)
I agree, yours are practically identical in quality.

>>knodi1+(OP)
How are two completely different models from different groups, converging on what looks like the exact same person? Number 1 and 3 are eerily similar. I don't understand.

>>celest+p9
https://nonint.com/2023/06/10/the-it-in-ai-models-is-the-dat...

>>knodi1+(OP)
While they are similar in quality, your images have much more of the saturated and high contrast nature of AI generated images, and this is very noticeable to my eye.

>>celest+p9
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.

>>jeffbe+Nb
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.

>>celest+p9
Because the central limit theorem applies to web-trained image models.

>>passio+kb
That's an incredibly interesting observation. Thanks for sharing.

>>knodi1+(OP)
I really don't understand how they came up with the _exact_ same image. This goes against my previous understanding of how these technologies work, and would appear to lend credence to the "they just regurgitate training material" argument.

>>doctob+SW
Pretty sure they didn't come up with the same image. Images 1, 3, and 4 are the three images the GP generated and they put the Imagen-generated image (2) into the set for ease of comparison.

>>celest+p9
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.

>>jsnell+C31
Ok yes if that is the case then it makes much more sense.

>>jeffbe+Nb
>>38633910

>>jsnell+x41
Because imgur scrambled the order during upload. /facepalm