Re:$10M AI Mathematical Olympiad Prize
by larodi on Monday November 27, 2023 @10:05AM
(#38433043)
Well this thing about fingers, etc in drawings. Lets put it this way - for us mere mortals the generative images look very much okay. To artists and people who actually draw something, well ... they very often spot inconsistencies in the whole production, including how fingers, arms, overall body posture, etc is presented. So it is exactly what we can expect - good enough on average, but actually a mediocre result of commonality. Thing is the wide audience chews in mediocrity all the time, and nobody seems to have been able to change this for ages...
[ Parent
| on HN ]
Re:$10M AI Mathematical Olympiad Prize
by disgruntledphd2 on Monday November 27, 2023 @10:28AM
(#38433373)
It's a weighted average over the prompts and data. Mediocrity is exactly what we'd expect from such an approach.
Now, if we end up seeing mastery, that would be extremely interesting.
> Mediocrity is exactly what we'd expect from such an approach.
No no, you see I prompted the AI with "masterpiece, photorealistic, 35 mm photography, cinematic, dslr, volumetric lighting, trending on artstation, 4k, 8k, hyper-detailed, epic digital painting by Greg Rutkowski" /s
This is a very mediocre understanding of deep learning :)
Re:$10M AI Mathematical Olympiad Prize
by disgruntledphd2 on Tuesday November 28, 2023 @04:29AM
(#38444032)
What else is it then? Basically all statistical models are weighted averages. I'm not sure why deep learning would be any different.
Re:$10M AI Mathematical Olympiad Prize
by Der_Einzige on Monday November 27, 2023 @11:56AM
(#38434711)
Using controlnet fixes all of these problems and makes it where even real artists won’t be able to tell AI art apart from real art.