It is actually even worse, if you look at the lighting direction in the original granny picture, the seemingly only light source is the spark of the magic wand. To me this creates a sense of mystery, caution and tension, and it highlights that magic is the only tool to light the darkness.

Then in the sloppified version, they just blast the scene in lighting from the right for no reason. Their ai bot even subdues the light of the wand, making it look like a cheap prop. I also get the feeling that they change her gaze from looking at something to looking directly at the camera. So while the 2x5090 GPU slop might technically highlight more details, the entire artistic feeling just ends up with a grandma looking in a makeup mirror.

I quite like .ion or .iot

I feel like I met some recursive endgame boss… I made a penguapplepenguinpenguapplepenguapplepenguin partially from pineapples and penguins and something else I spam combined

This certainly could be part of the motivation for publishing it this way, to make themselves more noticed by the big players. Btw, publishing in open source nature is expensive, it’s like 6-8000 euro for the big ones, so there definitely is a reason.

While in not in the field either, I do know that it is quite unusual in computer science academics to publish in actual peer reviewed journals. This is because it can be a long process, and the field is very fast moving, so your results would be outdated by the time you publish. Thus, a paper is typically synonymous with a conference proceeding, and can be found on arxiv. I found this Paper on the arxiv from 2017/2018 which seems to be when this paper was originally published for the scientific community and presented at a very “good” (if I had to guess) conference. Google scholar says this paper has 650 citations, so it probably has had quite some impact. However, I would guess this method is well known and is already implemented in many models, if it was truly disruptive.