This was for general diffusion model outputs a few years ago, but a lot of the speculation of why the outputs are similar likely hold here

There are also only so many good data sets available for people to use to build image models, Phillip Isola, a professor at the MIT Computer Science & Artificial Intelligence Laboratory, told me, meaning the models might overlap in what they’re trained on. (One popular one, CelebA, features 200,000 labeled photos of celebrities. Another, LAION 5B, is an open-source option featuring 5.8 billion pairs of photos and text.)

[…]

Five years ago, he explained, image generators tended to create really blurry outputs. Researchers realized that it was the result of a mathematical fluke; the models were essentially averaging all the images they were trained on. Averaging, it turns out, “looks like blur.” It’s possible that, today, something similarly technical is happening with this generation of image models that leads them to plop out the same kind of dramatic, highly stylized imagery—but researchers haven’t quite figured it out yet. Additionally, “most models have an ‘aesthetic’ filter on both the input and output that reject images that don’t meet a certain aesthetic criteria,” Hany Farid, a professor at the UC Berkeley School of Information, told me over email. “This type of filtering on the input and output is almost certainly a big part of why AI-generated images all have a certain ethereal quality

[…]

The third theory revolves around the humans who use these tools. Some of these sophisticated models [this is not as sophisticated as the author is implying] incorporate human feedback; they learn as they go. This could be by taking in a signal, such as which photos are downloaded. Others, Isola explained, have trainers manually rate which photos they like and which ones they don’t. Perhaps this feedback is making its way into the model

[…]

This could be intentional: If such imagery has a market, maybe companies would begin to converge around it. Or it could be unintentional; companies do lots of manual work in their models to combat bias, for example, and various tweaks favoring one kind of imagery over another could inadvertently result in a particular look

https://archive.is/TlzVj