> Are these considered good capability examples?

No. Or at least not what I'd expect from one. Maybe if you hired a cheap artist. But I'm pretty sure a cheap artist would just take an existing scan.

Compared to other works?

Yeah. That's the context I'm judging under.

Though the more I'm playing with it the more I'm seeing weirdness.

I think we should be clear (and I wish even the research community would take this point to heart): research is not product development.

The two are related and research is on the early path to product development but one thing I hate is that papers are often evaluated as if they are products. Tons of papers aren't even about the demonstration, but the demonstration is just a good experimental platform. Like I've done some stuff where my focus was actually on information gain but the experiments are showing image generation. If we were to solely look at the output of the images we'd miss the point of the paper (that said, it is quite common for reviewers to do this too!). If we were developing products, then really all the best papers would be determined by who has the most compute as you can often just hyperparameter tune your way to the top of any benchmark (oh wait...). I mean others might, but that's not how I evaluate research and it's not something I want to promote because it is destructive to the progress of research. We'd never get anywhere if the new thing had to outperform the old thing on the first go (the old thing which has been studied in much more detail and benefited from a lot of optimizations).

So really, by "pretty good" I mean "looks like progress"