Of course it can. It's extremely new, and people are already creating fantastic results since it has been released literally just over two weeks ago.
The models, processes, and collective knowledge will just develop more over time to create MUCH better visuals, videos, and temporally coherent animations.
This is like a new form of art canvas, and we're all getting used to the basics of using the "paints" and "brushes" for it. In a few months/years, some of us will master the skill and produce fantastic artpieces.
But for know, the stunning stuff tends to be fantasy, sci-fi, impressionistic. Photos of people that are not a portrait are pretty often anatomically impossible. Getting hands, arms and stuff right seems quite difficult for these networks.
Funny enough, I've seen underwater pictures that to me looked quite believable, but to they expert are ridiculous. Lot's of impossible stuff going on. Human brains are ready to fill in a lot of detail.
Interesting. The results so far look pretty good, though only for fantasy and science fiction "fan art" style. That's why I was wondering whether the models are only trained from such inputs. If I understand you correctly, this is not the case and other styles of art can also be produced. Right?
Another question: Do the people who run the software claim copyright on the results even though these are (mostly) produced by the software? It sounds like that when you write "some us will [...] produce fantastic artpieces." I guess it's also legally the case but wonder whether that's also how people experimenting with it understand it.
As it takes a lot of iterations, curation and knowledge about how to best steer the systems, most users (rightfully) feel some sort of creativity and skill went into the works even if the AI did the pixels, except if you're really lucky and you get something amazing out of a simple prompt.. In the end, it's each to his own I guess. This will just be another tool in the toolbox of a digital creator.
Btw it simply isn't true that the AI generators are "only good for fantasy and sci-fi". I guess you've been seeing a biased selection. They can do pretty much anything. MidJourney is for sure more fine-tuned towards artsy stuff though.
The models, processes, and collective knowledge will just develop more over time to create MUCH better visuals, videos, and temporally coherent animations.
This is like a new form of art canvas, and we're all getting used to the basics of using the "paints" and "brushes" for it. In a few months/years, some of us will master the skill and produce fantastic artpieces.