The issue with image models is that their style becomes identifiable and stale quite quickly, so you’ll need a fresh intake of different, newer, styles every so often and that’s going to be harder and harder to get.
Also Pixtral is not a text-to-image model.
Jonathan Ho, one of the authors of the CFG paper, now works for Ideogram, and Ideogram 2 is one of the very few models (or perhaps the only one) where I don't see the artifacts caused by the CFG, maybe he has achieved a breakthrough.
This is a not a diffusion model -- it doesn't create images, it answers questions.
The more and more platforms lock down access to their data, the harder it’ll be for models to stay up to date on art trends.
We just haven’t had image gen around long enough to witness a major style change like the skeuomorphic iPhone icons of old to the new modern flat ones.
If an artist born today develops their own style that takes the world by storm in 20years, the image generators of the time (for this thought experiment, imagine we’re using the same image gen techniques as today) would not know about it. They wouldn’t be able to replicate it until they get enough training data on that style.