yeah

although I guess it's that the author used the same context with the original generated image and thus it just reused that icon+text thing

but in general, these models do seem to be kind of just go for an information-dump type of style where its just listing everything and putting as much stuff in that is associated with the words, which is what these LLMs do

so you'd probably need to steer them heavily with explicit instructions on what to do and how to get rid of it, which I'd bet nobody will actually do when making these posters