So a few things : 1 - what is art to the viewer, honestly you can hand craft slop and I don't want to see it, here it's the meaning you get the story you the viewer make from it 2 - AI art is bad in two ways in my experience, the story (ie see one) has something critically wrong from the human world, and two most tools today don't listen to the prompt so no matter how much writting is fed in the result is limited. But if you use it as a tool yes it can make some backgrounds and clip art.. The problem is most consumer systems don't have a good way to put this into a proper editor to finalize a meaningful image.. IE put the human story into the final thing.

But the real point isn't you made some clipart with image get or a paragraph in your story it's why it didn't fit in, contradictions it shows and do you the human know how to fix it? Is there tooling you can direct the llm to do better? (For images there really is not it is not good at partial edits in my experience.. Easier to have it generate all parts on their own and layer the final product otherwise something will be wrong)