I decided to see how an image-to-text generator (CLIP Interrogator 2.4) paired with a text-to-image generator (Stable Diffusion 2.1) performed at recreating some of the great historical art. I gathered 68 pieces of art from a variety of styles, movements, and artists that are all considered great works of art. I do not claim, however, that this selection is comprehensive. I then submitted the art to CLIP Interrogator 2.4. If the prompt contained the exact name of the artwork, I modified the prompt to exclude it, but I did not exclude the names of artists. I then submitted these prompts to Stable Diffusion 2.1 and accepted the first output.
Here are the results (in no particular order).
Prompts were generated using CLIP Interrogator 2.4.
Illustrations were drawn using Stable Diffusion 2.1.