I think what you're uncovering is an interesting property of these models to do something like a soft semantic search for images: you *almost* asked for a particular painting, and it *almost* gave you back that painting.
It'll be interesting to see these models being augmented with explicit retrieval capabilities. People might want to seamlessly switch between retrieving existing images (e.g. stock photos) and creating new ones, especially in the brainstorming phase of a more elaborate design workflow. Similarly to how LaMDA generates language, but also retrieves evidence.
Very creative experiments! Your article made me wonder whether Midjourney memorizes its training set, i.e. if it can produce these paintings when explicitly prompted with the name and author of the painting. And it does so reasonably, see what it produces for "The Starry Night by Vincent van Gogh": https://media.discordapp.net/attachments/998046753087553546/1002635924175335574/prinnori_The_Starry_Night_by_Vincent_van_Gogh_8fd81eef-1f44-43c9-b1c1-dc411bd22ffc.png
I think what you're uncovering is an interesting property of these models to do something like a soft semantic search for images: you *almost* asked for a particular painting, and it *almost* gave you back that painting.
It'll be interesting to see these models being augmented with explicit retrieval capabilities. People might want to seamlessly switch between retrieving existing images (e.g. stock photos) and creating new ones, especially in the brainstorming phase of a more elaborate design workflow. Similarly to how LaMDA generates language, but also retrieves evidence.