I haven't really kept up with what Midjourney has been doing the past year or two. While I liked the stylistic aspects of Midjourney, being able to use image examples to maintain stylistic consistency and character consistency is SO useful for creating any meaningful output. Have they done anything in that respect?
That is, it's nice to make a pretty stand-alone image, but without tools to maintain consistency and place them in context you can't make a project that is more than just one image, or one video, or a scattered and disconnected sequence of pieces.
That's because it's a two-way street, a multi-modal model that is highly proficient at real-life image generation is also highly proficient at interpreting real-life image input, which is something sorely needed for robotics.
This is a cultural flaw that predates image generation. Even PG has made statements on HN in the past equating “rendering skill” with the quality of art works. It’s a stand-in for the much more difficult task of understanding the work and value of culture making within the context of the society producing it.
Suppose the deck for Midjourney hit Paul Graham's desk, and the CEO was just an average Y Combinator CEO - so no previous success story. He would have never invested in Midjourney at seed stage (meaning before launch / before there were users) even if he were given the opportunity.
Better to read that particular story in the context of, "It would be very difficult to make a seed fund that is an index of all avant garde culture making because [whatever]."
