alt Hacker NewsI still use Midjourney, because all of these major players are so bad at stylistic and creative work. They're singularly focused on photorealism.
Replies
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 the opinionated vs user choice dynamic. When the opinions are good, they have a leg up
This is surprising. Is there a gallery of images that illustrates this?
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.
In my experience, MidJourney creates the best overall-looking images, but it's the worst at sticking to your prompt.