2 Comments
User's avatar
vincent huang's avatar

this makes a lot of sense! i like the idea of users eventually learning to make changes on their own because info has been presented to them at the right level of abstraction

curious if you have ideas on how to accomplish the same thing for ai art - i feel like even though there are affordances for finer-grained control of the result (segmentation, inpainting, ...), watching an ai make lots of precise edits would not help me learn how to illustrate on my own?

Expand full comment
connie's avatar

thanks vincent! I definitely think it could apply for art, I've talked a bit about decision making in prior writing https://corny.substack.com/p/on-generated-images, although I do also think there's a portion of art where you're observing from real life as part of the image making, which might be hard to simulate with AI (?)

but definitely for high level composition and color!

Expand full comment