Do you have a dumb question that you're kind of embarrassed to ask in the main thread? Is there something you're just not sure about?
This is your opportunity to ask questions. No question too simple or too silly.
Culture war topics are accepted, and proposals for a better intro post are appreciated.
Jump in the discussion.
No email address required.
Notes -
Breaking Balenciaga is the best I’m aware of.
I watched some of it and it’s…mid. My problem with AI art is that it’s all mid. Although here the idea is also mid.
I feel that so far, even good GenAI is either an excellent idea or lucky (or trial-and-error) output, and in both cases a real artist could’ve executed better. Even for works where more effort would be wasted, like jokes and concept art, I prefer a simple handmade drawing like a sketch.
The one exception may be hidden images via Stable Diffusion ControlNet (e.g. text, QR code, spiral), because I haven’t seen any human-made pictures nearly as detailed and seamless. Also, GenAI is great for intentionally bad works, like memes making fun of AI.
GenAI is genuinely useful for routine tasks, forms, etc. where quality isn’t important; and with code, where quality is only important to an extent (nobody will notice your micro-optimizations or unnecessarily readable implementation) and there are decent objective metrics (lints and tests, and I still think AI code is hard to read). But art has no practical limit to quality, and good artists apply themselves to every noticeable detail. Also, art (like music, food, and attractiveness) is best slightly imperfect, in a way that human amateurs execute without trying, and experts learn (“learn the rules, then break them”), but AI seems to struggle.
You may like Harry potter by balenciaga
I think AI acting is getting better and maybe more serious stories could also be told, see for example this proof of concept (the actual content of what she's yapping about is quite boring, but the facial expressions and voice tone are getting more and more realistic).
I agree it’s getting better.
Although I think it will only surpass human art if/when the user has fine-grained control, because my favorite art is that I can relate to, and a general LLM isn’t relatable. I’d rather use AI to make art I really like (even with difficulty, as long as there’s a clear progression…I’ve wanted to get into art, but it’s overwhelming and I’m particularly bad at it), than have the AI autonomously make something I mildly like.
Or if/when we get ASI.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link