Originally published at: Kermit the Frog in everything | Boing Boing
…
1 Like
Every single one of those (at least those unobscured by glasses) had circular pupils, which just look wrong on Kermit.
9 Likes
Yeh, I’m not sure if the likelihood of those images would change much if you omitted the word “kermit”. There’s a lot of talk in the AI community about the ability of DALL-E models to reason: many of these seem to just be combining concepts “frog” “insert movie title still” rather than doing reasoning about Kermit in these situations. Still impressive, considering where we were 5 years ago, but not quite what I think the OP wants to demonstrate.
3 Likes
Seems like a bleak future for illustrators. I can’t help but think that the technology would discourage people from learning how to draw and paint.
None of the twitter pictures looked like Kermit.
1 Like
DALL•E obviously knows little about Kermit other than that he’s a frog. Still, an impressive collection.
3 Likes
I’m fascinated by the selection and variation of skin textures that were used. And the Willy Wonka one, how it knew to pick/construct a particularly grotesque frog with a bizarre nose and over-painted eyes…
1 Like
It could be worse than that actually: it could just be ignoring “Kermit” entirely.
Less than you might think, at least for now. If you have only a vague idea of what you’re going for, AI creates very impressive results. But art directing AI to match a particular goal is still an exercise in frustration. AI image generation is more of a threat to stock image services than illustrators.
2 Likes
DALL-E, like many artists, struggles drawing hands.
1 Like
After all the makeup, prosthetics, and CGI, of course it doesn’t resemble the real life Kermit.
This topic was automatically closed after 5 days. New replies are no longer allowed.
