So lately I've been getting a kick out of asking DALL-E3 for images labeled with text. They're just good enough to be legible, but yet:
The food that gets duplicated seems to vary from spread to spread.
I also asked DALL-E 3 to do the dessert
Still amazed by this:
Here's CLIP+VQGAN
[https://aiweirdness.com/post/655607559221379072/the-art-of-asking-nicely]
(trained on internet photos and their accompanying text), prompted two different
ways:
"A car driving down a desert road in monument valley"
A car driving down a desert road in monument valley"