//=time() ?>
Interesting to think about how the AI is doing the painting styles of made-up artists. Maybe proximity to other names it knows about?
Here's "City of the Cretaceous" by James Gurney, Lisa Frank, and "Lisa Gurney".
https://t.co/lDuS7LsIjf
Pretty striking the difference that a byline makes when asking CLIP+VQGAN to generate images.
"Internet infrastructure"
versus
"Internet infrastructure by James Gurney"
https://t.co/4WyAFgNqsa
Here's CLIP+VQGAN doing "Cyberpunk toaster", vs
"Cyberpunk toaster | dramatic atmospheric ultra high definition free desktop wallpaper"
Very fond of Long Toaster with its single flying buttress.
Asking CLIP+VQGAN to generate
"a car driving down a road in monument valley"
versus "A car driving down a desert road in monument valley | dramatic atmospheric ultra high definition free desktop wallpaper"
https://t.co/26AZbQkXbi
I had VQGAN+CLIP generate "A herd of sheep grazing on a lush green hillside | dramatic atmospheric ultra high definition free desktop wallpaper by lisa frank" and got this absolutely apocalyptic landscape.
I think those slippery purple things may be what's become of the sheep.
Using the spammy "A herd of sheep grazing on a lush green hillside | dramatic atmospheric ultra high definition free desktop wallpaper" prompt as a starting point leads CLIP+VQGAN to some irritatingly gorgeous places.
Here, I added "cubist cezanne".
Adding "by Tim Burton" to "a herd of sheep grazing on a lush green hillside" got CLIP+VQGAN to generate this very cool looking image. Not sure what happened to the sheep though.
Because CLIP is trained on internet images and text, it associates the "good" images with certain phrases.
"A herd of sheep grazing on a lush green hillside" before vs after adding "in the style of disney trending on artstation | unreal engine"
https://t.co/GykNx66iYF