this post was submitted on 26 Sep 2023
1215 points (95.4% liked)

Memes

45673 readers
689 users here now

Rules:

  1. Be civil and nice.
  2. Try not to excessively repost, as a rule of thumb, wait at least 2 months to do it if you have to.

founded 5 years ago
MODERATORS
gary_host_laptop@lemmy.ml
sexy_peach@feddit.de
cyclohexane@lemmy.ml
cypherpunks@lemmy.ml
1215
Cute cats, but squint your eyes (feddit.de)
submitted 1 year ago by Oiconomia@feddit.de to c/memes@lemmy.ml
82 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] jballs@sh.itjust.works 56 points 1 year ago (2 children)

Those kittens have been hanging out with these puppies.

[–] SasquatchBanana@lemmy.world 9 points 1 year ago (2 children)

These have to be AI generated right?

[–] Miqo@lemmy.world 10 points 1 year ago (1 children)

Yep, has that signature AI image look.

[–] SasquatchBanana@lemmy.world 1 points 1 year ago (2 children)

I am a bit impressed they were able to integrate the message in. I wouldn't have thought an AI to be able to do this yet

[–] Zoomboingding@lemmy.world 7 points 1 year ago* (last edited 1 year ago)

It's super impressive to me, and getting this kind of fidelity is honestly brand new. You can include an image in an AI image generator to serve as an outline. In this case a blank image with bold text. It'll fill in the prompt using the reference as best it can (in this case, a bunch of kittens/puppies).

Prior to a few weeks ago, I'd only ever seen this using a posed figure--basically a stick figure--to generate the prompt's subject around.

[–] general_kitten@sopuli.xyz 5 points 1 year ago* (last edited 1 year ago)

I think the way stable diffusion works makes this kind of message imprinting quite easy to implement.

the wikipedia article has some good pictures

I would imagine it works by inserting the text on some of the first steps so the ai has the text as it's seed instead of just random noise.

[–] figaro@lemdro.id 4 points 1 year ago

It's that or some kind of next-level art project

[–] TheMadnessKing@lemdro.id 8 points 1 year ago (3 children)

What's the prompt to get this stuff done? This looks wild and interesting.

[–] elrik@lemmy.world 11 points 1 year ago

I suspect these are using additional tools to guide the AI beyond a simple prompt. For example the spiraling medieval village was generated with stable diffusion and controlnet.

https://arstechnica.com/information-technology/2023/09/dreamy-ai-generated-geometric-scenes-mesmerize-social-media-users/

[–] ChaoticNeutralCzech@feddit.de 4 points 1 year ago* (last edited 1 year ago)

I think the prompt is not much other than "puppies" and "kittens". Major, middle and minor features of the image can be controlled individually in some AIs (they can be differentiated using a Fourier transform or Gauss convolutions and fed into different discriminators) so I think:

  • major features (scenery) are controlled by the prompt (grass or couch)
  • middle features (text) are a source image that the AI is punished for straying from
  • minor features (details) are controlled by the prompt (faces and fur)

Or it's just Stable Diffusion that starts with a text rather than random noise.

[–] jballs@sh.itjust.works 3 points 1 year ago

Not sure what this prompt was, since I didn't make this one. I linked the site I used above, and they're pretty simple to do but need a few tries to get a good one.