this post was submitted on 30 Sep 2023
78 points (100.0% liked)

chapotraphouse

13951 readers
663 users here now

Banned? DM Wmill to appeal.

No anti-nautilism posts. See: Eco-fascism Primer

Slop posts go in c/slop. Don't post low-hanging fruit here.

founded 4 years ago
MODERATORS
 

The only time a cat scratched me was when I pulled its tale when I was 2

you are viewing a single comment's thread
view the rest of the comments
[–] alexandra_kollontai@hexbear.net 6 points 2 years ago (1 children)

That's "what", but not "how". How is it done?

[–] JohnBrownsBussy2@hexbear.net 12 points 2 years ago* (last edited 2 years ago) (1 children)

This is done through ControlNet, an extension architecture for the open source Stable Diffusion latent diffusion models. Basically, ControlNet takes a reference image, in this case an image of text, and then modifies the model inference to meet certain parameters/weights vis-a-vis that reference image. While this has been possible for a while, the popularity of this meme took off with the development of a QR code controlnet that allowed for hidden QR codes to be embedded in an image. Since this controlnet forces a high contrast based on the white and black reference image, it can force any generated image to match the original image. Since latent diffusion is a denoising process, applying a simple gaussian blur (literally by squinting or moving the image away) is enough to see the outline of the original image embedded.

[–] alexandra_kollontai@hexbear.net 6 points 2 years ago

This is the first real explanation I've heard, and now it makes sense (though some still went over my head), so thank you very much!