this post was submitted on 01 Oct 2023
1368 points (97.8% liked)

Memes

45130 readers
1484 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
 
you are viewing a single comment's thread
view the rest of the comments
[–] TropicalDingdong@lemmy.world 31 points 11 months ago (7 children)

any link to the site you using

[–] Oiconomia@feddit.de 34 points 11 months ago (6 children)

Would like to know that as well. I just stole the meme from non-fediverse meme site

[–] CodeInvasion@sh.itjust.works 17 points 11 months ago

This is done by combining a Diffusion model with ControlNet interface. As long as you have a decently modern Nvidia GPU and familiarity with Python and Pytorch it's relatively simple to create your own model.

The ControlNet paper is here: https://arxiv.org/pdf/2302.05543.pdf

I implemented this paper back in March. It's as simple as it is brilliant. By using methods originally intended to adapt large pre-trained language models to a specific application, the author's created a new model architecture that can better control the output of a diffusion model.

load more comments (5 replies)
load more comments (5 replies)