this post was submitted on 08 Feb 2024
994 points (98.9% liked)
Funny: Home of the Haha
5772 readers
981 users here now
Welcome to /c/funny, a place for all your humorous and amusing content.
Looking for mods! Send an application to Stamets!
Our Rules:
-
Keep it civil. We're all people here. Be respectful to one another.
-
No sexism, racism, homophobia, transphobia or any other flavor of bigotry. I should not need to explain this one.
-
Try not to repost anything posted within the past month. Beyond that, go for it. Not everyone is on every site all the time.
Other Communities:
-
/c/[email protected] - Star Trek chat, memes and shitposts
-
/c/[email protected] - General memes
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
No, it does not. At least not in the same way that generative pre-trained transformers do. It is handling natural language though.
The research is all open source if you want details. For Stable Diffusion you'll find plenty of pretty graphs that show how the different parts interact.
Correct. The clip encoder is trained on images and their corresponding description. Therefore it learns the names for things in images.
And now it is obvious why this prompt fails: there are no images of empty rooms tagged as "no elephants". This can be fixed by adding a negative prompt, which subtracts the concept of "elephants" from the image in one of the automagical steps.