this post was submitted on 07 Aug 2025
614 points (95.7% liked)

Trippin' Through Time

5304 readers
213 users here now

Tripping' Through Time

A Lemmy community for historic art pieces overhauled into modern memes.

Rules

  1. Only image uploads allowed
  2. Only edited, historical images may be shared
  3. The instance rules of https://lemmy.ca/

founded 2 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] Cethin@lemmy.zip -2 points 1 month ago (2 children)

No. LLMs are still what generates images.

[–] Lemminary@lemmy.world 2 points 1 month ago

Large Language Models generate human-like text. They operate on words broken up as tokens and predict the next one in a sequence. Image Diffusion models take a static image of noise and iteratively denoise it into a stable image.

The confusion comes from services like OpenAI that take your prompt, dress it up all fancy, and then feed it to a diffusion model.

[–] Honytawk@feddit.nl 1 points 1 month ago

You can't use LLMs to generate images.

That is a completely different beast with their own training set.

Just because both are made by machine learning, doesn't mean they are the same.