this post was submitted on 29 Jan 2025
18 points (95.0% liked)
Stable Diffusion
4463 readers
2 users here now
Discuss matters related to our favourite AI Art generation technology
Also see
Other communities
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Here's the bullet point summary of findings from page iii for anyone who doesn't want to go digging through the PDF:
So far nothing new. Does the pdf say anything about the training data?
Emphasis mine. So, probably have to wait for Part 3 or 4 or whatever.
The report details how they think pretty much everything but straight prompts is eligible for some kind of protection. Clarification that was much needed before. Even prompting has been upgraded from "not eligible" to "probably not eligible" with them stating that they will likely be eligible in the future when prompting alone provides more control.