vogon

the evil "Website Boy"

member of @staff, lapsed linguist and drummer, electronics hobbyist

zip's bf

no supervisor but ludd means the threads any good


twitter (inactive)
twitter.com/vogon
bluesky
if bluesky has a million haters I am one of them, if bluesky has one hater that's me, if bluesky has no haters then I am no more on the earth (more details: https://cohost.org/vogon/post/1845751-bonus-pure-speculati)
irl
seattle, WA

Pixl
@Pixl

i was mistaken and now my notifications regret it


twilight-sparkle
@twilight-sparkle
This page's posts are visible only to users who are logged in.

vogon
@vogon

people who create AI models don't actually want to train on other AI art because it creates a feedback loop

a small note to expand upon this: yesterday I found out that Stable Diffusion (another AI art generator) silently watermarks all of its output invisibly to the human eye, to attempt to ensure that it can detect and prune out images it created from its input. it's likely that other model developers have at least considered doing this as well, and one would assume that at some point they'd settle on a standardized way of doing it, since it's in all their best interest to ensure that they can recognize all of their output.


You must log in to comment.

in reply to @Pixl's post:

in reply to @twilight-sparkle's post:

i kinda had a feeling the stuff spreading was fake but this is a really nice breakdown of some of the process behind these generators that really puts my wonders to rest, tyvm 🙇‍♀️🙇‍♀️🙇‍♀️

in reply to @vogon's post:

yeah, the watermark is embedded in the frequency domain so you can pretty easily remove the watermark the same way it was added, and with only minor impacts to the output image