this post was submitted on 28 Jun 2024
396 points (100.0% liked)

196

16459 readers
33 users here now

Be sure to follow the rule before you head out.

Rule: You must post before you leave.

^other^ ^rules^

founded 1 year ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 72 points 4 months ago (7 children)

Not sure why he lost. He could have claimed to run it through an AI that was only trained on the one picture.

[–] [email protected] 8 points 4 months ago (2 children)

To train a diffusion model that only outputs one image with difference is I think not possible you could do an image to image and then fix the seed so you would get a consistent result and then picking the nearest result that is nearly an identical copy

[–] [email protected] 9 points 4 months ago

It's very much possible and indeed such a problem that it may be done by mistake if a large enough data set isn't used (see overfitting). A model trained to output just this one image will learn to do so and over time it should learn to do it with 100% accuracy. The model would simply learn to ignore whatever arbitrary inputs you've given it

load more comments (1 replies)
load more comments (5 replies)