196

16500 readers

2118 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

[email protected]

395

Rule (lemmy.blahaj.zone)

submitted 4 months ago by [email protected] to c/[email protected]

10 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] [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] 15 points 4 months ago

It very much is possible. It'll only ever output that one image and it's a huge waste of resources but it's very much possible.

[–] [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