you can do that with stable diffusion and loras, yes
Comment on Meta’s new AI image generator was trained on 1.1 billion Instagram and Facebook photos
mannycalavera@feddit.uk 6 months ago
Is there an example of AI generated images that aren’t hyper realistic or have perfect bokeh? I’m taking about an out of focus shot or the subject looks like a regular slob like you and I?
zwaetschgeraeuber@lemmy.world 6 months ago
Dkarma@lemmy.world 6 months ago
Loras are amazing. You can do anything or create anyone.
lud@lemm.ee 6 months ago
Create me.
Usernameblankface@lemmy.world 6 months ago
On the focus part, I’ve seen some impressive results from people who input a specific camera, lens, and focal distance.
Unforeseen@sh.itjust.works 6 months ago
I assumed this was becuase it’s making an average. Human attraction is highly sensitive to symmetry so this creates that symmerty by thr way it works.
Mahlzeit@feddit.de 6 months ago
The models are deliberately engineered to create “good” images, just like cameras get autofocus, anti-shake and stuff. There are many tools that will auto-prettify people, not so many for the reverse.
There are enough imperfect images around for the model to know what that looks like.
BetaDoggo_@lemmy.world 6 months ago
It’s mostly bias in the training data. Most people aren’t posting mediocre images of themselves online so models rarely see that. Most are also finetuned to specifically avoid outputting that kind of stuff because people don’t want it.
Out of focus is easy for most base models but getting an average looking person is harder.