submitted 11 months ago by Even_Adder@lemmy.dbzer0.com to c/stable_diffusion@lemmy.dbzer0.com

6 comments fedilink hide all child comments

They say you shouldn't train on synthetic data, still worth a shot.

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

[-] Even_Adder@lemmy.dbzer0.com 5 points 11 months ago

I didn't know that. People make it seem like your model will explode if you do that.

[-] pennomi@lemmy.world 5 points 11 months ago

Yep. What’s the worst that can happen? You bias your model towards what you’re actually trying to achieve?

It’s really only a problem for targeting realism, because generated images simply aren’t real.

this post was submitted on 07 Oct 2023

20 points (79.4% liked)

Stable Diffusion

4256 readers

12 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

founded 1 year ago

MODERATORS