Stable Diffusion

4310 readers

5 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 1 year ago

MODERATORS

db0@lemmy.dbzer0.com

Embedding Training always makes me female (lemmy.dbzer0.com)

submitted 1 year ago by Luckaneer@lemmy.dbzer0.com to c/stable_diffusion@lemmy.dbzer0.com

4 comments fedilink hide all child comments

Using automatic, I am embedding training, using text file descriptors per image, but consistently I am being made female.

The text descriptions are all accurate. What am I missing here? I've tried it with multiple models.

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

[–] Luckaneer@lemmy.dbzer0.com 0 points 1 year ago* (last edited 1 year ago) (1 children)

Ok so if the description was "a man in a suit with flowers in the background" it would be better to say "a suit, with flowers in the background"?

[–] Nicktar@beehaw.org 1 points 1 year ago

I'd tag it as "wearing a suit, flowers in background" or "wearing a suit in front of flowers". Basically what you're doing with the description is saying "I'm going to show you an image of this_awesome_person, please ignore that they're wearing a suit, flowers in background". If you also describe that it's a man, you ask SD to ignore the fact for the training.

P.S.: Please ignore the different accounts, I got confused, made two, this one's the main one...