Sign In

Romy Schneider

35
355
3
Updated: Oct 5, 2024
celebritypersonwoman
Verified:
SafeTensor
Type
LoRA
Stats
355
Reviews
Published
Apr 30, 2023
Base Model
SD 1.5
Training
Steps: 1,736
Epochs: 8
Hash
AutoV2
0D36C94338
default creator card background decoration
chairfull's Avatar
chairfull

7th attempt. Decent enough to release, but not very flexible. You'll have to play with the weights depending on the rest of your prompt.

I find training on old photos gives flatter results, to tried setting noise_offset to 0.1. I think it gives more pop to the images, but sometimes they get too dark.

It overtrained on smiling pics so you may need to place smiling in negative prompt.