Emma Stone Lora for SDXL 1.0
Low-quality trained Lora’s will be subpar forever, whereas high-quality ones can easily be resized, provided that you don’t mind a loss in quality. That’s why I always strive to train and distribute the Lora to the best quality. You can always resize them in Kohya with just a few clicks if you’re constrained by storage.
My sample pictures don’t employ tricks like Roop or restore face. They always display a vanilla output from hires.fix upsampling.
I highly recommend to hi.rez-fix the image with ESRGAN-4x with a strength from .25 to .45 that will increase de details and fix the defects in the eyes mostly
Negative prompt seems heavily remove the likeness on the Lora. So keep that in mind.
If you like my work you can always show me your support by buying me a beer or you can always to summit your model suggestion and it will be added to the queue.
Enjoy
Disclaimer: This artificial intelligence model (“the Model”) is developed solely for artistic expression and technological demonstration, not for creating or distributing illicit or inappropriate content. The creator expressly disapproves of such use. By downloading or using the Model, you (“the User”) agree not to misuse it in any manner contrary to these intentions and accept all responsibility for compliance with these terms.