Creates the likeness of the actress, Sydney Sweeney
Guidance of 4-6 works best.
v1.2 is trained at 512px with the keyword sw33n3y, it is trained with better data at a lower learning rate, and it significantly improves issues with glitching and frozen faces.
v1.1 is trained at 1024px with a keyword (sw33ny) (yes I spelled it incorrectly, it was an accident)
v1.0 is trained at 512.
Description
FAQ
Comments (9)
wow. the quality of the new version's videos are insane
I KNOWWWWWWWWWWW, I'm going back and updating all of my old models
@vfx_ai can you please share with us what is the training config that produced that high quality comapred to first and second lora
@zaza 2e-5, captioned using llama3.2-vision:14b, the major difference is using at least 50 great images instead of 10-20
@vfx_ai how many repeats, epoch or steps for 50 images
Thank you.
such great work! do you consider requests or commissions? thanks!