Download
1 variant available
ALL SHOWCASE IMAGES ARE PRODUCED FROM A SINGLE TEXT2IMG PASS + ADETAILER
FEATURES:
-all dataset images were upscaled to full HD. expect good quality output
-extensively tagged captions, allowing for granular control and inclusion/exclusion of props and clothing like her bodysuit, shoulder armor, clothing curtains, collar, hairband, etc.
-NSFW supported
-dataset includes re-rendered realistic images along with usual CGI images
USAGE TIPS:
-clip skip:1
-CFG: 5-7
-strength:1
use of Adetailer is recommended. use the lora in the positive prompt of adetailer along with (detailed face) and set inpaint denoising strength to 0.5 or 0.6
ADETAILER PROMPT: <lora:X_valentina_def_mlbb_IL:1>, detailed face, hairband, realistic, forehead jewel, cyan eyes

