π LoRA is trained purely on anime screencaps
π Activation tags are in the right panel
π Note:
Recommended negatives: lips <-- i tried to retrain her, for some reason she likes to generate with lips O.o
Bankai outfit: There's literally only one (powerpoint) image in the whole series -_- don't expect it to generate precisely.
πΈ Always use ADetailer to get detailed eyes
π Technical notes:
LoRA is compatible with various styles - Lower the weight & remove "anime screencap" from the prompt, if you are getting too strong anime style
Hi. res fix used on all sample images:
Upscaler: R-ESRGAN 4x+ Anime6B
Steps: 10-15
Denoising: 0.3
π¬Leave a like, comment, review but first of all, ENJOY ;)