π LoRA is trained purely on anime screencaps
π Activation tags are in the right panel
π Note: That see-through part is real pain in the ass. Pray to AI RNG God for a good geneneration. I couldn't get it more stable even after 4 retrains and experiments with different tag combinations.
πΈ Always use ADetailer to get detailed eyes
π Technical notes:
LoRA shoud be compatible with Illu models & NoobAI. (Not tested.)
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 ;)