π LoRA is trained purely on anime screencaps
π Activation tags are in the right panel
π Note: "γ¨γγγγ³γ¬γε η" white shirt works the best if combined with the concept lora. Otherwise you might get random letters more often. Still it's not exactly perfect, but passable.
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 ;)



