Verified: 3 months ago
SafeTensor
Type | |
Stats | 450 733 357 |
Reviews | (108) |
Published | Feb 23, 2025 |
Base Model | |
Usage Tips | Clip Skip: 2 Strength: 0.9 |
Trigger Words | long hair, black hair, grey eyes NanahoshiShizuka, white collar, blue cloak, buttons, red bowtie, loose belt, black belt, red skirt mask, black hair |
Hash | AutoV2 29C4781AA5 |
π LoRA is trained purely on anime screencaps
π Activation tags are in the right panel
π Note: Mask isn't extra stable, I recommend generating her face :)
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 ;)