🎞 LoRA is trained purely on anime screencaps
🗝 Activation tags are in the right panel
Check about version for differences over previous version.
📸 Always use ADetailer to get detailed eyes
🛠 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
📬Leave a like, comment, review but first of all, ENJOY ;)
Description
Difference over v1.0:
added additional images from the anime to the training dataset
fixed some dataset tags
FAQ
Details
Downloads
737
Platform
CivitAI
Platform Status
Available
Created
11/23/2025
Updated
4/27/2026
Deleted
-
Trigger Words:
hair between eyes, short hair with long locks, brown hair, colored tips, orange hair, orange eyes, orange eyeshadow, horizontal pupils
striped scarf, orange scarf, white scarf, collarbone, black dress, cleavage cutout, large breasts, striped sash, open dress, skinny, navel, detached sleeves, wide sleeves, white sleeves, torn sleeves, arm belt, sleeves past fingers, white panties, slim legs, leg ribbon, orange ribbon