Verified: a month ago
SafeTensor
Type | |
Stats | 454 133 38 |
Reviews | (86) |
Published | Apr 2, 2025 |
Base Model | |
Usage Tips | Strength: 0.9 |
Trigger Words | short hair, blue hair, blue eyes pendant, multicolored capelet, blue ribbon, multicolored dress, hood down, blue belt, belt pouch earrings, off shoulder, yellow capelet, white dress, red necktie holding staff |
Hash | AutoV2 B6B092FD70 |
π LoRA is trained purely on anime screencaps
π Activation tags are in the right panel
π Note: 2nd outfit isn't stable as there wasn't enough data and belt from the 1st outfit tends to bleed into it.
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 ;)