Verified: 3 months ago
SafeTensor
Type | |
Stats | 902 419 152 |
Reviews | (158) |
Published | Jan 28, 2025 |
Base Model | |
Usage Tips | Clip Skip: 2 Strength: 0.9 |
Trigger Words | short hair with long locks, multicolored hair, hair between eyes, purple eyes ShizukuSchool, open jacket, cropped jacket, green jacket, collared dress, long dress, white dress, black necktie, school emblem, long sleeves ShizukuBikini, flower hairband, purple rose, halterneck, tankini, collarbone, purple bikini, clothing cutout ShizukuDress, collarbone, pink capelet, light purple dress, hairclip, elbow gloves, white gloves |
Hash | AutoV2 53151FC666 |
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 ;)