
The basic goal of this LORA is to recreate the character's in game appearance. This LORA's dataset is comprised entirely of in game screenshots of her model and a Koikatsu approximation.
The model primarily uses the following tokens for the character and her outfit:
-
glimmer, hairband, hairpiece, ponytail, long hair, chest jewel, brown hair, brown eyes
-
halterneck kimono, obi, ribbon, wide sleeves, fingerless elbow gloves, pink skirt, black choker, white belt, high pouch, thigh belt, white footwear
It should also be able to sort of generate Pyra and a few of her outfits:
-
cosplay, backless shirt, short shorts, black fingerless gloves, cape, gauntlets, thigh boots
-
one-piece swimsuit/turtleneck swimsuit, loose suspenders
描述:
-
Drew outlines for the hairpiece. This is a step that I had forgotten to do after remaking the dataset after version 42.
-
Pre-processed the dataset using a script that preserves the original image's aspect ratio by padding the canvas with transparent pixels rather than cropping.
Drew outlines for the hairpiece. This is a step that I had forgotten to do after remaking the dataset after version 42.
Pre-processed the dataset using a script that preserves the original image's aspect ratio by padding the canvas with transparent pixels rather than cropping.
These changes should improve the odds of accurately recreating the hairpiece during inference.
训练词语: glimmer, hairband, hairpiece, ponytail, long hair, chest jewel, brown hair, brown eyes,halterneck kimono, obi, ribbon, wide sleeves, fingerless elbow gloves, pink skirt, black choker, white belt, high pouch, thigh belt, white footwear
名称: glimmer xl 053 fro 95.safetensors
大小 (KB): 63330
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success