
一款的优菈·劳伦斯lora,,我做lora的目标是最大限度的还原游戏角色的真实面貌,希望做拉了优菈不会记我的仇,总之希望大家喜欢,
I made Lora with the goal of maximizing the realism of the game's characters, and I hope that Lora won't hold it against me if I do, anyway, I hope you all enjoy it.
描述:
ora模型以墨幽人造人1010为基底炼制,训练底图大小768*768,触发词为eula_in_genshin
The lora model is refined on the basis of 墨幽人造人 v1010,the size of the training base map is 768*768, the trigger word is eula_in_genshin
Positive prompt:absurdres, highres, ultra detailed, (1 young beautiful girl, solo:1.1),black hairband,a leotard with a white top and black bottom, white long sleeves, blue necktie, jewelry on the shoulder,
Negative prompt:EasyNegative, (worst quality, low quality:1.4), [:(badhandv4:1.5):27],
参数选择Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7,高清修复采用 R-ESRGAN 4X+ Anime6B,LORA权重建议0.7~1,权重为1即可。
Parameter selection Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, R-ESRGAN 4X+ Anime6B for HD repair,LORA weights are recommended to be 0.7 to 1, and a weight of 1 is sufficient.
训练词语:
名称: eula_NOFACE.safetensors
大小 (KB): 147567
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success