ArmRestraints-Set (Armbinder,Straitjacket,Yoke)
详情
下载文件
关于此版本
模型描述
这是一个针对臂部束缚训练的LORA模型,使用了30×5组人工+互联网数据(z-image)。
该模型共支持5种变体,准确率约为80%。(模型存在过拟合,有时难以区分束缚类型;面部、体型和风格可能出现变化。)
权重范围:0.6~0
触发词(句子)
she is wearing a monoglove_armbinder which binds her arms behind her back.
she is confined in metal_yoke which locks her neck and wrists in a thick pipe.
she is confined,secured in dark oak wooden_yoke which locks her neck and wrists in a thick wood .
she is wearing a latex bolero_straitjacket_front_tie which confines her arms crossed tightly over her chest .
she is wearing a latex bolero_straitjacket_back_tie which confine and binds her arms tightly behind her back
开发者说明:
LORA训练参数如下:
使用了z-image LORA训练适配器:
rank64,
batch 6 ,
steps 6600,
lr 0.0002
对于v2版本:
训练z-image较为困难,因此我计划在基础模型发布后重新尝试。
在生成合成数据时,我使用了@Joschek的LORA对部分数据进行后处理。感谢@Joschek创建了如此出色的LORA。




