, masterpiece, best quality,yellow eyes,smile, squatting, dress.jpeg)
, masterpiece, best quality,yellow eyes, blue sky, cloudy sky,.jpeg)
, masterpiece, best quality,yellow eyes, arms behind back, smile,.jpeg)
, masterpiece, best quality,yellow eyes, arms behind back, crying,(handheld knife_1.331).jpeg)
Type | |
Stats | 828 |
Reviews | (174) |
Published | Apr 5, 2023 |
Base Model | |
Trigger Words | nana7mi 1girl |
Training Images | Download |
Hash | AutoV2 7F7193C935 |
已上传训练集，需要PSD，jpg及txt原始文件请联系我，B站：鱼泠溟；私信我，暂时只向官方，其他lora训练者或认为我使用了您作品的画师提供
The training Data has been uploaded
提示词：nana7mi,1girl,
额外可选提示词：dress, yellow eyes ,asymmetrical legwear,
可以把white background加入负向提示词
跑图建议使用DPM ++2M或DPM ++SDE算法
权重根据模型不同可以在0.75-0.9之间调整；
可以配合hire fix使用，放大算法请选择为R-ESRGAN 4x+Anime6B
第一次训练过程使用了17张七海地雷女仆官方3d模型作为训练素材
第二次训练过程使用了12张由AI生成并经过修改的图像，+8张3D模型图像进行校正，版权归八恰力阿鲁和彩虹社公司所有
严禁商用，严禁公开传播由此lora生成nsfw图像及做出任何损害海子姐名誉权的行为，如有不妥之处，请联系我删除此Lora
Prompt words: nana7mi, 1girl,
Additional optional prompt words: dress, yellow eyes ,asymmetrical legwear,
Additional optional negative prompt words: white background
It is recommended to use DPM ++2M or DPM ++SDE algorithm. The weight can be adjusted between 0.75-0.9 according to different models;
It is recommended to use with hire fix, please choose R-ESRGAN 4x+Anime6B as the zoom algorithm
The first training process used 17 3D model images made by VirtuaReal as training Data.
The second training process used 12 images generated by AI and modified, and 8 3D model images for correction.
The copyright belongs to VirtuaReal and nijisanji.
Commercial use is strictly prohibited, and public dissemination of nsfw images generated by this lora and any behavior that damages the reputation of 七海nana7mi is strictly prohibited. If there is anything wrong, please contact me to delete this Lora