Sign In

阿梓从小就很可爱|阿梓|Azusa|Azi|网友小z|Vtuber Vup

74
432
1
Updated: Oct 5, 2024
animevtuberwomanvupbilibili
Type
LoRA
Stats
432
Reviews
Published
Mar 27, 2023
Base Model
SD 1.5
Trigger Words
azusa
1girl
Training Images
Download
Hash
AutoV2
BEDF11B282

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:Azusa,1girl,

额外可选提示词:dress, fox mask

如果豆豆眉没有出现,可以使用short eyebrows

跑图建议使用DPM ++2M或DPM ++SDE算法

权重根据模型不同可以在0.5-0.9之间调整;

推荐配合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30张在懵鹿公布的3d模型基础之上,由自己修改后模型生成的图片,第二次训练过程使用了35张由AI生成和自己瞎画的图像,版权归八恰力阿鲁公司所有。

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梓宝名誉权的行为,如有冒犯,请联系我删除此Lora.

之后可能还会做个华梓。

Associated prompt words: Azusa, 1girl,

Additional optional prompt words: dress, fox mask, short eyebrows

The DPM++2M or DPM++SDE algorithm is recommended for running the map. The performance is pretty good with a weight of 0.5-0.9;

It is recommended to use it with hire fix. Please select R-ESRGAN 4x+Anime6B for magnification algorithm.

The first training process used 30 3D models published by 懵鹿, and the second training process used 35 images generated by AI. The copyright belongs to VirtuaReal.

Commercial use is strictly prohibited. It is strictly prohibited to publicly disseminate nsfw images generated by this lora and make any behavior that damages Reine’s reputation.If there is anything wrong, please contact me to delete this Lora