推荐设置:
正:1girl,solo,looking at viewer,(我喜欢的起手式,自行添加)
负:EasyNegativeV2,(badhandv4:1.2),
推荐参数:
vae:840000
采样:DPM++ 2M SDE Karras(我用的这个,其它的也行,步数自己测试)
步数:20~30 (常用30)
高分辨率修复参数:
放大算法:4x-UltraSharp
重绘幅度:0.3
放大倍数:2
cfg:7
欢迎点赞关注,多多返图
推荐设置:
正:1girl,solo,looking at viewer,(我喜欢的起手式,自行添加)
负:EasyNegativeV2,(badhandv4:1.2),
推荐参数:
vae:840000
采样:DPM++ 2M SDE Karras(我用的这个,其它的也行,步数自己测试)
步数:20~30 (常用30)
高分辨率修复参数:
放大算法:4x-UltraSharp
重绘幅度:0.3
放大倍数:2
cfg:7
欢迎点赞关注,多多返图
Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges
Sell generated contents
Use on generation services
Sell this model or merges