混元亚洲写真摄影
LORA
Run6
Version Detail
Trained by Tensor
HunYuanDiT
80
有点偏日系的写真风格,混元这个模型作为底模有点强大。除了不能瑟瑟我觉得很强大了。负面词:错误的眼睛,糟糕的人脸,disfigured,糟糕的艺术,变形,extra limb,模糊的颜色,blurry,重复,病态,残缺,watermark,bad hands,多余的手指,崩坏的人体,错误的肢体,错误的手指, tag直接用中文就行,不要太复杂的tag,会崩图,采样用Euler a 20步也可以,分辨率大于768*1024,不要放大不要放大现在放大会崩图,想要好的效果建议ddim 50步起CFG Scale:4—5
Project Permissions
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
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges
Commercial Use
Comments
Related Posts
No posts yet
Describe the image you want to generate, then press Enter to send.