固态3D模型 Stylized 3D Model LoRA

https://s2.xiaonaofu.top/material/0920f6ac-1083-41f4-8ab8-69fc283c6eba.jpeghttps://s2.xiaonaofu.top/material/ce6153a6-4112-4051-856c-9313c8c919ae.jpeghttps://s2.xiaonaofu.top/material/71ae94e1-c208-45f5-8745-24fe697113d1.jpeghttps://s2.xiaonaofu.top/material/18cc26c0-3e27-486f-a498-9129c863016c.jpeghttps://s2.xiaonaofu.top/material/8e78540b-5291-427a-a112-b366df2ecb3c.jpeghttps://s2.xiaonaofu.top/material/e969ecdc-6ab6-4679-b37d-72d25272c1de.jpeghttps://s2.xiaonaofu.top/material/b03ada44-0e9a-45f7-8e5c-f9c07d551520.jpeghttps://s2.xiaonaofu.top/material/a59a231c-9413-4b17-9efe-47c643648749.jpegStylized 3D Model LoRA
This is a LoRA trained on stylized 3D model images.

It can provide a figure-like material and a distinctive silhouette.

Changes in 3.0
Increased the training resolution (ver.2: 768, ver.3: 896)

Revised the tagging

Removed the trigger word as well

Reviewed the training parameters

Improvements in 3.0
It can reproduce a more stereoscopic effect than ver.2

LoRA can be applied without a trigger word

The effect of LoRA can be adjusted by adding the 3d tag to either Positive or Negative Prompt

Precautions
Depending on the base model, the face may become overly deformed.

If it doesn’t work well, consider using the following models, which are used for verification:

Facebomb Mix

Alstroemeria Mix

发表回复

后才能评论