这是试验品，并不稳定
This is an experimental sample and is not stable
所有示例图均未使用插件
None of the example images used plugins.
瞎几把融，发出来主要是把C站当网盘使
negative prompt
worst quality, low quality, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, artist name第一次尝试融合模型，是比较简陋的试验验型，本意是为了解决3D、2.5D模型使用动漫LORA容易出现崩坏、画风剧变等问题
wai佬实在太强了
This was my first attempt at fusion modeling, and it was a rather rudimentary experimental model. The original intention was to solve the problems that often occurred when using anime Lora models in 3D and 2.5D, such as the breakdown of the animation and drastic changes in art style
欢迎反馈
Feedback is welcome.
Description
CFG:1.5-5.5
STEP:8+
大于1024*1536的图特别是横图需要抽卡，但也能出1920*1080、2048*1024之类的，小抽几张就行
Images larger than 1024*1536, especially horizontal images, may require multiple attempts, but you can still get images like 1920*1080 or 2048*1024. Just try a few times
FAQ
Comments (2)
v2.0 DMD2 is 100% identical as v2.0, as you can see by the identical hash codes. Is this on purpose or did you upload the wrong file by mistake?
A mistake, let me correct it.