[Other][Checkpoint]Uenomigi_DB V1

0xSoul

目前已知的一些问题：

• 有概率会出现水印，你可以使用类似logo这样的tag来抑制

• CFG过高可能会导致画面崩坏，个人建议不超过8

• 需要挂载通用VAE

虽然我知道已经有这个LoRA了：https://civitai.com/models/6509/uenomigi-90-style-lora
但是这个是我自己训练的ckpt模型，也就意味着你可以用它来和别的ckpt模型进行融合或者分块融合

个人感觉我这个效果更好（具体实际情况如何你可以自行判断）
我尝试过和几个模型进行分块融合，效果都挺不错。

Translate：
Some known problems:

There is a probability that watermarks will appear. You can use tags like logos to suppress them

Too high CFG may cause the picture to collapse, and I suggest not to exceed 8

Universal VAE needs to be mounted

Although I know this LoRA already exists: https://civitai.com/models/6509/uenomigi-90-style-lora

But this is my own training ckpt model, which means that you can use it to merge with other ckpt models or merge block weighted

Personally, I think this effect is better (you can judge the actual situation by yourself)

I have tried to merge block weighted, and the results are very good.