权重从0.1开始。

Weights start at 0.1.

我的其他检查站和Lora。

My other checkpoints and Lora.

--

SDXL_V1為lora版本被錯誤標記為LyCORIS。

SDXL_V1 is a lora version that is mistakenly labeled as LyCORIS.

--

SD1.5-V1為LyCORIS。

SD1.5-V1 is LyCORIS.

此"LyCORIS"来自多个汉服与中国风模型的合并后提取LoHa。

This "LyCORIS" is extracted from LoHa after merging multiple Hanfu and Chinese style models.

--

我使用了"FULL"的提取方式，所以档案较大，在意硬碟空间不足的人不建议下载。

I used the "FULL" extraction method, so the file is larger. It is not recommended for people who are concerned about insufficient hard disk space to download it.

--

如果你喜欢我的lora，可以用"buzz"鼓励我。

If you like my lora, you can encourage me with "buzz".

--

我只有在” civitai”发布我的模型和lora，其余的地方皆是盗用。

I only publish my models and lora on ” civitai” , the rest are all stolen.

--

面部局部重绘可使用adetailer或sd-face-editor.

高解析度放大可使用"ultimate SD upscale".

--

For partial facial redrawing,adetailer orsd-face-editor can be used.

High resolution upscaling can be done using "ultimate SD upscale".

--

SDXL-加速器(SDXL-accelerator):

dmd2_sdxl_4step_lora

權重(Weight):0.8~1

取样方法(Sampler)=LCM

Schedule type: Karras

CFG:1

4~8步(steps)

--

trigger word-触发词:

hanfu,chinese clothes

--

客製化lora:我的Telegram ID:@iamddtla0620

我的微信ID:iamddtla

我的line ID:iamddtla

时间宝贵，请直接说明来意，例如:订制LORA.

Customized lora: My Telegram ID: @iamddtla0620

My WeChat ID: iamddtla

My Line ID: iamddtla

Time is precious, please state your intention directly, for example: customized LORA.

--