Intro

This clothing LoRA generate gradient or two-tone pantyhose. Works on both anime and realistic checkpoints. 这是一个 SD1.5 服饰LoRA，用于生成彩色的渐变丝,二次元/写实大模型均可使用，查看示例图片所使用的模型,

Main trigger word 主要触发词 :

two-tone legwear,

then pick from The available colors 再搭配颜色触发词 :

? green_pantyhose,

? yellow_pantyhose,

? blue_pantyhose,

? purple_pantyhose,

? pink_pantyhose,

? black_pantyhose， doesn't quite work（很难生效）

You can also try other colors and see if it works out well. 即可产生效果，可自行尝试其他颜色,

Settings

1. LoRA Block Weight Setting

By now I assume that everyone knows what LBW (LoRA Block Weight) is so I'll just put my preset here. 我将假设你已经知道如何使用LBW插件（在线生成服务不支持）从而防止LoRA对于画风、姿态或背景带来的污染，因此我会直接给出LBW预设,LBW文档

Preset 预设 (copy to your LBW weight setting box):

StocTest:0.9,0,0.4,0,0,0,0.4,0,0.5,1,0.8,0,0,0,0,0,0

How to use 使用方法 :

The prompt has changed (as in webUI version > 1.5). Now you must add ":lbw=XLFace" right after the weight of LoRA.

e.g. <lora:gradient_v1.0:1:1:lbw=StocTest>

将以上预设粘贴至LoRA Block Weight插件的权重设置中，保存并重载预设和标签；

依照LoRA名称，填写<lora:gradient_v1.0:1:1:lbw=StocTest>

请关注上述LoRA引用格式中的划线部分，1:1取代了原本填写LoRA权重的单个数值，这个比值的意思是Text-Encoder与U-Net的比，例如1:1 意味着“BASE权重为1.0，IN00 - OUT11权重均为1.0”，同理，1:0.5意味着“BASE权重为1.0，IN00 - OUT11权重均为0.5”,

Regarding the weird "1:1" parameter, see issue#126

2. General Settings 其他设置

Step: 36

Sampler: DPM++ 2M SDE Karras

CFG Scale: 7

Resolution: 512*768

don't use hi-res fix or refiner, not necessary. hi-res fix 或 refiner 均不需要使用,

Training

Images: 1024*1536 px, 160 pics,

Tagging: wd-14 auto tagging with manual correction,

min_snr_gamma: 5,

offset_noise: 0.1,

network_dim: 32,

network_alpha: 16,

描述:

Initial. SD1.5

训练词语: ,two-tone legwear