Shenhe skirt colleague | Realistic Genshin LORA

LORA
Original


Updated:

1.9K
<h3 id="heading-601"><strong><em>我创建了一个lora和发图交流的qq群欢迎大家加入:817686141</em></strong></h3><p><strong><em>求求大家的返图和星星</em></strong></p><p><strong><em>seeking everyone's return pictures and stars</em></strong></p><h3 id="heading-602"><strong><em>这是我原神写实系列之一,lora质量还行,脸部我推荐用<span style="color:rgb(250, 82, 82)">After Detailer</span><span style="color:rgb(243, 244, 246)">插件,能生成更好的脸部。但是手部的训练还是不足不能很好的完成手部的动作。权重给0.55-0.85,如果你有lora分层插件的化可以使用默认</span><span style="color:#fa5252">分层MIDD</span><span style="color:rgb(243, 244, 246)">,会得到更好的效果,请关注我后续我会发上更多模型。如果你喜欢永劫无间系列的话。tag的话可以不用加。背景词语要提高权重,不然默认出夜景。</span></em></strong></h3><h3 id="heading-602"><strong><em><span style="color:rgb(243, 244, 246)"> this is one of my genshin impact realistic series,lora's quality is good,i recommend using the </span><span style="color:#fa5252">after detailer </span><span style="color:rgb(243, 244, 246)">plugin for the face,can generate better facial features,but the training of the hands is still insufficient to complete the hand movements well,weighting 0.55-0.85,if you have a lora layered plugin, you can use the default layered midd,will achieve better results,please follow me and i will post more models in the future,if you like the eternal armageddon series,if there is a tag, there is no need to add it,increase the weight of background words,otherwise, default to night view,</span></em></strong></h3><p></p>

Version Detail

SD 1.5
&lt;p&gt;&lt;strong&gt;&lt;em&gt; 这个版本我修正了原来上传错文件的问题,并且经过尝试权重给0.6-0.8左右,采样方法用2m++系列效果最好,半身图时不用开After Detailer,开启有可能会把独眼的特征给重绘了,解决这个问题的办法就是把lora拖到重绘提示词框内。背景泛化能力比较差,如果tag有street就一定生成的是夜景。不想要夜景就尽量不要输入street这类tag。&lt;/em&gt;&lt;/strong&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt; i have fixed the issue of uploading incorrect files in this version,and after trying to give weights of around 0.6-0.8,the best sampling method is to use the 2m++series,you don&#39;t need to open the after detailer when taking a bust,opening it may redraw the features of one eye,the solution to this problem is to drag lora into the redraw prompt word box,poor background generalization ability,if the tag has a street, it must generate a night scene,if you don&#39;t want a night view, try not to input tags like street。&lt;/em&gt;&lt;/strong&gt;&lt;/p&gt;

Project Permissions

    Use Permissions

  • Use in TENSOR GREEN Online

  • As a online training base model on TENSOR GREEN

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.