Tensor.Art
在线生图

Xiao_魈_Genshin Impact_原神

LORA
原创

7.8K

V3更新:

基于anythingV5底模制作,例图使用mix-pro4直出,大幅度改善了过拟合、换装难和娘化的问题

使用方法:

因为魈的角色特征较为复杂,还原原版服装,推荐权重0.8~0.9,触发词为:1boy, male focus, yellow eyes, (official:1.2)

换装则推荐较低权重0.6~0.8,并拉高服装权重,触发词为:1boy, male focus, yellow eyes

版本详情

SD 1.5
<p>V3更新:</p><p>基于anythingV5底模制作,例图使用mix-pro4直出,大幅度改善了过拟合、换装难和娘化的问题</p><p>使用方法:</p><p>因为魈的角色特征较为复杂,还原原版服装,推荐权重<strong>0.8~0.9</strong>,触发词为:<em>1boy, male focus, yellow eyes, (official:1.2)</em></p><p>换装则推荐较低权重<strong>0.6~0.8</strong>,并拉高服装权重,触发词为:<em>1boy, male focus, yellow eyes</em></p><p>translate by GPT:</p><p>V3 Update:</p><p>Based on the anythingV5 base model, the example images are output using mix-pro4, which greatly improves the problems of overfitting, difficulty in changing costumes, and feminization.</p><p>How to use:</p><p>Due to the complex character features of Xiao, it is recommended to use a weight of <strong>0.8-0.9</strong> to restore the original costume, with trigger words:<em>1boy, male focus, yellow eyes, (official:1.2)</em>.</p><p>For changing costumes, it is recommended to use a lower weight of <strong>0.6-0.8</strong> and increase the weight of the clothing, with trigger words:<em>1boy, male focus, yellow eyes</em></p>

项目权限

    使用权限

  • 使用时无需注明出处

  • 用于模型融合

  • 分享融合模型时使用不同的许可

    商用许可

  • 生成的图片用于商业用途

  • 作为图片生成服务来商用

  • 转售模型或出售融合模型

评论

相关帖子

描述想生成的画面,回车发送