Models>

jiruxue_姬如雪——不良人

masterpiece,best quality,1girl,blue clothes,  <lora:jiruxue-000019:0.8>,cowboy shot,dynamic pose, dynamic angle
masterpiece,best quality,1girl,blue clothes,  <lora:jiruxue-000019:0.8>,cowboy shot,dynamic pose, dynamic angle,outdoors, day,
masterpiece,best quality,1girl,miao,headware,((day time)),(((cowboy shot))), outdoors,dynamic pose, dynamic angle,<lora:jiruxue-000019:0.8>,
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

V1.0是不良人第五季后姬如雪建模的LoRA模型,采用国风3(guofeng3_v32.ckpt [0bb33c7041]
模型做为底模,基于秋叶的lora整合包进行训练,权重在0.8左右效果比较稳定,配合EasyNegative等负面提示词模型效果更好。这个模型有两种发型,可以通过long hair, ponytail或short hair两组tag来控制长短发。(如果带剑的话,剑的位置不太好控制,容易出现在很奇怪的位置或变成奇怪的样子)

V2.0是不良人第四季姬如雪建模的LoRA模型,采用国风3(guofeng3_v32.ckpt [0bb33c7041]
模型做为底模,基于秋叶的lora整合包进行训练,权重在0.8左右效果比较稳定,配合EasyNegative等负面提示词模型效果更好。这个模型有两套服饰,两种发型,可以通过blue colothes或miao两组tag来切换两套服装,加headware可以画出苗族头饰。(剑和1.0一样依然不好控制,有的时候背后还会背上龙泉剑,因为素材中有,但是细节还原度不高)

权重在0.8时,面部还原度较高,但是场景、姿势比较固定,v2.0由于训练数据夜景和室内比较多,因此光线有些暗,可以适当降低模型权重或者增加白天等光线tag权重。权重在0.4时,能保留模型主体特征,并提供更大的自由度以更换姿势、服装及背景,画出更通用但不那么还原的图。

初始分辨率540x960,采用R-ESRGAN 4x+放大算法,重绘幅度0.3放大2倍进行高清修复,然后图生图用SD upscale脚本,选择同样的算法,重绘幅度0.1进行超分放大,可以得到效果不错的4k高清图片。(此方法第一步直接生成1080P的图片,比较看脸,不易批量操作,16G显存最多只能同时生成4张图片,出图及修图效率较低,但是质量较高)

jiruxue_姬如雪——不良人 - v1.0 | 吐司 [Blocked Link] (tusiart.com)

jiruxue_姬如雪——不良人 - v2.0 | 吐司 [Blocked Link] (tusiart.com)(这里可以在线跑图看效果,需要开高清修复看脸抽卡,速度还可以,每天有免费额度)

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.