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
This is a fan-oriented character model, if you are interested in this art style, please visit Old-Fish and nyan-mix.
3D女团四禧丸子成员恬豆的常服人物LoRA
声明:
训练集由官方提供的二创素材、直播截图与本人制作MMD素材组成，不含任何第三方作者素材(例如官方转发的二创)，若仍有侵权或其他不适宜发布理由请联系我。
简介
有两种，一种是没分离帽子和行星环的版本的3个epoch，一种分离了没帽子和行星环的版本2epoch。
没分离的版本没有过拟合，推荐使用epoch4这个，比较有特点。分离了的版本对mmd模型有点过拟合(因为这版数据集提供了更多mmd特写)，但可以在prompt里通过tiandou_infm_asteroid,tiandou_no_hat,tiandou_no_asteroid来控制头饰种类(只能写一种)。
只训练了常服LoRA，不是通用人物LoRA，个人觉得丸子几版人设特征差异较大。
5个epoch的大致效果见粗略的宫格图，没有详细测试，本着小圈自娱心态，恳请丸友们自行测试并反馈哪个好点。
底模是anything v4.5，但demo图是用的一个风格模型Old Fish，和nyanmix。
训练分辨率是768x1024，所以生图应该推荐这个3:4分辨率。
有什么问题丸频二创区找我，训练集也发布在丸频。
Images Generated With This Model
N/A
Hidden For Public Users
((masterpiece)),(((best quality))),illustration,1girl,protrait,complex background
N/A
Hidden For Public Users
((masterpiece)),(((best quality))),illustration,1girl,protrait,complex background
N/A
Hidden For Public Users
masterpiece, best quality, identity v, button eyes, detailed, 8K, 1girl, sad, upper body, day, white hair,
N/A
Hidden For Public Users
masterpiece, best quality, identity v, button eyes, detailed, 8K, 1girl, sad, upper body, day,
Similar Models
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.