Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting

Model Description by Creator

NoobAI-XL V-pred

由于自己训练的SDXL的Lora和Illustrious-XL训练的Lora不兼容NoobAI-XL的V预测模型,所以特意训练了一个基于NoobAI-XL为底模的版本配合NoobAI生态,个人使用感觉比自己训练的4.0(SDXL)4.1(Illustrious-XL)版本好用。其他步数版本在夸克盘,基本上就是拟合的区别,可以自行尝试:

链接:https://pan.quark.cn/s/6c4a40f311b4

Illustrious-XL

基于Illustrious-XL训练,Lion优化器,其他优化器版本在夸克盘:

链接:( https://pan.quark.cn/s/d03fac3c40d5 ) 一些说明:

Civitai:顾名思义,直接在Civitai云训练的,全默认参数,打标也全默认,优点:更听话,细节比较到位。缺点:欠拟合,提示词要把梦美的对应特点加上比如:blue hair,green eyes,等。

AdaFactor:细节一般,直出画风偏旧,中规中矩,稍微欠拟合。

Prodigy :虽然大伙都在赞扬这个优化器,但是感觉训练出来的也没有特别优秀,中规中矩,有些过拟合,盘里有练了12步的版本,过拟合问题应该会有所改善。

当你使用的画风Lora与Lion优化器版本配合不理想,可以尝试切换其他优化器版本(优先建议Civitai版本)。

SDXL

基于新发布的Animagine XL 4.0模型训练,为了能够使用SDXL相关Lora画风模型特意炼了这个版本,优点是对于头饰的学习比较好,服装中规中矩。

Flux

使用Flux.1模型训练 个人感觉效果非常不错。触发词:Yumemi

V2.0(过时)

2.0的泛化有稍微降低,推荐权重1,此次更新主要是fullbody的特化,对下半身服装做了一定优化,所以对Tag:fullbody极为敏感,谨慎使用。使用2.0建议加入视角类,姿势类Tag,否则您可能会得到单一姿势的生成图,咱一直在追求服饰配饰的还原度,但进度缓慢,只能慢慢来。顺便,2.0直出图可能质量普遍有所降低,所以想要高质量出图更依赖于高清修复,Tag尽量详细,这都是出高质量图的必要条件。

V1.0(过时)

推荐权重0.6左右,请根据不同Checkpoint模型进行不同的权重调整,以达到最佳效果
测试Anything4.5,DOSMIX,PVCStyleModel,CounterfeitV25等Checkpoints模型的兼容性都不错
缺点:背景容易异常,发光缎带容易异常,以后可能会进行优化

Images Generated With This Model

AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
masterpiece,1girl,solo, <lora:yumemihoshino_pixiv:0.65>,flat chest,
N/A
Hidden For Public Users
masterpiece,1girl,solo, <lora:yumemihoshino_pixiv:0.65>,flat chest,
masterpiece, simple background,best quality,1girl,solo, flat chest, <lora:yumemihoshino_pixiv:0.6>
N/A
Hidden For Public Users
masterpiece, simple background,best quality,1girl,solo, flat chest, <lora:yumemihoshino_pixiv:0.6>
masterpiece,1girl,solo, <lora:yumemihoshino_pixiv:0.65>,flat chest,
N/A
Hidden For Public Users
masterpiece,1girl,solo, <lora:yumemihoshino_pixiv:0.65>,flat chest,
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
masterpiece, simple background,best quality,1girl,solo, flat chest, <lora:yumemihoshino_pixiv:0.6>
N/A
Hidden For Public Users
masterpiece, simple background,best quality,1girl,solo, flat chest, <lora:yumemihoshino_pixiv:0.6>
masterpiece, best quality,1girl,solo, flat chest, outdoors,  <lora:yumemihoshino_pixiv:0.6>
N/A
Hidden For Public Users
masterpiece, best quality,1girl,solo, flat chest, outdoors, <lora:yumemihoshino_pixiv:0.6>
masterpiece, best quality,1girl,solo, flat chest,outdoors,  <lora:yumemihoshino_pixiv:0.6>
N/A
Hidden For Public Users
masterpiece, best quality,1girl,solo, flat chest,outdoors, <lora:yumemihoshino_pixiv:0.6>
masterpiece, best quality, outdoors,  closed eyes, smile, <lora:Yumemi_v2:1>
N/A
Hidden For Public Users
masterpiece, best quality, outdoors, closed eyes, smile, <lora:Yumemi_v2:1>
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
masterpiece, best quality, <lora:Yumemi_v2:0.95>
N/A
Hidden For Public Users
masterpiece, best quality, <lora:Yumemi_v2:0.95>
masterpiece, best quality, outdoors, looking at viewer, from below,  <lora:Yumemi_v2:1>
N/A
Hidden For Public Users
masterpiece, best quality, outdoors, looking at viewer, from below, <lora:Yumemi_v2:1>
masterpiece, best quality, outdoors, looking at viewer,  <lora:Yumemi_v2:1>
N/A
Hidden For Public Users
masterpiece, best quality, outdoors, looking at viewer, <lora:Yumemi_v2:1>
masterpiece, best quality, <lora:Yumemi_v2:0.95>
N/A
Hidden For Public Users
masterpiece, best quality, <lora:Yumemi_v2:0.95>
masterpiece, best quality, <lora:Yumemi_v2:1>
N/A
Hidden For Public Users
masterpiece, best quality, <lora:Yumemi_v2:1>
Loading Free Tools...

Similar Models

AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting

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.

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.