cyq,<lora:sssss-000016:1>,(upper_body:1.1),(Just one person),(One person),(ultra wide angle shooting),best quality,(realistic photograph),mysterious,looking at viewer,Highest pixel,highest quality,large aperture,cinematic_angle,<lora:é²é¢å¤´é«é©¬å°¾:0.3>,forehead,pony tail,<lora:FilmVelvia3:0.5>,
(8k, Best Quality, Masterpiece),Super Detail,(High Detail skin),illustration,
advanced fashion human photography,(dynamic pose:1.1),background fade,(nude:1.4),solid gradient background,beautiful shadows,(artoise:1.1),(advanced photography:1.1),<lora:å
æ»è
¹é¨:0.25>,cinematic_angle,<lora:sssss-000020:0.8>,a world of ice and snow,
cyq,<lora:sssss-000020>,(upper_body:1.1),(Just one person),(One person),(ultra wide angle shooting),best quality,(realistic photograph),mysterious,looking at viewer,Highest pixel,highest quality,large aperture,<lora:Flashlight éªå
ç¯è¶çé£_v1.0:0.2>,<lora:è¶çæå¾®ç³é£æ ¼_v1.0:0.5>,cinematic_angle,<lora:é²é¢å¤´é«é©¬å°¾:0.3>,forehead,pony tail,
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
本模型不支持商用，仅可用于学习。
底模： 墨幽的姐姐——墨幽岚_v1
两个版本只是训练参数不一样，数据集都是一样的。
我使用的：
直接使用权重：0.8左右
如果用After Detailer
则正向提示词权重 0.2-0.4，After Detailer权重：0.9-1
模型：MoyouArtificial_v1060 majicmixRealistic_v7 墨幽的姐姐——墨幽岚_v1
采样：dpm++ 2M Karras、DDIM、Restart
步数：30-50
分辨率：512*768
高清：4xUltrasharp 8x_NMKD-Superscale_150000_G 15步 重绘幅度0.3
CFG：7
Images Generated With This Model
Loading...
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.