Models>

Lee Kwang-soo | 이광수 | 李光洙 | Running Man

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

韩国著名演员、综艺人,RunningMan成员之 李光洙

这是初版的lora,用了60张照片训练的,欢迎使用返图并留下建议。

推荐使用麦橘大佬的majicMIX realistic底模。

参数设置可参考:

steps: 25, sampler: DPM++2M Karras, CFG Scale: 8,lora权重0.8左右。

Lee Kwang-soo is a well known South Korean actor, entertainer who is a member of the TV program Running Man.

This is the first version that was trained with 60 photos.

I'll keep working and updating.

majicMIX realistic 麦橘写实 - v6 | Stable Diffusion Checkpoint | Civitai

is recommended.

Try using DPM++2M Karras with 25 steps and 8 of CFG Scale, Lora weight of 0.8 or lower.

Images Generated With This Model

1boy, kwangsoo, indoors,  <lora:Celebrity-lee_kwangsoo_v1:1>, smile, 
simple background, 
masterpiece, high quality, highres, realistic,
1boy, kwangsoo, indoors, <lora:Celebrity-lee_kwangsoo_v1:1>, smile, simple background, masterpiece, high quality, highres, realistic,
1boy,  <lora:Celebrity-lee_kwangsoo_v1:0.8>, kwangsoo, smile, indoors, suit,
masterpiece, high quality, highres, realistic,
1boy, <lora:Celebrity-lee_kwangsoo_v1:0.8>, kwangsoo, smile, indoors, suit, masterpiece, high quality, highres, realistic,
1boy, smile, portrait ,<lora:Celebrity-lee_kwangsoo_v1:0.8>,kwangsoo, suit,
simple background, 
masterpiece, high quality, realistic,
1boy, smile, portrait ,<lora:Celebrity-lee_kwangsoo_v1:0.8>,kwangsoo, suit, simple background, masterpiece, high quality, realistic,
link of zelda
 simple background <lora:pksp_trainer_V1:0.8>
link of zelda simple background <lora:pksp_trainer_V1:0.8>
spiderman
simple background   <lora:pksp_trainer_V1:0.8>
spiderman simple background <lora:pksp_trainer_V1:0.8>
santa claus, strong old rich man
 simple background <lora:pksp_trainer_V1:1.0>
santa claus, strong old rich man simple background <lora:pksp_trainer_V1:1.0>
man in a suit, bicycle
 simple background <lora:pksp_trainer_V1:0.8>
man in a suit, bicycle simple background <lora:pksp_trainer_V1:0.8>
elsa in frozen
 simple background <lora:pksp_trainer_V1:0.8>
elsa in frozen simple background <lora:pksp_trainer_V1:0.8>
vampire Dracula
simple background   <lora:pksp_trainer_V1:1.0>
vampire Dracula simple background <lora:pksp_trainer_V1:1.0>
werewolf, man-wolf,
simple background   <lora:pksp_trainer_V1:0.9>
werewolf, man-wolf, simple background <lora:pksp_trainer_V1:0.9>
sexy nurse,
simple background   <lora:pksp_trainer_V1:0.9>
sexy nurse, simple background <lora:pksp_trainer_V1:0.9>
homeless
simple background  <lora:pksp_trainer_test2:1>
homeless simple background <lora:pksp_trainer_test2:1>

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.