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

I found a new AI tool Shakker, a best image to image tool. You can try it via https://www.shakker.ai

SDXL 的 LCM2 的基础模型,做了一些调整和优化,所以不适用LCM采样器,对SDE类别的采样器十分友好。


如果您不阅读繁琐的文档,那么这里推荐的配置如下:

采样器:DPM++ SDE Karras

CFG:1.5-2.5

步数:5


采样器推荐

针对SDE采样器比较友好,推荐采样器如下

  1. DPM++ SDE Karras - 速度慢,细节更完美(5步+)

  2. DPM++ 2M SDE Karras - 速度快(5步+)

  3. DPM++ SDE - 适合高步数(8步+),速度慢,细节更完美


CFG 推荐

CFG通常设置为1即可,可以调整为1-3,值越大,收拢速度越快,也就是可以使用更少的步数完成图片的生成。


测试用例

Prompt: (Well-bred's works:1.13),a beautiful girl, 24yo, skinny, pretty, [k-pop:detailed eyes, detailed beautiful face:0.5],

Negative Prompt: ng_deepnegative_v1_75t,negative_hand,disfigured,ugly,deformed,worst quality,low quality,extra limbs,extra legs,extra arms,deformed hands,deformed anatomy,umbrella,

采样:DPM++ 2M SDE Karras 或者 DPM++ SDE Karras

步骤:5+

尺寸:768 x 1024 以上


采样器测试

以5步为例,不同采样器效果如下

以10步为例,不同采样器效果如下

以20步为例,不同采样器效果如下


DPM++ 2M SDE Karras 步数测试

DPM++ 2M SDE Karras比较适合快速抽卡,从1步到8步的效果如下

第4步就形成了可用的图像,随着步数的增加,细节逐渐完善。

更多测试报告:https://www.yuque.com/mengxiangyuan-7fhri/eo7oa2/gtifyimxamueeixg?singleDoc# 《SDXL-LCM采样器测试报告》


My Github:

https://github.com/SoftMeng/ComfyUI_Mexx_Styler

https://github.com/SoftMeng/ComfyUI_Mexx_Poster

https://github.com/SoftMeng/ComfyUI_Mexx_Image_Mask

https://github.com/SoftMeng/stable-diffusion-prompt-pai

https://github.com/SoftMeng/Fooocus-zh

Or My LibLib:

https://www.liblib.art/userpage/0f37258e861044879b8728309c0ac3b0/publish

Images Generated With This Model

technical drawing render, (a girl) made of crystal and morganite and Aster, BREAK, pained, (Headshot:0.5), ash brown dreadlocks, luminous style, detailed eyes, detailed face, The Greatsword of Flame, tribalpunk, roses,
N/A
Hidden For Public Users
technical drawing render, (a girl) made of crystal and morganite and Aster, BREAK, pained, (Headshot:0.5), ash brown dreadlocks, luminous style, detailed eyes, detailed face, The Greatsword of Flame, tribalpunk, roses,
a beautiful girl,
N/A
Hidden For Public Users
a beautiful girl,
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
a beautiful girl,
N/A
Hidden For Public Users
a beautiful girl,
a beautiful girl,
N/A
Hidden For Public Users
a beautiful girl,
a beautiful girl,
N/A
Hidden For Public Users
a beautiful girl,
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
Anime style,a cartoon woman,very beautiful,very pretty,skinny,detailed Garnet eyes,pirate hat,wind,Ice and Snow World,[k-pop:0.018]
N/A
Hidden For Public Users
Anime style,a cartoon woman,very beautiful,very pretty,skinny,detailed Garnet eyes,pirate hat,wind,Ice and Snow World,[k-pop:0.018]
a beautiful k-pop girl,
N/A
Hidden For Public Users
a beautiful k-pop girl,
a beautiful k-pop girl,
N/A
Hidden For Public Users
a beautiful k-pop girl,
a beautiful girl,
N/A
Hidden For Public Users
a beautiful girl,
Leica M50 F/1.9, xxmixgirl, sophie gengembre style, dark style, photo of beautiful age 18 beautiful woman, sexy, 8k, hdr, (textured poison ivy skin:0.5), [full body:1.02], happy, BREAK, detailed, nightmare, horror, night view, fog, dim light, eerie moonlight lighting, grace, [lifelike, realism, vivid, naturalness:0.69]
N/A
Hidden For Public Users
Leica M50 F/1.9, xxmixgirl, sophie gengembre style, dark style, photo of beautiful age 18 beautiful woman, sexy, 8k, hdr, (textured poison ivy skin:0.5), [full body:1.02], happy, BREAK, detailed, nightmare, horror, night view, fog, dim light, eerie moonlight lighting, grace, [lifelike, realism, vivid, naturalness:0.69]
a beautiful k-pop girl,
N/A
Hidden For Public Users
a beautiful k-pop girl,
a beautiful k-pop girl,
N/A
Hidden For Public Users
a beautiful k-pop girl,
Loading Free Tools...

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.