底模:SDXL

主页:https://civitai.com/models/827184/wai-nsfw-illustrious-sdxl?modelVersionId=1068947

版本:v7.0

比如这个,虽然ai味儿很重但准确率很高,多人都行

If you want to use more my checkpoint online generation, please visit here.

https://tensor.art/u/762555264535746522

All example images are generated at 1024x1360, without using AD and hires fix.

 

Online generation has been added.

 

Style and Character reference

https://civitai.com/articles/8977/epis-embedding-maps-and-graphs

 

Fusion style reference for v7 (chinese)(Thanks to Endericedragon606105 for the provision.)

网友提供的v7融合画风参考( 感谢Endericedragon606105提供)

300Styles-waiNSFW.html · sieecc/SOKI at main

 

 

 

 


v7

 

  • Adjusted the color balance,

  • Reduced the probability of overexposure,

  • Added more composition elements, incorporated some special effects,

  • More NSFW.

 

 

Some of the pony LoRA can be used, but please pay attention to the format when using them.

Please add a comma at the end.

Such as :

<lora:xxxxx:1>,

 

 

Steps: 30

CFG scale: 5-7

Sampler: Euler a

Not very necessary to use ADetailer correction

 

Positive Prompt

masterpiece,best quality,amazing quality,

 

Negative Prompt

Base:bad quality,worst quality,worst detail,sketch,censor,
Optional:simple background,transparent background

 

 

 


 

 

V6

Positive Prompt and Negative Prompt is Updated, please check again.

More NSFW , overall balance adjustment.

 

Steps: 30

CFG scale: 5-7

Sampler: Euler a

Not very necessary to use ADetailer correction

 

Positive Prompt

masterpiece,best quality,amazing quality,

 

Negative Prompt

Base:bad quality,worst quality,worst detail,sketch,censor,
Optional:simple background,transparent background

 

 

 


 

V5

I further adjusted the weights to better support the SDXL and Pony LoRA, optimizing some of the composition logic and backgrounds.

 

V4

Increased more training materials and adjusted the default weights.

Some of the pony LoRA can also be used, and you may need to adjust the weight to over 1 for testing.

 

 

 

V3

adjusted the weights and changed the default style.

 

V2

I adjusted the default style weight to make the model easier to use. I optimized the composition and human anatomy, and added more NSFW materials.

 

The example images are all generated directly at 1360x1024. NO AD NO hires fix.

 

Please try experimenting with artists and characters on your own. I have only tested a portion of popular artists and characters that can be used directly.

 

Steps: 30

CFG scale: 5-7

Sampler: Euler a

Not very necessary to use ADetailer correction

 

Positive Prompt

masterpiece,best quality,amazing quality,very aesthetic,absurdres,newest,

 

Negative Prompt

lowres,(bad quality,worst quality:1.2),bad anatomy,sketch,jpeg artifacts,ugly, poorly drawn,(censor),blurry,watermark,simple background,transparent background

 

 

 


v1

 

Base: IllustriousXL

Since the adjustments were minimal, the artists and characters available in the base model can still be used directly.

 

Steps: 30

CFG scale: 7

Sampler: Euler a

Not very necessary to use ADetailer correction

 

Positive Prompt

 

masterpiece, best quality, high resolution, absurdres,uncensored,

 

Negative Prompt

 

worst quality,bad quality,bad hands,very displeasing,extra digit,fewer digits,jpeg artifacts,
声明:本站所有文章,如无特殊说明或标注,均为本站原创发布。任何个人或组织,在未征得本站同意时,禁止复制、盗用、采集、发布本站内容到任何网站、书籍等各类媒体平台。如若本站内容侵犯了原著者的合法权益,可联系我们进行处理。0
发表评论 共有条评论