Sign In

WAI-NSFW-illustrious-SDXL

13.3k
173.8k
11.1m
3.4k
Updated: Feb 16, 2025
base modelanimesexyhentai
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
14,706
878,737
Reviews
Published
Feb 14, 2025
Base Model
Illustrious
Usage Tips
Clip Skip: 2
Hash
AutoV2
C3688EE04C
New Years 2025 Badge
WAI0731's Avatar
WAI0731

Wai v11 online generation attention

Please adjust the CFG to between 4 ~ 5, step 12~30

this model has issues with online generation on civitai

Local CFG 7 can be used normally


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

https://tensor.art/u/762555264535746522

You can run WAI-NSFW-illustrious-SDXL and use its API on SinkIn: https://sinkin.ai/m/nGyN44N

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


Wai v11 useful information: by anotherstabledif1714

1. If you want a more flat/anime kind of picture, add "3d" into the negative. Persoanlly I use the negative of "bad quality,worst quality,worst detail,sketch,3d"

2. Personally I would use a CFG scale of 3.5-5 at max if you use loras, otherwise you can go up to 6, but 7 and higher could lead to some artifacts on bodies in NSFW pictures.

3. You can throw in all Illustrious Loras and even the most PONY Loras and they work!

4. Handles complex prompts like very well, so you dont have to stick to 100% to Danbooru tagging

5. Schedule type can be Automatic or Karras, depends on what you like more

6. You dont really need any positive tags like "masterpiece", if you want classical anime pictures or work with Loras that increase the quality of the picture


v11

The overall weight adjustment, the default art style is not so childish. Further attempt to adjust the level of detail in the image.

All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.35.

The VAE is already integrated, please do not ask such questions anymore.

Steps: 30

CFG scale: 5-7

Sampler: Euler a

Positive Prompt

masterpiece,best quality,amazing quality,

Negative Prompt

Base:bad quality,worst quality,worst detail,sketch,censor,

v10

  • Improved drawing accuracy

  • More composition.

All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.35.

The VAE is already integrated, please do not ask such questions anymore.

Steps: 30

CFG scale: 5-7

Sampler: Euler a

Positive Prompt

masterpiece,best quality,amazing quality,

Negative Prompt

Base:bad quality,worst quality,worst detail,sketch,censor,

v9

  • Increased body stability and accuracy.

  • Adjusted the composition logic.

  • Added training with some new materials.

  • more better pony lora support.

All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.

Steps: 30

CFG scale: 5-7

Sampler: Euler a

Positive Prompt

masterpiece,best quality,amazing quality,

Negative Prompt

Base:bad quality,worst quality,worst detail,sketch,censor,


v8

  • Optimized composition and background logic.

  • Tried to fix some minor issues.

All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.

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,

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,