SDXL Vanilla LCM
Introduce:
Model has been fixed Asian face and enhanced Asian-porn, tried your prompt to create beautiful highly realistic nudity Asian girls.
The Base model DOESN'T incorporate any LoRa. (Prevent a decrease in LoRa performance.)
Recommend:
Train LoRa using the base model and accelerate image generation using the LCM version.
In the case of the sampler Euler a/LCM, only 8 steps can be used to generate clear images. (CFG is set to 2.5 or less.)
When multiple prompts (>75 tokens), facial features become unstable. Recommended to enable After Detailer yolov8n_v2 plugin to keep an Asian feature.
Parameters setting:
Sampler: Euler a/LCM
Steps: 6~10
Denoising strength: 0.2~0.5
Resolution : fixed one side 1024 (eg. 1024×1024, 1024×1280,768×1024)
CFG scale: 1.5-3
clip skip: 2
Trigger: 1girl
Negative prompts:
cartoon and cgi and painting and text
(suggestion: sdxl is best to only use a few negative prompts)
Does not require VEA.
And Enjoy it!
![](https://files.tungsten.run/uploads/5089/eff21f32aa9243739b8ae1cb6151852c/Bild1.webp)
![](https://files.tungsten.run/uploads/5089/9251b3f1c5f84c84abab2eaa0545782b/Bild2.webp)
![](https://files.tungsten.run/uploads/5089/71385f8b2bdf4bf5aa1435f83de64d0d/Bild3.webp)
![](https://files.tungsten.run/uploads/5089/a232bf4599614b2bae2742ab6b314c48/Bild4.webp)
![](https://files.tungsten.run/uploads/5089/dd87f16fb65d4d2f8d422cd5ae29245e/Bild5.webp)
![](https://files.tungsten.run/uploads/5089/96418bb74fd240deaaff4456ad60c92e/Bild6.webp)
![](https://files.tungsten.run/uploads/5089/2e3eb6f29d194f8d97982dfeaf7be330/Bild7.webp)
![](https://files.tungsten.run/uploads/5089/274cbd3dfb1b4162b97d2ed0f2614346/Bild8.webp)
SDXL Vanilla LCM
Introduce:
Model has been fixed Asian face and enhanced Asian-porn, tried your prompt to create beautiful highly realistic nudity Asian girls.
The Base model DOESN'T incorporate any LoRa. (Prevent a decrease in LoRa performance.)
Recommend:
Train LoRa using the base model and accelerate image generation using the LCM version.
In the case of the sampler Euler a/LCM, only 8 steps can be used to generate clear images. (CFG is set to 2.5 or less.)
When multiple prompts (>75 tokens), facial features become unstable. Recommended to enable After Detailer yolov8n_v2 plugin to keep an Asian feature.
Parameters setting:
Sampler: Euler a/LCM
Steps: 6~10
Denoising strength: 0.2~0.5
Resolution : fixed one side 1024 (eg. 1024×1024, 1024×1280,768×1024)
CFG scale: 1.5-3
clip skip: 2
Trigger: 1girl
Negative prompts:
cartoon and cgi and painting and text
(suggestion: sdxl is best to only use a few negative prompts)
Does not require VEA.
And Enjoy it!
![](https://files.tungsten.run/uploads/5089/eff21f32aa9243739b8ae1cb6151852c/Bild1.webp)
![](https://files.tungsten.run/uploads/5089/9251b3f1c5f84c84abab2eaa0545782b/Bild2.webp)
![](https://files.tungsten.run/uploads/5089/71385f8b2bdf4bf5aa1435f83de64d0d/Bild3.webp)
![](https://files.tungsten.run/uploads/5089/a232bf4599614b2bae2742ab6b314c48/Bild4.webp)
![](https://files.tungsten.run/uploads/5089/dd87f16fb65d4d2f8d422cd5ae29245e/Bild5.webp)
![](https://files.tungsten.run/uploads/5089/96418bb74fd240deaaff4456ad60c92e/Bild6.webp)
![](https://files.tungsten.run/uploads/5089/2e3eb6f29d194f8d97982dfeaf7be330/Bild7.webp)
![](https://files.tungsten.run/uploads/5089/274cbd3dfb1b4162b97d2ed0f2614346/Bild8.webp)