ModelsLab/Hardcore-Hentai-V12

https://civitai.com/models/136054?modelVersionId=232266

[This model is using BAKED VAE]

Prompt

best quality,

I like to keep the filler tags to a minimum, but you can get good result with more tags too.

Use danbooru tags or sentence-based prompts

Extension for tag autocompletion tagcomplete

Prompt Order for good composition

Tags at the start have more influence than the ones at the bottom.

The 7 blocks template (Work in progress):

1. view angle,

2. participants ->1girl, 1boy, sex acts, sexual positions,

3. posture, secondary actions,

4. body -> breasts size, body fat, age, stature, body part focus,

5. hair color, hair style, eyes, face expressions, cum location,

6. clothing,

7. location, furniture, objects,

You don't need to fill in every category, it's just for reference.

Negative prompt

worst quality, low quality, normal quality,

And whatever you don’t want to be on the image

Some people use the standard (worst quality, low quality: 1.4) + negative embeddings with good results too.

Samplers

I like DPM++ SDE Karras but you can use any sampler. Some samplers converge at a defined image, others keep changing with each step.

You can find better explanations here and here.

Steps

25+

CFG

• 7: standard

• 3–15: working range

Lower cfgs don’t follow the prompt as much. Higher cfgs will make “burned” images

The extension sd-dynamic-thresholding can play around with different CFGs at different steps

Sizes

• 1:1         [512, 512], [768, 768]

• 2:3         [512, 768]

• 3:2         [768, 512]

You can use Hires fix to get a bigger picture with more details