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):
-
participants ->1girl, 1boy, sex acts, sexual positions,
-
posture, secondary actions,
-
body -> breasts size, body fat, age, stature, body part focus,
-
hair color, hair style, eyes, face expressions, cum location,
-
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