bad_pictures - v3.0
Related Keywords & Tags
Highlighted images
Recommended Prompts
masterpiece, 1girl, looking at viewer, white hair, blue eyes
Recommended Negative Prompts
bad_pictures,(bad_pictures:1.1),(bad_pictures:0.8)
bad_pictures
Recommended Parameters
samplers
steps
cfg
resolution
other models
Tips
Keep your token usage to below 75 for best effect.
Most of the time, you don't need to add other quality specifiers to your prompts (e.g. worst quality, bad quality).
If you notice any artifacts, try adjusting the weighting of the negative prompt (bad_pictures) between 0.8 and 1.2.
Version Highlights
I used the previous version as positive prompt to generate 75 additional images and used those to further train for 100 epochs.
A very versatile negative embedding that helps generate high quality images. Higher chances of producing normal looking hands in realistic images.
Best Practices:
Keep your token usage to below 75 for best effect. Most of the time, you don't need to add other quality specifiers to your prompts (e.g. worst quality, bad quality).
Usage:
Negative prompt: bad_pictures
If you notice any artifacts, you can try increasing or decreasing the weighting like this: (bad_pictures:1.1) or (bad_pictures:0.8).
Values between 0.8 and 1.2 seems to work best (clip size 2):
Tested on:
VersaMix (https://civitai.com/models/20865/versamix)
Anything V5 (https://civitai.com/models/9409?modelVersionId=30163)
Contributor
Model Details
Model type
Base model
Model version
Model hash
Trained words
Creator
Discussion
Please log in to leave a comment.
