bad_pictures - v3.0
精選圖片
推薦提示詞
masterpiece, 1girl, looking at viewer, white hair, blue eyes
推薦反向提示詞
bad_pictures
bad_pictures
推薦參數
samplers
steps
cfg
resolution
other models
提示
Keep your token usage below 75 for best effect.
Typically, you don't need to add other quality specifiers like worst quality or bad quality to your prompts.
To adjust artifacts, try increasing or decreasing the weighting of the negative prompt between 0.8 and 1.2.
版本亮點
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)
