Download
1 variant available
This asset is only available as a PickleTensor which is an insecure format. We've taken precautions to ensure the safety of these files but please be aware that some may harbor malicious code.
51,5610 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9,0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
3.6M0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9M
523.3K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
(4,798)
May 9, 2023
SD 1.5
I used the previous version as positive prompt to generate 75 additional images and used those to further train for 100 epochs.


3470 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
6.8K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
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)
