Sign In

bad_pictures

5k

54.1k

4m

587

Verified:

PickleTensor

Type

Embedding

Stats

49,676

4m

503.3k

Reviews

Published

May 9, 2023

Base Model

SD 1.5

Training

Steps: 17,500
Epochs: 100

Trigger Words

bad_pictures

Hash

AutoV2
522AC70BA9
VI

Vivipeg

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: