Download
1 variant available
1.3K
24.2K
Holding Pendulum / Hypnotizing Viewer LoRA
LoRA request queue on my discord: https://discord.gg/DAfjhRfyEM
This model was trained using 24 images of characters holding a pendulum. It was trained on the NAI model so it should work with most anime based models. It has some issues that you will have to work around tho. If you don't prompt character traits it tends to add too many pendulums, and it still happens even if you do. It also adds some weird things behind the character sometimes due to there being hypnosis things and other stuff there in the imageset. So be prepared to inpaint those out, or let me know what to put in the negative prompt to get rid of it :3c
Recommended weight is between 0.8 and 1.
The triggerwords are hypnotizing viewer, holding pendulum.
Note: This was made exclusively on anime images and on an anime checkpoint. Feel free to post images on realistic, semirealistic etc. checkpoints, but do not rate it on that! This was made to be used on anime checkpoints so keep reviews for that!