Please react to my videos: https://civarchive.com/user/ntc/images?sort=Most+Reactions
Trained on 2000 steps
"#0.0393|~eyes looking up towards camera from above:0.2"
https://github.com/ntc-ai/conceptmod
Lora -4 - 3.5 on animation using lora_anim python file in the conceptmod repo.
Animation command:
> python3 lora_anim.py -s -4.0 -e 3.5 -l "zoomin" -lp ", eyes looking up towards camera from above" -np "nipples, weird image." -n 25 -sd 7 -m 3.5
all examples use the trigger phrase
Description
FAQ
Comments (10)
Thanks for including the code and example command line. Going to have to check that out.
Make zoom out please!
how on earth does one do that? that is so cool!
can someone say how can i do that ?
Hey, the instructions are in the description. I used the command line on linux to:
1) train the lora on the given phrase (train_sequential.sh)
2) create the animation with lora_anim.py
Can you tell me how this is made
Hey,
It's made by training a lora on the #0.0393... words. Then that is plugged into the lora_anim.py
This is so underrated, published 4 months ago and barely got noticed.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.