Trigger words: falling
Caution: Low success rate (depending on character/pose but around 10~15%)
Recommendation: Posing/anatomy is hard. You should use controlnet or have good descriptive prompt and specify the pose/anatomy or else you'll have low success rate.
Trained on 326 images. I might make a v2 and separate the falling dataset based on the pose, still thinking what would be the best strategy for better success rate.
I have a discord server (https://discord.gg/AmdETXDfHs) where you can have AI and off-topic discussions, ask for help, and having fun (gaming, playing with AI, etc).
I'll appreciate it if you support me on Patreon. I plan on sharing early access to my models and releasing more based on my milestones on Patreon .
Best place to DM me is via Twitter: twitter.com/CatNatsuhi928
Description
FAQ
Comments (1)
(Trial and error)
Falling LORA
LORA tries to depict falling and floating from the air like a certain director, but there are many messed up elements such as "not falling", "above the ground", "walking on the sea (this may be from below adding sky)".
It floats in the sky or abandons it in response to some tag. It is still a gacha element.