V1.0
New trigger on this version: "a woman doing a standing full frontbend pose"
But it seems like describing the pose works just as well if not even better,
example "a woman bending forward with her head between her legs standing on a rug"
V0.5
This first version seems buggy, might be bad keywording.
Might work better with longer prompts.
And it seems like WAN has trouble with upside down faces, much like other models
Description
New version with more consistent dataset, and less strange movements
FAQ
Comments (1)
I know you're putting in some level of effort, but your examples look like they should have been what prompted you to make this lora in the first place.
It's like you made a lora that can only produce the "before" image, instead of the "after" that it was meant to fix.