Trouble getting my Lora to work? Start here.
If you love my work: Consider supporting the cause ;)
This seems to produce fairly good results now. Still may break some bones and screw up some occasionally, but I'm quite happy where i got with this model.
If you can't get good results with this model: Try the following steps:
-change your checkpoint. Some have an easier time with this pose than others
-clean up your prompt. try getting the pose to work first and then selectively add your desired elements back in.
-clean out your other lora: some of them may fight with this model and none of them will win.
-as always: try higher steps, lower cfg. Upscaling will probably not save you on this one though. Don't Upscale before you have a decent base.
-use some of the tags below
Taglist
To get the model to understand what's what, some pretty extensive manual tagging was necessary. Now the lora has a pretty long list of charged tags, that you may use (with varying effectiveness) in positive or negative: (don't go overboard though;)
Perspective: From above | from side | from angle | facing viewer -- these may also be combined
(From behind confused the model to much so it was removed from the dataset)
Setting: On floor | on ground | on table | on bed ...
Pose: arched back | head down | head back | feet crossed | feet together | knees together | knees apart feet together | elbows together | hands together elbows apart
Bondage related: (color) + gag | (color) + rope | natural rope | feet linked to hands | feet linked to shoulders | feet linked to hair | bound + (bodypart)