Basically, someone asked me to make a ragdoll lora. I haven't tested them, but I am told other ragdoll loras are not consistent enough.
After playing with this Lora for some time, I do not think that this is a good lora. However, I decided to share it anyway. It does what you need it to do for the most part, so I will have my own use cases for it. Not my best work, but play around with it. I can improve it down the line.
Here are the triggers so you can customize as you'd like:
Mandatory: ragdoll
Clothing: dress shirt, dress pants, dress shoes
I do not do this for money. It is a public service. If you want to thank me, post your generations on this page so I can see where the model can improve. Together, we will make Loras consistent!
If you want the same results as me it is imperative that you use the checkpoint this was trained on, which is in the suggested resources. In this case, Illustrious XL v2.
Why does this exist
I believe there should be a high quality lora or "super lora" for every character in existence. 30,000 steps, all angles, consistent results.
SERIOUS KNOWN ISSUE!!!!!: Because I am still learning, I mistakenly tagged things such as facial expressions in the dataset. This can be worked around by describing it a different way or lowering the weight. They still work, but some generations may have bleeding. The affected tags; biting lip, winking, confused, sad, smirk, angry, happy.