A LoRA trained on high quality images to produce satisfactory facesitting images in Illustrious XL. Multiple angles supported, but results may vary depending on the base model and strength.
**some NSFW models understand this concept already, but by adding this LoRA it can be re-enforced to help with composition
Clip Skip: 2
Optimal Strength: 0.5-0.8
Trigger word: facesitting
V2: Manually Removed Tensor layers to reduce style bleed