Modify the weights of the LoRA to achieve the desired result.
This was also trained with the expanded VAE located here. Please use this VAE when inferring with this LoRA.
Description
Faces still don't look good at a distance, so you'll have to inpaint them.
Changelog:
Initial release
Training Data:
Used bmaltais's implementation of kohya_ss LoRA training scripts.
Total Images: 15 total high resolution images: six full body, four head shots, five chest-up
Regularization Images: 300 total "sexy woman" regularization images from ProGamerGov's dataset at huggingface.
Trigger word: lauren boebert
Training Steps: 2700
Unet Training Rate: 5.0e-06 (0.000005)
Text Encoder Training Rate: 5.0e-05 (0.00005)