Modify the weights of the LoRA to achieve the desired result. The base model for SD 1.5 will look the best. However I had great results with Protogen, Dreamlike Photoreal, and Realistic Vision as well, and various blends.
This was also trained with the expanded VAE located here. Please use this VAE when inferring with this LoRA.
Description
Used bmaltais's implementation of kohya_ss LoRA training scripts.
I don't quite have her smile trained yet! You can get different expressions by providing words like "smiling" or "grinning".
Total Images: 19 total high resolution images
Regularization Images: 300 total "sexy woman" regularization images from ProGamerGov's dataset at huggingface.
Trigger word: alexandriaocasiocortez woman
Training Steps: 1900
Unet Training Rate: 5.0e-05 (0.00005)
Text Encoder Training Rate: 5.0e-05 (0.00005)