This is the first SDXL LoRA I have trained. It is using the same dataset from the SD 1.5 version, excluding any images less than 1024x1024. While SDXL works well for many things out of the box, it still can't draw the traditional one-piece nurse uniform well, hence I made this LoRA.

What you should know about SDXL LoRAs:

• This LoRA is trained on SDXL 1.0 and will not work on non-SDXL based checkpoint such as animagine. (I might train a dedicated animagine version if there is enough interest)

• This LoRA can ONLY output photo realistic pictures. This seems to be a limit for SDXL LoRA training. You can no longer train a realistic clothing LoRA at CLIP1 and use it on a CLIP2 anime checkpoint. For anime outputs, I have to prepare a dedicated data set and train a separate LoRA.

While the model was trained on base SDXL model, it worked better on fine tuned checkpoints such as NewRealityXL.

If you know how to work around the limits mentioned above, please let me know!