UPDATE:
USE the recommended Lora art-full or any other cinematic Lora to counter-balance this one. It makes results significantly better. My Lora should be set at -1 and the art-full Lora at +1.
Use at -1 for better images. It literally obeys your prompt words better (to an extent).
You'll see in the example images that base PonyXL doesn't have equal prompt understanding to this Lora set on negative.
Use at 1 or more for extreme ugliness.
There was no negative prompt in all the example images.
Description
FAQ
Comments (3)
This is another experimental Lora. The main goal is to make the algorithm not make mistakes, by training a Lora on its mistakes.
I even know what the problem is. There are too many artpieces in the negative dataset that are super-realistic or 3d. That's why the Lora keeps pushing towards painterly abstract art. But Civitai has an 1000 image limit for training and I would have to produce much abstract art/sketch failures for a sublime dataset.
Well,it's amazing!!!!!please add more!!!!!