This lora was trained on some horror movies. I don't really know how good it is, I think 3000 samples may not have been enough, or it might have slight overfit.
For best results use h0rr0r, and then date of the movie, like 1982, 2020 or 2005, etc... then directed by James Cameron, or whoever you want, and then the prompt. You don't have to use year and director, it's just a trend I saw in the tagging and seems to give some extra flavor.
Like I said, there may be overfit, so if your prompt is not very long I suggest a lower power than 1. Longer prompts seem to yield better results.
Description
FAQ
Comments (1)
I don't know how to use the one style, yet I will pick this one up in case. The look is rafter nifty looking. I wonder if an Illustrious version will be made one day.
I wonder if 3,000 pictures is normal for making such loras. Most loras I make tend to be between 15 to 150 pictures.











