General purpose for settings, environments, landscapes. This is the culmination of a decade of Fractal Exploration.

The basic idea is that I've built up a large collection of Fractal Art over the years, and have passed those fractals through an AI upscaler with fascinating results. So I trained a LoRA based on these images with HollowStraberry's LoRA training setup (https://github.com/hollowstrawberry/kohya-colab).

I was very happy with the results. I use it on most of my SDXL projects. Can also be used on things besides Landscapes with interesting results. I recommend 60-80% weight, maybe <50% if you are doing something character-focused, but you can even go over 100% with cool results. There is no keyword prompt.

You can see some of the source images here: https://fractalvisions.space/fractaiscapes/ and see more "fractai" and the process of creating the training images here: https://fractalvisions.space/fractai/

If you like this LoRA, share some images you made with this, leave a like, and/or leave a comment of what you think.

Donations are greatly appreciated: https://ko-fi.com/mitchellflautt