Verified: 4 days ago
SafeTensor
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
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