Something Unlimited Style Lora. I recommend using 0.8~1.0 strength.
Trigger Word: somethingunlimited
Please look at example images for help
I use additional tools for my generations so my images may be different from yours. If you want to know what I use, please look at my guide.
My Socials | Support me on Patreon or Ko-fi (If you want)
Description
Trained on 89 images with new training method.
*I recommend using 0.9 strength if you are using it for general stuff. Combining with other loras use 0.5-0.6 strength. I personally like 0.6 and I tend to get better results.*
FAQ
Comments (7)
I think this might need a little more tinkering. I've noticed I get a grey background almost all the time. Even with scenery prompts.
yeah it's kind of unfortunate, most of the images I trained off of have a grey background. I'm still learning how to make backgrounds more relevant for the generations and i do want to improve this a tiny more because it isn't perfect but comes very close.
new to the ai art how do i do this
I recommend looking at this. There is no simple answer really and this explains it better than what i can. https://github.com/civitai/civitai/wiki/How-to-use-models#lora
first you need to get automatic 1111 working either from a premium account for google colab or a very beefy home computer, then you download a base model and the LORA you want to use and put them in the folders Automatic 1111 tells you to.
@malroth_returns687 @crackanutbar119 beefy might not be the best word for this but have at least a gpu with 4GB of Vram. You can also try using a service that is partnered with civitai. The allow free uses.
@malroth_returns687 very beefy is subjective, if u have 8gb of vram it is good enough...