The combined versions lean most heavily toward realism.
I am generating images in more cartoon/amine styles and using those to balance the datasets one concept at a time.
Version 2.0 and Refined both do fisting really well. It was the easiest concept to train, so I will likely wait to do self-fisting until last.
Recommended settings:
Cfg: 5
Steps: 25-28
Weight of 1 or 0.9.
Hi-res your image with a lower weight 0.6 or 0.7.
This Lora does a lot of different things. Look at the prompts to see how to group triggers, and please share your posts to my model.
Description
This is a single concept version. I'm attempting to diversify the datasets with more illustrated images. For this concept, there is no booru tag, and really no way that I could find to get cartoon, anime, pics for a dataset. So, I've added in some more cartoon and semi-real generated images to help reduce the realism influence on the dataset.
It's a work in progress.
For now, I'd recommend generating at or near 1.0 and doing your hi-res at .5 or .6.
Using a lower cfg and steps also helps.
It'd help me a lot with my ultimate goal if you use my lora and post your more cartoony or anime style images.