Experimental, the goal was a better likeness of the body in training images as well as better face. I used a few more images than i normally do and the added photos were poses. Small disclaimer: the training images weren't the best I got lazy. I trained at a lower resolution than I normally do as well as used lower resolution photos. It can also be tricky to get him to smile.

I recommend a strength of 1. The trigger word is l4c4, sometimes it helps make an image better, other times it'll add an extra finger or object. I believe it just depends on the prompt.

I usually generate images on Fitfux with Euler.

This is not based on a real person. Based on an image I generated.