V1. The model works just fine out of the Box. The Face is a bit distorted. Best to use "restore Faces" or even better just generate the pictures and upscale them with GFPGAN turned on.

V2. works without "resrtore faces" but the face looks sometimes older. So use "young" or similar in the prompt.

You don't need a trigger word to get this model working, however I used "EmilyBloo" in the training.

Hope you like it, and I am waiting for your feedback