If you like my contributions to the community, please consider Buying Me A Coffee or check out my other sites on AllMyLinks
CFG 3-5 works best. Anything over 5 is trash.
Trained on 55 photos (face & full body)
Trained at 768 resolution
PROMPTS - "Mop", "from behind", "growling" and others are trained into the Lora. For a full list of the prompts/captioned used for training, check the Lora file's metadata in your webgui
WEIGHT - A weight of 0.8-1.0 will give the best mix of likeness and flexibility.
The checkpoint you use can heavily influence the likeness of a celebrity Lora. I train my Lora's on SD15, so you'll get the best likeness on any model that used SD15 as the base model. See this example for how a checkpoint can influence the look of a Lora.