If you like my contributions to the community, please consider Buying Me A Coffee or check out my other sites on AllMyLinks

TRAINING INFO

• Trained on 17 photos (face only)

• Trained at 768 resolution, so 768x768 inpainting works great.

RECOMMENDED SETTINGS

The training images used were cropped in from shitty early 2000's dslr's, so image quality wasn't great. I recommend using 'restore faces' but in your auto1111 settings, lower the restore faces strength to something like 0.7-0.8 which makes the effect less than the default setting of 0.5.

For txt2img, a weight of 0.7-0.9 will give a little more flexibility, but 1.0 isn't bad. A weight of 1.0 works really well for inpainting.

GETTING THE BEST LIKENESS WITH LORA'S

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.