Introduction: This version is based on a major update and improvement of 3.2. It can be adapted to full-body. Even if your tag is not good, the model will automatically modify the screen, but as a result, the model's face will be quite similar.

If you feel younger, you can try using another character, LoRa, or improve your TAG.

This model doesn't seem to need extra points. My plot size is 768*1024, and the sharpness is pretty good. Vertical images are recommended; horizontal images may not be clear.

Eulera is all you need.

(dpm++sdekarras, DDIM is good too) == Introduction: This version is a major update and improvement based on 3.2, which can adapt to full bodies. Even if your tag is not good, the model will automatically modify the screen, but the faces produced by the model will be quite similar.