Xiao Xuner's new creation model restoration edition

1. Drawing Notice:

The original version has good fidelity and generalization, while the generalized version may not be as faithful but the skin and clothes will be smoother. I recommend using the original version.

There are some extra elements added during refining, but well, those who know, know.

Due to the laziness of the author, there is usually no information provided for the models. However, some images generated by the models will be shared below each model. If needed, you can directly refer to the information below the image to draw.

1: Training material is 512*512, it is recommended that when using this model for drawing, do not exceed the size of 1024*1024. For the same effect, you must use the base model I used for training! And be sure to use negative prompt words!

2: The Lora weight reference is based on the cover image.

3: ※For half-body portraits, high-frequency repair is not necessary, as it already yields a good effect. If adding detail repair, use model R-ESRGAN4x+Anime6B with a re-rendering range of around 0.3 to 0.4

※If full-body portraits are needed, high-frequency repair is essential, with a re-rendering range selected around 0.5.

※For full-body portraits, it is recommended to enable the ADetailer for the facial features!

Enjoy using this model! Your interactions, collections, likes, and reposts are my greatest motivation and support. Thank you to all supporters once again!

2. Disclaimer (2024 Edition):

1. Without the permission of the creator (me), do not sell this model on any website.

2. Without explicit written consent, do not use this model to profit on other platforms.