Ancient Xuner Generalized Version

1. Notes on Drawing:

The fidelity and generalization of the original version are very good. The generalized version may not be very faithful, but the skin and clothing will be smoother. I recommend using the original version.

When refining, some things have been added, well, those who understand, understand.

Because the author is lazy, usually the models do not have information, but some images created by the model will be posted below each model. If needed, you can directly refer to the information of the images below to draw.

1: Training materials are 512*512. It is recommended that the output image size of this model should not exceed 1024*1024. For a similar effect, be sure to use the base model I trained with! And be sure to use negative prompts!

2: The weights of this Lora reference the cover image.

3: ※ For half-length portraits, high-resolution restoration is optional. It yields a good effect without it, but if you choose to enhance details, use the model R-ESRGAN4x+Anime6B and set the redraw amplitude to around 0.3-0.4

※ If full-length portraits are needed, high-resolution restoration is a must, with a redraw amplitude of around 0.5

※ For full-length portraits, it is recommended to enable ADetailer for the face!

If you like this model, feel free to start running it! Your interaction through collections, likes, and feedback images provides me with the greatest motivation and support. Once again, thank you to all supporters!

2. Disclaimer (issued in 2024):

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.