Ning Yao Restore Version

1. Notes on Image Generation:

When refining the model, if additional elements are added, well, those who understand, understand.

Because the author is lazy, there is usually no information about the model, but some images made with the model will be posted below each model. You can directly refer to the information below the image to draw your own.

1: Training material is 512*512, it is recommended that the image size generated using this model does not exceed 1024*1024. For a similar effect, you must use the base model I used for training! And be sure to use negative trigger words!

2: The Lora weight should refer to the cover image.

3: ※ For half-length portraits, you can leave out high-resolution repair, and still achieve good results. To add details with high-resolution repair, use the model R-ESRGAN4x+Anime6B, with a redraw level of about 0.3-0.4.

※ If full-body portraits are needed, high-resolution repair is a must, with a redraw level of around 0.5,

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

If you like this model, feel free to start running it! Your interaction, collections, likes, and reposts are the biggest motivation and support for me. Thank you once again to all supporters!

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.