Yao Xi

1. Notes for Generating Images:

When refining the model, if you added something extra, well, those who understand will get it.

1: Training material is 512*512, it is recommended not to exceed 1024*1024 when generating images using this model. For similar effects, make sure to use the base model I trained with! Also, be sure to use negative prompt words!

2: The LoRA weight reference is the cover image.

3: ※ For half-length portraits, high-resolution restoration is not necessary, and good results can be achieved. If adding details with high-resolution restoration, use model R-ESRGAN4x+Anime6B with a redraw range of around 0.3-0.4.

※ If you need a full-body portrait, high-resolution restoration is a must, with a redraw range of around 0.5,

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

If you like this model, feel free to start running it! Your interaction, collection, likes, and sending back images are my greatest motivation and support, thank you once again to all supporters!

2. Disclaimer (2024 declaration):

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

2. Without explicit written consent, do not profit from using this model on other platforms.