Perfect World Xia Youyu

1. Notes on Generating Images:

1: Training materials should be 512*512, it is recommended that when using this model, the image size should not exceed 1024*1024. To achieve the same effect, the image must be generated using the base model I used for training! And be sure to use negative trigger words!

2: Reference the LoRa weight shown in the cover image.

3: ※ For bust portraits, you may not enable high-resolution restoration for good results. If you want to add details with high-resolution restoration, use the model R-ESRGAN4x+Anime6B with a redraw rate of around 0.3-0.4.

※ For full-body portraits, high-resolution restoration must be enabled, with a redraw rate of around 0.5.

※ It is recommended to enable the ADetailer facial feature for full-body portraits!

If you like this model, please feel free to star* ***ng it! Interaction from all of you, such as collecting, liking, and returning images, provides me with the greatest motivation and support. Once again, thanks to all the supporters!

2. Disclaimer (2024 Edition):

1. Do not sell this model on any website without the permission of the creator (myself).

2. Do not profit from using this model on other platforms without explicit written consent.