Wang Dong'er Veil Restoration Version

1. Notes for Image Output:

I can restore the original version very well in terms of fidelity and generalization, while the generalized version may not be as faithful but skin and clothing will appear smoother. I recommend using the original version.

Some elements may have been added during synthesis, but well, those who know, know.

Due to the laziness of the author, general models may lack information. However, some images produced using the model will be shared below each model. If needed, you can refer to the information below the images to draw.

1: Training material size is 512*512. It is recommended that the output size of the model should not exceed 1024*1024 for equivalent results. Be sure to use the base model I used for training and always use negative trigger words!

2: This Lora weight refers to the cover image.

3: ※ For half-portraits, high-resolution restoration can be skipped for good results, but if detailed enhancement is desired, use the model R-ESRGAN4x+Anime6B with a redraw magnitude of around 0.3-0.4.

※ For full-body portraits, high-resolution restoration is a must with a redraw magnitude of about 0.5.

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

Feel free to star* ***ng this model if you like it! Your interaction such as collecting, liking, and sharing the images is the greatest motivation and support for me. Thank you once again to all the supporters!

2. Disclaimer (2024 Edition):

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

2. Do not use this model for profit on other platforms without explicit written consent.