Sancai Ershen Restored Version

1. Attention when preparing the image:

When refining, if you add something, well, those who understand will get it.

Because the author is a bit lazy, usually there is no information about the model. However, some images made with the model will be posted below each model. If needed, you can directly refer to the information below the image to draw.

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

2: The Lora weight is referenced in the cover image

3: ※ Half-length portraits may not require high-resolution repair to achieve a good effect. If you want to add details with high-resolution repair, the model R-ESRGAN4x+Anime6B should be used, with a redraw range of about 0.3-0.4.

※ If a full-length portrait is needed, high-resolution repair must be applied, with a redraw range of about 0.5,

※ It is recommended to open ADetailer for facial features in full-body portraits!

If you like this model, feel free to start running it! Your interaction in collecting, liking, and returning images is the greatest motivation and support for me. Thank you to all supporters once again!

2. Disclaimer (Announced 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.