Generalization Version of Cheng Ling

1. Attention when generating images:

When training, if you added something, well, those who understand will understand.

Because the author is lazy, generally there is no information about the model, but some images produced by the model will be posted below each model. If needed, you can directly refer to the information below the image to create the picture.

1: Training material 512*512, it is recommended not to exceed 1024*1024 when using this model to generate images. For the same results, you must use the base model I used for training! And be sure to use negative trigger words!

2: The weight of this lora model refers to the cover image.

3: ※ Half-length portrait can be generated without high-resolution restoration, and it will have a good effect. If adding details with high-resolution restoration, use model R-ESRGAN4x+Anime6B with a redraw range of about 0.3-0.4

※ If you need a full-body portrait, definitely use high-resolution restoration, with a redraw range of about 0.5;

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

If you like this model, feel free to start running it! Everyone's interaction through collection, likes, and sharing pictures is my greatest motivation and support, thank you again to all supporters!

2. Disclaimer (Announced in 2024):

1. Without the creator's (my) permission, do not sell this model on any website.

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