Jiqing generalization version

1. Notes on Image Generation:

When refining the image, if something was added, well, understanding is mutual.

Because the author is somewhat lazy, generally the models do not have information. However, some images produced by each model will be posted beneath each model. If needed, you can directly refer to the information below the image to draw.

1: Training material size should be 512*512, it is recommended that the image size produced by using this model should not exceed 1024*1024. For the same effect, it is essential to use the base model when generating images! And definitely use negative trigger words!

2: The Lora weights reference the cover image.

3: ※ Portraits don't necessarily require high-resolution restoration; good results can be achieved without it. If adding details with high-resolution restoration, for the model R-ESRGAN4x+Anime6B, use a redraw ratio of around 0.3-0.4.

※ If full-body portraits are needed, high-resolution restoration must be used, with a redraw ratio of around 0.5.

※ For full-body portraits, it is recommended to activate ADetailer for the face!

If you like this model, feel free to start running it! Everyone's interaction, collection, likes, and returning images provide me with the greatest motivation and support. Thanks again to all supporters!

2. Disclaimer (as of 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.