Please do not download.

1. Attention when generating images:

When refining, if you add something, well, those who know, they know.

Because the author is lazy, generally the models do not have information. However, there will be some images made with the models below each model. If needed, you can directly refer to the information below the image to draw.

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

2: The lora weights in this should refer to the cover image.

3: ※For half-body portraits, high-resolution repair is not necessary, and it already yields good results. When adding details with high-res repair, the model used is R-ESRGAN4x+Anime6B, with a redraw rate of around 0.3-0.4.

※If full-body portraits are needed, high-res repair must be used, with a redraw rate of around 0.5.

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

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

2. Disclaimer (2024):

1. Without the permission of the creator (me), do not sell this model on any website.

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