1. Notes for Generating Images:

1: Training material size is 512*512, it is recommended that the image output size does not exceed 1024*1024 when using this model. To achieve the same effect, be sure to use the base model I used for training and make sure to use negative trigger words!

2: Please refer to the cover image for this LoRa weight.

3: ※For bust shots, high-resolution repair is not necessary to achieve good results. If adding details with high-resolution repair, use model R-ESRGAN4x+Anime6B with redraw amplitude around 0.3-0.4.

※For full-body shots, high-resolution repair is necessary. Choose a redraw amplitude of around 0.5.

※For full-body shots, it is recommended to open ADetailer for the face!

If you like this model, feel free to start running it! Your interactions, collections, likes, and returned images are the greatest motivation and support for me, thank you to all supporters once again!

2. Disclaimer (Year 2024):

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

2. Without explicit written consent, do not use this model to profit on other platforms.