Xiao Wu Original Version

1. Considerations for Image Output:

When refining the image, if something was added, well, for those who understand, they know.

Due to the laziness of the author, there is usually no information on the model, but some images produced using the model will be posted below each model. Those who need it can directly refer to the information of the image below to draw.

1: Training materials are 512*512, it is recommended that the output size of the model should not exceed 1024*1024. To achieve the same effect, you must use the base model I used for training! And be sure to use negative trigger words!

2: The Lora weight should reference the cover image.

3: ※ For half-body portraits, you can choose not to enable high-resolution restoration, which will still yield good results. If you choose to add details with high-resolution restoration, the recommended model is R-ESRGAN4x+Anime6B, with a re-creation proportion around 0.3-0.4.

※ If you need a full-body image, high-resolution restoration must be enabled with a re-creation proportion around 0.5.

※ For full-body images, it is recommended to activate the ADetailer for facial features!

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

2. Disclaimer (effective 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.