The lora was trained on approximately 1200 images of various types.
It can be set to realistic or anime style.
About 37% of the data are fursuit. The rest are images of various different styles.
Simple NSFW training was conducted.
Due to the limitations of the device's memory, the training resolution is 512.
Some display images:
模型在约1200张多种类型的图像上训练。
可以进行写实或动漫风格。
数据中大约37%是fursuit。其它是各种不同风格的图像。
进行了简单的NSFW训练。
受限于设备显存，训练分辨率为512