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
Description
FAQ
Comments (7)
W Furry LoRA. Sad I can't generate this at native 2K resolution though
Too much biased to penis, it's hard to generated female furry😢
Try using other nodes for disabling restrictions or LoRa.
To be honest, the model basically didn't learn the specific content of nsfw at all here. It didn't even learn the main features of my nsfw data, not even the main canine data.
I might just have guided the model to activate its own capabilities. According to my tests, reducing the Lora weight actually performed better in terms of shape quality.
In the nsfw aspect, I don't have much data and added it relatively late. However, during the initial preparation, I considered data balance, and the quantity won't differ too much. But in the overall training data, the female data is indeed insufficient.
@hxyy got it
Having opposite problem lol, making half penis half vagina, really need a gay model that isn't synthetic data slop
@hxyy Same experience
@GPUPoorChad I can't do this well because I only have a 5060 Ti; I'm limited to training at 512 resolution with low model precision.
NSFW content isn't the focus of my training.