It is forbidden to sell the images generated by this model for profit, and it is forbidden to sell this model. Thank you
禁止将此模型生成出的图片进行出售盈利行为，禁止出售此模型。谢谢
Please read about this version
The model generalizes and transfers very well, and you can use it on almost any submodel (except SDXL).
If you want to restore the original painting style, you need a lot of prompt words to correct, the model's data set contains all nekopara images, the game illustrator artbook and fanclub cover, theoretically it can restore all images
Recommended weight 0.5-1.1
prompt
heterochromia,nekoyezi,1girl, cat girl, bell, solo, long hair, jingle bell, animal ears, neck bell, <lora:super-yezi-SUrh-v9:0.85>
Description
FAQ
Comments (8)
I need to clarify
Some people say that my model does not support nsfw images, which I think is wrong, its compatibility with nsfw graphics is related to the bottom model, and the training set contains almost all nekopara nsfw images. The generalization of the model itself is also great, but I personally do not like nsfw images, not in the image set to generate it
After some testing I agree with you. By the way, are you planning to do a Nekopara OVA style checkpoint?
@CarolLui ova? Anime style?
@Rnglg2 Yeah, basically its anime style
@CarolLui This may have to wait, my training method is very demanding on the data set. And I have been training the Feng model recently, the previous Feng model was too old, I had to update it.
@CarolLui But I'll probably try to train one by then, and I'll release him whether it turns out well or not
@CarolLui However, you can use some large models similar to ova anime style, using my lora, should be able to achieve similar results
@Rnglg2 Anime style model sounds like a good idea! I think I already know what I can use it for..