新版本是在Illustrious模型上训练的,我没有测试它与其他模型的兼容性,不能保证它能正常工作。
The new version was trained on the Illustrious model, I didn't test it for compatibility with other models and can't guarantee it will work.
训练图像均来自于公开网络,本模型仅用于学习,请勿用于盈利与非法途径。
The training images are from the public network, this model is only for learning, do not use for profit and illegal ways.
我推荐0.3~0.8的权重。
I recommend a weight of 0.3~0.8.
Description
FAQ
Comments (5)
大佬出现了uvu
SCREEEE!!
🐺
怪形这玩意其实不适合很多模型 现在不少跑色图跑的很好的模型 本身是对图片有一定的美化的 你用这种模型训练的话 图片还是会偏移 练tag啥的最好还是基础光辉或者noob,wai我试了,色图没问题,概念和这种猎奇的基本理解力不如noob
Ty for the updates on this, its a fun model. I am curious though, I see 1.5 and pony and illus being newer, did you ever make 1 in sdxl?

