I found a new AI tool Shakker, a best image to image tool. You can try it via https://www.shakker.ai ,it can help you:
-Remix: Upload a picture. Just switch the prompts, and you can create stunning images in the same style.
-Style Transfer: Shakker not only extracts the style,but also switches among various styles.
Besides, Shakker also offers Object Control,Composition Control,Collage Redrawing etc.
首先:尊重公众人物,请勿发表NSFW内容,本模型不支持商用,仅可用于学习。
机翻:Respect public figures, do not publish NSFW content, this model does not support commercial, can only be used for learning.
在C站看了好几个小鞠的模型,但都觉得差点什么,看了下它们的留言,据说小鞠挺难训练的。我平时给朋友们训练模型出来还都挺像,就想试试。结果这次换了好几个底模,方法,训练出来果然差强人意,这不应该啊??欢迎大佬们讨论。
V2:底模更改为: 墨幽的姐姐——墨幽岚_v1
更改部分不突出主角特色的训练素材
我使用的:
模型:MoyouArtificial_v1060 majicmixRealistic_v7
采样:dpm++ 2M Karras、DDIM、Restart
步数:30-50
分辨率:512*768
高清:4xUltrasharp 15步 重绘幅度0.3
CFG:7