主要是想试试衣服lora怎么练。
v0尝试了用给脸加马赛克的方法,结果发现效果并不好,还会影响出图人脸,于是v1还是用了正常的带脸人物照。
v1只练了连衣裙,丝巾和帽子。后续会加上衬衫。
Just to try practicing training an outfit Lora.
In v0, I attempted to use a mosaic on the face, but the results weren't satisfactory as it affected the overall appearance of the character. So, in v1, I used regular photos of people with visible faces.
Till v1, I only practiced drawing dresses, scarves, and hats. I'll add shirts in the following iterations.
trigger words: EAuniform, EAuniform dress, EAuniform hat, EAuniform scarf, black stockings, high heels
Description
The previous one sometimes give bad quality images because of the poor training dataset.
v2.0 solves that issue.
FAQ
Comments (2)
求海航的青花瓷旗袍~~~
回头整一下,找素材图比较麻烦,网图清晰度不够,很容易影响lora的效果
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.
