基础测试
先基础测试一下。
默认是中文的。
当前省去了下载中文插件的步骤了。但是只有基本模型。
正向词：
Star face, long black hair, beauty, wearing a white shirt, upper body frontal photo, ultra-clear, cute, lolita, natural black pupils, bright eyes, Chinese style, well-proportioned, regular facial features, no stretching, first love, light blue Color background, tie, campus, desks and chairs, school uniform, long hair to waist, smile, dimples
反向词：
(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, pgly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
效果：
准备图片训练集
后台上传训练集
先打开【JupyterLab】
将图片上传一下：
直接拉进入就行。
上传完毕
修改训练设置
设置里面勾选第一个选项节约显存。
设置完毕，点击保存，并重启webui
创建Embedding
创建完会给个地址。
/root/stable-diffusion-webui/embeddings/v1-mytest-suisui.pt
创建超网络
训练
拉下去，点训练。
开始训练。
训练过程能看到成长
慢慢等着吧，中途别退出啊，不然还得从新跑，我就不小心扣屏幕了。。。。呜呼~
