上一篇文章下载了模型,但是在刷新模型发现根本不行,原来是在下载模型时候选择错误。
第三步要选红色框这个——然后点击4th-Download Model才是对的
回到我们的colab要看见下载有多大,有多少个G开始下载才正确
今天才选择正确,开始我们的模型,第一个模型是动漫风格
正面提示词:analog photo of 25 y.o beautiful serbian scientist, 1980s suit (showing cleavage:1.3), endearing look, 1980s, glasses, tight bun hair, masterpiece, DSLR photo, analog style, nikon d5, real 80s photo, working in the lab, dramatic lighting, (detailed facial features), (detailed shiny eyes), dynamic angle, jeremy mann
负面提示词:(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, 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
(注:正面提示词和负面提示词都可以自己增删改,生成不一样的图片)
模型换成中文,可以看见每一个名字的含义
文章来源地址https://www.toymoban.com/news/detail-530844.html文章来源:https://www.toymoban.com/news/detail-530844.html
到了这里,关于《Stable Diffusion web UI 使用—1文生图 (动漫风)》的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!