手把手教你入门绘图超强的AI绘画,用户只需要输入一段图片的文字描述,即可生成精美的绘画。给大家带来了全新保姆级教程资料包 (文末可获取)
1 txt2img
txt2img是指文生图,即根据文字描述生成图片,其页面如下图所示。
图2 txt2img
完整设置示例如下:
****Prompt:**** coral full dress,((collagreen botton shirt)),(upper body),long hair,1gir,tall,skinny,photorealistic,masterpiece,highres,8k,character concept,depth of field,perfect pupils,perfect smiles,blurry background,heart shape face, outdoors,,side light, morning,high heel,detailed clothing,ultra details,earring,((full face))
****Negative prompt:**** lowres,bad anatomy,bad hands,text,error,missing fingers,extra digit,fewer digits,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,missing arms,long neck,Humpbacked,missing limb,too many fingers,mutated,poorly drawn,out of frame,bad hands,unclear eyes,poorly drawn,cloned face,bad face,(worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)),ng\_deepnegative\_v1\_75t,nipples,((half face)),(( half head)),((no face)),((no head))
**Steps:** 30, **Sampler:** Euler, **CFG scale:** 9, **Restore faces**, Size: 512x512, **Model hash:** dcd690123c, **Model:** v2-1\_768-ema-pruned.safetensors, **Seed:** 4171216357, **Script:** X/Y/Z plot, **X Type:** Steps, X Values: “10,20,30”, **Y Type:** Sampler, Y Values: “Euler a, Euler”。
1.1 Stable Diffusion checkpoint
Stable Diffusion checkpoints用于选择当前加载的模型,模型设置与加载可参考上一篇博文《AI图片生成Stable Diffusion环境搭建与运行》,地址为“https://blog.youkuaiyun.com/suiyingy/article/details/128896426”。用户可根据需要在hugging face网站下载以.safetensors为后缀的模型文件。
这里需要注意,不同模型生成的图片风格也会有差别,比如漫画风格或写实风格。除Stable Diffusion官方模型之外,程序还支持chilloutmix\_Ni、anything-v4.5-pruned、dreamshaper\_33、protogenV22Anime\_22、artErosAerosATribute\_aerosNovae和cheeseDaddys\_35等模型。