文生图Stable-diffusion-webui环境搭建

文生图Stable-diffusion-webui环境搭建

    正在检查是否收录...

 想自己生成AI美女吗?跟我一起下来搭建Stable-diffusion-v1-5进行文生图、图生图吧。

该webui支持Mac/Linux/Windows环境,这里以windows环境为例。前提是你已经在本机搭建好了GPU运行环境,建议6G以上GPU,当然,CPU也可以运行,就是奇慢无比。

1. 安装python3.10.x版本

2.下载最新版本源代码

https://github.com/AUTOMATIC1111/stable-diffusion-webui

3.运行webui_user.bat自动安装(这个过程比较长哦)

怎么样?是不是非常简单?(中间会踩坑,需要自己爬起来)

界面效果:

 4. 中文版本(extensions扩展页面安装)

https://github.com/VinsonLaro/stable-diffusion-webui-chinese 

5. 重要外挂(extensions扩展页面安装)

https://github.com/Mikubill/sd-webui-controlnet 

6.最重要的Stable-diffusion模型chilloutmix(需要魔法上网)

https://civitai.com/images/707062?period=AllTime&periodMode=published&sort=Newest&view=categories&modelVersionId=11745&modelId=6424&postId=193423

7.Lora模型权重(cuteGirlMix4_v10,seeThroughSilhouette_v10)

https://huggingface.co/luxluna/cuteGirlMix4_v10/tree/main
https://huggingface.co/samle/sd-webui-models/blob/main/seeThroughSilhouette_v10.safetensors

8. 美女图片一张

 对应的提示词:

extremely detailed CG unity 8k wallpaper,(masterpiece),(best quality),(ultra detailed),(ultra realistic),(Best character details:1.36),nikon d750 f/1.4 55mm,dynamic angle,professional lighting, photon mapping, radiosity, physically-based rendering, outdoors,looking at viewer,blush,(taut shirt), jeans, 1girl,(mature female:0.2),tall body,golden proportions,(Kpop idol),(shiny skin:1.2),(oil skin:1.1),makeup,[:(high detailed face:1.2):0.2]:, <lora:cuteGirlMix4_v10:0.8>, (close up), park, depth of field, <lora:seeThroughSilhouette_v10:0.5>,( closed mouth: 0.5) ((wavy gray hair and a sophisticated sense of style)),(aegyo sal:1),(puffy eyes),(eyelashes:1.1),(parted lips:1.1),red lipstick,wide shoulders, Negative prompt: Multiple people,More than one person,2girl,DeepNegative, sketches,lowres,polar lowres,(worst quality:2),(low quality:2),(normal quality:2),((monochrome)),((grayscale)),blurry,cropped,mutation,deformed,text,error,signature,watermark,username,extra digit,fewer digits,jpeg artifacts, skin spots, acnes, skin blemishes, bad anatomy,bad anatomy,bad proportions,gross proportions,long neck,cross-eyed,malformed limbs,blurred hands,fused fingers,poorly drawn face,poorly drawn hands, (mutated hands and fingers:1.3),(mutated legs and foots:1.3),bad body,bad limbs,bad arms,bad hands,bad fingers,bad leg,bad feet,missing limbs,missing arms,missing hands,missing fingers,missing legs,missing footextra limbs,extra arms,extra fingers,extra leg,extra foot, Steps: 28, Sampler: DPM++ SDE Karras, CFG scale: 7.5, Seed: 1340860639, Face restoration: CodeFormer, Size: 640x960, Model hash: fc2511737a, Model: chilloutmix_NiPrunedFp32Fix, Denoising strength: 0.4, Hires upscale: 1.5, Hires steps: 30, Hires upscaler: Latent (bicubic antialiased) 

codewebwebuigitdiffusiongithubwindowsutmgpuhuggingfacechromeurlcpuamllinuxerpunitcontrolnetide图生图app提示词sopunityiospromptmac生成aipython文生图fix
  • 本文作者:李琛
  • 本文链接: https://wapzz.net/post-5737.html
  • 版权声明:本博客所有文章除特别声明外,均默认采用 CC BY-NC-SA 4.0 许可协议。
本站部分内容来源于网络转载,仅供学习交流使用。如涉及版权问题,请及时联系我们,我们将第一时间处理。
文章很赞!支持一下吧 还没有人为TA充电
为TA充电
还没有人为TA充电
0
  • 支付宝打赏
    支付宝扫一扫
  • 微信打赏
    微信扫一扫
感谢支持
文章很赞!支持一下吧
关于作者
2.3W+
5
0
1
WAP站长官方

Whisper与ChatGPT联手,轻松实现音频转录文本

上一篇

必学AI绘图技巧,如何用Midjourney实现连续性人物的创作,SEED功能

下一篇
  • 复制图片
按住ctrl可打开默认菜单