当前位置:AIGC资讯 > AIGC > 正文

免费体验!快速生成超逼真真人美图的Stable Diffusion模型!

环境安装

1、安装Python

下载地址:https://www.python.org/ftp/python/3.10.6/python-3.10.6-amd64.exe

备注:把安装目录加入环境变量!

2、安装git

下载地址:https://github.com/git-for-windows/git/releases/download/v2.46.0.windows.1/Git-2.46.0-64-bit.exe

安装 stable-diffusion-webui

1、下载地址:文末获取安装包。下载到本地后解压,可以存储到C盘或D盘,哪个盘空间大就放到哪个盘。

2、启动


双击webui-user.bat,自动下载必须的安装包和配置相关环境,约2G左右,下载速度和网络相关,需要耐心等待下。
运行结束后出现如下界面,说明安装成功了!


汉化


设置里选择用户界面,

chinese-only-0313:中文

chinese-and-english-0313:中英对照

WuhaXL_realisticMixV4.0 真人模型免费下载

1、下载地址:https://www.mediafire.com/file/p58ns2txvg8irs4/wuhaXL_realisticMix_4.0.safetensors/file


一个非常出色的基于SDXL的真人大模型:wuhaXL_realisticMix V4.0版本

最新V4.0版本在V3.0版本的基础上增加了光影效果,改善了部分人像的假脸问题,特别是针对之前使用After Detailer插件,某些场景会出现人脸正方形边框的问题进行了修复。

该大模型推荐参数设置:

采样方法:Euler a

采样迭代步数:20。

提示词相关性(CFG Scale): 5-7

出半身: 512*768

全身图:768*1024

直出图效果较好,如果非要放大用R-ESRGAN_4x+ Anime6B算法

2、存储目录

大模型下载到指定目录:stable-diffusion-webui\models\Stable-diffusion\


下载到指定目录后,到web-ui界面就可以选择大模型了,如果没有,先点击刷新。

效果

提示词
xxmix_girl,1girl,fluffyshorthair,darktheme,blondehair,messyhair,filmgrain,fog,blackthememTyndall   Negative prompt: sketches, (worst quality:2), (low quality:2), (normal quality:2), lowers, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, bad anatomy,DeepNegative,(fat:1.2),facing away, looking away,tilted head, 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,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,cross-eyed,mutated hands,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit, extra arms, extra leg, extra foot   Steps: 20,Size: 1024x1536,Seed: 2815779962,Model: ,Sampler: Euler a,useLcm: false,CFG scale: 7,Clip skip: undefined,   
提示词
xxmix_girl,portrait of a woman,fluffy short hair,polaroid,film, graininess,smile,cold   Negative prompt: sketches, (worst quality:2), (low quality:2), (normal quality:2), lowers, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, bad anatomy,DeepNegative,(fat:1.2),facing away, looking away,tilted head, 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,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,cross-eyed,mutated hands,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit, extra arms, extra leg, extra foot   Steps: 20,Size: 1024x1536,Seed: 3401052391,Model: ,Sampler: Euler a,useLcm: false,CFG scale: 7,Clip skip: undefined,   
提示词
1 girl,close-up,solo,underwater,drowning,bubbles,loneliness,struggle,surreal imagery,dreamy atmosphere,contrasting colors,complex and detailed elements,   Negative prompt: sketches, (worst quality:2), (low quality:2), (normal quality:2), lowers, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, bad anatomy,DeepNegative,(fat:1.2),facing away, looking away,tilted head, 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,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,cross-eyed,mutated hands,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit, extra arms, extra leg, extra foot   Steps: 20,Size: 1024x1536,Seed: 604566384,Model: ,Sampler: Euler a,useLcm: false,CFG scale: 5,Clip skip: undefined,   
提示词
xxmix_girl,portrait of a woman,fluffy short hair,polaroid,film, graininess,smile,cold   Negative prompt: sketches, (worst quality:2), (low quality:2), (normal quality:2), lowers, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, bad anatomy,DeepNegative,(fat:1.2),facing away, looking away,tilted head, 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,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,cross-eyed,mutated hands,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit, extra arms, extra leg, extra foot   Steps: 20,Size: 1024x1536,Seed: 3401052391,Model: ,Sampler: Euler a,useLcm: false,CFG scale: 7,Clip skip: undefined,   
提示词
cinematic photo ,Best quality , (masterpiece:1.2) , cinematic photo,1girl,A beautiful girl in red hanfu, Standing in the wind andsnow, long hair blown by the wind,snow in the sky , upperbody,snowing,snowy day,in winter ,motion blur ,(sad:1.1),(crying:1.1),close-up,(tears:1.1),(face focus:1.1),(close mouth:1.1),front view ,35mm photograph, film, bokeh, professional, 4k, highly detailed,helgirls    Negative prompt: sketches, (worst quality:2), (low quality:2), (normal quality:2), lowers, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, bad anatomy,DeepNegative,(fat:1.2),facing away, looking away,tilted head, 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,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,cross-eyed,mutated hands,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit, extra arms, extra leg, extra foot   Steps: 20,Size: 1024x1536,Seed: 746754644,Model: wuhaXL_realisticMix,Sampler: DPM++ 2S a Karras,useLcm: false,CFG scale: 6,Clip skip: 2,   

这里直接将该软件分享出来给大家吧~

1.stable diffusion安装包

随着技术的迭代,目前 Stable Diffusion 已经能够生成非常艺术化的图片了,完全有赶超人类的架势,已经有不少工作被这类服务替代,比如制作一个 logo 图片,画一张虚拟老婆照片,画质堪比相机。

最新 Stable Diffusion 除了有win多个版本,就算说底端的显卡也能玩了哦!此外还带来了Mac版本,仅支持macOS 12.3或更高版本。

2.stable diffusion视频合集

我们在学习的时候,往往书籍源码难以理解,阅读困难,这时候视频教程教程是就很适合了,生动形象加上案例实战,一步步带你入坑stable diffusion,科学有趣才能更方便的学习下去。

3.stable diffusion模型下载

stable diffusion往往一开始使用时图片等无法达到理想的生成效果,这时则需要通过使用大量训练数据,调整模型的超参数(如学习率、训练轮数、模型大小等),可以使得模型更好地适应数据集,并生成更加真实、准确、高质量的图像。

4.stable diffusion提示词

提示词是构建由文本到图像模型解释和理解的单词的过程。可以把它理解为你告诉 AI 模型要画什么而需要说的语言,整个SD学习过程中都离不开这本提示词手册。

5.SD从0到落地实战演练

如果你能在15天内完成所有的任务,那你堪称天才。然而,如果你能完成 60-70% 的内容,你就已经开始具备成为一名SD大神的正确特征了。

这份完整版的stable diffusion资料我已经打包好,需要的点击下方插件,即可前往免费领取!

总结

### 文章总结
**环境安装与stable-diffusion-webui配置**
1. **必要软件安装**:
- **Python**:需安装Python 3.10.6版本,并确保环境变量设置正确。
- **Git**:下载并安装Git 2.46.0版本。
2. **stable-diffusion-webui安装**:
- 下载stable-diffusion-webui安装包并解压至空间大的磁盘。
- 双击`webui-user.bat`一键安装,自动下载所需依赖,完成后启动成功。
- **汉化**:在设置中选择合适的中文界面选项。
**WuhaXL_realisticMixV4.0真人模型使用**
1. **下载与安装**:
- 从指定地址下载WuhaXL_realisticMix_4.0模型。
- 将模型文件存储至`stable-diffusion-webui\models\Stable-diffusion\`目录下,确保web-ui界面能找到并正确使用该模型。
2. **参数设置推荐**:
- 采样方法:Euler a
- 采样迭代步数:20
- 提示词相关性(CFG Scale): 5-7
- 半身图尺寸:512*768
- 全身图尺寸:768*1024
**效果展示与提示词案例**
- 提供了多组示范性的提示词案例,涵盖不同风格与主题的图像创作,展示了高清、复杂的图像生成效果以及避免低质量输出的负向提示策略。
**资源分享**
- **安装包视频**:提供Stable Diffusion安装包及视频合集资源,帮助新手快速入门。
- **模型与提示词资源**:分享多个stable diffusion模型下载链接及提示词手册,助力用户优化图像生成效果。
- **实战演练**:提供从零基础到熟练应用的实战演练资料,鼓励用户通过实际操作提升技能。
### 结论
本篇文章详细指导了环境搭建、stable-diffusion-webui安装及其配置过程,重点介绍了WuhaXL_realisticMixV4.0真人模型的使用及参数设置,通过实战效果和提示词展示了AI绘图的强大能力,并分享了丰富的学习资源和实战练习材料,旨在帮助用户快速上手并提升AI图像创作技巧。

更新时间 2024-09-15