前言
大家好,AIGC-LisonAI艺术,关注AI发展趋势与专注AI绘画!
以下是Prompt(提示词)和对应效果:
Prompt : masterpiece,best quality,super wide angle,magnificent,celestial,ethereal,painterly,epic,majestic,magical,fantasy art,cover art,dreamy,elegant,cinematic,background illuminated,rich deep colors,ambient dramatic atmosphere,creative,perfect,beautiful composition,intricate,detailed,adamcn myth style,(1girl,( playing a bamboo flute:1.4)),hanfu,be wreathed in mist,lora:xl\_more\_art-full\_v1:1,
3959768850
3279371688
Prompt : ultra high resolution,(masterpiece),(best quality),(super detailed),(extremely delicate and beautiful),cinematic light,detailed environment,(real),(1girl, solo, male focus:1.2),(holding sword:1.2),(Chinese Kung Fu fighting stance:1.3),(dark red and light gold:1.2),(hair pulled back, floating hair:1.1),designed by greg manchess,smoke,a model woman,bright eyes,glossy lips,hanfu,trending on art station,photoreal,8 k,octane render by greg rutkowski,art by Carne Griffiths and Wadim Kashin,in the style of Dau-al-Set,Pollock,and inspired by MAPPA and Zdzislaw Beksinski,((outdoors, valley, bamboo forest)),lora:xl\_more\_art-full\_v1:1,
3379787639
2213303492
33210942
4157369456
2761349790
3040119706
618926269
Prompt : ultra high resolution,(masterpiece),(best quality),(super detailed),(extremely delicate and beautiful),cinematic light,detailed environment,(real),(1boy, solo, male focus:1.2),(holding sword:1.2),(The fighting posture of Chinese Tai Chi Kung Fu:1.3),(dark red and light gold:1.2),(hair pulled back, floating white hair:1.1),designed by greg manchess,smoke,a model man,bright eyes,glossy lips,hanfu,trending on art station,photoreal,8 k,octane render by greg rutkowski,art by Carne Griffiths and Wadim Kashin,in the style of Dau-al-Set,Pollock,and inspired by MAPPA and Zdzislaw Beksinski,((outdoors, valley, bamboo forest)),lora:xl\_more\_art-full\_v1:0.8,
142431191
1166523423
3147909076
1163791999
2883309693
Prompt : ultra high resolution,(masterpiece),(best quality),(super detailed),(extremely delicate and beautiful),cinematic light,detailed environment,(real),(focus:1.2),(holding sword:1.2),(A black-haired girl I A white-haired boy),(a man and a girl,fighting posture of Chinese Kung Fu:1.3),(dark red and light gold:1.2),(hair pulled back, floating hair:1.1),designed by greg manchess,smoke,a model man,bright eyes,glossy lips,hanfu,trending on art station,photoreal,8 k,octane render by greg rutkowski,art by Carne Griffiths and Wadim Kashin,in the style of Dau-al-Set,Pollock,and inspired by MAPPA and Zdzislaw Beksinski,((outdoors, valley, bamboo forest)),lora:xl\_more\_art-full\_v1:0.8,
本文涉及模型、插件下载请扫描免费获取哦
513420310
2118963683
3431181894
474659505
3967428563
1906434475
Prompt : chinese ancient battle field,many chinese ancient soilders fighting eachother,angry shouting,blood on armor and ground,fire and smoke,from above,Glowing ambiance,enchanting radiance,luminous lighting,ethereal atmosphere,evocative hues,captivating coloration,dramatic lighting,enchanting aura,masterpiece,best quality,epic cinematic,soft nature lights,rim light,amazing,hyper detailed,ultra realistic,soft colors,photorealistic,Ray tracing,Cinematic Light,light source contrast,Martial Art Style,<lora:筑梦工业 _ 墨染红尘-武侠修仙XL_v1.0:0.8>,lora:xl\_more\_art-full\_v1:0.8,ral-dissolve,lora:ral-dissolve-sdxl:0.8,
279608414
1417382612
3081466372
171137084
使用的模型:RealMythXL-神话丨武侠写实国风-电影感丨Super
参数设置:
Sampler : DPM++ 3M SDE Karras
Steps : 35
CFG Scale : 3
Size : 768*1152px
Hires.fix (高分辨率修复) : 8x_NMKD-Superscale_150000_G
高分迭代步数 :20
重绘幅度 :0.3
放大倍数 :2
开启脸部修复 :ADetailer (face_yolov8n.pt)
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!