欢迎关注我的CSDN:https://spike.blog.csdn.net/
本文地址:https://spike.blog.csdn.net/article/details/132072482
来源于 Anna Dittmann 安娜·迪特曼,艺术家风格的图像,融合幻想、数字艺术、纹理等样式。
SDXL 是 Stable Diffusion 的最新版本,是潜在扩散模型,能够从文本描述中生成高分辨率、高质量、高逼真的图像。SDXL 版本相比于之前的版本,在文本理解、图像细节、色彩表现等方面都有显著的提升。SDXL 不仅能够生成写实风格的图像,也能够生成各种艺术风格的图像,例如卡通、油画、水彩、素描等,只需要在文本描述中加入相应的风格提示词,就可以让 SDXL 按照预定的设计来创作。
设置图像样式关键字,包括 17 种常用的图像样式,参考 SDXL Various Styles keywords,修改 styles.csv
文件,在文件中添加,如下:
"Style: Enhance","breathtaking {prompt} . award-winning, professional, highly detailed","ugly, deformed, noisy, blurry, distorted, grainy"
"Style: Anime","anime artwork {prompt} . anime style, key visual, vibrant, studio anime, highly detailed","photo, deformed, black and white, realism, disfigured, low contrast"
"Style: Photographic","cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed","drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly"
"Style: Digital art","concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed","photo, photorealistic, realism, ugly"
"Style: Comic book","comic {prompt} . graphic illustration, comic art, graphic novel art, vibrant, highly detailed","photograph, deformed, glitch, noisy, realistic, stock photo"
"Style: Fantasy art","ethereal fantasy concept art of {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy","photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white"
"Style: Analog film","analog film photo {prompt} . faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage","painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured"
"Style: Neonpunk","neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional","painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured"
"Style: Isometric","isometric style {prompt} . vibrant, beautiful, crisp, detailed, ultra detailed, intricate","deformed, mutated, ugly, disfigured, blur, blurry, noise, noisy, realistic, photographic"
"Style: Lowpoly","low-poly style {prompt} . low-poly game art, polygon mesh, jagged, blocky, wireframe edges, centered composition","noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo"
"Style: Origami","origami style {prompt} . paper art, pleated paper, folded, origami art, pleats, cut and fold, centered composition","noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo"
"Style: Line art","line art drawing {prompt} . professional, sleek, modern, minimalist, graphic, line art, vector graphics","anime, photorealistic, 35mm film, deformed, glitch, blurry, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, mutated, realism, realistic, impressionism, expressionism, oil, acrylic"
"Style: Craft clay","play-doh style {prompt} . sculpture, clay art, centered composition, Claymation","sloppy, messy, grainy, highly detailed, ultra textured, photo"
"Style: Cinematic","cinematic film still {prompt} . shallow depth of field, vignette, highly detailed, high budget Hollywood movie, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy","anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured"
"Style: 3d-model","professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting","ugly, deformed, noisy, low poly, blurry, painting"
"Style: pixel art","pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics","sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic"
"Style: Texture","texture {prompt} top down close-up","ugly, deformed, noisy, blurry"
如果没有 styles.csv 文件,直接创建,注意添加表头 name,prompt,negative_prompt
,即可。
具体使用方式,注意优先选择提示词,再选择样式,即:
测试模型 DreamShaper_XL1.0_alpha2 ,整体效果优于原版 SDXL 1.0 模型,而且不需要使用 Refiner 模型。
图像尺寸 1024x1024,未使用 高分辨率修复
,配置如下:
1. 图像样式 (Style)
测试提示词:
a close up of a woman's feet wearing pink socks and high heeled shoes with laces on the sides
(穿着粉色袜子和两侧有鞋带的高跟鞋的女士脚部特写)
负向提示词 (解决肢体问题): (ng_deepnegative_v1_75t:1.2)
负向Embeddings,ng_deepnegative_v1_75t
非常好用,支持 SDXL 1.0
Enhance (增强):
breathtaking a close up of a woman’s feet wearing pink socks and high heeled shoes with laces on the sides . award-winning, professional, highly detailed
Negative prompt: (ng_deepnegative_v1_75t:1.2), ugly, deformed, noisy, blurry, distorted, grainy
Steps: 30, Sampler: DPM++ 2M SDE Karras, CFG scale: 7, Seed: 1389692067, Size: 1024x1024, Model hash: 0f1b80cfe8, Model: DreamShaper_XL1.0_alpha2, Clip skip: 2, Version: v1.5.1
Raw Image、Enhance (增强)
Anime (动漫)、Photographic (照片级)、Digital art (数字艺术)、Comic book (漫画书):
Fantasy art (幻想艺术 )、Analog film (模拟电影)、Neonpunk (霓虹朋克)、Isometric (等距图像):
Lowpoly (低多边形)、Origami (折纸)、Line art (线条艺术)、Craft clay (工艺粘土):
Cinematic (电影)、3d-model (3D模型)、Pixel art (像素艺术)、Texture (纹理):
2. 艺术家 (Artist) 风格
在已有的图像样式的基础上,可以继续添加艺术家风格,参考:https://clio.so/rabbitsxl
例如 Anna Dittmann,参考:
(by Anna Dittmann:1.2),digital painting,illustration,portrait,fantasy,
提示词,注意选择合适的风格,例如 Fantasy Arts:
(by Anna Dittmann:1.2),digital painting,illustration,portrait,fantasy,
ethereal fantasy concept art of a close up of a woman’s feet wearing pink socks and high heeled shoes with laces on the sides . magnificent,celestial,ethereal,painterly,epic,majestic,magical,fantasy art,cover art,dreamy,
Negative prompt: (ng_deepnegative_v1_75t:1.2),photographic,realistic,realism,35mm film,dslr,cropped,frame,text,deformed,glitch,noise,noisy,off-center,deformed,cross-eyed,closed eyes,bad anatomy,ugly,disfigured,sloppy,duplicate,mutated,black and white,
Steps: 30, Sampler: DPM++ 2M SDE Karras, CFG scale: 7, Seed: 1389692067, Size: 1024x1024, Model hash: 0f1b80cfe8, Model: DreamShaper_XL1.0_alpha2, Clip skip: 2, Version: v1.5.1