Stable Diffusion - SDXL 1.0 全部样式设计与艺术家风格的配置与提示词

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:

bash 复制代码
"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:

bash 复制代码
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

相关推荐
空白诗2 天前
CANN ops-nn 算子解读:Stable Diffusion 图像生成中的 Conv2D 卷积实现
深度学习·计算机视觉·stable diffusion
学易3 天前
第十五节.别人的工作流,如何使用和调试(上)?(2类必现报错/缺失节点/缺失模型/思路/实操/通用调试步骤)
人工智能·ai作画·stable diffusion·报错·comfyui·缺失节点
心疼你的一切3 天前
基于CANN仓库算力手把手实现Stable Diffusion图像生成(附完整代码+流程图)
数据仓库·深度学习·stable diffusion·aigc·流程图·cann
Niuguangshuo4 天前
DALL-E 3:如何通过重构“文本描述“革新图像生成
人工智能·深度学习·计算机视觉·stable diffusion·重构·transformer
Niuguangshuo4 天前
深入解析 Stable Diffusion XL(SDXL):改进潜在扩散模型,高分辨率合成突破
stable diffusion
Niuguangshuo4 天前
深入解析Stable Diffusion基石——潜在扩散模型(LDMs)
人工智能·计算机视觉·stable diffusion
迈火4 天前
SD - Latent - Interposer:解锁Stable Diffusion潜在空间的创意工具
人工智能·gpt·计算机视觉·stable diffusion·aigc·语音识别·midjourney
迈火12 天前
Facerestore CF (Code Former):ComfyUI人脸修复的卓越解决方案
人工智能·gpt·计算机视觉·stable diffusion·aigc·语音识别·midjourney
重启编程之路12 天前
Stable Diffusion 参数记录
stable diffusion
孤狼warrior15 天前
图像生成 Stable Diffusion模型架构介绍及使用代码 附数据集批量获取
人工智能·python·深度学习·stable diffusion·cnn·transformer·stablediffusion