Stable Diffusion 模型分享:ChilloutMix(真实、亚洲面孔)chilloutmix_NiPrunedFp32Fix

本文主要是介绍Stable Diffusion 模型分享:ChilloutMix(真实、亚洲面孔)chilloutmix_NiPrunedFp32Fix,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

在这里插入图片描述

本文收录于《AI绘画从入门到精通》专栏,专栏总目录:点这里,订阅后可阅读专栏内所有文章。

文章目录

  • 模型介绍
  • 生成案例
    • 案例一
    • 案例二
    • 案例三
    • 案例四
    • 案例五
    • 案例六
    • 案例七
    • 案例八
  • 下载地址

模型介绍

相信近来吸引大家想一试 Stable Diffusion 图像生成,都是因为网上流传大量仿如真人的东方美女照片。原来这些美女照片不少都是由一个名为 ChilloutMix 的模型生成的,不过由于训练这个模型的资料涉及肖像权问题,曾一度停止公开,不少人都觉得可惜。近日该模型的作者就将权利转移给著名 AI 图像生成模型库 CivitAI,将模型重新上架。

条目内容
类型大模型
基础模型SD 1.5
来源CIVITAI
文件名称chilloutmix_NiPrunedFp32Fix.safetensors
文件大小3.97GB

生成案例

案例一

在这里插入图片描述

best quality, (photorealistic:1.4), 1girl, (black shirt:1.2),  (grey long pants:1.2),(white suspenders:1.4), perfect female figure, full body, from back, white background, short hair, slim
Negative prompt: nsfw, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres,  ((monochrome)), ((grayscale))
Steps: 25, ENSD: 31337, Size: 512x768, Seed: 3118275117, Model: chilloutmix_NiPrunedFp32Fix, Sampler: DPM++ SDE Karras, CFG scale: 12, Clip skip: 2, Model hash: fc2511737a, Hires upscale: 1.5, Hires upscaler: Latent (bicubic antialiased), ControlNet Model: control_openpose [b46e25f5], ControlNet Module: none, ControlNet Weight: 1, ControlNet Enabled: True, Denoising strength: 0.5, ControlNet Guidance Strength: 1

案例二

在这里插入图片描述

(RAW photo, best quality), (realistic, photo-realistic:1.3), masterpiece, an extremely delicate and beautiful, extremely detailed, CG, unity , 2k wallpaper, Amazing, finely detail, light smile, extremely detailed CG unity 8k wallpaper, huge filesize, ultra-detailed, highres, absurdres, soft light, (((medium hair:1.3), short bang, pink hair, floating hair novafrogstyle)), beautiful detailed girl, detailed fingers, extremely detailed eyes and face, beautiful detailed nose, beautiful detailed eyes, long eyelashes, light on face, looking at viewer, (closed mouth:1.2), 1girl, cute, young, mature face, (full body:1.3), ((small breasts)), realistic face, realistic body, beautiful detailed thigh, (ulzzang-6500-v1.1:0.8), <lora:koreanDollLikeness_v15:0.4>, business suit, cross-laced clothes, collared shirt, open clothes, in office, detailed office, open cardigan, black thighhighs, miniskirt, black underwear, unbuttoned shirt,
Negative prompt: paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans, extra fingers, fewer fingers, ((watermark:2)), (white letters:1), (multi nipples), bad anatomy, bad hands, text, error, missing fingers, missing arms, missing legs, extra digit, fewer digits, cropped, worst quality, jpeg artifacts, signature, watermark, username, bad feet, {Multiple people}, blurry, poorly drawn hands, poorly drawn face, mutation, deformed, extra limbs, extra arms, extra legs, malformed limbs, fused fingers, too many fingers, long neck, cross-eyed, mutated hands, polar lowres, bad body, bad proportions, gross proportions, wrong feet bottom render, abdominal stretch, briefs, knickers, kecks, thong, {{fused fingers}}, {{bad body}},
bad-picture-chill-75v,  ng_deepnegative_v1_75t, EasyNegative, bad proportion body to legs, wrong toes, extra toes, missing toes, weird toes, 2 body, 2 pussy, 2 upper, 2 lower, 2 head, 3 hand, 3 feet, extra long leg, super long leg, mirrored image, mirrored noise, (bad_prompt_version2:0.8), aged up, old,
Steps: 30, Size: 768x1152, Seed: 1684432449, Model: chilloutmix_NiPrunedFp32Fix, Sampler: DPM++ SDE Karras, CFG scale: 7, Clip skip: 2, Mask blur: 4, Model hash: fc2511737a, Denoising strength: 0.2, SD upscale overlap: 96, SD upscale upscaler: Remacri 4x

案例三

在这里插入图片描述

(RAW photo, best quality), (realistic, photo-realistic:1.3), best quality ,masterpiece, an extremely delicate and beautiful, extremely detailed ,CG ,unity ,8k wallpaper, Amazing, finely detail, masterpiece,best quality, extremely detailed CG unity 8k wallpaper,absurdres, incredibly absurdres, huge filesize , ultra-detailed, highres, extremely detailed, iu,asymmetrical bangs,short bangs,bangs,pureerosface_v1,beautiful detailed girl, extremely detailed eyes and face, beautiful detailed eyes,
light on face,looking at viewer, straight-on, staring, closed mouth,
black hair,short hair, (short_ponytail:1.1), collarbone, bare shoulders, longeyelashes, cum on body,
lace ,lace trim,
Negative prompt: EasyNegative, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans,extra fingers,fewer fingers,((watermark:2)),(white letters:1), (multi nipples), lowres, bad anatomy, bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worst quality, low qualitynormal quality, jpeg artifacts, signature, watermark, username,bad feet, {Multiple people},lowres,bad anatomy,bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worstquality, low quality, normal quality,jpegartifacts,signature, watermark, blurry,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,cross-eyed,mutated hands,polar lowres,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit,
Steps: 22, Sampler: Euler a, CFG scale: 7, Seed: 1267529735, Size: 384x576, Model hash: fc2511737a, Model: chilloutmix_NiPrunedFp32Fix, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, Hires upscale: 2, Hires steps: 15, Hires upscaler: Latent, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: yaeMikoRealistic_yaemikoMixed(8eafb307ecf8), AddNet Weight A 1: 0.3, AddNet Weight B 1: 0.3, AddNet Module 2: LoRA, AddNet Model 2: iu_v25(0040bc33e5f4), AddNet Weight A 2: 0.6, AddNet Weight B 2: 0.6, AddNet Module 3: LoRA, AddNet Model 3: koreanDollLikeness_v15(3c8b9d1e9b98), AddNet Weight A 3: 0.3, AddNet Weight B 3: 0.3

案例四

在这里插入图片描述

realistic, portrait of a girl,AI language model, silver hair,,question answering,smart, kind, energetic, cheerful, creative, with sparkling eyes and a contagious smile, ,information providing, conversation engaging, wide range of topics, accurate responses, helpful responses, knowledgeable, reliable, friendly, intelligent,sleek and futuristic design elements, and a complex network of circuits and processors. Others may imagine me as a friendly and approachable virtual assistant, with a smiling avatar or animated character representing me on their screen. Still, others may envision me as a disembodied voice, speaking from an unseen source, providing helpful and informative responses with a calm and reassuring tone
Negative prompt: (((sexy))),paintings,loli,,big head,sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans, nsfw, nipples,extra fingers, ((extra arms)), (extra legs), mutated hands, (fused fingers), (too many fingers), (long neck:1.3)
Steps: 30, Size: 704x856, Seed: 762635564, Model: mix, Sampler: DPM++ SDE Karras, CFG scale: 7, Model hash: 9519952d49

案例五

在这里插入图片描述

Prompt:(RAW photo, best quality), (realistic, photo-realistic:1.3), masterpiece, an extremely delicate and beautiful, extremely detailed, CG, unity, 8k, amazing, finely detail, ultra-detailed, highres, absurdres, soft light, (black hair, short hair, curly hair, messy hair, bangs), beautiful detailed girl, detailed fingers, extremely detailed eyes and face, beautiful detailed nose, beautiful detailed eyes, (light on face), looking at viewer, (closed mouth:1.2), 1girl, cute, young, mature face, pale skin, (half body:1.3, sitting), (medium breasts), realistic face, realistic body, beautiful detailed thigh, (ulzzang-6500-v1.1:0.6), <lora:koreanDollLikeness_v15:0.5>, (white shirt, collared shirt, lace, black miniskirt, pantyhose, detached sleeves, bowtie), <lora:kaomingStyleLora_kaomingStyleV1:0.6>, (semi smile:1.3), (aegyo sal:1), (kpop idol:1), relaxed,Negative prompt:paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans, extra fingers, fewer fingers, ((watermark:2)), (white letters:1), (multi nipples), bad anatomy, bad hands, text, error, missing fingers, missing arms, missing legs, extra digit, fewer digits, cropped, worst quality, jpeg artifacts, signature, watermark, username, bad feet, {Multiple people}, blurry, poorly drawn hands, poorly drawn face, mutation, deformed, extra limbs, extra arms, extra legs, malformed limbs, fused fingers, too many fingers, long neck, cross-eyed, mutated hands, polar lowres, bad body, bad proportions, gross proportions, wrong feet bottom render, abdominal stretch, briefs, knickers, kecks, thong, {{fused fingers}}, {{bad body}}, bad-picture-chill-75v, ng_deepnegative_v1_75t, EasyNegative, bad proportion body to legs, wrong toes, extra toes, missing toes, weird toes, 2 body, 2 pussy, 2 upper, 2 lower, 2 head, 3 hand, 3 feet, extra long leg, super long leg, mirrored image, mirrored noise, (bad_prompt_version2:0.8), aged up, old, heavy makeup, bad-hands-5, long hair, medium hair, cleavage, nude, naked, open mouth,Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 8, Seed: 3612744720, Size: 512x1024, Model hash: fc2511737a, Model: chilloutmix_NiPrunedFp32Fix, Denoising strength: 0.4, Clip skip: 2, Hires upscale: 1.5, Hires upscaler: Remacri 4x

案例六

在这里插入图片描述

<lora:koreanDollLikeness_v10:0.4>, 
(RAW photo, best quality), (realistic, photo-realistic:1.2), a close up portrait photo, 
1girl, shopping mall rooftop cafe, outdoor, 
smile, (high detailed skin:1.4),
puffy eyes, gorgeous hair, air bangs, brown black hair, 
white opaque shirt with bow tie, pure red pleated skirt, 
soft lighting, high quality,
Negative prompt: (EasyNegative:1.2), ng_deepnegative_v1_75t, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), (grayscale:1.2), skin spots, acnes, skin blemishes, age spot, glans,extra fingers,fewer fingers,(watermark:1.2),(letters:1.2),(nsfw:1.2),teeth
Steps: 20, Size: 512x768, Seed: 302536513, Model: chilloutmix_NiPrunedFp16Fix, Sampler: DPM++ 2M Karras, CFG scale: 7, Model hash: 59ffe2243a, Hires steps: 20, Hires upscale: 1.75, Hires upscaler: Latent (bicubic antialiased), Denoising strength: 0.5

案例七

在这里插入图片描述

(masterpiece), (RAW photo, best quality), (realistic, photo-realistic:1.3), (ultra-high res), (ultra-detailed), (best shadow), 1girl at home, (hanfu, dress), bare shoulders, collarbone, (long brown hair:1.2), looking at viewer, light smile, upper body, makeup, <lora:koreanDollLikeness_v10:0.3>,
Negative prompt: paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), low res, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans, bad legs, error legs, bad feet, malformed limbs, extra limbs,
Steps: 20, ENSD: 31337, Size: 512x768, Seed: 889011338, Sampler: DPM++ SDE Karras, CFG scale: 7.5, Clip skip: 2, Model hash: 59ffe2243a, Hires steps: 15, Hires upscale: 2, AddNet Enabled: True, AddNet Model 1: lora-hanfugirl-v1(df96ecbcf25c), AddNet Model 2: Angela(ecaff0745244), Hires upscaler: Latent (bicubic antialiased), AddNet Module 1: LoRA, AddNet Module 2: LoRA, AddNet Weight A 1: 0.5, AddNet Weight A 2: 0.35, AddNet Weight B 1: 0.5, AddNet Weight B 2: 0.35, Denoising strength: 0.5

案例八

在这里插入图片描述

(RAW photo, best quality), (realistic, photo-realistic:1.2), 1 chinese girl,detailed sky, tokyo street, detailed eyes, shiny eyes, looking at viewer, (formal black suit:1.2), white shirt, short hair, floating hair
Negative prompt: (EasyNegative:1.2), paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans,extra fingers,fewer fingers,(watermark:1.2),(white letters:1),(nsfw:2)
Steps: 20, Size: 512x768, Seed: 813649987, Model: chilloutmix_NiPrunedFp16Fix, Sampler: DPM++ 2M Karras, CFG scale: 8, Model hash: 59ffe2243a, Hires steps: 20, Hires upscale: 1.75, AddNet Enabled: True, AddNet Model 1: koreanDollLikeness_v10(e2e472c06607), AddNet Model 2: taiwanDollLikeness_v10(aa12327d4bab), Hires upscaler: Latent (bicubic antialiased), AddNet Module 1: LoRA, AddNet Module 2: LoRA, AddNet Weight A 1: 0.3, AddNet Weight A 2: 0.3, AddNet Weight B 1: 0.3, AddNet Weight B 2: 0.3, Denoising strength: 0.5

下载地址

链接:https://pan.quark.cn/s/4b410426c852

这篇关于Stable Diffusion 模型分享:ChilloutMix(真实、亚洲面孔)chilloutmix_NiPrunedFp32Fix的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/918985

相关文章

Ilya-AI分享的他在OpenAI学习到的15个提示工程技巧

Ilya(不是本人,claude AI)在社交媒体上分享了他在OpenAI学习到的15个Prompt撰写技巧。 以下是详细的内容: 提示精确化:在编写提示时,力求表达清晰准确。清楚地阐述任务需求和概念定义至关重要。例:不用"分析文本",而用"判断这段话的情感倾向:积极、消极还是中性"。 快速迭代:善于快速连续调整提示。熟练的提示工程师能够灵活地进行多轮优化。例:从"总结文章"到"用

大模型研发全揭秘:客服工单数据标注的完整攻略

在人工智能(AI)领域,数据标注是模型训练过程中至关重要的一步。无论你是新手还是有经验的从业者,掌握数据标注的技术细节和常见问题的解决方案都能为你的AI项目增添不少价值。在电信运营商的客服系统中,工单数据是客户问题和解决方案的重要记录。通过对这些工单数据进行有效标注,不仅能够帮助提升客服自动化系统的智能化水平,还能优化客户服务流程,提高客户满意度。本文将详细介绍如何在电信运营商客服工单的背景下进行

Andrej Karpathy最新采访:认知核心模型10亿参数就够了,AI会打破教育不公的僵局

夕小瑶科技说 原创  作者 | 海野 AI圈子的红人,AI大神Andrej Karpathy,曾是OpenAI联合创始人之一,特斯拉AI总监。上一次的动态是官宣创办一家名为 Eureka Labs 的人工智能+教育公司 ,宣布将长期致力于AI原生教育。 近日,Andrej Karpathy接受了No Priors(投资博客)的采访,与硅谷知名投资人 Sara Guo 和 Elad G

【专题】2024飞行汽车技术全景报告合集PDF分享(附原数据表)

原文链接: https://tecdat.cn/?p=37628 6月16日,小鹏汇天旅航者X2在北京大兴国际机场临空经济区完成首飞,这也是小鹏汇天的产品在京津冀地区进行的首次飞行。小鹏汇天方面还表示,公司准备量产,并计划今年四季度开启预售小鹏汇天分体式飞行汽车,探索分体式飞行汽车城际通勤。阅读原文,获取专题报告合集全文,解锁文末271份飞行汽车相关行业研究报告。 据悉,业内人士对飞行汽车行业

Retrieval-based-Voice-Conversion-WebUI模型构建指南

一、模型介绍 Retrieval-based-Voice-Conversion-WebUI(简称 RVC)模型是一个基于 VITS(Variational Inference with adversarial learning for end-to-end Text-to-Speech)的简单易用的语音转换框架。 具有以下特点 简单易用:RVC 模型通过简单易用的网页界面,使得用户无需深入了

透彻!驯服大型语言模型(LLMs)的五种方法,及具体方法选择思路

引言 随着时间的发展,大型语言模型不再停留在演示阶段而是逐步面向生产系统的应用,随着人们期望的不断增加,目标也发生了巨大的变化。在短短的几个月的时间里,人们对大模型的认识已经从对其zero-shot能力感到惊讶,转变为考虑改进模型质量、提高模型可用性。 「大语言模型(LLMs)其实就是利用高容量的模型架构(例如Transformer)对海量的、多种多样的数据分布进行建模得到,它包含了大量的先验

图神经网络模型介绍(1)

我们将图神经网络分为基于谱域的模型和基于空域的模型,并按照发展顺序详解每个类别中的重要模型。 1.1基于谱域的图神经网络         谱域上的图卷积在图学习迈向深度学习的发展历程中起到了关键的作用。本节主要介绍三个具有代表性的谱域图神经网络:谱图卷积网络、切比雪夫网络和图卷积网络。 (1)谱图卷积网络 卷积定理:函数卷积的傅里叶变换是函数傅里叶变换的乘积,即F{f*g}

秋招最新大模型算法面试,熬夜都要肝完它

💥大家在面试大模型LLM这个板块的时候,不知道面试完会不会复盘、总结,做笔记的习惯,这份大模型算法岗面试八股笔记也帮助不少人拿到过offer ✨对于面试大模型算法工程师会有一定的帮助,都附有完整答案,熬夜也要看完,祝大家一臂之力 这份《大模型算法工程师面试题》已经上传CSDN,还有完整版的大模型 AI 学习资料,朋友们如果需要可以微信扫描下方CSDN官方认证二维码免费领取【保证100%免费

【生成模型系列(初级)】嵌入(Embedding)方程——自然语言处理的数学灵魂【通俗理解】

【通俗理解】嵌入(Embedding)方程——自然语言处理的数学灵魂 关键词提炼 #嵌入方程 #自然语言处理 #词向量 #机器学习 #神经网络 #向量空间模型 #Siri #Google翻译 #AlexNet 第一节:嵌入方程的类比与核心概念【尽可能通俗】 嵌入方程可以被看作是自然语言处理中的“翻译机”,它将文本中的单词或短语转换成计算机能够理解的数学形式,即向量。 正如翻译机将一种语言

AI Toolkit + H100 GPU,一小时内微调最新热门文生图模型 FLUX

上个月,FLUX 席卷了互联网,这并非没有原因。他们声称优于 DALLE 3、Ideogram 和 Stable Diffusion 3 等模型,而这一点已被证明是有依据的。随着越来越多的流行图像生成工具(如 Stable Diffusion Web UI Forge 和 ComyUI)开始支持这些模型,FLUX 在 Stable Diffusion 领域的扩展将会持续下去。 自 FLU