Stable Diffusion模型资源合集(附整合包)

(模型资源在ComfyUI、WebUI以及ForgeUI中都通用)

之前的Stable Diffusion笔记受到了不少小伙伴的关注,很感谢大家的建议和支持。有很多小伙伴私信我问我一些AI绘画的模型资源在哪来下载,一般来说有两个网站比较常用,分别是Huggingface和Civitai。

今天这篇笔记就分享一部分我用得比较多的模型,大部分的CheckPoint模型可以看我上面的那篇文章链接,这里我就不分享重复的了。

由于每个人审美都不一样,我这里放的都是Civitai上下载和点赞数最高的一批模型。

这些都是****免费的 免费的 免费的!

CheckPoint

1、majicMix 麦橘系列

https://civitai.com/user/Merjic

这个算是C站的顶流checkpoint之一了,尤其是麦橘写实算是我个人最常用的真人系大模型,这个模型我经常提示词随便写然后参数稍微拉高一点就能生成很多好看的图片。

1girl,sweater,white background,

Negative prompt: (worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,

2、Realistic Vision

https://civitai.com/models/4201?modelVersionId=501240

在真实系的模型中Realistic Vision也是一个不错的选择,比起其他的模型这个生成出来的人像偏向是欧美那边的。

closeup face photo of caucasian man in black clothes, night city street, bokeh

Negative prompt: (nsfw, naked, nude, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation

3、Beautiful Realistic Asians

https://civitai.com/models/25494/beautiful-realistic-asians

这个模型我还没用过,如果有用过的小伙伴欢迎在留言分享自己的看法,不过看出图效果还是不错的。

Cinematic Photo of a beautiful korean fashion model bokeh train

Negative prompt: (worst_quality:2.0) (MajicNegative_V2:0.8) BadNegAnatomyV1-neg bradhands cartoon, cgi, render, illustration, painting, drawing

4、国风3

https://civitai.com/models/10415/3-guofeng3

这个模型我之前用过,不过最新的版本反馈提到偶尔会出现一点问题。

从出图效果上来看好像页游风的感觉,不过这个模型在Civitai上的点赞和下载量都很高,感兴趣的小伙伴可以到网盘里下载试试。

best quality,masterpiece,highres,1girl,blush,(seductive smile:0.8),star-shaped pupils,red china hanfu,hanfu,chinese clothes,hair ornament,necklace,jewelry,Beautiful face,upon_body,tyndall effect,photorealistic,dark studio,rim lighting,two tone lighting,(high detailed skin:1.2),8k uhd,dslr,soft lighting,high quality,volumetric lighting,candid,Photograph,high resolution,4k,8k,Bokeh,

Negative prompt: (((simple background))),monochrome,lowres,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,lowres,bad anatomy,bad hands,text,error,extra digit,fewer digits,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,ugly,pregnant,vore,duplicate,morbid,mut ilated,tran nsexual,hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed,blurry,bad anatomy,bad proportions,malformed limbs,extra limbs,cloned face,disfigured,gross proportions,(((missing arms))),(((missing legs))),(((extra arms))),(((extra legs))),pubic hair,plump,bad legs,error legs,username,blurry,bad feet,

**5、Juggernaut XL

**

https://civitai.com/models/133005/juggernaut-xl

这个模型我倒是还没有用过,不过看下面的反馈图感觉这个模型可以驾驭多种风格。

photograph, photo of woman with blonde hair, selfie, upper body, solo, wearing pullover, outdoors, (night), mountains, real life nature, stars, moon, cheerful, happy, gloves, sweater, beanie, forest, rocks, river, wood, smoke, fog, looking at viewer, skin texture, close up, RAW photo

Negative prompt: bad eyes, cgi, airbrushed, plastic, watermark

6、MeinaMix

https://civitai.com/models/7240/meinamix

这个模型用来生成各类二次元同人角色的效果还不错,很适合那些想要定制自己喜欢的角色的桌面或者壁纸。

1girl, parted lips, blush, makeup, light smile, school uniform, classroom, light rays, glow, thighs, collarbone, narrow waist, (masterpiece), wallpaper

Negative prompt: (worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers:1.2)

**7、MeinaHentai

**

https://civitai.com/models/12606/meinahentai

realistic, 1girl, ponytail, parted lips, blush, makeup, light smile, white hair, sportswear, skirt, wet clothes, glow, thighs, purple eye, bare shoulders, collarbone, narrow waist, sunbeam, sunlight, rose, wind, cleavage, (masterpiece), sweat,

Negative prompt: (worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers:1.2),

**8、万象熔炉

**

https://civitai.com/models/9409/or-anything-xl

这个模型我的评价是我个人最喜欢的二次元模型之一

1girl, Best quality, genshin,Touhou Project,Honkai StarRail, mamimi(mamamimi),blade (galaxist),((fuzichoco,butterchalk,yoshinari you,mika pikazo)), school uniform, blunt bangs, holding pokemon, open mouth, one-hour drawing challenge, on head, blue background, looking at viewer, straight-on, one eye closed, white shirt, pokemon (creature), index finger raised, collared shirt, smile, animal, shirt, brown eyes, wing collar, blunt ends, teeth, long sleeves, hime cut, black hair, long hair, necktie, purple eyes, tongue, portrait, purple necktie, ;3, blue necktie, crossover, animal on head, grin, holding, cat, masterpiece, newest, absurdres, safe

Negative prompt: (worst quality, low quality:1.4), negative_hand Negative Embedding,verybadimagenegative_v1.3, 2girls, nsfw:1.4,bad anatomy, bad hands, cropped, missing fingers,too many fingers, missing arms, long neck, Humpbacked, deformed, disfigured, poorly drawn face, distorted face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, long body, missing toes, too many toes,monochrome, symbol, text, logo, door frame, window frame, mirror frame

9、Dark Sushi Mix

https://civitai.com/models/24779/dark-sushi-mix-mix

这款模型所生成的二次元图片无论是整体质量还是细节都是我觉得比较好的。

masterpiece, best quality, 1girl, full body,white hair,long hair,purple eyes, slim body,slim legs,playing violin,white dress,night,moon,shootig star,cloud,lakeshore,

Negative prompt: sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs, nipples,nsfw,

10、Rastel-Mix

https://civitai.com/models/5414/pastel-mix-stylized-anime-model

**LoRA

**

**1、Detail Tweaker LoRA

**

https://civitai.com/models/58390/detail-tweaker-lora-lora

这个模型用作者的话说就是:这是一个用于增强/减少细节,同时保持整体风格/特征的LoRA;它适用于各种基础模型(包括动漫和现实模型)/风格LoRA/角色LoRA等。

2、Anime Lineart / Manga-like

https://civitai.com/models/16014/anime-lineart-manga-like-style

这模型可以用来绘制各类像是漫画线稿一样的画作,然后可以通过填充的方式给线稿上色

**3、Cute_girl_mix4

**

https://civitai.com/models/14171/cutegirlmix4

这个没啥好说的,如果要生成真实系女生的话可以添加这个LoRA试试。

4、Add More Details

https://civitai.com/models/82098/add-more-details-detail-enhancer-tweaker-lora

这个模型也是给画作添加细节的,和上面的一个功能差不多,大家可以分别试试看哪个更能帮助自己达成想要的效果。

5、M_Pixel

https://civitai.com/models/44960/mpixel

这个能够生成像素小人的LoRA是比较有趣的一个LoRA,尤其是想我之后做游戏要做像素风格的就很合适。


其实还有很多很有趣的LoRA和Checkpoint要么是篇幅限制、要么是我之前的那篇笔记讲过了,就暂且不放在这篇里。

两篇合集中所提到的所有模型我都上传到了我的百度云网盘中,链接我就放在了下面。里面还包括了我没有提到但是有用过的模型,想什么黑丝白丝LoRA在里面都有。

希望我这篇笔记能够帮助到那些苦于无法找到模型资源的小伙伴们,资源都是免费的,希望大家不要被骗了。

那我们就下篇笔记见啦,拜了个拜!

相关推荐
paixiaoxin29 分钟前
CV-OCR经典论文解读|An Empirical Study of Scaling Law for OCR/OCR 缩放定律的实证研究
人工智能·深度学习·机器学习·生成对抗网络·计算机视觉·ocr·.net
OpenCSG1 小时前
CSGHub开源版本v1.2.0更新
人工智能
weixin_515202491 小时前
第R3周:RNN-心脏病预测
人工智能·rnn·深度学习
Altair澳汰尔1 小时前
数据分析和AI丨知识图谱,AI革命中数据集成和模型构建的关键推动者
人工智能·算法·机器学习·数据分析·知识图谱
机器之心1 小时前
图学习新突破:一个统一框架连接空域和频域
人工智能·后端
AI视觉网奇1 小时前
人脸生成3d模型 Era3D
人工智能·计算机视觉
call me by ur name1 小时前
VLM--CLIP作分类任务的损失函数
人工智能·机器学习·分类
吃个糖糖2 小时前
34 Opencv 自定义角点检测
人工智能·opencv·计算机视觉
禁默2 小时前
2024年图像处理、多媒体技术与机器学习
图像处理·人工智能·microsoft
KeepThinking!2 小时前
YOLO-World:Real-Time Open-Vocabulary Object Detection
人工智能·yolo·目标检测·多模态