One obsession_Anima（Open free download）
https://civarchive.com/models/2695493/one-obsessionanima
Mature.性感 木珠 NoobAi.Vpred:
https://civarchive.com/models/1368727/one-obsession-branchmaturenoobaivpred
Please support my new NoobAI model: https://civarchive.com/models/2558457/oneobsession-hybridtheory-noobaiillustrious
请支持一下我的NoobAI新模型：https://civarchive.com/models/2558457/oneobsession-hybridtheory-noobaiillustrious
If you like my work, please give me a good review and click the thumbs-up icon. Please give me more feedback! It's free, and it can keep me motivated to create.
如果你喜欢我的作品，请给我一个好评并点击大拇指图标。多多返图！这是免费的，而且能让我保持创作动力。
You can make a good picture without lora, without complicated tags, and it is extremely friendly to beginners!!!!!
不用lora也能出好图，不用复杂的tag，对新手极其友好呦！！！！！
Still, I repeat, the new version may not necessarily be the best. Experience it yourself and have fun!
^^!绘画标签都藏在图片提示词中！寻找画师串也是乐趣所在！例图未加任何lora，其他自己探索吧！还是那句话，各有特色新版本不一定是最好的。自己体验，玩得开心！
AI绘画QQ交流群：
（在用）点击链接加入群聊【痴迷AIGC备用群】：https://qm.qq.com/q/XZutAVZVei
点击链接加入群聊【痴迷AIGC生活继续新新新1群（第三次转生）】：https://qm.qq.com/q/Uqw8uS7I0C
点击链接加入群聊【痴迷二次元AIGC永远不说再见之新新新新1群（第四回）】：https://qm.qq.com/q/EdWjbCj1Bu
点击链接加入群聊 少女宗所在群，这里不欢迎木珠 【痴迷AI新3群二次元少女宗】：https://qm.qq.com/q/DkcPLAh1uw
请认真回答从哪来？瞎回答的不予通过！
感谢QQ扩群的群友募捐： 木珠门大长老 夏雨声烦 antanc 109°28’ duiker 普通男性 摸鱼仙人 夜小钗 风纪委员 pipiai 天子doro paff 飘忽 夏沫 苏沐凝萱 牢冰 China头子 underlzy 锐子 库里垮炎 pixard 沉默的威斯东 多出来的几十块推到下一年，还缺谁Q我！
前三个个群如果都搜索不到就进DC，毕竟DC&TG可以涩涩
Discord：https://discord.gg/7RNWedD59H
tg：https://t.me/+ar2q0dOvGVAxZDA1
^^! The painting tags are all hidden in the picture hints! Finding artists to collaborate with is also a lot of fun! The example picture hasn't been enhanced with any lora, and the rest is up to you to explore! As I've said before, the new version may not be the best. Experience it yourself and have fun!
Discord：https://discord.gg/7RNWedD59H
TG:https://t.me/+ar2q0dOvGVAxZDA1
推荐一个forge或webui的插件，方便 Illustrious的动漫角色的选择，插件可以扩展URL安装，插件链接如下：https://github.com/lanner0403/WAI-NSFW-illustrious-character-select
可盐可甜可干爽可油腻可3D可2D 可涩涩可清纯 打造泛用性最强二次元Illustrious微调大模型！（狗头）
光影方面建议加：(chiaroscuro,high contrast:0.5),(sunbeam), 等来强化光影
如果希望画面变暗可加： (dark,chiaroscuro,hight-contrast:1.7),
人物半写实可加：((realistic, photorealistic, realistic shading)),
还原动漫可以加：(anime screenshot),(anime coloring ), 动漫截图，动漫上色，来还原
2.5D半写实画风：(photorealistic, realistic, 3d, photography),
2D画风：((flat color:1.8)),(abstract:0.5),只用前面的平涂不带后面的抽象也可以。也可以再加上：(anime screenshot),动漫截图，(anime coloring ),动漫上色。
关于画风的绘画标签，画师串太多，自己研究吧！
The thief website [PixAI] has illegally used my model without my permission. Moreover, my model is free and has been published on...
小偷网站[PixAI]，未得到我的许可，非法使用我的模型。而且我的模型是免费的，发布在
★NOW★
推荐分辨率：1024X1536 、832 x 1216、896 x 1152、768 x 1344、640x 1536、
recommended resolution：1024X1536、832 x 1216、896 x 1152、768 x 1344、640x 1536、
V21动漫实验版本：质感更润了，加强了光影，弱化了一些3D，人物偏可爱，对画风，画师串敏感；画风兼容性不错，有些画风会有点抽象。
Anime experimental version, texture is more moist, strengthen the light and shadow, weaken some 3D, characters are cute, sensitive to painting style, painter string; painting style compatibility is good, some painting styles will be a little abstract.
V20版本：回归到v18 v17的风格，增强质感，风格化。
Continue v18.v17 style, enhance texture stylization.
V19版本：奶奶比上个版本大，算不算优点，^_^更加明亮鲜艳，线条更加细腻，较上个版本减少油腻感和风格化，在2D和3D中找到平衡。
The breasts are larger than the previous version. Is this a merit? ^_^ They are brighter and more vivid, with more delicate lines. Compared to the previous version, the greasiness and stylization have been reduced, Finding balance between 2D and 3D.
18版本 强化了手和脚，还有略微调整，tag精准，很高兴我在熟女和萝莉之间找到了平衡，它们都可以完美实现，图像偏柔和一些，细节比较多。
Version 18 enhanced hands and feet, there are slight adjustments, tag accuracy, I am glad I found a balance between mature women and loli, they can be perfectly achieved, the image is softer, more details.
17 例图没有添加任何lora，更加完美的手脚！！！颜色重新调整了，使其更加鲜艳！比14版本弱化了3D。更加适合新手，简单的tag可以制作出高质量的图像。
Example picture without adding any lora, more perfect hands and feet!!! The color has been readjusted to make it more vivid! Weakened 3D than the 14 version. More suitable for beginners, simple tags can make high-quality images.
16 优化了直出效果，比前一个版本增强了3D，不想3D可以下载15.在不添加大量质量词的情况下也能很好的出图。同时提升了对御姐的理解，可以跑出大约25~28岁的成熟女性，强化了肢体的稳定性，其他轻微调整，使我感觉更舒服。（非常抱歉开通了EA，我需要Buzz支付每周的竞价和在线绘画，还有后续的计划。）
16 Optimized the direct output effect, which enhances 3D compared with the previous version. If you don't want 3D, you can download 15. It can also draw pictures well without adding a lot of quality words. At the same time, it improves your understanding of the imperial sister, and can run out of mature women aged about 25-28. It strengthens the stability of the limbs. Other minor adjustments make me feel more comfortable. (I'm very sorry for opening EA, I need Buzz to pay for the weekly bidding and online painting, and follow-up plans.)
You can use ADetailer to enhance facial details：https://github.com/Bing-su/adetailer
可以使用 ADetailer 来增强面部细节：https://github.com/Bing-su/adetailer
推荐我喜欢的分辨率：768X1344 832X1216 768X1280 704X1408 1024X1536
Model Recommended Resolution：768X1344 832X1216 768X1280 704X1408 1024X1536
Illustrious 1.0（noobAI）：896 x 1152、1216 x 832、832 x 1216、1344 x 768、768 x 1344、1536 x 640、640 x 1536，
Illustrious 2.0{Rouwei Illustrious1.1}支持更大分辨率：1536x1536、1728x1344、1344x1728、1824x1248、1248x1824、2016x1152、1152x2016
正面词 Positive Prompt：
masterpiece, best quality, amazing quality, very awa,absurdres,newest,very aesthetic,depth of field, highres,反义词 Negative Prompt：
worst quality,normal quality,anatomical nonsense,bad anatomy,interlocked fingers,extra fingers,watermark,simple background,transparent,low quality,logo,text,signature,face backlighting,backlighting,Recommended settings:
Steps: 25-35
CFG scale: 3-6
Sampler: Euler a Euler
Description
18版本 强化了手和脚，还有略微调整，tag精准，很高兴我在熟女和萝莉之间找到了平衡，它们都可以完美实现，图像偏柔和一些，细节比较多。
Version 18 enhanced hands and feet, there are slight adjustments, tag accuracy, I am glad I found a balance between mature women and loli, they can be perfectly achieved, the image is softer, more details.
FAQ
Comments (114)
”红色不是邪恶，它是正义！是为了庆祝反法西斯战争胜利 80 周年，呼吁营救加沙妇女和儿童！！！反对军国主义！反对霸权！反对侵略！！！“
大力支持国人模型制作，顺便给绿蛙们发放100万金圆券祝他们发家致富。
This is beautiful!
Super strong, always in use
that's good
In my opinion, the author's model is perfect. Furthermore, I support the author speaking up for China. Justice prevails! Peace prevails! The people prevail!
在我看来作者的模型是完美的。并且我支持作者为中国发声，正义必胜！和平必胜！人民必胜！
I believe that a creative environment like this site should contain no references to politics whatsoever. We're primarily engaged in creativity here, not politics.
V18 is V-Pred?
V18 is Eps
爆赞
太棒了
C C B
Really an amazing model.. no joke i used to use A LOT of loras to make images look any good.. but with this one there is no need.. maybe if i really wanna go for specific style but even then i can mostly just name artists in prompt and it does amazing things!
I buy the last version, and i have a problem with Adetailer, the face become weird, and the classic inpaint is ugly '-' why ? is that my neg prompt ?
I think it's your setup.
Come on, we almost reach the donation goal
first of all, thanks for another interesting model.
about this version it is said that: "Strengthened hands and feet, slightly tweaked, tag accurate, glad I found a balance between mature and loli, they all work perfectly."
but in relation to which verison? the 17RED?
I mean, this v18 is it supposed to be a direct upgrade of some specific version? Because I use both 15 and 16 for the more 3d and anime focus of each, and 17 because I like the theme hehehe but it would be good to understand if this 18 is a direct upgrade of some of these or an independent model : )
In fact, v18 preceded v17, which was later stylized.
@maxfeifei8 indeed v17RED seems differente, special. But 15 and 16 are differente. Are v18 more 3D like 16 or does it enhances more the outputs of drawing like 15?
mhmm i did some tests and used the set and seeds and i dont get the same result as in the shown image my question are u sure its the right version that u uploaded? sure some images looks to like the chars but i tryed jinhsi,fern but i never got the same picture result ( jinhsi sits allways only in water and the whole background that in the preview is shown is gone), fern doesnt do the pull out move just holding her own shirt open thats it..check it pls if something is wrong but i used the same settings ofc
Could be so simple as a workflow difference, if he has different seeds in different nodes that could cause some difference, or if he has something between loader and ksampler for example that could cause a difference too
大概有多少画师串呢？
cool
正在使用 v16 和 v18 ，感覺同一段 prompt v18會得出比較暗的圖片，v16 則比較亮。但 v18 的細節多一些。
对，是比较16和17版本，18的图像比较柔和，没那么亮，暗倒是谈不上，除非写“黑暗”的tag
同一段 prompt (big breasts)，v18 女孩再豐滿一些 (腿都粗一些)，v16比較苗條
現時看情況，兩個版本都會使用！🫡
@shenhaixianyu 可能跟我调整另一个Mature版本有关系吧！确实丰满了一些吧，没仔细注意啊，你真细心！
any one know how to get rid of those "shock wave "effect?
有大佬知道怎么不要那些“撞击”“特效”吗
非常非常好，期待能一直更新下去，就是不知道为什么，开高清，总是比别的要调低倍数（别的1.5倍，用这个只能1.2倍），是不是因为细节太多了？但还是很喜欢
放大2倍都没问题啊，重绘幅度小一些，不会改变
I've been testing v18 for a while now and I've noticed that 9-8 out of 10 outputs produce feet with four toes or messed up toes. This wasn't happening nearly as often with previous versions (I've used v17, v16 and v15 a lot). Maybe I'm doing something wrong?
大佬们我在用v17 遇到一个问题 每次生成的图片不管是白天还是夜晚，基本上脸上都是没有光的，生成50张图可能才能有一张是脸上带有光影的，身体的上的光影都是正常的，但就是脸上总是在阴影里。 不知道因为什么 有大佬能帮忙解答一下么
脸上有阴影很正常
@maxfeifei8 大佬居然回复我了, 我看到 v17介绍里的封面图好多都是正面脸部是有光的 ，我自己生成时候 就是生成不出来。 基本上脸都是在阴影里 偶尔带点光，生成不出脸上大面积有光的照片，
@Qqbingliang 可能你太关注这个了，别在意就好
@maxfeifei8 嗯嗯谢谢大佬回复 确实是我太在意了 模型很棒
我对比了一下V18和V1322D，有些时候18的头身比例不太对，具体的说就是头部太小了，显得身体很长。大概10几张图左右就会有几张比例不对的。V1322D在这方面表现要好。还有一些词V18不能理解，V13倒是能理解。还有V13在一些图片中会自主加一些丰富的背景元素，也是个优点。
喜欢哪个版本用哪个
每个版本都有它的优缺点，没有办法做到人人满意，属于各花入各眼吧
嗯。我两个版本都保留了。如果V18身材比例更准一些就更好了。它的画风确实更柔和一些。
想问一下v18你用什么prompt能使身体变长呢？我的身体比例还是很差
I really don't know how I feel about you're newest 18 model.....It seems extremely unstable at higher resolutions. I will do one more day of testing...
It's better to zoom in with the basic resolution. I don't recommend too much original resolution. It's XL model. It can't withstand too much original resolution. If you need 4K, zoom in a few times is better!
recommended resolution：896 x 1152、832 x 1216、768 x 1344、1536 x 640、1024X1536、1024X1024
@maxfeifei8 IT WAS SOME OF THE LORAS I WAS USING WITH YOUR CHECKPOINT CAUSING IT TO MELT!!! I'M SO SORRY! :(
Also, beware of those optimized 'hyper/lightning' LORAS, like dmd. I used a 'dmd2_sdxl' with 360mb recently (I use to change checkpoints between sdxl, pony and illustrous), and it somewhat turned the results far worse. Then I remembered this is an illustrous checkpoint, so I used noobai_hyper_dmd and it was better. There are 'hyper and hypers', be careful if you want optimization
Another solid incremental improvement. He can't keep getting away with it!
Right, so I spent the last few days using model 18, and my conclusion is: It's a very solid model, a very good evolution in anatomy and art style, but it has the disadvantage of being more difficult to mimic other artists' styles, since its standard style is more prominent. Overall, congratulations Max, your model is very good, it's no wonder you make some of the best models.
Applicable to all kinds of artist styles, if the style is not outstanding, artist style can improve permissions.
@maxfeifei8 I don't think I understand what you're saying
@Leamas_ The next version will be optimized
大佬们，多眼皮的问题有什么解决方案啊，这个是模型通病吗
Which VAE should I use because my images are black
Model comes with VAE, no need for another
clip: -2
As the name implies, it does red very well. Thumbs and toes all the way up!
My favorite model, great hands and feet.
some images are totally black, and I can't figure out why. There is one particular prompt which I used in v15, v16, v17 and they were all outputted right, but v18 can't understand something in the prompt and are giving me a totally black image, no matter what I do.
Any help would be appreciated. I can give the prompt with the details.
whats the prompt and what are you using to generate with? auto1111 comfy or something else?
@JustLateNightAI I'm using Forge. I have a few prompts that I use to test models. They are 4. For this model (oneobsession vs18), 3 out of 4 wen well, but this one did not:
(front view), 1boy, brock_(pokemon), pokemon, pokemon_rgby, brown_hair, (closed_eyes), full_body, male_focus, (standing), (topless_male), masculine, muscular, gay, manly, pubic hair, hairy legs, underwear, underwear only, bulge, erotic, sexy, (holding coffee mug), looking away, ((leans upright against the kitchen counter:1.6)),
looking out of the window, (is illuminated by the sun from the side:1.5), dynamic shot, window on the side, (view from head to knee), body turn to the window, ,
perfect lips, perfect detailed mug, full body view, white wrist bandage, white foot bandage, seductive, tired after hard training, scars on leg and pectoral, dirty bandages, narrow waist, trained body, dirty marks on body, marked by training,
BREAK full body view,
indoors, modern light grey kitchen,, dark room, sunlight from the side, counter, potted plant, light rays, light particles, sunlight, scenery, beautiful, subsurface scattering, bokeh,
breeze, soft breeze, wind coming in, open window, scenery, detailed background, sky outside, tree,
BREAK
dynamic pose, dramatic lighting, bloom, portrait,
masterpiece, best quality, amazing quality, very awa, absurdres, newest, very aesthetic, depth of field, highres,
movie quality, focused subject, colorful theme, colorful, (anime coloring), (chiaroscuro, high contrast:0.5), (sunbeam),
Negative prompt: Smooth_Negative-neg, SmoothNegative_Hands-neg, lazyhand, lazyneg
Steps: 25, Sampler: Euler a, Schedule type: Automatic, CFG scale: 4, Seed: 3546931045, Size: 1024x1280, Model hash: a208ff5dfb, Model: oneObsession_v18, Clip skip: 2, TI: "Smooth_Negative-neg, SmoothNegative_Hands-neg, lazyhand, lazyneg, Smooth_Negative-neg, SmoothNegative_Hands-neg, lazyhand, lazyneg", Version: f2.0.1v1.10.1-previous-669-gdfdcbab6, Module 1: fixFP16ErrorsSDXLLowerMemoryUse_v10
Time taken: 6 min. 8.5 sec.
Worth note that it outputs, EXACTLY like this, the correct image for v15, v16 and v17_RED. Only v18 is giving a black image. But only for this prompt, the other 3 I tested went ok.
I’ve been using it a lot lately and really enjoying it.
I feel that in version 18, the character proportions look a bit more compact and rounded to 17, so I personally preferred version 17.
I’m looking forward to seeing its successor!
А почему все изображения блестят? Зачем столько глянца? Это же неестественно. Это можно исключить полностью с этих моделей каким нибудь тегом?
скорее всего у тебя промпте что-то делает изображение блестящем, если нет попробуй лору Shading slider или что-то на подобии
Тоже заметил такую особенность конкретно этой модели. Похожие не использовал, так что сравнить особо не с чем — в основном модели под 2D всегда использовал. В итоге решил для себя, что лучше взять годную модель под 2D (Dark Illusoria, например. У неё стиль красивый) и докинуть 3D Slider + Smooth Detailer Booster, и будет картинка лучше, чем здесь, и без «пластиковости»/глянцевости. Вообще, рекомендую обмазаться LoRA-ами с припиской Slider и пачку стилей подобрать, и можно превратить модель с красивым стилем (Dark Illusoria в моём случае) в то, на что она изначально даже близко неспособна, при этом сохраняя стиль, тогда как кривая анатомия и «плывущие» детали есть везде (а я тестировал около двух десятков разных моделей)
Не говорю, что это плохая модель. Сам ей пользовался поначалу долгое время, когда только влился в генераторы картинок. Возможно, тэг «glossy» в отрицательном запросе может помочь с глянцевостью. Или перейти на версию 14, где как будто бы этой глянцевости особо и нет
My model can give a picture of sparkling effect, but also can give a picture without sparkling effect, why bother with this?
@maxfeifei8 Я писал сообщения глядя на довольно большой объём глянцевых картинок. Я подумал что этот чекпоинт состоит весь из такого глянца.
@lentor It's up to you to write the effect picture, my example picture also has pictures without flash effect.
@Synapse25 Yes
为什么用这个模型有时候一直出黑图，重新部署一次sd又好了，过段时间又变成出黑图，但是我用别的模型就立马正常了🤨这也太玄学了
说清楚用什么工具？详细设置，最好进QQ群问
@maxfeifei8 今天又试了下这模型，它又自己正常能出图了，搞不懂了真是，设置啥的基本是没怎么动的默认，用的是绘世启动器
vae问题吧 模型出黑图换其他大模型跑一张图 再换回来就正常了
换这个vae试试 sdxl_vae_fp16fix
模型自带VAE，不要添加，别动就是最好的选择
@maxfeifei8 我没加vae，我知道现在的模型基本自带vae，反正就是感觉很玄学那种bug
Majestic model, perfect balance in prompt, nice anatomy, Excellent feet and hands .
这个模型光泽度很高，显得有些油腻，有什么办法可以控制吗
用comfyui出图，就不会油腻啊
负面加shine skin
@maxfeifei8 我用的是comfyui，加上flat color 的tag能好一些，我再研究研究
@rcstone我试一试
@1974320861274 我也是Comfyui，我用shine skin有时会有用
下个版本不延续这种风格了
@maxfeifei8 其实这个模型我之前试过挺多，不知道为什么脸容易崩，大神有什么办法吗？
@maxfeifei8 期待期待
@maxfeifei8 期待：）
@rcstone 脸崩可能是因为图片里脸的占比太小，就是脸的像素太少，放大图片就可以解决，这不是我的问题。
@maxfeifei8 已解决，感谢大神
where do get the work flow
I really like your work. ¿ can Loras be applied to v18??
¿¿¿???
@enntf12180 Since it's a checkpoint, you can add whatever loras you want to it.
Didn't use any version of One-Obsession model before. Also, I was out for a long time, so I don't know much about how much these models have been improved and which new models have become available.
Seeing that, this model has high generation usage. So, should I just start using the most recent version (V18) or look for other models, what do you guys recommend? Those who are using this model for a long time, what do you think?
7-18
The older versions are potentially worth using. It depends which specific look you prefer, and what kind of images you're trying to make. My go-tos are 10 (for anime-screencap type images), 14 (for realistic type images), and 18 (general use). To sum it up, I'd say the most recent versions are slightly superior but not by so much that it renders the old ones obsolete.
AMAZING model!🤩 It works great on everything , easy to use, there is a noticeable improvement over the previous version. However, generating colored eyes still gives me headaches
Кто нибудь знает как в stable делать анимации такие? есть ссылки на уроки, что бы делать анимированные ролики прям в программе?
可以在comfyui里的中国开源模型wan2.2制作动画
@maxfeifei8 знать бы ещё где и что это,как пользоваться, я думал какие нибудь видео по этому поводу есть))
真的对新手很友好，我不太习惯用lora，相同的提示词下，最喜欢这个模型生成的图片
very good
只能说真🐂🍺，个人最喜欢的还是v16，要是能再进一步优化更新就好了