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
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
FAQ
Comments (69)
One Obsession - 17_RED is absolutely stunning. The first thing that struck me was how luminous and full of life the outputs can be — they carry a radiant clarity that feels uplifting and powerful, almost like the images are glowing from within. It’s the kind of brilliance that instantly catches your eye and makes you want to keep creating.
But what makes it truly special is the way that same energy can twist into the shadows. With just a shift in tone, the light transforms into something dark, sinister, and haunting. Suddenly the results feel heavy with atmosphere, dripping with menace and mystery, like they’re telling stories from the darker corners of imagination.
That duality is what sets this checkpoint apart. It doesn’t just give you one mood — it gives you the full spectrum, from radiant beauty to wicked intensity. Every output feels alive, expressive, and emotionally charged, making the creative process feel exciting and unpredictable.
Honestly, this is one of the most impressive checkpoints I’ve tried. It nails both extremes — dazzling light and chilling darkness — and makes every experiment feel like uncovering something powerful.
这个检查点简直令人惊叹。首先让我印象深刻的是,输出结果的明亮度和生命力——它们带着一种耀眼的清晰感,让人感到振奋且充满力量,几乎就像图像本身在发光。这种光芒能立刻抓住你的目光,让你忍不住想要继续创作。但真正让它与众不同的是,同样的能量可以转化为阴影。只需调整一下语气,光线就会变成黑暗、阴森且令人不安的东西。瞬间,结果便充满了浓厚的氛围,散发着威胁与神秘,仿佛在讲述想象中黑暗角落里的故事。这种双重性正是这个检查点的独特之处。它不仅仅给你一种情绪,而是给了你整个光谱,从耀眼的美丽到狂野的强度。每一个输出都显得栩栩如生、富有表现力且情感充沛,让创作过程变得既兴奋又充满未知。老实说,这是我试过的最令人印象深刻的检查点之一。它完美捕捉了两个极端——耀眼的光明与刺骨的黑暗——让每一次实验都像是在发掘某种强大的东西。
可以在V16的基础上加强手脚吗?球球了 真的很好用!!
我翻译下Spitfire_502这位夸夸侠老兄的评论:
One Obsession - 17_RED 简直令人惊艳。首先吸引我的是其输出效果的明亮度和生命力——它们有着一种熠熠生辉的清晰感,令人感到振奋且充满力量,仿佛图像从内部散发光芒。这种光彩夺目的效果瞬间就能吸引你的目光,让你想要不断创作。
但真正让它与众不同的是,同样的能量,竟能顺滑的扭转光明与黑暗之门。只需语气(tag)稍作转变,光明便化作阴暗、险恶且令人毛骨悚然之物。瞬间,这些成果便充满了氛围感,弥漫着威胁与神秘,仿佛在讲述来自想象中阴暗角落的故事。
这种二元性正是这个检查点(模型)的独特之处。它不只是给你一种情绪——而是给你整个情绪光谱,从灿烂的美丽到邪恶的强烈。每一个输出都感觉充满活力、富有表现力且情感充沛,让创作过程变得令人兴奋且难以预测。
老实说,这是我在玩过的检查点(模型)印象最深刻的一个。它完美地兼顾了两个极端——炫目的光明与令人胆寒的黑暗——让每一次尝试都像是在揭开某种强大的力量。
Hey, this model is my favorite and most frequently used one. However, I feel that the controllability of artist tags might have started to become less effective, especially when the data volume on Danbooru is around 200, as it fails to reflect the style. Do you have any plans to update the training dataset? Many characters we are familiar with are already supported by other models, but this model definitely can't handle characters from 2025. For instance, characters like "忍冬" (Rendong) from Arknights, released in November 2024, are supported by many other models, but this model still cannot generate them.大佬,这个模型是我最喜欢最常用的模型,但我感觉可能艺术家标签的操纵性尤其是Danbooru网上数据量在200左右的时候已经开始不佳了,体现不出风格。大佬有没有更新训练集的打算?很多我们熟悉的角色,其他模型已经可以支持了,但是这个模型25年的角色肯定不行,24年11月的忍冬(明日方舟)很多模型都可以支持,但是这个模型还是不行。
@maxfeifei8 thx i'll try it
You test the V19 version, which has a new dataset.
this v19 it is better than v18?
孩子们,这个模型太牛逼了,对比度和动作解析度非常厉害!强推!
请问14 2.4d版本还能用吗
I also like the V17. The depiction of shadows is particularly noteworthy. Of course, the model reproduction is excellent, but it stands out among the various models, and it's this that makes me want to use it for a long time. It inspires my creativity. Thank you to the wonderful engineers.
Guys,this model even suppurot keyword: smegma ,I never seen any 2D model support it. So surprised!
Change your name to "smegma"
Change your name to "smegma"
I dont want to know it😱😱
what is ******?
@getSomeAnime If you didn't google'd it, good, don't. But if I'm late, RIP
Hello, I'm having problems to install v18 model on Invoke. When I install it, I get a blue screen error related to memory, only with this model. Installing before your mature max model or another models and everything goes well.
I installed in the past one or two times v18 and all went ok, I don't know what has changed.
ideal.
One Obsession v19, like v18, is incredible. But I think v17 is still my go-to. Probably just boils down to personal taste, but the look and feel of what v17 is able to create is still second to none amongst checkpoints (including the other One Obsession versions) in my eyes.
大佬,v19我整体用下来感觉你是不是融合了wai或者hassaku?风格和之前不同了,然后手和四肢的控制又非常强,这个模型简直无敌了!
没有wai或者hassaku。
@maxfeifei8 哦,那就是illu原始的样子咯?总之,非常好
Comparing v17 and v19 here are my thoughts when using both across the same prompts:
v17: much more stylized, glossy, stronger shadows, stronger contrast
v19: more realistic under the same prompts, flatter and smoother shadows and reflections
If you want a touch more realism v19 is better. v19 has much more realistic lighting. If you want stronger style v17 is better. Personally, I like v17
That's really amazing 🫨
which seems to have better prompt adherence in general, would you say?
@DenkiSolosShippuden tldr: I didn't use v19 all that much past initial testing, but I will say v17 is really good at following prompts, at least for my purposes. I have yet to run into any major issues.
Most of my stuff is pretty straight forwards though, usually just one character in a frame. I've had difficulty with getting consistency with multiple different characters at once, but that's just an AI thing and would likely be fixed with character Loras. I usually use no or minimal Loras for clothes and poses and it works great, unless there's something really specific I want. It has pretty strong consistency with characters and clothing even without using Loras as long as you're specific with your prompts. Even at CFG 3.5 it works really well.
大佬国产的Z-image模型怎么样,是否考虑炼一版
Do you have a list of artists I can use in promts?
Too big, not easy to organize, quite a lot of online.
This is far from comprehensive, but it's helpful:
https://civitai.com/articles/16938/yet-another-exploration-of-illustrious-styles
对lora的支持比之前好了,几乎不会出现内因性崩坏或者非指令风格变化
Can we normalize not posting videos for non-video models? The model doesn't do that. It's super annoying.
I for one don't mind videos at all
Filters —> Media Type —> Video —> uncheck —> problem solved
I just started with ai generating images and its very interesting, but i agree, stuff like this confuses me.
As someone who posts quite a lot of videos to this model, here is my take on the issue:
- I try to post my vids together with the source image and they are meant to be more of "bonus" for those who like the image. (the image being the cover of the post.)
- The on-site descriptions led me to believe that for videos generated using an image as the base, the prompt and model selections should reflect the image, rather than the video. I also checked various posts to see how others have handled this and that understanding seemed to be correct, so I went along with it.
- I make sure to properly tag "Grok" as the tool to generate my vids and "img2vid" as the technique. Without video posts like these, I never would have gotten into image-to-video generation, and thus I'm grateful they exist.
- You can easily filter out the videos as mentioned above by another user.
can we normalize not uploading images with high resolution fix in model cover and model showcase so we can have actual idea of how good a model actually is.
It's fine for eye-catchers, but yeah, really.
v19 ruined furry generations, please fix it.
V19 is difficult to work with compared to V18. V18 is more flexible in creativity and seems to understand the prompt better.
貌似侧面容容易偏御姐? 我这试了试正面没问题 少女角色侧脸往往就御姐风格了…
而且大场景的图侧脸好像也容易崩(可能面部占比问题)… 感觉必须配面部修复用…
V18 is wayyyyy superior
fr
赞同
One Obsession is my favorite but I was getting much better results with v17 and v18.
pls bring back v18
I've tested both V19 and V18 and let me just say this, the colors are more vibrant and the body composition is more on the mature side with V19. However, it sacrifices some creativity, texture, depth, and detail to the overall appearance of the character.. It also seems to be more flat and tends to prefer 2D style over 2.5 or 3D. Also, it seems as if hand generation is more accurate and consistent on V18 than on V19, but it might just be me. Feel free to reply if you have experienced something different.
Now then, if you are okay with those small sacrifices and trade offs, then this will be an upgrade for you. If not, stay on V18.
I absolutely love the noobai v16 model! It has the best style among all the models I've tried (and I've tested quite a few). Thank you so much for creating such an amazing model! Are you planning to release more noobai models in the future?
v19 > v18 in generating famous anime scenes and characters but v18 > v19 in any other custom generations. v19 seems to be something different and unrelated to previous versions
Yes
mind upload it to www.seaart.ai ?
有没有考虑拆分成不同的模型?不同版本之间的画法差异实在是太大了
i like that this model have a more 3d style on it, but i find the background a bit scuffed
one obssession真牛逼,这几天被animeginev4xl搞的天天鬼图不断,头都秃了换成佬的这个直接起飞,质量轻松上乘!咱就是牛逼
v19版本感觉过于明亮了,以至于加了很多调整亮度的lora和提示词都效果甚微。而且在皮肤光泽上经常会有小光圈而不是光滑细腻的泛光,也就是shiny skin的效果并不好。希望能改善这两点喵!
I really like V19. I agree it's different from the rest - that's why you named it 'Atypical', I guess. I would encourage you to continue V19 as its own series, if you decide to go back to V18, because I think it's superior to WAI (V16).
The only thing that bugs me is that the girls turn out slightly more mature than their original design. Fix that and V19 is perfect!
I've been using this model since v15 and it's great. My only complain is that it sometimes gives overly bright images. It's like sometimes the lighting source is just right in front of the character. how do I make the lighting consistent like other illustrius models?
use this to make the initial image, and the qwen image edit to fix the lighting scene
@leandro_z_842 how to use qwen image if my image always got flagged as nsfw? or is this a local qwen image?
Fvck BID
I really do love the V19 one, when will be able to generate onsite again?🥺
Friday
Details
Files
oneObsession_v19Atypical.safetensors
Mirrors
oneObsession_v19.safetensors
oneObsession_v19Atypical.safetensors
oneObsession_v19.safetensors
oneObsession_v19Atypical.safetensors
oneObsession_v19.safetensors
oneObsession_v19Atypical.safetensors
oneObsession_v19.safetensors
0N30B535510N_XIX.safetensors
0N30B535510N_XIX_0r1.safetensors
oneObsession_v19.safetensors
oneObsession_v19.safetensors
oneObsession_v19Atypical.safetensors
oneObsession_v19.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.

















