全部 NSFW 模型
按“下载量最高”排序的成人向 AI 模型榜，每日从模型仓库及经核验的项目来源更新。
- 1
[LoRA] Braless
This is my first LoRA model. It was trained using my [Photo]s4w3d0ffBlend model. I made this with the intention to make a LoRA model that can burn the bra off a "photo real" subject. I was finding it difficult to get that "free booba" look using just prompts, so created this model hoping to make it WAY easier. This model seems to work best with weights around 0.5-0.8 in conjunction with my [Photo…
35,829下载量 - 2
SCG-Anatomy-Flux1.d - NSFW LoRA for Flux!
Like the work I do and want to say thanks? Buy me a coffee or Support me on Patreon for exclusive early access to my models and more! Join us on SCG-Playground where we have fun contests, discuss model and prompt creation, AI news and share our art to our hearts content in THE FLOOD! 💖💖💖 This is a very rough first attempt at an anatomy model that can create semi-decent artful nude women and me…
35,797下载量 - 3
SL Assorted Female Nobodies
Each version is a unique mix and will give you a different consistent face, they are not building upon the last. I updated the names of the files. The names might not match older gens but they are the same. Please share your gens below and rate/react, it means a lot and helps me know which y’all like and dislike. I love seeing what is made with them, even if they are at a low weight. I am bad at…
35,758下载量 - 4
Standing Full Body with Background Style LoRA (带背景立绘/背景付き立ち絵)
Trined on tachi-e (standing full body) with background from multiple mobile games. This LoRA is suited for both portrait landscape orientation images. Usage: Trigger words: white background, full body : tachi-e with background (separately described), try using (white background:1.5) if it's not working; the higher the strength of white background , the larger the white area simple background, ful…
35,690下载量 - 5
LTX 2.3 - I2V T2V Video Reasoning lora VBVR
This was the first VBVR lora trained for LTX 2.3 You can make money with my models. Sell what you generate, use it in paid work, run it on paid services, merge it, sell the merge all of it, no permission needed. Credit is appreciated but never required. New releases might have a short early access window behind Buzz, then go free and free is permanent. Once a model is free, I will never re-paywal…
35,686下载量 - 6
POV Breast Grab Cowgirl | LoRA
Version v2_b: 70 images added to the dataset Better chances of generating the arm. The new trigger words are: breast grab, cowgirl position, girl on top, straddling, grabbing Beware of the LoRA.It may sometimes generate unsatisfactory results, but within a few tries it will for sure do its job. My recommendation, in case takes too long to generate a good image, is to add higher weights to the tri…
35,651下载量 - 7
Crazy Expressions
A lora born of my irritation with the lack of the AI's ability to output truly insane or traumatized looking characters. I recommend for most use cases you refer to the "constricted pupils" tag followed by a facial expression. Check out "About This Version" for more details.
35,622下载量 - 8
Wan POV Cowgirl Insertion
Support me so I can make more models, faster: https://ko-fi.com/the_cook i2v POV Cowgirl insertion LoRA, similar to the POV Missionary insertion LoRA. There are two High Noise LoRAs: A is trained normally and has good movement, but might influence the likeness of the person. B is undertrained and has least amount of influence on the person's likeness. So to get the best balance between good movem…
35,488下载量 - 9
Huge Ass and Boobs
The comment section is locked on this account because I'm being targeted by people. Trained on 1163 Images scraped from Danbooru. Good at Generating Perfect Ass, Big Ass, Big Boobs, and genitals. When this Lora is used, without the trigger words or respective tags, it'll produce thicc girls. Use your regular prompts from Danbooru to trigger them and it'll show the power. will appreciate if you sh…
35,449下载量 - 10
Anti Long Torso/Legs | SDXL/SD1.5 LoRA
for Illustrious: https://civitai.com/models/1689890/anti-long-torso-or-il longtorso for Pony v0.63 recommended weights: -1 ~ 1 longlegs for Pony v0.22 recommended weights: -2 ~ 2 for Pony v0.61 recommended weights: -2 ~ 3 Specific feedback welcome. If you want to shorten the torso, set lora weights positive value(ex. :0.5) and write "long torso" in negative prompt. If you want a longer torso, set…
35,385下载量 - 11
Cumflood (NOOB and PonyXL version)
Ver NOOB V-PRED V2 EQ Trained with improved parameters based on NOOB V-PRED EQ VAE exprimental version: https://civitai.com/models/1858821/noobai-v-pred-10-with-eq-vae Ver NOOB V-PRED 1.0 Trained based on NOOB V-PRED V1.0 with OneTrainer. See about this version for training details. Changed trigger words to prevent unwanted shower head or waterdrop. Pros: Better response to trigger words. There i…
35,335下载量 - 1235,264下载量
- 13
DreamART Style LORA
This Lora is developed by me to make it possible to bring a special style to the generation. So far I'm still at the beginning and it will take a while because of the limited hardware at the moment, but I want to create a Lora that works with as many checkpoints as possible and can generate landscapes, pictures and people with this style. I'm grateful for any help and feedback on problems and com…
35,233下载量 - 14
Classic ahegao
A LoRA trained on classic ahegao pictures featuring almost empty eyes, half-closed lower eyelids and small irises.
35,181下载量 - 15
Jinx League of legends
Trained with NAI on 160 images in of Jinx this LoRA is capable of convincingly reproduce Jinx. It has outfit flexibility and most of the time gets the tattoo right. The triggerword is JinxLol Very good with NSFW images , especially fellatio. Do let me know what you think about this model! Feel free to support my work on patreon Rakosz | Creating NSFW/Erotic illustrated Ai art | Patreon
35,142下载量 - 16
Muscle Slider - LoRA
Simple LoRA to help with adjusting a subjects muscle mass. You can swing it both ways pretty far out from -3 to +5 without much distortion. Positive gives them more muscles. Negative gives them less muscles. One issue you will find is that the more muscles they get, the more tan they get, and vise versa. Bodybuilders grease themselves up with shoe polish, and muscular guys probably get more sun..…
35,121下载量 - 17
Tinker bell (Peter Pan) Disney - FLUX | SD 1.5 | XL PONY | Illustrious XL - by YeiyeiArt
New version new fun! We now have 3 versions of everyone's favorite fairy available. SD 1.5 - PONY - FLUX - Illustrious XL Remember to see the version details to see the new notes to use the model, follow me and continue enjoying the most beautiful models in our community ;D Tinker bell is a well-known Disney character from Peter Pan . Use the keyword “( TinkerWaifu )” for greater precision, and I…
35,080下载量 - 18
Shirt Pull | Test Sex Act Lora 101
Lora trained on 101 images of a shirt being pulled down from the front. It's a little bit random and sometimes the hand doesn't gen \o/ oh well just testing it out. Basic Prompt: lora:FRONT1-000025:1 , blue hair, short hair, eyelashes, yellow eyes, looking down, motion lines, no bra, open mouth, red sweater, sweater pull, bare shoulders, collarbone, unaligned breasts, large breasts, bouncing brea…
35,079下载量 - 19
MGE Monster Girls
Last updated - 22/06/2026 Note - As the supporting articles for this LoRA cover all of MGE's monsters, they contain some NSFW content, so you'll need to log into Civitai.Red to see them. (The first Anima version has been released separately due to the difference in architecture, for those interested.) I now have a Ko-fi for those that'd like to support my projects. While nothing there will remain…
35,056下载量 - 20
Folded Anal Sex | Goofy Ai
If you like my work, drop a 5 review and hit the heart icon. it's free and keeps me motivated All my models are officially hosted and maintained by me on Tensor.art . use my Exclusive and public model for free on tensor.art Get early access to my upcoming NSFW Lora in my Patreon . Support my work by joining any one of them and get early access to all my upcoming loras and other perks such as fan…
35,003下载量 - 21
【Concept】Tentacle pit|【概念】苗床
SDXL version update ! Trigger word is still the same, and 1.0 is a good weight if you want more background tentacles, give tentacle-pit more weight parameter i use : Comfyui : if you are using it too, you can just copy my workflow Base model : perfect PonyXL v3 latent : 512x768 upscale to 1280x1980 Sampling for t2i : eula a ,for upscale: eula ascestral cfg pp, and method is ESRGAN4X Clip skip : 2…
34,894下载量 - 22
Dark Magician Girl LoRA
Dark Magician Girl LoRA Turn on visibility to see all the examples Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕ Great character design from a great franchise. Should work on most anime models at 1 weight (0.6-0.7 for the old one). Triggers with dark magician girl plus her outfit description so she can be customized…
34,879下载量 - 23
Waist Slider (Microwaist) / 细腰
It's generally hard to get Stable Diffusion to make "a thin waist". The waist size of a character is often tied to things like leg width, breast size, character height, etc. This is meant to fix that, to the extreme if you wish. Instructions: Simply add to the prompt as normal. No Trigger word is necessary. V0.5 is far superior to the other versions. You can scale the weight between -2 and 2 with…
34,863下载量 - 24
Detailer IL
Hello there, here is a Detailer for IL dont forget the trigger :) I hope you like it and im tense about the results ! If you like what i do consider leaving me a like or a comment , much appreciated and helps me to continue 🖤 You can also follow me or buy me a coffee ☕ at: https://ko-fi.com/jedas Have a great day ! :)
34,805下载量 - 25
True Buruma
Latest Notes Oct 26,2023 V2.6 "Green" released "Green" is unstable. I recommend to use LoRA Block Weight plugin. Parameters can be seen on this gallery or below. I had removed some images in this gallery due to a violation. I wouldn't like to activate monetization now. True Buruma Buruma(not bloomers) is a world heritage. Features It was trained with over 130 photographs of Japanese old school gy…
34,795下载量 - 26
AI beauty:Ithlinni
This is not refer to any real person. All the training images are generated by stable diffusion. My first try to merge an AI beauty. Have fun.
34,785下载量 - 27
Stomach bulge
10eros_sulphur_1.1 Filtered dataset , should work in most poses without initial bulge Doesn't work as much with clothes Use stomach bulge trigger with description Example made with lcm sampler and 6 steps for 1st stage ltx23 - i2v 1.1 Slower but better audio and hip movement , use at 0.8-1.0 ltx23 - i2v 1.0 Same as previous ones , use at 0.9 or less to have speech Audio doesn't always sync up ltx…
34,778下载量 - 28
Breasts out (exposed breasts concept/helper)
If you like this and wanna throw over some support, buy me a coffee. This is a helper concept that will try to expose breasts without (hopefully) messing with the outfit and location as much. The existing "breasts out" and "exposed breasts" keywords, if they do work, tend to often throw out the outfits. Keyword: breastsout Strength: ~0.7 - 1.0 Usage: ... breastsout lora:breastsout24_rvkwi:1 ... E…
34,575下载量 - 29
Undressing another
Support my work on Patreon and Ko-Fi and get access to tutorials and exclusive models. Rate and leave a like if you enjoyed it, and follow for new models! LoRA trained to generate undressing a character by pulling or lifting clothes. This one is a bit more complicated than usual because of the diverse dataset, multiple poses and tags. You may need to combine tags and change weights and sometimes…
34,461下载量 - 30
Harrlogos XL - Finally, custom text generation in SD!
🚀HarrlogosXL - Bringing Custom Text Generation to SDXL!🚀 Teaching Stable Diffsuion to spell, one LoRA at a time! Harrlogos is an SDXL LoRA trained on my own art and graphic design work, unlocking the ability to generate custom text. It does not require any control net, any img2img, or characters from fonts on the canvas. All you need is the LoRA, and you're ready to go! Versatile, Responsive, P…
34,448下载量 - 31
Character Friendly Body Types - FLUX
Character Friendly Body Types FLUX Will not affect the facial features of other character LORAs. Use the STRONG versions if you're just generating normal images. Use the WEAK versions if you're combining it with different LORAs or if you're using my Lying Down Breast-Morph . Example pictures are a mixture of the strong and weak versions. Keywords: Naked Suggested Weight: 0.8 - 1.4 Other Tips: Mix…
34,447下载量 - 32
Jim Lee (DC Comics / Marvel) Style LoRA
Jim Lee (DC Comics / Marvel) style LoRA Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕ Been wanting to try this for a long time now. I think this came out pretty nicely and captures the style of Jim Lee quite well. I tested it on AnyLoRA and AbyssOrangeMix2 with my negative embeddings and it's pretty convincing at wei…
34,365下载量 - 33
Standing Sex/ Doggystyle | LoRA
Recommended values:0.6-0.9 Enjoy ! If you like the model, you are free to share your creations, I really like seeing everyone's results! :)
34,325下载量 - 34
Underwear less
Donate Coffee for Gtonero Main tag : nippleless bra, cupless bra, crotchless panties, pearl thong, LoRA str : 0.8-1.2 Denoising str : 0.3 to 0.45
34,297下载量 - 35
MahjongSoul/雀魂/じゃんたま Characters ( 23/11/24 Update : Kirara )
My Discord Channel, have a chat with me! 2023/06/15 : Try to update current LoRAs from character only to characters with ingame clothes. See "About this version" for trigger words!. 2023/06/15 : 尝试把现有的LoRA更新成能画多种服装的版本， 触发词请看"About this version"。 Read before using these LoRAs: It's not guaranteed that you will have a result that can reappear ingame characters (Due to the limitations of training se…
34,249下载量 - 36
Micro Bikini SD1.5/FLUX | olaz
Enjoy! If faces generates poorly follow this guide. Flux Prompt: micro bikini Other usefull prompts: from behind Recommended LoRA weight: 0.7-1.0 SD 1.5 Prompt: micro bikini Other usefull prompts: from behind, bent over Recommended LoRA weight: 0.7-1.0 You can vote or give your idea for next trained model here! I'm gonna try to train most popular ones. If you liked my lora consider buying me a Co…
34,201下载量 - 37
Blowjob Top of Head POV Lora👑
👑 Blowjob Top of Head POV Lora👑 🔧Model base: sd1.5 _____________ 📝🌟 Trigger: BlowjobTopofHeadPOVQuiron pose, 1girl, oral,penis, lora:quiron_BlowjobTopofHeadPOV_V2_lora:0.87 _____________ 📝💡💡 CLIP Skip: 1,2,3 (more realistic) 📝 Variation: lora:quiron_BlowjobTopofHeadPOV_V2_lora:Y , Y=0.7 to 1.0 📝 Denoising strength: 0.30 to 0.8 ______________ 🗒️💡Sample: (best quality:1.1), (masterpiece…
34,170下载量 - 38
M legs | Pose Lora 800
Lora trained on 800 images of m legs. You can probably do this just by prompting, you do not need this if you already know how to do this. Made on request. Trained on NAI gen'd on AOM2 nsfw.
34,147下载量 - 39
(neon)CyberpunkAI - konyconi
“The sky above the port was the colour of television, tuned to a dead channel” Perpetual coffee request: Keep me motivated and caffeinated: https://www.buymeacoffee.com/konyconiN https://ko-fi.com/konyconi7992
34,058下载量 - 40
アニメ塗り Anime Style LoRA with Better Flat Color
※重要 当方の環境での検証の結果、EasyNegativeとの相性が非常に良いことがわかりました。一緒に使用してください。 アニメ塗りになるLoRAです。アニメ塗りと言われているモデルよりも本来の意味でアニメ塗りになります。 通常、綺麗なアニメ塗りを呼び出すには複雑なプロンプトと当たりが出るまでガシャを回し続ける根気が必要ですが、このLoRAではそれらは不要です。また、 教師画像にロゴやテキストが存在しないため、それらが出現しません 。 0.5-0.8ぐらいで使用するのが良いかと思います。トリガーワードは「anmnr」ですが、あってもなくてもアニメ塗りにはなります。どちらが良いかはよくわからないです。 v1.0 for AOM3A1_orangemixs : AOM3A1_orangemixsで作ったもの v1.0 for anything-v4.0 : anything-v4.0で作っ…
33,980下载量 - 41
Ultimate Ahegao
The ultimate Ahegao Lora. Spent a lot of time perfecting this one. Support me on patreon so I can justify spending more time on these and get prompts, tips and more. Have lots more planned: https://www.patreon.com/moistdd V1A - produces images similar to base model V1B - produces slightly more realistic images V1C - produces high contrast realistic images Prompt: naughty face, rolling_eyes, cross…
33,847下载量 - 42
deep_penetration concept slider (for pony XL)
lets you control penis depth with the lora value, 0~1 recomended for vaginal and anal 0~X recomended for deepthroat deepthroat is more sensitive to the lora, anywhere from 0.2 to 0.4 might be the same as all the way to the base , but you can put it higher, if you do, then it trends to top-down bottom-up mainly trained on pov but it also works okay for from side
33,845下载量 - 43
Spider Gwen | Goofy Ai
If you like my work, drop a 5 review and hit the heart icon. it's free and keeps me motivated All my models are officially hosted and maintained by me on Tensor.art . use my Exclusive and public model for free on tensor.art Get early access to my upcoming NSFW Lora in my Patreon . Support my work by joining any one of them and get early access to all my upcoming loras and other perks such as fan…
33,782下载量 - 44
Asian Cute Face
Mix from koreanDollLikeness_v10 and something I trained, work with Chilloutmix . Making models takes a lot of time and hard work. If you like this LoRA, please click the like button! Recommended weights: Recommended weights: 0.5~0.7 (Note: If the weight is below 0.4, the LoRA may not work effectively.)
33,777下载量 - 45
Photorealistic Skin ⛔️ No plastic [FLUX]
Please post the first picture directly here in the Model Gallery. This is the best way to support creators :) Hello ♥ For whatever reason you want to show me appreciation, you can: ❤️ Ko-Fi ❤️ _________________ This is the try to get a real skin texture. The Version isn´t perfect, but many results are still amazing. Settings 0.5 - 0.85 (1.0) - be careful with too high strength Trigger aidmarealis…
33,690下载量 - 46
Stylized 3D Model LoRA
(日本語は後半にあります) Stylized 3D Model LoRA This is a LoRA trained on stylized 3D model images. It can provide a figure-like material and a distinctive silhouette. Changes in 3.0 Increased the training resolution (ver.2: 768, ver.3: 896) Revised the tagging Removed the trigger word as well Reviewed the training parameters Improvements in 3.0 It can reproduce a more stereoscopic effect than ver.2 LoRA ca…
33,674下载量 - 47
Folded Pose
Lora for drawing the folded pose. Recommended weight 0.6-0.8 Trained on AOM2 (Also works fine with AOM3) The result can be influenced by tags like spread legs, knees to chest, legs up, legs over head, leg hold, . Important: often generates censored images, so use the censored tag in your negative prompt. This time, I was much more careful about preparing the dataset, and now cropped images are ra…
33,653下载量 - 48
[LORA] Chinese Doll Likeness
Hello everyone, this is my first LORA of a non-real person. I specifically trained it based on a database of several idols from SNH48 and a few Chinese actors. My main inspiration here is the Korean Doll Likeness @Kbr , but my LORA training skills are bloodly nascent, so please let me know if you have any questions. Since the model is basically based on portrait photos, it is likely that said FUL…
33,636下载量 - 49
concept Spread pussy(finger)
最近生病，发点清淡的。 三次元版本已经有了所以我做了个对应的。动作比较固定，手指依然靠roll，训练分辨率为960*960，基于NAI。 由于我自己的lora目录比较混乱，命名相似难以分辨是谁做的，我以后的lora都会加个ID作为前缀（这只是方便我收纳，你不喜欢就自己改） I've been sick recently, so I'll upload something lighter. The real version already exists so I made an anime one. The movement is relatively fixed, the fingers still rely on luck, and the training resolution is 960*960, based on NAI. Because my own lora directo…
33,554下载量 - 50
Asian Beauty Collection
Patreon Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord Recommended settings: Make sure you are aware on the usage instructions of LORA Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers) CFG Scale : 5 to 10 LoRA weight for txt2img: reccomended 1 Insutrctions These models…
33,506下载量 - 5131,970下载量
- 52
Shiny Nai style for pony / illustrious/anima | Goofy AI
Get early access to my upcoming NSFW Lora on my Patreon . private lora share on discord for patreon I was hoping you could support my work by joining any one of them and get early access to all my upcoming loras and other perks, such as fan requests and a Discord role. Join my Discord Server check the images for prompts use lora at 0.7-1 Adetailer for faces Img2img upscale 4x-ultra sharp comment…
26,657下载量 - 5326,456下载量
- 5425,911下载量
- 55
LTX 2.3 - LTX2 better NSFW motion
You can make money with my models. Sell what you generate, use it in paid work, run it on paid services, merge it, sell the merge all of it, no permission needed. Credit is appreciated but never required. New releases might have a short early access window behind Buzz, then go free and free is permanent. Once a model is free, I will never re-paywall it or pull it for a paid platform, and you're w…
21,859下载量 - 5619,916下载量
- 57
LTX-2.3 Deepthroat
LTXdeepthroat — LoRA for LTX-2.3 A LoRA for generating oral/deepthroat content with LTX-2.3 video models. Test workflows in training data. Trigger Word LTXdeepthroat Recommended Settings LoRA strength (Stage 1) 1.0 LoRA strength (Stage 2) 0.85 Distilled LoRA (Stage 2) 0.6 Prompting Tips This LoRA responds best to literal, descriptive prompts. Describe what you want to see as if you're directing a…
17,024下载量 - 58
LTX 2.3 - Enhancers
Soft Enhance LoRa This soft enhance LoRa for text to video, is a natural detail enhancer LoRA made for users who want a cleaner, more refined look. The text to video workflow can be found HERE just swap out the lora and prompt. All the sample vids are text to video. It adds subtle detail, improves overall clarity, and helps soften some of the stronger contrast characteristics of LTX 2.3. The resu…
16,512下载量 - 59
❤️Heart & Star⭐ Shaped Pupils Inpaint - LoRA
Follow this guide to see how it works: New Inpaint Guide Here old guide _______________________________________________________________________________ Added Star-Shaped Pupils. The LoRA can now do both. _______________________________________________________________________________ For realistic pictures, change back to an anime model before generating inpainted pictures. "example: pic 2" in ver…
14,329下载量 - 60
LTX-2.3 Riding pov (I2V)
eros 1.0 - i2v without audio. It already works fine this just makes it compatible and fluid with 10eros 1.0 - i2v with audio. Attempt to add audio , might be over trained set to 0.8 0.9 - i2v no audio. i2v trained on mix of ai mostly for bouncy look , ty to Allardice Set 0.5-0.8 strength with keywords or with descriptive prompt for smoother results. 1.0 will also work but has repetitive AI look t…
14,246下载量