All NSFW models
Adult-oriented AI models, sorted by most downloaded and synced daily from Civitai and Hugging Face.
- 1
Hipoly 3D Model LoRA
(日本語は後半にあります) High-poly 3D Model LoRA This is a LoRA trained on high-polygon 3D model images. It can provide clean, high-resolution skin and hair materials, as well as detailed clothing elements. For those interested, I have compiled the technical insights gained during the training of ver.2 in the following article. https://note.com/takumi__ncr/n/n21016c358ea5 Changes in 2.0 Increased the number…
149,162Downloads - 2
Lenovo UltraReal
--Krea2 Actually i tested with different combinations raw and turbo. For best quality i use raw with cfg4, for fast result i use raw, but witth cfg1 and turbo lora (it really gives better quality then kreo2 turbo model). U can use with other loras freely, also works good with nicegirls lora and nsfw loras. recommended weight 0.8 for raw and 1.2-2 for turbo --Ideogram4 Works good with realism engi…
145,947Downloads - 3
Labiaplasty Innie Pussy Adjuster [KR2 K9B ZImage SDXL Qwen Chroma SD1]
SDXL v2 is an adjuster/slider model that comes in a SDXL and SD 1.5 model variant. It's trained on front, below and from behind images. It was trained before pony and illustrious models existed but seems to work on many mixes if the weight is set high enough (more than 2 on some models) Krea2 v8a is trained on krea2 raw. I recommend using krea2 turbo for inference. Other nsfw models can be used b…
145,858Downloads - 4
Aesthetic Quality Modifiers - Masterpiece
Aesthetic Quality Modifiers - Masterpiece Training data is a subset of all my manually rated datasets with the quality/aesthetic modifiers, including only the masterpiece tagged images. ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models, trigger usage, and workflow/training information. Recommended prompt…
145,803Downloads - 5
CyberRealistic CyberIllustrious
You can get this model through Civitai Early Access, or grab it along with many others by joining The Tinkerer on Whop. Membership gets you early releases, private tools and members-only pages. There are free pages too, no membership needed. 👉 Join on Whop 💬 Join the community for support, free tools and early news on Discord CyberIllustrious blends the artistic flair of Illustrious-XL with a b…
144,925Downloads - 6
Pure Eros Face
This embedding will generate good-looking girl faces , close concept of kpop idols or Instagram girls . For SD1.5 based models. what means "Pure Eros"? Pure Eros is a simple translation of the Chinese word " 纯欲 ", which is a popular memes in the Chinese internet, the english words close to the semantics of this word are "ulzzang face", "korean idol face", so obviously this embedding will be close…
143,996Downloads - 7
Ultimate DeepThroat I2V Wan2.2 Video LoRa - K3NK
☕KOFI https://docs.google.com/forms/d/e/1FAIpQLScltzaQXTF2VFWRWVaqPSzJXYyNBF9hUQOLI8aBCyLrpCM1_w/viewform?usp=dialog Ultimate Deepthroat Blowjob LoRa for Wan2.2 I2V Trained on a dataset of 593 clips with various resolution, 1sec to 3sec Both models trained at 211 res bucket Thi is the dataset used in the SideView Deepthroat - Wan2.2 Video LoRa - Low Noise trained with the I2V models. It can handl…
143,987Downloads - 8
LTX 2.3 高速版 GTAnimation | 25 frames in 5S! 12G VRAM
Red Craft- 红潮 REDMix Bake d 做好工具人 服务艺术家 Forever in memory of METAFILM Studio founder Mr. Yuan Bo 1 秒 5 帧 ！25 frames in 5 seconds LTXV 2.3 GTAnimation 高速版 KREA 2 赤佬 Bastard3 Edition REDZ 2 红潮 造相2 HDEdition INT8/INT4 Convrot for ComfyUI 0.27 [ Native 原生节点支持 ] Uploaded File name: REDGTA1.0_LTX23_ComfyUI-int4_convrot(on this page ) File name: Krea2RedMix1.1-INT8-Convrot-ComfyUI ( original native ) Fi…
141,631Downloads - 9
[NSFW Flux|Wan 2.2|Qwen] Mystic XXX
Unlock xxx images using flux, Qwen or Wan 2.2. ATTENTION Second version for WAN 2.2 T2V works with the usual models BUT for T2V I recommend some different models and LoRas: https://huggingface.co/lightx2v/Wan2.2-Lightning/blob/main/Wan2.2-T2V-A14B-4steps-250928-dyno/Wan2.2-T2V-A14B-4steps-250928-dyno-high-lightx2v.safetensors instead of wan 2.2 high https://huggingface.co/eddy1111111/WAN22.XX_Pal…
141,410Downloads - 10
[Flux/Pony] Perfect Full Round Breasts & Slim Waist
If you like my work and would like to help me out follow my new X account https://x.com/fitcorder_ai If you want to generate an I2V you can start here If you wish to contact me you can at https://fitcorder.com the videos in the wan series was generated from this workflow https://civitai.com/models/2048404?modelVersionId=2321009 I trained the Wan2.2 loras on my 4090 and the fidelity could be highe…
141,042Downloads - 11
LEOSAM's Clothing +/- Adjuster 衣物增/减 LoRA
🖥️Welcome to try out the open-source GPT4V-Image-Captioner , developed by my friend and me. It offers a one-click installation and comes integrated with multiple features including image pre-compression, image tagging, and tag statistics. Recently, we also launched the webui plugin version of this tool, everyone is welcome to use it! 🌍 欢迎加入 QQ群"兔狲·AIGC梦工北厂"，群号 ： 780132897 ；"兔狲·AIGC梦工南厂"，群号 ： 83…
140,207Downloads - 12
JapaneseDollLikeness (v1.5)
Hi, this is author Kbr , thank you voting for the poll release on Twitter, I bring you update for JapaneseDollLikeness. The next release would probably be TaiwanDollLikeness update. (Please double check the naming of the LORA file when using sample images generation data, Civitai love to rename the LORA file automatically into something different) If you are wondering where are the older versions…
139,994Downloads - 13
POV Doggystyle LoRA [1 MB]
This is my first LoRA sex position - and it's for POV Doggystyle . It's a very basic LoRA I suggest using this at 0.9-1.0 weight for best results. Always add this prompt to activate it: lora:POVDoggy:0.9 , 1boy, penis, doggystyle, from behind. After that you can add other descriptive tags - Examples pov hands, ass grab, deep skin (Good results) facing away, nude, implied sex (Good results) pov ha…
139,574Downloads - 14
MoriiMee Gothic Niji | LoRA Style
Style LoRa based on the Niji Midjourney aesthetic of goth style from MoriiMee ( Twitter / DeviantArt )
139,394Downloads - 15
Illustrij
hey guys, ☺ as u know I rlly love comic-anime-hybrid based checkpoints and digital art rendering with a touch of 3D on its way to semirealism. So I've thought it would be time to test Illustrious. This is how I wanna present to u ~ Illustrij ~ my first merged Illustrious checkpoint :) NEW ♥ 💌 v21 " Illustrij ~ imperfectly authentic, a real little nose dimple. Yes, you heard right ~ there she is:…
136,639Downloads - 16
RealCartoon-Realistic
You can also run this model on Magespace and Sinkin.ai ! https://www.mage.space/ (Really helps out if you want to support to) V11 - https://www.mage.space/play/ec69395ac694a4fb4bd7729262721ea2 V15 - https://www.mage.space/play/102f7cf50ae26b70a7b57d432b287fc6 V16 - https://www.mage.space/play/77270517ce81b305f08ef1b2fde9277e V17 - https://www.mage.space/play/67bcacff11673afd9bad260dd79a8ec3 https…
136,118Downloads - 17
AlbedoBase XL
If you've found value in the model, please consider offering your support. Your contribution will be devoted entirely to advancing the SDXL community. 🙋🏼♂️ join us ( discord ) ㅤ |ㅤ 🛒 purchase ㅤ |ㅤ 🌱 donate AlbedoBase XL (SFW NSFW) The refiner is unnecessary, and VAE is included. GOAL Stable Diffusion XL has 3.5 billion parameters (excluding the Refiner), which is about 3.6 times more than th…
135,134Downloads - 18
DivineEleganceMix
If you ran into any troubles with my mix, please read description below. There is plenty of useful information. Also, you can contact me through message system on CivitAI. Если вы столкнулись с каким-либо проблемами при использовании моего микса, пожалуйста, прочитайте описание ниже. Там есть много полезной информации. Также вы можете связаться со мной через чат на CivitAI. Also try: DivineAnimeM…
135,128Downloads - 19
Instant Cumshot
Load up your generations with this cum fiesta of a LoRA! It seems to work well on whatever checkpoint and subject you're using, including characters from other LoRAs and embeddings, realistic or anime, etc. Checkpoints that already understand nsfw are more flexible but not required. To create the examples, I mostly started with well-known prompt/model combos from top checkpoints and then added so…
134,877Downloads - 20
Fluxed Up [Flux NSFW Checkpoint]
A nude/NSFW capable model that focuses on images with a female primary subject. It is heavily biased towards nude images. Recommended Settings Sampler is dpmpp_2m (DPM++ 2M) and the scheduler is beta No VAE or CLIP is baked in. Use separate sources for those. Each sample/preview image contains the used workflow. Here's a quick article with simpler more beginner-friendly workflow. This is a recomm…
134,419Downloads - 21
Lightning Lora, massive speed up for Wan2.1 / Wan2.2 made by Lightx2v / Kijai
2.2 For I2V this motion helper node is extremely useful: https://github.com/princepainter/ComfyUI-PainterI2V 10/30 High lora was further refined. New I2V 1022 versions are out. They have by far the best prompt following / motion quality yet. (The lora key warning is fine, it just contains extra modulation keys that comfyui does not use. It does not matter.) https://github.com/VraethrDalkr/ComfyUI…
134,357Downloads - 22
CharTurner - Character Turnaround helper for 1.5 AND 2.1!
CharTurner Edit: controlNet works great with this. Charturner keeps the outfit consistent, controlNet openPose keeps the turns under control. Three versions, scroll down to pick the right one for you. If you're unsure of what version you are running, it's probably 1.5, as it is more popular, but 2.1 is newer and gaining ground fast. Version 2, for 2.0 and 2.1 models Version 2, for 1.5 models Vers…
133,633Downloads - 23
Hardcore Hentai
My models Hardcore Hentai Hardcore Asian Cosplay Porn Support Place bid in the Auctions section for availability in the generator Pony model At this point I feel like there's not much reason to keep using the SD 1.5 models since the pony models have better understanding of pretty much everything. And since I can only have 2 models for on site generation I'll see if this one gets added instead of…
133,258Downloads - 24
Indigo Furry mix
V120_hybrid is gonna be the last model of this series, there will be no more hybrid, anime or realistic models, I will only update the vpred models, Thank you for liking my model and supporting me!!! I AM A LAZY DOG XD so I am not gonna go deep into model tests like I used to do, and will not write very detailed instructions about versions. Plz understand, read ' about this version ' and try them…
132,795Downloads - 25
Murky's - After Sex Lying LoRA
Do you want to support me? Consider being a patron on Patreon to vote on train polls and access stuff early. ❤️ Trained with over 300 images. This LoRA enhances "After Sex" concept mostly with lying semi senseless on bed covered in cum. Most of the training data trained lying on stomach and back but you can try some other poses too. You can see some X/Y plot on end of examples List of prompts you…
130,962Downloads - 26
Flat-2D Animerge
Description (for best results, read the full description - usage guide below) This is a merge of some random anime based and cartoon based models to achieve a somewhat cartoony anime style, more similar to what you would actually see in anime as opposed to the more common hyper-detailed anime models. Versions 3, 4, and 4.5 include some custom training to further enhance the style. More details av…
130,259Downloads - 27
Wan2.2-Remix (T2V&I2V)
You can click on the link below and try it out directly. If the effect is good, you can deploy it locally. Online Workflow: Wan2.2 Remix i2v 3.0 Image-to-Video Automatic Reverse Experience link: https://www.runninghub.ai/post/2033536710499373058/?inviteCode=rh-v1325 Online Workflow: Wan2.2 Remix I2V v2.1 SVI2Pro Fully Automatic Reverse Long Video Experience link: https://www.runninghub.ai/post/20…
129,742Downloads - 28
Smooth Embeddings
SMOOTH EMBEDDINGS This is a set of quality enhancing embeddings for NoobAI, Illustrious/SDXL and Pony models. No need for more quality prompts. They should be enough for getting great results! I recommend using both positive and negative embeddings together. NoobAI Checkpoints Smooth Positive NoobAI / Smooth Negative NoobAI Recommended only for NoobAI trained models since these embeddings use som…
128,765Downloads - 29
Detailed Perfection style (Hands + Feet + Face + Body + All in one) XL + F1D + SD1.5 + Pony + Illu + zit + zib
Update : Please if you see any of my models somewhere else report or let me know! Thnx Trained on base model xl 1.0 + F1D + zit + zib Update: SD1.5 version added. Update: Pony version added! ( Please read version info. before using it ) Update: Illustrious version added Please read info. (Box on right) about this version . This model will work best when combined with Detailed style XL (Hand focus…
128,428Downloads - 30
Babes
- Download 1.2i15 as digital product or with Membership July 2026 models collection. - Download 1.2i14 as digital product or with Membership June 2026 models collection. - Download 1.2i13 as digital product or with Membership May 2026 models collection. - Download 1.2i12 as digital product or with Membership March 2026 models collection. - Download 1.2p11 as digital product or with Membership Feb…
127,973Downloads - 31
Clarity
Please Read Description Clarity XL Released: Link Buy me a coffee ❤ https://ko-fi.com/ndimensional All donations will be used to fund the creation of new Stable Diffusion fine-tunes and open-source AI tools. Changelog : 8-20-23 v3 inpainting Uploaded inpainting version of Clarity v3. 8-16-23 v3 Rebuilt from the ground-up using a fine-tuned base model, made specifically for Clarity. More realistic…
127,888Downloads - 32
STYLES | PONY & ANIMAGINE
Style1 : ...got no idea what's this style called, soo its style1 AIU 0.1 : mostly like skin texture with slightly different style compared to tpony (trigger words: sweat, wet, oiled, shiny skin) VEY 0.1 : guess I'll have to train it again. it doesn't get a very different style (which I dun like) compared to pony base style sometimes. ALH 0.1 : ahh not one of my favourite styles, but trained to te…
127,687Downloads - 33
EnvyBetterHands LoCon
This model is a LoCon. You MUST install the Lycoris extension for it to load. I'm using Lora Block Weight . I believe you can also use Additional Networks and SD Webui Lycoris . UPDATE 4/27/2023: I've hit a training plateau so I'm in the process of adding a bunch more images to the dataset, including some more complicated stuff like intertwined fingers. I'm probably going to have to drop the lear…
126,687Downloads - 34
Slingshot swimsuit [SD1.5/Pony/Illustrious/Anima]
Donate Coffee for Gtonero Main tag : slingshot swimsuit Secondary tag : wedgie, pubic hair, partially visible vulva, pussy peek, Extra Tag : clothing aside, Color tag : color slingshot swimsuit, DELTA NORM Anima Unet - Avg = 0.023 TE - Avg = 0.0125 Training LoRA Powershell info : train_speed_mode = fast resolution = 512 [Anima/Illus 768] Batch size = 2 network_dim = 32 network alpha = 32 mix/save…
126,548Downloads - 35
WAI-REAL_CN
If you want to use more my checkpoint online generation, please visit here. https://tensor.art/u/762555264535746522 V15 关于例图, 我使用了1024x1360的大小,都是直接输出没有经过AD跟高修. For the example images V15, I used 1024x1360, generated directly without AD or hires fix. 调整了数据,不在需要正负面质量词. The data has been adjusted, and positive/negative quality tags are no needed. Recommended Setting Steps: 30 CFG scale: 7 Sampler: E…
126,472Downloads - 36
DynaVision XL - All-in-one stylized 3D SFW and NSFW output, no refiner needed!
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! 💖💖💖 DynaVision XL was born from a merge of my NightVision XL model and several fantastic LORAs including Sameri…
122,129Downloads - 37
Ahegao
Here is a Form you can request me Lora there (for Free too) https://forms.gle/h9iuLCCnaEs6W9ZB8 The one you always needed. I literally had to manually crop each images in this one and it sucks. Needs tons of triggers because I made it so. Use weight between 0.4-0.9, even 1.0 is better but since this is 128 DIM it starts adding noise at 1.0. Every image in the dataset was manually gathered and it…
121,544Downloads - 38
ControlNet Pre-Trained Models
STOP! THESE MODELS ARE NOT FOR PROMPTING/IMAGE GENERATION Note: These are the OG ControlNet models - the Latest Version (1.1) Models are HERE. These are the models required for the ControlNet extension , converted to Safetensor and "pruned" to extract the ControlNet neural network. I have tested them, and they work. These models are embedded with the neural network data required to make ControlNe…
120,502Downloads - 39
LOFI
L.O.F.I: Limitless Originality Free from Interference [update:240515] 🚀 LOFI V5 - Final This is the last version in the LOFI series of models. There likely won't be any more updates to the LOFI model in the future (unless an SD3.0 is released, in which case, a LOFI version for 3.0 might be trained). Version 5 is quite special, as it even produces an effect somewhat similar to using "LCM". You mu…
118,546Downloads - 40
Osorubeshi Pony style LORAs
Self-advertising - I am looking for a job in the generative AI industry, if you are interested in hiring me, please write a private message! NEW DISCORD SERVER (work in progress) - https://discord.gg/bPRpQQRc4Y Almost all models often requires useage of ADetailer or Hires fix! If you like my work you can tip me on - patreon.com/Natakaro or buymeacoffee.com/natakaro :) GemuHentai model is harder t…
118,532Downloads - 41
A-Zovya Photoreal
Update June 28th, added V3+VAE, pruned and fp16 versions also added. V3 More training added to supplement some things I feel are missing in current models. Skin textures, darker lighting and more variety in race in people. V2 After weeks in the making, I have a much improved model. No longer a merge, but additional training added to supplement some things I feel are missing in current models. Lot…
118,426Downloads - 42
Smooth Workflow Wan 2.2 (I2V/T2V/first2last frame/MMAudio)
Update: WAN 2.2 Smooth Workflow v6.0 - 07/18/2026 "WAN 2.2 Smooth Workflow v6.0" update: The new version now has a First2LastFrame Workflow. Make sure to fully update your Comfyui and the extensions. At the time of making the Showcase: Stability Matrix v2.16.1 and ComfyUI v.0.28.0. Changed the Interpolation extension: Now using the ComfyUI-FrameInterpolation Changed the default Resolution and add…
116,925Downloads - 43
MeinaPastel
MeinaPastel aims to make illustrations with a 2d feeling to like pastel or colorful images! I have a discord where you can share images , discuss prompt and ask for help . https://discord.gg/meinaverse 我有个可以让你分享图片和参与讨论与询问问题的discord群。 I also have a ko-fi and Patreon page where you can support me or buy me a coffee 3 , it will be very much appreciated: https://ko-fi.com/meina and https://www.patreo…
116,861Downloads - 44
Penis Size Slider - Pony/Illustrious
New and custom content here: https://aicollective.ghost.io/ Infinite penis size control with this slider, can make more or less any size. Minimal picture impact unless you drastically adjust weight. Works for Futa as well. PS: I made an error when training the Pony Lora so the Pony version is inverted (negative for bigger) I figured people looked at the example images which makes that very clear.…
115,777Downloads - 45
AingDiffusion
Read "About this version" to see what changes were made to the model. I might make changes you don't like and you may want to stay on the older version. The only authorized generation service outside Civitai is yodayo.com Maintaining a stable diffusion model is very resource-burning. Please consider supporting me via Ko-fi . AingDiffusion will ALWAYS BE FREE. EXP models will be updated here to re…
114,885Downloads - 46
MeinaUnreal
MeinaUnreal objetive is to be able to do anime art with a 2.5d feeling. I have a discord where you can share images , discuss prompt and ask for help . https://discord.gg/meinaverse ヾ(≧▽≦*)o 我有个可以让你分享图片和参与讨论与询问问题的discord群。 I also have a ko-fi and Patreon page where you can support me or buy me a coffee 3 , it will be very much appreciated: https://ko-fi.com/meina and https://www.patreon.com/Meina…
114,815Downloads - 47
Skirtlift: the Astonishing Sequel to Shirtlift
A LORA that aims to do exactly what it says: lift skirts. NOTE: this is not as easy to plug-and-play as Shirtlift . There are simply too many different ways to pull up a skirt, so training here favored variety over consistency. Be prepared for the occasional extra arm. Should work with and without panties, but too many clothing instructions in the prompt can cause chaos. I did TRY to train it wit…
114,618Downloads - 48
LEOSAM's Instant photo 拍立得/Polaroid LoRA & LoHA
🖥️Welcome to try out the open-source GPT4V-Image-Captioner , developed by my friend and me. It offers a one-click installation and comes integrated with multiple features including image pre-compression, image tagging, and tag statistics. Recently, we also launched the webui plugin version of this tool, everyone is welcome to use it! 🌍 欢迎加入 QQ群"兔狲·AIGC梦工北厂"，群号 ： 780132897 ；"兔狲·AIGC梦工南厂"，群号 ： 83…
114,271Downloads - 49
F4C3SPL4SH Cumshot - I2V Wan 2.2 Video LoRa - K3NK
☕KOFI https://docs.google.com/forms/d/e/1FAIpQLScltzaQXTF2VFWRWVaqPSzJXYyNBF9hUQOLI8aBCyLrpCM1_w/viewform?usp=dialog Cumshot LoRa for Wan2.2 Trained on a dataset of 391 clips with 211 resolution, 1sec to 5sec, Num_Repeat = 1 Several different source videos. I get better results when using lighting at 0.5 in the high loras and lightx2v at 1.5 str in low loras, also using lightx2v in both samplers.…
113,291Downloads - 50
Ahegao, rolling eyes(realistic)
Ahegao in common sd models tend to be Anime style (and lacks of expression like rolling eyes), so I trained this lora on 20 photos as title. (Nice website to recommend. Plz! Keep in low profile.) Suggested weighted 0.5~0.95(it depends on your model feel free to try). This can go with my merged checkpoint.
113,247Downloads - 51
Wan Cumshot
Wan 2.2 (T2V only): Download both the highnoise and lownoise loras, and plug them both into your workflow. The "training images" download contains the example I used for the previews. I did not use any speed loras, as there aren't any made for Wan 2.2 yet. You can plug the lightx2v lora in, but it may cause a limitation on 2.2's full potential. Wan 2.1: I2V: This was trained specifically for I2V,…
112,780Downloads - 52
WAN DR34MJOB - Double/Single/Handy Blowjob
Presenting D R 3 4 M S C 4 P E' s WAN LoRA: D R 34 M J O B - Single and Double Blowjobs (POV+) ! It, as a nice surprise, is excellent at handjobs too! Please remember to like and share - if you like our work, give us a shout below! =========================================================================== 9/20 - Come and get it... WAN 2.2 I2V updates are here! Note: You need BOTH models to produ…
112,340Downloads - 53
DucHaiten-Pony-XL (no-score)
you like my content, support me at: https://ko-fi.com/duchaiten Patreon in here: https://linktr.ee/Duc_Haiten I created my discord server. I'm still quite new to discord server management, free to give opinions. https://discord.gg/vKEW6jqa49 special note : Using the model is very simple, like the scores, but also not like the scores. The idea behind it is training based on various artistic styles…
111,786Downloads - 54
Disney Pixar Cartoon Type A
There's no good pixar disney looking cartoon model yet so i decided to make one. This is a merge of Pixar Style Model with my own Loras to create a generic 3d looking western cartoon. In the examples I Use hires. fix, upscale latent, denoising 0.5, hires steps 20, upscale by 2 . Clip skip 2 . I will upload more variants of this in the future You need to use VAE or the color become pale and gray i…
111,364Downloads - 55
fantasticmix
It's a model that was merged using a supermerger ↓↓↓ fantasticmix2.5D ↓↓↓ https://civitai.com/models/20632/fantasticmix25d An example is using dynamic thresholding. Reduce the CFG scale to 7 or less when not in use You must use VAE VAE : vae-ft-mse-840000-ema-pruned.ckpt
110,301Downloads - 56
Realisian
▼ Recommended Settings ▼ Negative Prompt Realisian-Neg Sampling Method DPM++ SDE Karras Sampling Steps 12 (8 ≈ 16) Restore Faces Off Hires Fix ( ! Required ! ) On Upscaler: Latent (bicubic antialised) Hires Steps: 5 (4 ≈ 10) Denoising Strenght: 0.55 (0.4 ≈ 0.7) Upscale by: 2 CFG Scale 3 (2 ≈ 5) Clip Skip 1 (1 ≈ 2) VAE None (Baked) ▼ Merge Based On ▼ ChilloutMix LOFI 饭特稀 majicMIX realistic Lyriel…
109,834Downloads - 57
RealDosMix
!!pruned fp16 replaced with no ema. The change in quality is less than 1 percent, and we went from 7 GB to 2 GB. See example picture for prompt.There are recurring quality prompts. vae-ft-mse-840000-ema-pruned or kl f8 amime2 img2img SD upscale method: scale 20-25, denoising 0.2-0.3 After selecting SD Upscale at the bottom, tile overlap 64, scale factor2 caution! Sampler must be DPM++SDE karras.…
109,348Downloads - 58
MIHOYO Collection 米家全家桶 (Honkai Impact 3rd | Honkai Star Rail | Genshin Impact | Zenless Zone Zero)
一个面向米哈游角色的模型合集~A collection for MIHOYO Characters~ SDXL ver. click here ： Pony | A3 | Artiwaifu | NoobAI ！！！ 对应人物tag记录在版本信息里，可在右侧“ About this version ”选项中查看。The corresponding character prompts are recorded in the version information and can be viewed in the " About this version " option on the right. 打开目录寻找最爱~（附带链接，点击直达）~Open the catalog, find your favorites~ (with links, click to go directly): 崩…
109,062Downloads - 59
pose Pov missionary(collection)
版本之间不存在迭代差异，仅有姿势区别 There are no iteration differences between versions, only pose differences 我已有的数据集已经都练完了，暂时不会再更 My existing data sets have been trained and will not be updated for the time being 如果发现不稳定请加入一些相关的词来引导，比如penis,pussy,nude,lying，spread legs等等 If you find it unstable, please add some related words to guide, such as penis, pussy, nude, lying, spread legs, etc. 好的手需要运气这件事我想大家应该不用我再强调了吧…
109,060Downloads - 60
Doggystyle (Side View)
This is a LoRA to generate Doggystyle (Side View) I suggest using this at 0.7-1.0 weight for best results but make sure to always play around with the weight. It was generated and only tested using AOM2 , AOM3 A1 , My Own Mix, OrangeMix VAE and AnythingV3 VAE . Always add this to the prompt to activate it: sidedoggystyle, 1boy, ass, doggystyle, sex I suggest generating in 512x512 then upscaling t…
108,994Downloads