AI porn models for adult image and video generation

Browse the building blocks behind the factory. Filter checkpoints and LoRAs by image or video support, base model, and tags, then open any version directly in the unified generator.

1487 models available

LoRA · NAI

逆バニー/reverse bunnysuit

09
The recommended strength of the lora is around 0.8. If you like, pleasehttps://ko-fi.com/bolero537clothing

LoRA · Flux.1 D

Expression Helper 2.0

09
Expression Helper 2.0 enhances the Flux model by implementing facial expressions that are often missing or don't appear natural. It supports expressions like sad, angry, scared, happy, surprised, and disgusted, which can be activated using tags and captions. The model allows specifying the intensity of the expression using the "very" tag and additional tags to fine-tune the output.angryconceptconceptscrydisgustedemotionsexpressionexpression helperexpression helper 2.0expressionshappyhelperphotograpyposeposes and conceptreal liferealisticrealisticlorasadscaredscreamingsurprisedtearstool loratoolkittools

LoRA · IL

Cheek on Glass - Concept

09
This model generates images of characters with a "cheek on glass" concept. It focuses on appearances such as a character pressed against glass, often nude, and in various poses and settings.concept

LoRA · SD

hanfu tang 汉服唐风

29
The Hanfu Tang Style Lora model generates images in the style of the Tang Dynasty's Hanfu clothing. Key features include generating specific garments like "upper shan," "chest po skirt," and accessories like "pibo," and it supports various color combinations. This model is not intended for training styles based on celebrity or public figure portraits.clothinghanfutang

LoRA · IL

Grab Hair and Dangling

19
Lifting her by grabbing hair... Version 2.0 has been created. Improvements: • Enhanced grasping poses to match various hairstyles • Corrected unstable sex positionsposes

LoRA · SD

Murky's - Bondage And Dildos LoRA

38
This LoRA model generates images containing bondage and dildos. It was trained on 1000 images at 768x768 resolution and utilizes specified tags like "bound," "bondage," and "dildo." Use a weight between 0.6 and 1 for optimal results.bdsmbondageconceptsex

LoRA · IL

Cum in Hands LoRa | PonyXL & Illustrious

08
This LoRa model generates anime-style images depicting girls with cum in their hands after oral sex. It is designed for PonyXL and Illustrious model integration and uses trigger words to activate.animeconceptcumgirlswoman

LoRA · SD

Ferry (Granblue Fantasy) (6 outfits)

08
This LoRA model generates images of Ferry from Granblue Fantasy in six different outfits: classic, SSR, grand, Halloween, Santa, and summer. Use the corresponding costume tag (e.g., "classic_ferry") in your prompt to specify the desired outfit. The model was trained on anime-style images and may require adjustments to prompts and negative prompts to achieve optimal results for certain outfits or to control the presence of ghosts.animecharacterferrygranblue fantasygranbluefantasywoman

LoRA · IL

Fishnet bodystocking | Goofy Ai

08
The Fishnet bodystocking model by Goofy Ai generates images of, or enhanced by, fishnet bodystockings. Prompts and upscaling using Img2Img and Adetailer are recommended for best results. The model is designed to be used at a Lora strength of 0.7-1.clothingfishnetfishnet bodystocking

LoRA · IL

Check This ASS Pose

08
strength: 1memeposeposes

LoRA · IL

FFM threesome girl sandwich / hug from behind and nipple tweak (handjob, coop footjob, blowjob)

28
This model generates images of FFM threesomes involving a male and two females. It includes variations focusing on activities like handjobs, footjobs, and blowjobs, and can depict scenarios such as hugging from behind and nipple tweaking. Trigger words and recommended weights are provided for specific versions and poses.3pconceptfemdomffm3pfootjobhandjobhentai

LoRA · IL

Cum Pool - Concept

08
This model generates images with a post-sex theme. Key features include depictions of female orgasm, bodily fluids, and associated physical states like heavy breathing and blushing, often in a bedroom setting. It is triggered by specific keywords related to these elements.concept

LoRA · IL

Otokoyu challenge/男湯チャレンジ

08
企画「男湯チャレンジ」 transparent towel,nude towelを入れるとさらにそれっぽくなります。concept

LoRA · IL

Midjourney V7 meets FLUX 🎨 [+ILLUSTRIOUS]

08
This model, named Midjourney V7 meets FLUX [+ILLUSTRIOUS], generates images. It is triggered by the keyword "aidmamjv7" and works best with a CFG scale between 0.3 and 1.0.animedrawingmidjourneyphotorealisticstylewoman

LoRA · IL

mmmmf threesome 5p sex

08
lora for mmmmf threesome sex (cowgial+doggy+double handjob). NOTE It is better to use it with 1024X1024 form. It becomes more stable when using it with face_licking lora (https://civitai.com/models/1325143/facelicking (https://civitai.com/models/1325143/facelicking)).conceptgroup sexmmmmf threesome

LoRA · Pony

ZZZ | Emoji | Style | IL

08
The ZZZ | Emoji | Style | IL model generates images using the trigger word "zzzemoji" with a weight between 0.1 and 1. Recommended samplers include DPM++ 2M Karras (20-40 steps) and Euler a (25-40 steps), with a CFG scale of 1-5 and Clip Skip of 2; also using the word "chibi" is possible.style

LoRA · SD

Color Swirl Style [LoRA 1.5+SDXL]

08
Trigger: ral-colorswirl ☕ Buy me a coffee: https://ko-fi.com/ralfingerai (https://ko-fi.com/ralfingerai) 🍺 Join my discord: https://discord.gg/g5Pb8qNUuP (https://discord.gg/g5Pb8qNUuP)colorstylestylesswirl

LoRA · IL

Licking Penis From Side - Concept

18
This model generates images of a penis being licked from the side. It uses specific keywords to control the appearance, including elements of oral sex, nudity, and erection.concept

LoRA · IL

Tribal Carry - Concept (Illustrious)

08
use between - 1, 0.9 direction - facing up, facing downbdsmbondageboundcapturedcaptured princesscarrying anothercarrying personconceptdefeateddefeated heroineheroineillustrioustiedtribal carry

LoRA · SD

Natural Gemstone Style [LoRA 1.5+SDXL]

08
This LoRA model generates images in a natural gemstone style. The trigger word for this style is ral-ntrgmstn.gemstonenaturalismstyle

LoRA · IL

Doggystyle - Concept

18
Doggystyle - Concept is a model that generates images depicting a specific sexual act. Key features include a style with trigger words related to the position and associated acts.concept

LoRA · IL

Pet Play - Concept

18
Pet Play is a model focused on generating images related to the pet play concept. It uses trigger words such as "pet play, collar, animal ears, leash" and others to depict related scenes, including sexualized content. The recommended weight is 1.0.concept

LoRA · Wan Video 14B i2v 480p

Ultimate Deepthroat - Wan2.1 Video LoRa

38
This LoRA model, "Ultimate Deepthroat - Wan2.1 Video LoRa," is trained to generate videos of deepthroat scenes using a 480p i2v model. It utilizes a dataset created from Hun deepthroat LoRAs and is intended for use with specific WAN2.1 workflows. The model is shared without warranties and users are responsible for its lawful and responsible use.69actionblowjobdeepthroatnswfthroatpie

LoRA · IL

Reverse Fellatio - Concept

17
This model generates images depicting a specific sexual act. Key features include throat bulge, motion lines, and related terms as triggers.concept
Load more models

Showing 24 of 1487

How checkpoints and LoRAs fit together

Start with a checkpoint

A checkpoint controls the base rendering system. Its supported modes determine whether it can create images, edit an input, or produce video.

Match the base model

A LoRA must target the same base-model family as the checkpoint. Similar names do not guarantee compatible weights.

Check the validated workflows

A catalog version can be documented before it is generator-ready. Only versions with validated broker and artifact mappings can spend credits.