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 · Pony

MeMaXL Flat Anime Style - Noob/Illustrious/Pony/XL

3392
This model provides LoRAs trained on Megami Magazine images from 2018-2024, categorized into different types (A, B, C, D) based on 2D image styles, particularly eye styles, for flat anime style generation. Each LoRA version (V1-V5) is trained on different base models like AutismMix, Pony, and Illustrious XL, with specific image selection criteria. It is designed to produce optimized results when used with the corresponding base model.2d animeanimecutefemalegirlsmegami magazinescreenshotscreenshotssexystyle

LoRA · IL

SOME STYLES | NoobAI-XL (NAI-XL) | Illustrious-XL

1387
Trained on NoobAI-XL (NAI-XL) Epsilon-pred 1.0animegame charactergirlslorasexystylevideo gamewoman

LoRA · Pony

Golden Hour Slider

0387
The Golden Hour Slider enhances scenes with warm, radiant golden hour lighting, including glowing highlights and long shadows. It's designed for anime and realistic SDXL models, focusing solely on lighting and environment. Adjust the slider in 0.10 increments (up to 5.0 for anime, 3.0 for realistic models) to control the effect, no activation prompt needed.animecausticdramaticdramatic lightdramatic lightingeffectgirlsgolden hourlightinglighting conceptponyrawrealisticshadowssliderstylesunsunlightsunrayswoman

LoRA · SD

Bulge Mania

0385
This model generates images featuring extremely large bulges. It is designed to create images with prominent and emphasized genital areas.bulgeconceptgaymannsfwvisible penis line

LoRA · NAI

AI styles dump (Illustrious/RouWei/Noob)

4381
This model offers AI styles, with version names indicating the base model used for training. Different versions (Illustrious, RouWei, Noob) have specific compatibility and supported style tags. Later versions aim for cleaner results with fewer artifacts and incorporate updated datasets.2danimeartstyleecchihentaistyle

LoRA · Pony

Andava (Style) [IL/Pony]

0377
Andava (Style) [IL/Pony] is a model that captures the artistic style of the creator. Use the trigger word "andilf" and prompts from example images for optimal results. Hi-Res fix and Adetailer are recommended to enhance image quality.andavaanimecartooncutestyle

LoRA · SD

Mating press

11372
The model generates mating press images. Key tags include "mating press", ass, pussy, penis, and sex. Recommended quality and negative tags, as well as a checkpoint, are also provided for optimal results.hentaimating pressposeposessex

LoRA · SD

People Count Slider - LoRA

2371
Weights can swing very far on this one -8.0 to +8.0. It can do extremely large crowds the higher you go and I wanted to be able to keep granular control. Positive = More people Negative = Less people Simple LoRA to help with adjusting the number of people in a picture. You can swing it both ways pretty far out from -8 to +8 without much distortion.number of peoplepeopleslidertool

LoRA · SD

Breast Grab

7366
This LoRA generates images of breast grabs. Use a weight of 0.7-1.0 and include the tags "sbg, breast grab, breast lift" in your prompt, alongside descriptive tags. It currently works best for large breasts seen from the side.actionbreast grabbreastsekuneloransfw

LoRA · SD

Perfect Perky Breasts V3 -完美挺拔乳房和苗条身材

1364
This model modifies image generation to emphasize breasts. The trigger word is "breasts," and results may vary depending on the checkpoint used. This version adjusts composition effects compared to version 2.clothingwoman

LoRA · IL

Detail Tweaker Illustrious By Stable Yogi

1363
Detail Tweaker Illustrious By Stable Yogi is a model designed to work with specific negative embeddings and detail sliders for optimal results. It is intended to be used with related checkpoints created by the same author.conceptdetailerloraphotorealisticrealisticrealistic skinskinwoman

LoRA · SD

Fellatio (Side View)

7362
This LoRA generates images of fellatio from a side view. For activation, use the prompt "sidefellatio, 1boy, penis, fellatio" with a weight of 0.7-1.0. Note that it may produce images with elongated necks, misplaced penises, or additional figures.actionanimeblowjobekunefellatioheteronsfwsexside view

LoRA · SDXL

Real Pussy - Peach

5362
Real Pussy - Peach is a LoRA model designed for generating close-up images of female genitalia, specifically for inpainting purposes. It consists of various versions trained on manually selected, cropped, and tagged images, focusing on specific poses or features like front or rear views. The model offers control over aspects like leg position, pussy shape, and wetness, with different versions trained on various resolutions and models.conceptinpaintvaginavulva

LoRA · Wan Video 14B i2v 480p

Wan2.2_TV2_cum_in_mouth

492360
Wan2.2_TV2_cum_in_mouth is a model trained on the Wan2.2 base, optimized for character aesthetics, and capable of generating explicit content. It supports both Chinese and English prompts, with recommendations for LoRA usage and step counts, and aims to create realistic visuals of said content.conceptcum_in_mouthpenis

LoRA · IL

Size difference (larger female)

1359
This model controls the size difference between female and male characters, focusing on scenarios where the female character is larger. It uses prompts like "larger female," "Amazon," and "half-size male" to define the scale of the difference, with additional prompts for character positioning.conceptsize diffrencesize fetishsizedifferencesizefetish

LoRA · SD

Creamy Pies

3358
These pies will need to be put out on the window sill to cool, because they were made hot and creamy. This is an attempt to make a realistic creampie, not over done, but what would appear to be a natural creampie. This model can be finickey, you may need to increase the LORA weightconceptcreampiesexspermwoman

LoRA · Pony

Cuck/NTR POV (Pony LoRa)

4356
This Pony LoRa model generates images with a cuckold/netorare (NTR) theme from a first-person perspective. Key features include generating scenes of characters watching sexual acts, porn on devices, and involving elements like femdom, chastity cages, and masturbation.conceptcuckcuckoldhentainetorarentr

LoRA · SDXL

Cyberpunk Anime Style

3354
The model generates images in a Cyberpunk Anime style. It has PRO versions available, one for SDXL and another for Flux.animecyberpunkstyle

LoRA · SD

MengX girl_Mix

4348
MengX girl_Mix is an Asian female face model Lora that aims to make skin whiter and improve yellowing in images, sometimes adding a soft light effect, but potentially sacrificing skin texture. Optimal results are achieved with Asian models, ADetailer plugin use, and weights between 0.7 and 1.0. It produces expressive Asian female faces.characterfemalegirlspersonphotorealisticportraitsrealisticwoman

LoRA · Pony

Bukkake / Excessive cum / Cum bubble LoRa | PonyXL & Illustrious

2348
This LoRa model generates images with excessive cum, optimized for anime-style art using PonyXL and Illustrious models. It works by adding trigger words and is designed for specialized use, primarily with the AutismMix SDXL model.concept

LoRA · IL

Gideon Style [Illustrious]

0346
Gideon Style [Illustrious] is a model trained on Illustrious-XL. It generates images based on the prompt "masterpiece, best quality, amazing quality, 91d30n". It is recommended to use specific negative prompts to improve image quality.furrystyle

LoRA · Pony

All The Way Through - In Ass Out Mouth (Pony & Illustrious)

0342
Penis goes in ass, comes out mouth. Works with different types of penis: Monster, animal, horse, etc. Try including "anal, fucked from behind" in your prompt if you are consistently getting fellatio results. Results also seem to improve if you include one of the "grab" tags. Check showcase examples for prompts.analanimeconceptgirlshentailoraoralpenisrealisticsexywoman

LoRA · Pony

Realistic Anime Style (Illustrious/Pony/FLUX)

1342
This model generates semi-realistic/realistic anime style images. It is recommended to use prompts that enhance realism, such as "ultra realistic, masterpiece, high detailed skin," and to use Highres-Fix and Adetailer for improved results. Using the prompt "illustriouanime" may also improve image generation.animefluxflux1.dgame charactergirlslorarealisticsexystylevideo gamewoman

LoRA · SD

Tinker bell (Peter Pan) Disney - FLUX | SD 1.5 | XL PONY | Illustrious XL - by YeiyeiArt

3337
This model generates images of Tinkerbell from Disney's Peter Pan using SD 1.5, PONY, FLUX, and Illustrious XL. Use the keyword "TinkerWaifu" and descriptors like "(single hair bun), (strapless green dress), (fairy wings)" for better results.animecharacterdisneyfairyfantasyfemalegirlsprincess
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.