Porn Factory AILogin

nsfw models for adult image and video generation

Compare 158 public adult AI checkpoints and LoRAs tagged nsfw. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

158 models available

LoRA · SD

Doggystyle (Side View)

10756
This LoRA generates images of the "sidedoggystyle" pose, typically involving a male and female character. It is activated by including specific prompts like "sidedoggystyle, 1boy, ass, doggystyle, sex," and works best with a weight between 0.7-1.0. It may exhibit issues with extra characters or anatomical errors when upscaling.actionanimedoggystylensfwsexsex from behindside view

LoRA · IL

ma1ma1helmes | Shiiro's Styles | Niji

4751
The model, ma1ma1helmes | Shiiro's Styles | Niji, generates images with a weight between 0.1 and 1. Key features include glowing and sketch styles, and it's recommended to use samplers like DPM++ 2M Karras or Euler a with specific steps, CFG Scale, and Clip Skip values.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman

LoRA · Flux.1 D

New Incase Style (2024) | NoobAI | Illustrious | PonyXL | Flux.1 D

3569
This model generates images in the style of Incase's newer fantasy and monster-oriented comic art, using "art by incase" as the trigger word. It may tend to monsterize humans and benefits from negative prompts like "deformed, bad anatomy, extra limbs". It aims for high-quality results through careful dataset curation and tagging.nsfwstyle

LoRA · SD

Yiffing Around - ✨ Furry Lora Assistance for Yiff ✨

0538
This Lora assists in generating furry themed NSFW content. It is recommended to use a strength of 0.4 to 0.6, adjusting as needed for desired results.actionfurrynsfwpornyiff

LoRA · Wan Video 2.2 I2V-A14B

Anal/Anus Squirting/Orgasm Wan I2V

446500
This model generates animations focusing on anal squirting/orgasm. It aims to create detailed anus renderings and squirting effects, but may struggle with squirt placement and animations lacking explicit anus visibility or dynamic movement. Use trigger words like "returnthis4nussqu1rt" along with captions describing liquid squirting from the anus.anusbuttconceptnsfw

LoRA · SD

Chubby Girls / Bigger Girls LoRA

2492
This LoRA helps generate images of chubby or bigger female characters, addressing difficulties with standard models. It's trained on NovelAI and works best with anime-style models, utilizing keywords like 'chubby girl,' 'curvy,' or 'plump'. Suggested strength is between 0.6 and 0.8.animebreastschubbychubby figurefatfemalegirlsnsfwsexystylethickthick thighswide hipswoman

LoRA · SD

Blowjob Top of Head POV Lora👑

5482
This Lora model, based on sd1.5, generates images of a blowjob from a top of head POV. It's triggered using "BlowjobTopofHeadPOVQuiron pose" and related keywords, with adjustable Lora strength and denoising. Optimal results are achieved using specific prompt parameters.adultblowjobconcepthardcorensfworalporn

LoRA · SD

Fucked Silly From Behind | Sex Act Lora 220

6474
This Lora model generates images of a female character being penetrated from behind. It was trained on 220 images and is designed to work with character Loras. The model is trained on NAI, and produces output on AOM2 nsfw.animedoggystyleloransfwposessex

LoRA · IL

Pov Cowgirl (Looking Down) [Updated]

7469
This model generates images with a "Pov Cowgirl" perspective, specifically looking down from the female character's point of view during a sexual encounter. It allows for customization of positions and details like clothing, viewpoint, and intimacy level, with improved consistency and higher quality baseline generation compared to previous versions. The core prompt includes elements like "CG_LD, 1girl, 1boy, pov, girl on top, straddling".animecowgirlgirlshentailoransfwpornposeposespovsexsexywoman

LoRA · SD

Masturbation with dildo / Object insertion

8464
This model generates images of female masturbation involving object insertion, specifically dildos and other various objects, both vaginally and anally. Key features include the ability to depict dildo grabbing, assisted insertion from another character, and customizable object types. Recommended weight is 0.8-1.0.conceptdildofemale masturabtionmasturbationnsfwobject insertion

LoRA · Pony

Nipple Size Slider PonyXL

1462
Nipple Size Slider PonyXL is designed for SDXL models to precisely adjust nipple size in increments, from smaller to larger. It minimally impacts other body areas and requires no specific activation prompt.breastsconceptenhancergigantic nipplesgirlshuge breastshuge nipplesnipplesnsfwpepperoni nipplesponyrealisticsexyslidersmall breastswomanセクシー乳头大乳头小さな乳首小乳头

LoRA · SD

LEOSAM's Instant photo 拍立得/Polaroid LoRA & LoHA

10449
LEOSAM's Instant photo model generates images with a Polaroid-style aesthetic. It is a LoRA/LoHA model that aims to replicate the look and feel of instant photos, including the white frame. Different versions offer varying levels of frame accuracy and Polaroid texture, addressing user feedback.filminsinstantphotonsfwphotostyle拍立得

LoRA · Flux.1 D

(Detail Enhancer) 3D Blender Style

2424
The Detail Enhancer 3D Blender Style model aims to generate images with a high-quality, realistic look, similar to 3D renders produced in Blender. It supports trigger words like "ayn0_st", "realistic", and "3D" to control the level of detail and 3D elements, offering options ranging from photorealistic to stylized and themed renders. This model uses advanced techniques like ray tracing and ambient occlusion to achieve detailed textures, realistic lighting, and high-resolution output for a cinematic feel.3danimeartblenderepicgame charactermannsfwponyxlrealisticrendersfwstylestyleswoman

LoRA · Pony

Momofuki Rio Style Lora | PonyXL + SD 1.5

3422
Based on the works of Momofuki Rio Works great at 0.8-1.0 Now with more source-accurate PonyXL version!animefemalegirlshentaimaturemomofuki_rionsfwsexystylestyle loravenus body

LoRA · SD

POV Fellatio

6420
POV Fellatio V2 is an anime model trained on NAI to generate images of fellatio from a first-person perspective. The model is activated using the "povfellatio" prompt and works best at a weight of 0.9-1.0, with additional prompts available to add variations like cum, saliva, or specific hand placements. It's recommended to generate images at 512x512 resolution and then upscale them.animeconceptfellationsfwpovpov fellatiosex

LoRA · Wan Video 2.2 I2V-A14B

F4C3SPL4SH Cumshot - I2V Wan 2.2 Video LoRa - K3NK

8412
This LoRa model is trained on a dataset of 391 clips to generate cumshot scenes for use with the Wan2.2 video model. It aims to create realistic and detailed adult content featuring male ejaculation onto a woman's face and chest. Specific lighting and secondary LoRAs are recommended for optimal results.actioncumcumshotfacialnsfw

LoRA · Pony

[PonyXL] Pull out Penis Cumtrail

3398
PonyXL generates images featuring cum trails utilizing specific triggers. It supports various angles and scenarios like penis being pulled out from different orifices including vagina, mouth, breast, and anus. The model includes triggers for generating cum on various body parts and after sexual acts.after sexconceptcumcumdripnsfworal sexpenis

LoRA · Pony

Bukkake / Excessive cum

2398
This LoRA model enhances the depiction of bukkake or excessive cum in images, allowing for more precise placement and control of the fluid amount. Key features include triggers for specific body parts and control over the quantity of cum displayed. It also supports related actions like handjobs and projectile cum.bukkakeconceptcumexcessive cumnsfwsex act

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 · 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

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 · Pony

Pov sex looking down [Updated] (Missionary + doggy style + mating press)

5311
This model generates POV sex images from a looking-down perspective, focusing on missionary, doggy style, and mating press positions. It allows customization with prompts for angles, clothing, actions, and anatomical details.animedoggystylehentaimissionarynsfwpornposeposespovpov sexsexywoman

LoRA · SD

ReaLora/Realistic skin texture/

3296
ReaLora transforms art into realistic depictions of people with detailed skin texture, while also enhancing other image elements. It is recommended to use with a Lora strength between 0.1 and 0.7, a CFG scale of 7 or higher, and at least 24 steps.3daddaianatomicalanimeartcartooncinematicdetail facedetailsfantasyfemalefotorealismogame charactergirlsillustrationloramanmodelmonstersmore skinsnsfwpersonphotographyphotorealisticportraitsrealrealismrealisticrealorasexysfwskinstylestylesvideo gamewoman

LoRA · SD

Hyper Huge Gape Diffusion - Illustrious / Pony / Sd1.5 - LORA 👑

3293
This LORA model, based on Illustrious, generates images of hardcore content featuring hyper gape. It is triggered by the term "HyperAGapeQuiron" along with related keywords. Optimal settings include a CFG scale of 3-5 and Lora strength between 0.7 and 1.5.analanal gapeanusanus gapeassholeconceptextreme gapegapehuge gapeloransfwporn
Load more models

Showing 24 of 158

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.