Porn Factory AILogin

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 · Chroma

Expressive Kuroinu Style + Ogres IL&NoobAI&Pony&Chroma | Shrekman Hentai Loras

279
This model generates images in an expressive Kuroinu style. It incorporates elements from Ogres IL, NoobAI, Pony, Chroma, and Shrekman Hentai Loras. The model is available through official accounts on Tensor Art, CivitAI, and Seeart.hentaikuroinukuroinu kedakaki seijo wa hakudaku ni somaruogrespornstyle

LoRA · IL

BlushySpicy [Illustrious] Style Lora

179
BlushySpicy [Illustrious] Style Lora generates images in a specific art style. Use the trigger word "yciblu" and a strength of 1.0 for best results.animeblushyblushy spicyblushyspicycartoongirlsillustriousloramalemannoobnoob ainoobaispicystylewoman

LoRA · SD

Grabbing own Ass

1378
This model generates images of figures with their hands on their posterior. It aims to produce more anatomically correct images than other models when prompted for this specific pose. Extra trigger words include "ass stretch" and "ass spread".animefemalegirlshentainudespornposessexsexywomanwomen

LoRA · SDXL

Realistic Insta Influencers By Stable Yogi

078
This model creates realistic influencer images using SDXL+Pony-based LoRAs, trained with one face and one body image. It generates fictional characters through AI, and any resemblance to real persons is coincidental.charactergirlsinstainstagram babeinstagram starloraphotorealisticrealisticrealisticphotosexywaifuwoman

LoRA · SD

Finger Count Slider SD15 (Increase/Decrease Finger Number)

078
The Finger Count Slider SD15 model is designed to adjust the number of fingers in images generated by Stable Diffusion; it increases finger count with positive weights and decreases it with negative weights. It is not an automatic hand fixer for deformed hands, but rather a tool for fine-tuning the number of fingers present. The recommended weight range is -5 to +5, and adjustments may be needed depending on negative prompts.fingershandsmanpersonslidertooltoolswoman

LoRA · Wan Video 2.2 T2V-A14B

Wan 2.2 / 2.1 - Anal Reverse Cowgirl POV - t2v - i2v

878
Wan 2.2/2.1 is a text-to-video and image-to-video model trained on realistic videos. It generates high-quality animations, including depictions of sexual acts like anal sex, based on text prompts. Version 2.1 is compatible with both I2V and T2V models, trained using diffusion-pipe.actionanalcowgirlpovwan

LoRA · SD

Attack on Titan LoRA

077
This LoRA emulates the visual style of the Attack on Titan anime, trained on approximately 18,000 still images. It works well with simple prompts and can be combined with other LoRAs to render specific characters in the Attack on Titan style.animestyle

LoRA · Pony

robot tentacle & sex machine (illustrious, pony)

277
lora for robot tentacles with sex machine.concepthentaimonsterrobottentacles

LoRA · IL

Ugly Fat Man for illustrious | goofy Ai

177
The model, named Ugly Fat Man for illustrious | goofy Ai, generates images. It is recommended to use a Lora with a strength of 0.7-1 and ADetailer for faces, and to upscale images using Img2img and 4x-ultra sharp.animeconceptgirlslorawoman

LoRA · SD

POV Paizuri-Twisted Breasts | LoRA

377
This LoRA model generates images of paizuri scenes. Use the trigger word "paizuri" with a weight of 0.8-1, optionally including "breasts squeezed together" and "penis" for desired results.animeconcepthentainsfwpaizuri

LoRA · SDXL

LaxpeintXL (digital paint style LoRA)

077
LaxpeintXL is a LoRA for SDXL 1.0 that generates digital paint style images. It creates a painterly effect with sharp subject lines and blurred backgrounds, providing a naturalistic digital illustration look. Use it with your preferred SDXL model, adjusting the LoRA strength for desired intensity.artdigital paintingsdxl style lorastyle

LoRA · IL

Freaky dicks

276
This model, triggered by "fdicks", generates images of various unusual penises. Key features include spiked, horse, canine (with knot), alien, and tentacle-like genitalia, with options for flaccid depictions and foreskin. It has improved features for animalistic penis types.cockringconceptexcessive foreskinfdicksflaccidhorse penispurple veinssmall penisspiked penisveiny penis

LoRA · SD

(Outdated) PaizuriAllinOne (different angles and types)

376
This Lora model generates images of paizuri from various angles and types, including POV, side, front, above, and below views. It supports scenarios like paizuri with fellatio/irrumatio, double paizuri, and autopaizuri, using specific tags for each. Recommended weights are 0.6-1.0, and monochrome/greyscale may need to be added to the negative prompt.animebreastscharacterhentaipaizurisexualsexy

LoRA · Wan Video 2.2 I2V-A14B

POV Insertion [WAN 2.X]

1776
This LoRA is specifically trained to capture the moment of insertion when the penis is not initially in frame and can handle both missionary and doggystyle positions. Trigger Phrase: A man appears and inserts his penis into her pussyIf you like this model and want to support the creation of future models, please support my work by leaving positive reviews, or posting your generations to the model page.actiondoggystyleinsertionmissionarypenetrationpoint-of-viewpov

LoRA · IL

breeding mount (horse onahole)

075
Illustrious breeding mount, futanari,penis,testicle,standing, tiptoes,trembling, motion lines, excessive cum,x-ray PONY standing,bent over, sex toy, tiptoes, artificial vagina,futanari,penis,testicle,trembling, motion lines,ejaculation, masturbation, projectile cum,blush, cum,bent over,ejaculation, excessive cum, breast press,concept

LoRA · SD

Female Masturbation [Boob Fondling and Fingering]

975
This model generates images of female masturbation, specifically boob fondling and fingering. Using provided trigger words increases result accuracy. It can be used with the Ahegao model for enhanced results.animecharacterfemalehentainudespornsexsexywomanwomen

LoRA · Flux.1 D

UltraRealistic Lora Project

375
The UltraRealistic Lora Project creates more lifelike images with lively emotions and dynamic poses, aiming for either high-quality or slightly amateurish aesthetics. Key features include improved stability, enhanced anatomy (particularly hands), and flexible quality control influenced by prompts. It comes in different versions for different base models, like Flux and SD3.5.aestheticgirlsmanphotorealisticsexystylewoman

LoRA · IL

shiny wet skin

274
This Lora can generate a wet skin with a strong gloss. . No trigger word required. But, I recommend adding the tag "shiny skin" Recommended strength : 0.4-0.8 (Increasing the strength of Lora will cause features of the training data to appear.)style

LoRA · SD

Fifi La Fume (Tiny Toons)

074
Main Tags: • fifi Reinforcement Tags: • skunk • hair bow • striped tail, fluffy tail, big tail • narrowed eyes, hair over eyecharacterfurrylooney toons

LoRA · Pony

Mtu Virus

374
The Mtu Virus model generates images with the "mtu virus" tag. It is not recommended for realistic images and often includes multiple views. The model is trained with specific technical parameters including a LoRA strength of 1.0-1.2 and denoising strength of 0.25.concept

LoRA · SD

2D Pixel Toolkit (2D像素工具包)

473
The 2D Pixel Toolkit model generates true, clear, and unblurred 2D pixel art. It supports various Lora models and is especially useful for indie game development, providing resources such as characters, animations, weapons, plants, and isometric architecture. The model is best used with specific keywords and the palettize plugin for optimal results.2dassetassetsgamegame assetgamedevpixeltools

LoRA · SD

Droptop

273
Droptop is a LoRA model designed to create images of people with their tops dropped. It gives realistic results, but can also work with anime style models. Recommended weight range is 0.4-0.7.breastsflashingphotographyphotorealisticpornposesrealisticsexywoman

LoRA · Pony

Disgaea Style - Harada Takehito [Illustrious & NoobAI & Pony]

173
This model generates images in the art style of Harada Takehito, known for his work on Disgaea. It is a style Lora, meaning it captures the artistic style rather than specific characters, although some characters might be recognized. The model is intended to create magnificent and stylized images with a dark race aesthetic.animeart stylecutedisgaeaetnaflonnehalloweenharadaharada takehitoillustriousillustrious styleillustriousxllaharllaharl-chanmakai senki disgaeanippon ichi softwarenoobnoobaipirilikaprinnyred magerozalinseraphinasexystylesuccubustakehitovideo game styleyoutube video linkedディスガイア🎃

LoRA · Pony

Sitting on Lap | PonyXL & Illustrious

173
This LoRa model generates anime-style images of a girl sitting on someone's lap. It's designed for PonyXL & Illustrious models and uses trigger words to activate, but may not work well with realistic image models. It is intended for NSFW content and should be used responsibly.animegirlsposessexywoman
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.