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 · Pony

Defeated waifu | Imminent penetration | Concept version | Illustrious/NoobAI/Pony

284
This model generates improved images of defeated waifus, optimized for 1088x960 resolution with a Lora strength of 0.6-0.8. It comes in Illustrious and Pony versions. Use monochrome and grayscale for manga-style images.bdsmboundconceptdefeatedhumiliationimminent penetrationslavewoman

LoRA · SDXL

学校 School Building Scenery LoRA

384
This LoRA model reproduces scenes resembling Japanese elementary, junior high, and high school buildings. It allows users to generate images of classrooms, hallways, and stairs with specific prompts. The model was trained to illustrate Japanese school environments.backgroundclassroomillustrationjapanphotorealisticrealisticsceneryschool学校日本

LoRA · IL

lighting

184
Personal lighting preference Version 2 should perform better in darker areas than Version 1 due to being trained on more low-light images. It also features higher contrast.conceptlighting

LoRA · IL

Face in Ass (Ass Smother Standing): Pony & Illustrious

084
Face in ass conceptanimeass,conceptgirlslorasexywoman

LoRA · SDXL

UnifiedTheory [NoobAI / Illustrious]

084
UnifiedTheory is a LoRa model designed to enhance image quality, detail, and lighting when used with Illustrious or NoobAI. It does not impose a specific style, allowing for combination with various artist styles and aesthetic preferences. It is recommended to use it with NoobAI and a strength of 1.0.illustrious styleillustriousxllightingnoob loranoobainoobxlstyle

LoRA · Pony

Ass Smother Against Wall (Face in ass): Pony & Illustrious

284
Female pinning male to wall with ass or Female leaning against wall and sitting on male faceass smotherbuttconceptfacesittingfemdomgiantesshentaisize differencesmothering

LoRA · IL

Penis Size Slider - Illustrious

084
The Penis Size Slider adjusts penis size, focusing on girth and volume rather than just length. It's disentangled to avoid impacting age or unrelated anatomy and works bidirectionally with safe negative scaling to avoid unwanted side effects. The model is experimental and intended for varied prompts and styles.conceptfatgirthyhuge cockhuge penisilxllarge cockpenis sizeslidersmall penistesticlesthick penisveiny penis

LoRA · Wan Video 2.2 I2V-A14B

WAN 2.2 Anime Cumshot Aesthetics – Precision Load I2V (Beta version)

384
WAN 2.2 Anime Cumshot Aesthetics – Precision Load is a LoRA designed to enhance the density, precision, impact, and aesthetic realism of cumshots in anime-style scenes. It focuses on thickness, directional accuracy, and artistic expression, delivering impactful visuals and can pair with live-action content. This beta version features improved motion and detail through high and low noise models, but may still produce some unnatural results.aestheticsanimeanime cumshot aesthetics – precision loadconceptcumshot

LoRA · IL

Areolae size slider

083
Areolae size sliderareolaeconceptnipplensfw

LoRA · IL

Hentai Comic Random Generator (START STORY) (1Page to 3Page) Pony / IL XL | エロ漫画ランダムジェネレーター（ストーリ序盤 ）1ページ～3ページ

183
This LORA generates 1 to 3 page prologues for hentai comics, allowing specification of the number of pages. It focuses on creating basic characters, backgrounds, and suggestive situations typical of comic introductions. Width 832 Height 1216 is recommended.analanimeanuscomicconceptfellatiogangbanggirlsgroup sexhentaimasturbationnsfworalpornvaginawoman

LoRA · IL

Small Dom Big Sub

083
This is Lora for short male being dom over high female. (trained only on male + female and some futa + female) For some reasons Illustrious not as good in this as I would like it to be Activation tags: SDBSER, size difference, large breasts, 1girl, (1boy:1.3)Best Lora weight: 1.0 For better results you can add: age difference (but be careful mods are watching) Turned out to by really good in sex imagesconcept

LoRA · SD

Sensual face Type 1 / 官能的(悩ましげ)な表情 Type 1

081
This model reproduces a sensual anime-style face characterized by half-closed, slightly wet eyes and downward-angled eyebrows. It is suitable for creating seductive, smirking, or NSFW scenes, and works best with anime-style models. Activating the LoRA applies the effect without needing extra prompts.animecomicsconcepteyesfacelorasexy

LoRA · SD

BoltedOnButt

181
Used to have a patreon but you can now support me with donations over at ko-fi https://ko-fi.com/ziraxxx (https://ko-fi.com/ziraxxx) I think its a locon or one of the other lora types, forgor for big bubble butts, works well with my other boltedon Lora. To force a more front perspective use: front_boltedonbutt In some cases adding things like huge butt and wide hips can help get it more right.assbimbobuttconceptsexy

LoRA · SDXL

beautiful girl for SDXL

081
This LoRA generates images of beautiful girls, best used with a strength less than 1. The trigger word is "majicmix style," and the model is recommended for use with the realisticStockPhoto_v10 checkpoint. A V2 model based on feedback includes smiling images.girlsrealisticstylewoman

LoRA · NAI

Mai Shiranui (illustrious, NoobAI-vPred & PonyXL)

481
Mai Shiranui (illustrious NoobAI-vPred PonyXL)This was a requested one thank you! Nothing really to add really, the testing was pretty simple and fun to do. I've always liked this character...for reasons >.>animecharactergame characterillustriousloramai shiranuiponysexyvideo gamewoman

LoRA · Flux.1 D

Amateur Photography

280
This model provides settings for amateur photography image generation, specifically optimized for the v6 Flux Dev version. Key settings include a distilled CFG scale of 3.5, DEIS sampling with DDIM schedule, 20 steps, and a resolution of 896x1152, including a hires fix model with specific parameters. The recommended Lora weight is 0.8, but experimentation is advised.amateur photographyphotorealismphotorealisticrealisticstyle

LoRA · Wan Video 14B i2v 720p

Eye contact blowjob

280
This model generates images and videos of women performing blowjobs while maintaining eye contact with the viewer. It utilizes Pony and Flux LORAs, with the "Eye contact blowjob" keyword suggested for the Pony version, and works with various styles and detailed depictions. The model can also be used to generate videos with guided eye movements.1man1womanactionblowjobdeepthroateye contacteye contact blowjobeyesmouthnsfwone manone womanoralpenissex

LoRA · IL

Better ahegao LoRa | Illustrious

280
This LoRa model is designed to generate anime-style images with an "ahegao" expression. It's trained on a large dataset to minimize stylistic impact and optimized for Illustrious models. Use trigger words with Stable Diffusion to activate the effect.ahegaoconcepthentai

LoRA · IL

Nico Robin One Piece - Pre-Timeskip SDXL (Pony) / Illustrious

280
This model generates images of Nico Robin from One Piece, primarily based on her Enies Lobby outfit. It's trained on Pony Diffusion V6 XL and works best with prompts including "robinprexl, blue eyes, nico robin, black hair, blunt bangs, dark-skinned female, tan." Negative prompts can prevent unwanted clothing details.characternico robinone piecepre-timeskiprobin

LoRA · IL

Ignore Facesitting (Human Chair \ Human Furniture) Femdom

179
This model generates images depicting femdom scenarios involving facesitting and human furniture. Key features include variations on the "human chair" and "human sofa" concepts, often with a faceless male figure. It produces images of females sitting on faces in different poses.ass on faceface-sittingfacesittingfemdomhuman chairhuman furnitureposessitting on face

LoRA · IL

Multiple girls slider / Add or Remove subjects

179
This model adjusts the number of subjects in an image. Positive values add more subjects, while negative values remove subjects, potentially resulting in solo subjects or even removing all people from the scene. It minimally affects the style of the image.addgroupmultiple girlsmultiplierremoveslidersolotool

LoRA · Pony

Boss Battle - By HailoKnight

179
The Boss Battle LoRA generates cool boss fight images inspired by games like Dark Souls and Elden Ring, and spirit animals. Use the trigger word "Bosstyle" to activate it. It is recommended to experiment with LoRA weight and sampler settings for optimal results.bossconceptfantasyfightknight

LoRA · SD

Photo Comparison / Phone View [BETA v2] + XL

779
This BETA model generates images depicting a "photo comparison" concept, showing a background character and another character displayed on a phone. It requires specific prompts for both the background and phone image and performs best with wide shot images (Width >= Height, 768 minimum width). Regional prompting improves results.animecharacterfemalenudenude photograph of a beautifulpornsexywoman

LoRA · IL

Diives (Artist Style) [Illustrious & Noob AI & Pony & SD1.5]

079
The Diives (Artist Style) model is a Lora trained on NoobAI, which was itself trained on Illustrious. It aims to replicate the art style of the artist Diives and is designed for use with SD1.5. This model can be used to generate images in the Diives style, as demonstrated with the provided prompt for Gaghiel.animeart stylecutefurrygaghielillustriousillustrious styleillustriousxlnoobsexystylestyles
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.