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 · Flux.1 D

SECRET SAUCE

14
The Secret Sauce, trained on (≈5600 images) -This model's dimension is large, so combining it with other LoRA models may not be beneficial.style

LoRA · IL

Fellatio From Below - Concept

04
The model generates images depicting fellatio from a below perspective. Key features include a focus on hetero scenarios, explicit nudity, and visual details such as sweat and body fluids. It is triggered by specific keywords to produce the desired imagery.concept

LoRA · SDXL

Schizowave

04
Schizowave is an SDXL LoRA that generates very colorful images suitable for both realistic and stylized checkpoints. The trigger word is SchizoWave, and it's best used with a value between 1.0-2.0 for creating eccentric and unique art.actressanimecolorfulfemalegame charactergirlsloramalemanpersonphotorealisticrealisticstylevideo gamewomanyamer

LoRA · IL

Planted Sinner - Concept

04
The Planted Sinner concept is a LoRA model. It generates images based on specified trigger words related to appearance and sexual acts. It aims to create visuals with elements like nudity, sex, specific poses, and settings, with weight 1.0.concept

LoRA · SD

Hinoa - (Monster Hunter Rise)

04
Character from the game "Monster Hunter Rise" long hair, bangs, gloves, long sleeves, black gloves, wide sleeves, partially fingerless gloves, white kimono, wagashi, yellow eyes,animecharacterfemalegamemonster hunterwoman

LoRA · IL

Netorare Talking On Phone - Concept

04
This model generates images depicting a netorare character talking on the phone. Key features include the character looking at and holding a phone, often in a state of partial or complete undress, potentially exhibiting suggestive expressions and poses. Trigger words such as "netorare talking on phone," "blush," and anatomical terms can be used to influence the generated image.concept

LoRA · SD

One Breast Exposed Concept LoRA

34
This LoRA generates images of girls with one breast exposed and the other covered. It's triggered by "one_breast_out" and improved with prompts like "clothes_pull" and "breast_slip", but may require negative prompts to control framing. The model aims to achieve this specific aesthetic.animeconceptone breast outphotorealistic

LoRA · Wan Video 2.2 I2V-A14B

Wan 2.2 Massage tits by MQ Lab

04
Wan 2.2 Massage tits LoRA by MQ Lab is a model trained with curated datasets and manual captions to generate images related to the specified theme. Users may need to adjust processing steps or FPS for optimal video output. The model is designed to evolve with future data and quality improvements.conceptmassagensfwtits

LoRA · IL

NTR in movie theater/映画館の寝取られ/电影院NTR

04
This model generates images depicting a "NTR" scenario featuring two men, one potentially sleeping. The trigger word is essential for the model to function, and generating satisfactory results may require multiple attempts with compatible checkpoints.conceptmanmmfmovie theatern't'rnetoraresexstealthstealth sex

LoRA · IL

Strangling On Stomach - Concept

04
This model generates images depicting a strangling on stomach concept. It includes elements like nipples, blush, open mouth, and other related features. The trigger word is: .concept

LoRA · IL

Sleeping On Desk - Concept

04
The model generates images of characters sleeping on a desk. Key features include the ability to render subjects sitting or sleeping indoors with closed eyes, often depicting them from the side in a cowboy shot with details like a skirt and hanging breasts. It's designed to be used with a weight of 1.0 and triggered by keywords related to sleeping on a desk.concept

LoRA · Flux.1 D

Flux.1 Turbo Detailer

04
Flux.1 Turbo Detailer is a LoRa model designed to enhance image detail and realism. It delivers exceptional detail, realistic lighting, and precision in features for various subjects and styles.detailerflux.1hyperrealismloraphotorealisticstyle

LoRA · SD

Bismuth Style [FLUX+SDXL+1.5]

03
Trigger: ral-bismut ☕ 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)bismutbismuthgemgemstonestylestyles

LoRA · Wan Video 14B t2v

Wan 2.1 Penis - Cock, Dick, , Lora, T2V, I2V

13
I created this mainly to help out a bit with my deepthroat LoRa, so a few of the example videos include that. It's best at a POV angle, and OK from the side - It can't really do any other angles. All in all it's a bit limited but figured I'd share it anyway in case anyone gets any use out it.conceptnsfwpenis

LoRA · Wan Video 2.2 I2V-A14B

Bouncy Walk - Wan I2V 14B

33
Bouncy Walk - Wan I2V 14B is a LoRA model designed for creating bouncing walk videos. It is trained on videos of people walking with bouncing motion and aims to provide good image continuation, using I2V-14B-720P as a base. The model captures bouncing movement, particularly in the breasts, and works with specific sample workflows.boobsbounceconceptwalk

LoRA · IL

Paw pose/犬のチンチンポーズ

03
｢犬のチンチンポーズ｣concept

LoRA · SD 1.4

Sex toy transformation

33
This model specializes in transformations, specifically related to sex toys. Key tags include transformation as the main tag, and color skin, colored skin, nude, and minigirl as related tags. It is not recommended for realistic models.animeconceptsex toytransformation

LoRA · Other

LottaLewds' balls_deep

73
This model specializes in generating images featuring specific sexual acts, particularly those associated with the `balls_deep` tag. It is trained to produce content focused on acts like deepthroat and irrumatio.animeblowjobdeepthroatsexual activity

LoRA · SD

Hugging own legs

23
This LoRA model generates images of characters sitting and hugging their legs. It improves upon base models that often struggle to accurately depict this pose. Use the trigger word "hugging own legs" and adjust the LoRA weight as needed.animeconceptshugging own legsposeposessitting

LoRA · SD

Trixie Lulamoon | My Little Pony / Equestria Girls

03
This model generates images of Trixie Lulamoon from My Little Pony/Equestria Girls. Use the trigger words "mlptrixie, colored skin, blue skin, star hair ornament" and optionally add "white hair" and "purple eyes." It defaults to a blue hoodie and purple skirt outfit.characterequestria girlsmy little ponytrixie lulamoonwestern animation

LoRA · IL

Hands Up Paizuri - Concept

03
This model generates images depicting hands-up paizuri. It focuses on elements like hands up, paizuri action, nude figures, and motion effects with a weight of 1.0. Trigger words include "hands up paizuri," "paizuri," and related descriptors.concept

LoRA · SD

POV Pronebone Vaginal + Creampie LoRA

53
This LoRA generates point-of-view pronebone vaginal images and includes creampie. It is recommended to use a LoRA strength of around 0.7 and is based on UberRealisticPornMerge. A separate anal version is also available.actionanalphotorealisticpornsexvaginalwoman

LoRA · IL

Slave auction | Sex slave | Concept version | Illustrious/NoobAI/Pony

03
This model generates images of slave auction and sex slave themes, aiming for better image quality within that specific concept. It recommends image resolutions of 896x1152 or 832x1216 with a Lora force of 0.4 to 0.8. It's advised to use monochrome and grayscale for manga style images.conceptholding moneyinterspeciesprostitutionsex salvesize differenceslaveslave auctionsmaller domination

LoRA · Pony

ID Card After Sex - Concept

03
This model generates images based on the concept of an "ID card after sex." Key features include depictions of aftermath elements like bed sheets, blush, and implied sexual activity, often incorporating an ID card prop. It utilizes specific trigger words to influence image generation.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.