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

Misty: Tomboyish Mermaid | カスミ (Pokemon) [Pony & Illustrious & SD1.5]

2168
This model generates images of Misty from Pokemon, specializing in recreating famous card art. It can produce images based on prompts, including specific outfits like her bikini and poses from various cards.animecharactercutefemalegirlsillustriousillustrious pokemonillustriousxlnintendoorange hairpokegirlpokemonsexytomboywater pokemon trainerwoman

LoRA · SD

Male Hero / Muscular / Soft Gay focus - {Anatomically Correct}

0168
This model creates anatomically correct male characters with a muscular physique, avoiding exaggeration. It's designed for generating soft gay-themed content, and it supports furry characters. The model benefits from checkpoints optimized for male figures.baraconceptgaymalemuscular

LoRA · SD

Real Mechanical Parts

3167
This model, Real Mechanical Parts version, generates images featuring mechanical parts integrated with organic bodies, primarily humanoids. To achieve intended results, users should use "cable, wires, reelmech and mechanical parts" in the positive prompt and "animal" in the negative prompt. The model is currently in alpha and trained on 768x768 resolution, requiring upscaling for best face clarity.animegame charactermechanicalphotorealisticrealisticstylewoman

LoRA · SD

Bulgerk-dickprint

0166
Bulgerk-dickprint is a LoRA trained on images of real people to create images with pronounced bulges. It's designed to be used with varying LoRA weights and CFG scales, and prompting with terms like "bulge" or "crotch bulge" along with specifying clothing types will influence the results. The model aims to provide bigger, more visible bulge effects compared to the original "bulgerk-soft" textual inversion.bulgeconcepthomoeroticloraman

LoRA · IL

まんぐり返し/folded pose(XL,ill,pony)

2165
The strength of Lora is recommended to be around 1.0.foldedposes

LoRA · Pony

Pussy sandwich

7165
This model generates images of sexual acts. It uses tags like "ass," "pussy," and "tribadism," and benefits from additional tags describing penis presence or positions. The model is optimized for Illustrious anime styles and requires quality prompts.conceptgirlshentaivaginayuri

LoRA · SD

Minimalist Anime Style

4164
Gives more detail when using negative weight. (Thanks for this information @superBlast)animeartstyleminimaliststyle

LoRA · Pony

Anime Feet - Detailed Soles

2164
Trained on 115 anime girl feet pics. Please follow and upvote if you like😄 It really helps getting my lora seen and making my 1000 follower goal! Thank you. If using with other Lora like a certain character, iv noticed its better to put it down to 0.3-0.4 instead. If just prompt + this lora you can do higher to get more foot focus.animeanime girlconceptfeetfeet picsfeet posefeet povfetishfootfootjobsoles

LoRA · Pony

Kawaii PastelCore 🌼 🌸 - slider

0161
The Kawaii Pastelcore Slider adjusts pastel intensity in visuals from subtle to vibrant. It's ideal for creating egirl-inspired portraits and playful pastel scenes. The slider ranges from 0 to 5, controlling the level of "pastelcore cuteness."adorableanimeconceptcutecute girlegirlgamerillustriousilxlkawaiipastelponysdxlslidertwitch

LoRA · IL

Incase + Vixon's Gothic Neon + Disney for Illustrious Style

1161
This Lora recreates a popular Pony style by combining elements of "All Disney Princess XL," "Vixon's Pony Styles - gothic neon," and "Incase Style." It was trained using images generated with the Pony Diffusion V6 XL model, potentially resulting in NSFW content, and is designed for use with Illustrious models. V2.0 aims for improved compatibility with Illustrious models and addresses hand issues, but may require specific sampler settings to avoid lip artifacts.disneygothicincaseneonstyle

LoRA · Flux.1 D

Hyper Realism Lora by aidma [FLUX + ILLUSTRIOUS]

2160
Hyper Realism Lora is designed to generate highly realistic images, aiming for professional photo quality. It enhances details, sharpness, color intensity, and image composition. Use it sparingly as its strength can significantly alter images.hyperrealismlandscapemanphotoprofessionalrealismrealisticstill lifestudiotoolwoman

LoRA · SDXL

Eldritch Comics (comic book style illustration)

1159
Eldritch Comics is a model that generates comic book style illustrations with stark outlines. This version improves upon previous iterations by reducing unwanted sci-fi elements and offers more space for scene composition, while maintaining a consistent and coherent style. It may still exhibit some scale and repetition issues.comic bookcomicsillustrationstyle

LoRA · SD

EjaculatingCum,Bukkake

1158
This LoRA generates images depicting ejaculation, often with themes like male masturbation or bukkake. Key features include projectile cum, facial shots, and cum on/in the mouth, achieved using trigger words and suggested tags. Users might need to fine-tune parameters for optimal results.animeconceptcumnsfwnudepenis

LoRA · SD

Surrounded by Penises

3157
This model generates images of a character surrounded by penises, trained primarily on aom2 nsfw data and a specific image set. It's designed for hentai content and works best with weights between 0.5-0.8 and CFG from 5-9, though these values may need adjustment.animecharacterhentaipenis

LoRA · SD

Gloomifier slider LECO

1157
The Gloomifier slider LECO modifies images, making them gloomier with positive weights and happier with negative weights. Different versions offer variations in intensity and response to positive/negative weights, allowing for diverse results. Trigger words are not required, but descriptors like "dark" or "glowing" can enhance the effect.conceptdarklightslider

LoRA · IL

Anal Tugging4PonyXL

2157
Anal Tugging4PonyXL is a LoRA model designed to generate images of anal tugging with various character types, including furry, anthro, feral, anime, and human. It is activated by the prompt "Anal tugging" and supports related prompts like "Anal Fingering" and "Anal knotting." The model has been updated to work with Illustrious-based models.analanal tuggingconceptfurryhentai

LoRA · SD

Brightness Tweaker LoRA (亮度调整LoRA)

1156
Brightness Tweaker LoRA adjusts image brightness, applicable across various models. Use weights between -2.0 and 2.0, with higher values increasing brightness and negative values decreasing it.brightstylestyle lora

LoRA · IL

penis/dildo size slider

1155
Penis/dildo size slider.conceptdildonsfwpenisslider

LoRA · Wan Video 2.2 I2V-A14B

WAN DR34ML4Y - All-In-One NSFW

23155
WAN DR34ML4Y is an all-in-one NSFW LoRA model designed to handle various specific concepts like double blowjobs, missionary position, reverse cowgirl, and doggy style. It accurately generates images based on specified keywords and positions. It is recommended to use both models to produce ideal outputs.blowjobconceptdoggymissionarynsfworalpovsexwan

LoRA · IL

Eye detail LoRA [Illustrious+FLUX]

0154
Trigger word: eye_focus Trigger word for dark eye detail: dark_eye_focus works best with close upsconcepteyeeye detaileye focus

LoRA · IL

Realistic Cum [Illustrious]

1154
This Lora changes semen to a more realistic look. strength 0.5~0.8. A strength of 1 is not recommended, as it will significantly affect the style of the artwork. This lora was created by ADDifT. Trigger Words: cum,conceptcum

LoRA · SD

NoiseOffset_By_Stable_Yogi

0154
NoiseOffset_By_Stable_Yogi is a LoRA model designed to enhance contrast and produce darker images. It works best with specific keywords like "dark," "rim lighting," and "low key," and the weight should be adjusted based on the sampler used. It improves the image's overall contrast and darkness.darkdarkenlowranoise injectionnoise offsettool

LoRA · IL

Lindong(龙胆) Style [ILXL]

1153
Lindong Style [ILXL] is a model trained on Illustrious-XL. It generates images in the style of Lindong, with optional prompts provided for different base models. The model also includes recommended positive and negative prompts for generating high-quality outputs, specifically for ILXL and NAI-XL.furrylindong030malestyle龙胆

LoRA · IL

Aosiai123 | Shiiro's Styles

2152
The Aosiai123 model, part of Shiiro's Styles, generates images in a traditional media style using the trigger words "traditional media,aosiai123_illu." It's optimized with samplers like DPM++ 2M Karras and Euler a, a CFG Scale between 1-7, and a Clip Skip of 2, with a weight range of 0.1 to 1.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman
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.