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 · NAI

Cleavage Bulge (Bursting Breasts/Spilling Out) [NoobAI + PDXL + 1.5]

1452
This model generates images focusing on prominent cleavage effects, specifically "bursting breasts," and is designed to work well with NoobAI, PDXL, and SD 1.5 base models. Keywords like "cleavage," "bursting breasts," and "tight clothes" enhance the effect with NoobAI, while adding "cleavage" helps with PDXL; SD 1.5 requires no additional trigger. The model has variants optimized for different base models, each with suggested prompts and considerations for desired results.breast overflowbursting breastscleavagecleavage overflowconceptspilling outtight bratight clothestight clothingtight shirttight top

LoRA · SD

Real Pussy - Lily

7451
Real Pussy - Lily is a LoRA model for generating close-up images of a specific female anatomy in various conditions and poses using SDXL. It's trained on hand-picked and improved images, best suited for close-ups and inpainting, and includes tags for controlling details like wetness, shape, and view. The model offers different versions trained with varying resolutions and image counts, and is designed for creating realistic or replacing existing anatomies in images.buttholeconceptcreampiefemalepornvaginavulva

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 · NAI

Aesthetic Quality Modifiers - Best Quality

2444
This model enhances image aesthetic quality, specifically trained on images tagged with "best quality". It is designed to improve image aesthetics and is recommended for use with the "Aesthetic Quality Modifiers - Masterpiece" model. Use the provided prompt structure for optimal results.conceptmasterpiece, best quality, very aesthetic, absurdres

LoRA · IL

Stuffy Ai style | Goofy Ai

2438
The Stuffy Ai style | Goofy Ai model generates images based on user prompts. It is recommended to use the Lora at 0.7-1 strength and ADetailer for faces. The model is hosted and maintained on Tensor.art.animegirlslorastuffy aistylestyleswoman

LoRA · IL

Penis size Slider

0437
You already know what this doeshugelolpenissizeslidertool

LoRA · SD

SL Assorted Female Nobodies 2

1431
SL Assorted Female Nobodies 2 is a collection of unique Lora models that generate different consistent female faces using a mix of various sources. Each version provides a distinct face and is not built upon previous versions. The creator encourages users to share their generated images and provide feedback.characterfemalegirlsphotorealisticrealisticwoman

LoRA · SD

Anime Screencap Style LoRA

4428
This LoRA generates images in the style of anime screencaps. Version 3 is a general style trained on various anime screencaps, while version 2 produces a "magazine" style with the trigger word `anime screencap` and a lower weight setting.animeanime screencapart styleartstylestyle

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

KIDS ILLUSTRATION

6422
This LoRa try to mimic the simple illustration style from kids book. !!!!!!!!! PLEASE DON'T POST LEWD IMAGES IN GALLERY, THIS IS A LORA FOR KIDS ILLUSTRATION !!!!!!!!!Training LoRa necessitate a lot of coffee. If you think that what I do is useful and want to help me keep doing this you can buy me a coffe here: https://ko-fi.com/clumsy_trainer (https://ko-fi.com/clumsy_trainer)bookscartoonillustrationkidssimplestyle

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 · SD

Classic ahegao

6418
A LoRA trained on classic ahegao pictures featuring almost empty eyes, half-closed lower eyelids and small irises.ahegaoanimeconceptfacehentaitongue

LoRA · SD

Realistic Titfuck

7417
This LoRA model generates images of simulated titfucks. It excels at placing a penis between breasts, performs best at strengths of 0.6 to 0.8, and is compatible with various models, although URPM yields the best results.photorealisticpornposespositions

LoRA · Pony

Better Bodies By Stable Yogi

1412
Better Bodies By Stable Yogi is a model that requires specific positive and negative embeddings at the beginning of your prompts for optimal results. Using the creator's negative embedding, detail sliders, and checkpoints is recommended for the best output.animeconceptgirlslarge breastsnudesphotorealisticrealisticsexyskinskin detaileswoman

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 · SD

Studio Ghibli Style LoRA

9404
This LoRA model brings the Studio Ghibli style to image generation. It's a style model best used with a weight of 1 (offset version) or 0.65 (old version) on Anything v4.5, triggered by the phrase "ghibli style," and can be combined with character LoRAs or TIs that don't overfit on style.animeart styleartstyleghiblilandscapesstudio ghiblistyle

LoRA · SD

Head Grab Blowjob/Fellatio - DarkMarauder

4402
A not perfect model of this pose, usually I generate a batch of 4 and select one or two good results. But anyway, it works.blowjobfellatiofemalegirlsphotorealisticpornposessexsex actsexywoman

LoRA · SDXL

Zavy's Dark Atmospheric Contrast - SDXL

2401
Zavy's Dark Atmospheric Contrast SDXL model enhances dark scenes by preserving tonal range and atmospheric depth. It addresses the limitations of other SDXL models, which often render dark scenes with an artificial effect. It brings out subtle details in shadows and allows for greater contrast adjustments in post-processing.atmosphericchiaroscurocontrastdarklow-keyphotographyphotorealisticstyle

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 · IL

Breast Size Slider LoRA | IllustriousXL

1398
This LoRA model for IllustriousXL allows users to adjust breast size using a bipolar slider. It aims to control breast size independently of age, offering a range from smaller to larger. Input values from -5 to 5 are supported, but the final size is influenced by the initial breast size prompt.breast sizebreat enlargementconceptillustriousillustriousxllorashedtheskinslider

LoRA · Pony

Point and Shoot - Pony Amateur Slider

1395
The Point and Shoot - Pony Amateur Slider is a LoRA model designed to add the aesthetic of early 2000s amateur photography, Polaroids, and low-fi digital cameras to AI image generations. It works with SDXL, Pony, and Illustrious, providing a soft-focus, grainy, and flash-heavy look, adjustable in small increments.2000amateuramateur styleanalogbrightdisposable cameraflashflash photographygirlsoverexposurepolaroidrawrawfullysexysliderstyle

LoRA · IL

BBC Thug

1395
Trained on the BBC men of 'The Pitt' Prompts: BBC_TP, BBC, dark skin, dark skinned male, gold chain, grey sweatpantsbarabbcblackblackedcharacterdarkdark skingaythug
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.