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

Breast Size Slider

11.5K
This slider model allows for precise control over breast size in SDXL models, from slight reductions to significant enhancements. It is designed to primarily affect breast size, with minimal impact on other body features, and offers broad compatibility across various SDXL bases. No specific activation prompt is needed; use the slider directly for immediate adjustments.breastsbustyconceptenhancergiganticgirlshuge breastspuffyrealisticslidersmall breastswoman

LoRA · IL

extreme insertion | ponyXL, illustriousXL

41.5K
extreme insertion or large insertion to generate anal content, lower the weight v2.0: added x-rayanimeconceptgirlssexsexyvaginawoman

LoRA · Pony

Realistic Skin for pony

11.5K
This LORA model enhances the realism of pony skin in images by adding blemishes and wrinkles. It offers two versions, v0.1gamma for a stronger effect on skin texture and v0.1beta for a more subtle application. The model is trained on ponyv6 and can be used with other pony-derived models.conceptphotorealisticrealistic

LoRA · IL

Angelauxes [IL]

51.5K
Angelauxes [IL] is a style Lora for Illustrious V2, designed to replicate a specific aesthetic. It is best used with certain models like NTR-MIX-IL and HassakuXL versions, and benefits from omitting standard positive prompts. The Lora strength should be set at 0.8-1.style

LoRA · SDXL

Detail Enhancer (SDXL)

11.5K
The Detail Enhancer (SDXL) Lora model adds more details to images generated by SDXL. Avoid using high weights, as it can significantly alter the style and subject. There are Light and Heavy versions, with the Heavy version potentially better at rendering fine details like hands.concept

LoRA · IL

BlackWhiplash (BWL) [Illustrious] Style LoRA

61.4K
BlackWhiplash (BWL) [Illustrious] Style LoRA is a model for character and style generation. It is recommended to use a strength of 1.0, with the trigger word "blaash". Style 2 is trained on data from 2024-2025, while Style 1 is anything before.animeblackwhiplashbwlcartoonfemboyfutafutanarigame charactergirlshentailoramalemanstylevideo gamevideogamewoman

LoRA · IL

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

41.4K
Zankuro is a Stable Diffusion 1.5 model designed to emulate the art style of Zankuro, specifically focusing on pointy ears. It draws inspiration from Illustrious & Noob AI, Pony, and Flux models.animeart stylecuteillustriousillustrious styleillustriousxlnoobnoob ainoobaipointy earspony stylesexysmugstylezankuro

LoRA · Pony

Anti Long Torso/Legs | SDXL/SD1.5 LoRA

31.4K
This LoRA model adjusts torso and leg lengths in generated images, compatible with SDXL and SD1.5. Use positive weights to shorten and negative weights to lengthen torsos/legs, adjusting prompts accordingly. Recommended weights vary depending on the specific length modification desired.adjusterconceptconceptssliderstylestools

LoRA · SDXL

Waist Slider XL (Microwaist XL)

11.3K
The Waist Slider XL LORA helps achieve thinner waists in Stable Diffusion XL images. It requires no trigger word; adjust the weight up to 1.5 for optimal results, as higher values can distort body proportions.slidertooltoolswaist

LoRA · SD 1.4

hyperbreasts

41.3K
This model generates images of waifus or semi-realistic characters with large breasts. V6 improves style consistency, adjusts breast sizes, and expands breast shape variety while using LoRA LoCon. It allows control over breast size using trigger words from "breasts" to "gigantic breasts" (V5).animeboobaboobsbreastsconcepthyperhyperbreaststits

LoRA · SD

POV Squatting Cowgirl LoRA [1 MB]

221.3K
animeconceptcowgirllow-file sizepovsexsquatting cowgirl

LoRA · IL

ShadyFoxAlart - Art Style / [Illustrious/NoobAI]

151.3K
ShadyFoxAlart is a Lora model designed to generate art in the style of ShadyFox. It works best with a weight between 0.8 and 1.0. The model is still being tested.illustriousloranoobaishadyfoxstylestyles

Checkpoint · SDXL

CyberRealistic XL

71.3K
CyberRealistic XL is a model designed for generating clean, photo-realistic images. It produces sharp and detailed results and commonly needs negative prompts to avoid unwanted styles. The model offers recommended settings and optional tools to enhance generated images.base modelgirlsloramanphotorealisicphotorealisticrealisticwoman

LoRA · NAI

Jumbo Venus XL (PonyV6+Illu+Noob)

11.3K
This model generates images of girls with extremely exaggerated hourglass figures, focusing on large breasts, ass, and belly while attempting to maintain an overall pleasing shape. It excels at creating characters with a massive physique without necessarily appearing conventionally obese, and can also be used to create muscular, plus-sized women.conceptgigantic assgigantic breastshyper hipsplumpprominent bellyprominent tummythick thighsvoluptuouswide hips

LoRA · SD

Skin Tone Slider - LoRA

31.3K
Simple LoRA to help with adjusting a subjects skin tone. You can swing it both ways pretty far out from -5 to +5 without much distortion. Positive gives them darker skin. Negative gives them lighter skin. It is a small LoRA. An experiment in concept strength shifting.dark skinpale skinskin toneslidertool

LoRA · SD

Shirtlift: a LORA for flashing tits

121.3K
This LORA model helps generate images of people lifting their shirts. It was trained on a dataset of images depicting this action, with adjustments made to improve thematic accuracy and reduce unwanted biases. The model utilizes specific settings in the Kohya LoRA Fine-Tuning Notebook, including FP16 precision and a cosine_with_restarts learning rate scheduler.breastsflashingposes

LoRA · Pony

Transformation (Furry)

21.2K
This model generates transformations based on e621 tags, designed for furry characters. It works best with furry base models and excels at transformations between anthro and human/feral forms. Its V2 version features a refined dataset trained on a newer base model.anthroconceptferalfurrygoosextransformtransformation

LoRA · ZImageTurbo

Pinterest Girls

1431.2K
This LoRA is designed to improve the overall quality, consistency, and aesthetics of female faces and bodies when using the Z image model. It enhances facial symmetry, skin clarity, proportions, and general visual realism while keeping the original style of the base model intact. reccomanded strength: 0.75concept

LoRA · SD

epiCRealLife Enhancer

21.2K
This Lora is an ATTEMPT to enhance your photoreality and uses more real world faces. Would love to see various tests on a wide range of models from you guysphotophotographyphotorealismphotorealisticrealismstyle

Checkpoint · IL

Realism Illustrious By Stable Yogi

81.2K
Realism Illustrious By Stable Yogi is a model designed for generating realistic images. To achieve results similar to the creator's images, use the provided positive and negative embeddings at the beginning of your prompts. Check the "About this version" section for model details and settings.animebase modelgirlsillustriousxlmalephotorealisticrealisticsexywoman

LoRA · Pony

Osorubeshi Pony style LORAs

51.2K
These LORAs are trained to generate images in a Pony style. They can be mixed in reduced proportions and don't require special generation parameters. The Shonka model integrates three styles, selectable via specific keywords.animefemalegirlslorarealisticsemirealistsexystylewoman

LoRA · IL

ExpressiveH & Incase Mixed Style v3 [ALL XL] by UOC

41.1K
ExpressiveH & Incase Mixed Style v3 [ALL XL] is a LoRA model trained to recreate a specific artistic style. It combines the styles of ExpressiveH and Incase Style PonyXL, aiming to solve double underscore naming issues present in earlier versions. The model is trained on images generated using these individual LoRAs, with recommended weights of 0.40-0.60 for each style.expressivehgothicincasemixed stylestylevixon

LoRA · Pony

Pov Blowjob + Titjob + Handjob [updated]

91.1K
This LoRA model generates images with customizable combinations of fellatio, handjob, and paizuri. It is designed to be flexible, using prompts like 'pov, 1girl, 1boy' as a base and offering additional prompts for further customization and control. Users can adjust prompt strengths to achieve desired results for specific actions and perspectives.animeblowjobdeepthroatfellatiohandjobnsfwpaizuriposeposespovpov sexsexsexytitjob

LoRA · SDXL

SDXL FaeTastic Details

31.1K
SDXL FaeTastic Details is a LoRA designed to enhance images with increased detail, saturation, and a magical aesthetic. It is trained on high-quality generated images and is not focused on realism. Recommended strength is 0.6-0.8.detailsfantasysdxl style lorastyle
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.