Porn Factory AILogin

concept models for adult image and video generation

Compare 592 public adult AI checkpoints and LoRAs tagged concept. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

592 models available

LoRA · SD

That's My Bush!

1120
That's My Bush! is a LORA model trained to add natural pubic hair to generated images. It works best with basic frontal poses and a weight of 0.2-0.4 and may cause unintended smiles. The model was trained on solo nude images using Realistic Vision 1.3 as the base.conceptfemalephotographyphotorealismpornportraitswoman

LoRA · Pony

Adjust details AND photorealism

0120
This model enhances images by adjusting details and photorealism. It can be used to add intricate details, improve lighting, sharpness, color grading, and overall composition to images; positive and negative strengths can be used to achieve either more or less realism and detail, respectively. It was trained for both illustrations and realistic photographs.conceptdetaildetailedenhanceenhancerphotorealismrealismrealistic

LoRA · SD

Mating Press (Experimental)

5118
This LoRA generates images of the "Mating Press" pose. It requires specific prompts like "matingpress, 1boy, penis, sex" to activate and was trained on 512x512 images. Be aware of potential issues like multiple testicles or disappearing limbs.animeconceptekuneheteromating pressmissionarynsfwsex발정

LoRA · Pony

Cum Through Clothing (Furry)

0114
Cum Through Clothing e621 tag, trained with Fluffyrock/Pony model. Best use with other furry base models. Prompt is cum through clothinganthroclotheingconceptcumcum through clothingfurrynsfwunderwear

LoRA · Pony

character sheet

2114
concept

LoRA · Flux.1 D

NEW FANTASY CORE - ILL-FLUX-PONY-SDXL (detailer)

1114
NEW FANTASY CORE is a model trained on dark fantasy images to enhance images with a dark style. This specific version, ILL-FLUX-PONY-SDXL, is versatile, encompassing anime styles (ILL), a mix of anime and semi-realistic styles (FLUX), semi-realistic/realistic styles (PONY), and compatibility with SDXL. It requires experimentation with LoRA strength and trigger words depending on the specific version.conceptfantasy

LoRA · SD

Smirking eyes / にやにやした目

1112
This LoRA model reproduces smirking eyes, best suited for anime-style models. Enabling the LoRA is generally sufficient, but using prompts like "smile" or "smirking" can improve results.animecomicsconcepteyesfacelora

LoRA · SD

Multiple Asses

9110
This LoRA generates images featuring multiple girls from behind. It supports various angles, poses, and actions focusing on the posterior view and related body parts. The model can generate groups of girls, though accuracy may decrease with larger groups and wider image frames.animeassconcepthentaimultiple girlsmultiple peoplepornsexy

LoRA · SD

Pronebone (Side View)

3109
This LoRA generates side-view images of a character in a prone position. It is designed for 512x512 resolution and requires specific prompts like "proneposition, prone bone" to activate, with added tags for variations.concept

LoRA · IL

グロマン Meaty Labia/Slutty Pussy[illustriousXL ]

1108
This LoRA model generates images of girls with prominent labia. Key features include the ability to create images with "meaty" or "long" labia, and the model responds to trigger words like "slutty pussy", "urethra", and "dark labia". Use a strength of around 0.8 for best results.animeconceptnuditysexyvagina

LoRA · SD

Ass support on object

4108
This model generates images focused on ass support themes. Recommended tags include high score ratings and optionally source_anime, while discouraging low scores, 3D renderings, and lips. AutismMix_confetti is the suggested checkpoint.animeassass supportbuttconceptconceptualdeep skinposeposing sexysittingthicc

LoRA · Pony

Huge Areolae [Concept] (Pony / NoobAI)

0106
This model generates images featuring large areolae, aiming for about 50% breast coverage across varying sizes. It was trained using 53 images and is intended for use with NoobAI ε-pred 1.0, using the trigger phrase "huge areolae." The dataset used for training is also available for download.areolaareolaebody modificationbreastsconceptnipples

LoRA · IL

Lesbian fingering

5102
This model generates images of lesbians fingering each other, with variations for pony and illustrated styles. Key triggers include "lefiys, yuri, on bed, fingering, nude," and optional triggers like "french kiss, pussy juice" for more detail. The strength varies depending on the specific version being used.animeconceptfrench kissgirlslesbiansexsexyvaginal

LoRA · IL

Deepthroat - Concept

0101
The Deepthroat model generates images depicting fellatio scenes. It uses trigger words like "deepthroat", "hands on another's head", and related terms to influence image generation.concept

LoRA · Pony

Hanging Breasts By Stable Yogi

2100
This model is designed to generate images of hanging breasts. Use specified positive and negative embeddings at the beginning of your prompts for best results, as detailed in the description. It is recommended to use the author's negative embedding, detail slider and checkpoints for optimal image generation.animeconceptflashing breastsgirlsloraphotorealisticpulling clothesrealisticsexywoman

LoRA · IL

sexy perspective

0100
This model enhances perspective in images, particularly those with sexy poses. Version 2.0 was trained on a larger dataset with less training to avoid overly altering the original style. The trigger word "sexyper" can be used to further increase the effect.conceptdetailerperspective enhancer

LoRA · IL

Multiple views sex LoRa | Illustrious

199
This LoRa model, Illustrious, generates anime-style images with specified sexual actions using trigger words like "deepthroat" or "vaginal." It is designed for use with Stable Diffusion and optimized for Illustrious models.conceptmultiple views

LoRA · SD

Hair over one eye, both eyes, LECO

099
This LECO model corrects issues with hair obscuring one or both eyes in generated images. It uses varying weights (1-2.5 for one eye, 3-4+ for both) to control the hair placement, though higher weights can alter composition and introduce unexpected effects. Negative weights result in unpredictable image outputs.bothconcepteyehaironeover

LoRA · Pony

Pony+illustrious Testicle Grab / Grabbing Balls / CBT / Ballbusting (commission)

099
Like and Follow! Comms always open.ballbustingcbtconceptfemdom

LoRA · Wan Video 14B t2v

Wan POV Blowjob

1599
The Wan POV Blowjob model generates images and videos of oral sex from a first-person perspective. It is capable of depicting cumshots and can handle images where the penis is not initially present. The model supports multiple angles and requires specific prompts to trigger certain actions, like the appearance of cum.blowjobconceptoralsex

LoRA · SD

Jack-O' Challenge Pose LoRA [1 MB]

897
This LoRA generates the Jack-o' Challenge pose (frontal only). It requires a weight of 0.9-1.0 and CLIP SKIP 2 with the prompt "jack-o' challenge, flexible, spread legs, top-down bottom-up" for activation, ideally at a resolution of 512x768. It was trained on the NAI Model.animeconceptekunejack-o challengejack-o' challengelow-file size

LoRA · IL

(IL+Pony) Rear Naked Choke / 裸絞め

197
This model generates images of the "rear naked choke" submission hold. It addresses the issue of base models often depicting incorrect choking techniques when prompted with "choke hold." Use the trigger word "choke hold (rnc)" with a recommended weight of 1.conceptnsfw

LoRA · Pony

Lying on Lap Blowjob PONY/Illustrious

296
This model generates images of a woman performing oral sex on a man while lying on his lap. The V2 version (Illustrious/NoobAI) requires specific prompts and a strength of 1.0. The V1 version (PONY) works best at 0.9 strength, with specific resolution recommendations and prompting styles for optimal results.blowjobconcepthead on laplying on lapsucking

LoRA · SDXL

OnOff LoRA for SDXL and Pony

196
This LoRA generates side-by-side images of a subject, typically one clothed and the other nude. It can also create compositions with both clothed and nude figures side-by-side. The "onoff" keyword is used in the prompt for SDXL versions to control the image generation, while earlier versions might require more explicit prompting for the desired effect.clothesconceptnudityonoffundress
Load more models

Showing 24 of 592

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.