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 · IL

🍆💦 FUCKED SILLY - Lewd Details Enchancer v2.0 | Extreme Sex | IllustriousXL NoobAI Pony XL

5584
This LORA model enhances details and expressions of characters during intense sexual scenes. It improves realism with features like expressive faces, sweat, drool, and accurate depiction of sexual acts and positions. It is designed to be used with models like IllustriousXL, NoobAI Pony XL, and SDXL.ahegaobrokenexpressionhentairough sexsexstylewoman

LoRA · Wan Video 2.2 I2V-A14B

Oral Insertion [WAN 2.2]

25583
This LoRA model, trained on the WAN 2.2 I2V 14B, generates images of oral insertion scenarios where the man is not initially present. It is triggered by the phrase "A man appears and she sucks his penis," and optimized sampling requires adjusting the CFG based on the chosen noise model (high or low). The model is provided in a zip file containing LoRAs for both noise levels.actionblowjobfellatioinsertionoral

LoRA · IL

cunnystyle

3578
Cunnystyle is a model for generating images, with different versions focusing on varying aspects of character likeness and image quality. Later versions aimed for clearer faces and eyes, while earlier versions experimented with different approaches. The model is not intended for commercial use.cunnyfunkystylestyle

LoRA · SDXL

Super Skin Detailer By Stable Yogi

0571
Super Skin Detailer enhances skin detail in images. For optimal results, use the recommended positive and negative embeddings. It is suggested to explore the creator's detail sliders and checkpoints as well.conceptdetailerloraphotorealisticrealisticrealistic skinskinwoman

LoRA · Pony

Hyperrealistic [Pony | Illustrious]

3571
This Lora model generates hyperrealistic images, focusing on close-up, portrait, and upper body shots. It utilizes high-quality images and is responsive to positive and negative prompts.3danimecartoongame charactergirlslorarealisticstylevideo gamewoman

LoRA · IL

748cm | Shiiro's Styles | Niji

2570
The 748cm | Shiiro's Styles | Niji model generates images using a weight of 0.1 to 1, and the trigger word "7481llu". It is recommended to use samplers DPM++ 2M Karras or Euler a with specific steps, CFG Scale of 1-7, and Clip Skip of 2.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistpaintphotorealisticrealisticshapesshiirostylestyleswoman

LoRA · Flux.1 D

New Incase Style (2024) | NoobAI | Illustrious | PonyXL | Flux.1 D

3569
This model generates images in the style of Incase's newer fantasy and monster-oriented comic art, using "art by incase" as the trigger word. It may tend to monsterize humans and benefits from negative prompts like "deformed, bad anatomy, extra limbs". It aims for high-quality results through careful dataset curation and tagging.nsfwstyle

LoRA · Wan Video 14B t2v

Hand in Panties - Masturbation - Wan 2.2 - Official Release!

16561
Wan 2.2 is a specialized model for generating images depicting masturbation, specifically a hand in panties. It requires both high and low models and uses specific trigger phrases. The workflow is provided in the training data file.conceptmasturbationpantiessexysolo

LoRA · Flux.1 D

Midjourney V6.1 meets FLUX 🖼️ [+ILLUSTRIOUS / SDXL]

5554
This LoRA model, trained with 34 Midjourney V6.1 images, was created using a new captioning method for improved results. It's designed for use with SDXL and offers a distinctive artistic style. The trigger words are aidmaMJ6.1 (v0.2+) or midjourneyv6.1 (v0.1).animeartartfulmidjourneymidjourney v6modelphotophotorealimphotorealisticrealismstyle

LoRA · SD

Rapunzel (Tangled) Disney Princess - | Illustrious XL | XL PONY | SD 1.5 | - by YeiyeiArt

2553
This model generates images of Rapunzel from Disney's Tangled in Illustrious XL, XL PONY, and SD 1.5 styles. Use specific activation words (RapunzelXL or RapunzelWaifu) and prompts to generate her main outfit or short hair variations. It's designed to create images that capture either a realistic or cartoon-like aesthetic.animeart stylecartooncharacterdisneyfantasygame charactergirlsloraphotorealisticprincessstyleswoman

LoRA · SDXL

SDXL/PDXL - Tuning Face Detailer Lora

0553
This Lora enhances facial details, especially for anime styles, and combines anime modeling with self-training. Recommended weights are 0.3-0.5 for realistic and 0.3-1.0 for anime; higher weights may affect other elements. It's beneficial for improving face clarity in low-step SDXL-Turbo/LCM outputs.detailerfacestyle

LoRA · Pony

Makeup Slider - Pony / Illustrious

2553
New and custom content here: https://aicollective.ghost.io/ (https://aicollective.ghost.io/) Slider for controlling makeup, seems to work well. This slider also have minimal effect on generation unless you use high or low weights, but I found 0 to 2 to be sufficient for most use cases. Also works with SDXL. As always any feedback and posted images are appreciated :)conceptmakeupno makeup

LoRA · IL

Syuro - [Style] [Pony/Illustrious/Noob]

2549
The Syuro model transfers a specific art style, with variations for Pony, Illustrious, and Noob versions. Key features include style transfer to characters and compatibility with other LoRAs, but it has potential issues with zoomed-in angles and, for some versions, male bias. The Noob version offers improved quality and anatomy with lower style transfer.furrystyle

LoRA · Flux.1 D

Dynamic Poses FLUX + SDXL

1548
The Dynamic Poses LoRA V2, compatible with SDXL and Flux, generates action-packed images with realistic and vibrant poses. Trained on a larger dataset, it excels at capturing energetic movements like acrobatics, gymnastics, and running. This LoRA brings enhanced realism and versatility to dynamic scenes.poses

LoRA · IL

Illustrious Style Pack

6544
The Illustrious Style Pack provides a set of styles trained for image generation. It includes various styles, some focused on SFW imagery while others are geared towards NSFW content, with several emphasizing anime aesthetics or mature female characters. The pack also includes deprecated styles that are no longer recommended for use.animeanime characterepicfemale charactersgame charactergirlsillustriouxlloramaturesexystylestyleswoman

LoRA · SDXL

Nude XL

3544
This is my first "decent" lora and it's not perfect. I trained it on about 2000 images I picked, with automatic WD14 captions. It works best in lower resolutions. In ComfyUI I recommend you to use clip strength between 0 and 0.1 and model strength between 0.1 and 0.6, and in A1111 between 0.1 and 0.2. Having the clip strength above 0.2 sometimes ruins the image.concept

LoRA · SD

Yiffing Around - ✨ Furry Lora Assistance for Yiff ✨

0538
This Lora assists in generating furry themed NSFW content. It is recommended to use a strength of 0.4 to 0.6, adjusting as needed for desired results.actionfurrynsfwpornyiff

LoRA · IL

Gay porn (SDXL / PONY)

2538
This model creates gay porn images and enriches gay content by introducing homoerotic elements and specific angles not commonly found in other models. It supports a wide range of poses, interactions, and fetishes through a detailed tag system, enhancing expressiveness and creativity. The model comes in different versions trained on varied datasets including anime and photorealistic images, offering flexibility in style and realism.bdsmconceptgayhomoeroticmale focusporn

LoRA · SD

ReaPhoLoRA (Realistic Photography LoRA)

0526
Trained on 293 of my own images with various subjects and styles.photophotographyphotorealisticphotoshootstyle

LoRA · SD

POV Doggystyle LoRA [1 MB]

14521
This LoRA generates POV doggystyle images, focusing on male subjects. Activate it with the prompt <lora:POVDoggy:0.9>, 1boy, penis, doggystyle, from behind, and use a weight of 0.9-1.0 for best results. It was trained on the NAI model.animeconceptdoggystylelow-file sizepovsex

LoRA · SD

Bimbo Lips

0521
This LoRA adds large, artificial-looking lips to female characters. It was trained on a mix of real and digital images and works well with realistic and semi-realistic models. The trigger word is "bimbolips," and additional terms like "big lips" or "huge lips" can control lip size.big lipsbimbobimbofiedconceptfake lipslip fillersexy

LoRA · SD 1.4

Slingshot swimsuit [SD1.5/Pony/Illustrious]

11520
This LoRA model generates images of characters wearing slingshot swimsuits, and is trained to work with Illustrious. Key features include producing images with tags like "wedgie" and "pubic hair," and it works best with a LoRA strength of 1.animeclothingslingshot swimsuitswimsuit

LoRA · IL

Add Micro Details - Concept (Illustrious | Pony | NoobAI)

4520
Strength – Varies (Sometimes it's hard to tell which one looks best) Add Micro Details v3 [Update]add more detailsanimeconceptdetailed loradetailsenhancementfine detailsintricate designmicro detailsphotorealisticundetailed

LoRA · Pony

Gangbang/Group Sex Slider - Pony / Illustrious

2518
This model adds multiple penises to an image, primarily generating missionary and blowjob scenes. It's trained for anime-style images and SDXL, with "group sex" prompts recommended for more characters. Higher weights can cause overexposure, so prompts should be adjusted before increasing weight above 1.5.conceptgangbang
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.