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 · SD

Yoji Shinkawa Style LoRA

242
This LoRA allows users to generate images in the style of artist Yoji Shinkawa within Stable Diffusion. Use trigger word "shinkawa youji" and a weight of 1 for a 1990s style effect, or lower weights to add subtle Shinkawa characteristics. It works well with models like AnyPastel and AnyLoRA.animeart styleartisticartstyleasianconcept artgirlsillustrationretrostyleyoji shinkawa

LoRA · IL

Queen of Spades tattoo

142
This model adds a Queen of Spades tattoo to images, particularly those generated with Illustrious anime models. Use the tag "qos on [placing]" to specify the tattoo's location; a "masterpiece" tag and Euler a sampler with 20-30 steps and a CFG of 4-7 are recommended.blackedconceptqosqueen of spadesspadessymboltattoo

LoRA · Pony

XXX HARD Irrumatio DeepThroat Generator / Pony IL XL | ハード イラマチオ 洋物 ジェネレーター

142
This LORA generates hentai anime, specifically focusing on depictions of deep throat actions. It was trained on real-world imagery and may require adjustments to negative prompts to achieve an anime style. It works best with landscape (wide) image ratios.blowjobbukkakeconceptdeepthroatfacialfellatiogirlsirrumationsfworalpornwoman

LoRA · Pony

Transparent Wedding Dress / Kinky Wedding Dress +18 - Concept / Clothes - | Illustrious XL | PONY XL | - COMMISSION - by YeiyeiArt

242
This model generates images of transparent or kinky wedding dresses for Illustrious XL and PONY XL. The trigger word is "WeddingDressXL", and adding terms like "bridal veil, see-through, naked body" can enhance the output. It is designed for creating explicit content.animeart stylescartoonclothesclothingdressfantasyhentailoramangarealismrealisticsexystyles

LoRA · SD

POV Reverse Cowgirl

342
This LoRA generates images in POV Reverse Cowgirl. Use with a weight of 0.9-1.0, or 0.6-0.7 with character LoRAs, and include "1boy, penis, vaginal, pov crotch, from behind" in the prompt to activate. It was trained on the NAI model and works best with anime-style models.animeconceptekunepovpov reverse cowgirlreverse cowgirlsex

LoRA · IL

Gyaruo (ギャル男) (チャラ男) - Concept

041
This model generates images of "gyaruo," a Japanese subculture type characterized by tanned skin and blonde hair. It is trained to produce images of dark-skinned, faceless males, often with short hair and facial hair. The trigger word 'gyaruo' and the lora tag activate these features.concept

LoRA · IL

Code Geass characters: Kallen Stadtfeld/Kallen Kōzuki, C.C., Sakuya Sumeragi, Rakshata Chawla, Nunnally vi Britannia, Leila Malcal, Catherine Sabathra, Kaguya Sumeragi, Villetta Nu

141
This model generates images of Code Geass characters including Kallen Stadtfeld/Kallen Kōzuki, C.C., Sakuya Sumeragi, Rakshata Chawla, and others. It includes various versions and improvements for specific characters, with updates based on user requests and dataset enhancements. The model aims to replicate the art style of Code Geass, including artwork from the Lost Stories mobile game.c.c.catherine sabathracharactercode geasskaguya sumeragikallen kōzukikallen stadtfeldleila malcalnunnally lamperougenunnally vi britanniasakuya sumeragivilletta nu

LoRA · Pony

JAV HARD CORE Gangbang Generator (2TNOZ) Pony XL | 輪姦（白仮面醜男）アダルト ビデオ ジェネレーター

041
This LORA model is designed to generate hentai anime scenes based on JAV (Japanese Adult Video) content, specifically focusing on the "2TNOZ" genre. It was trained on images featuring masked men and aims to allow users to create images of anime characters in similar scenarios. Using negative prompts helps prevent the generation of realistic images when creating anime scenes.animebondageconceptfellatiogangbanggirlsgroup sexmasturbationnsfworalpornvaginawoman

LoRA · SDXL

SDXL YAMER'S STYLE 😍 Princeps Omnia LoRA

041
SDXL YAMER'S STYLE 😍 Princeps Omnia LoRA is a model designed to reinforce the creator's artistic style or inject it into other checkpoints. It excels at generating colorful, chaotic, and aesthetically unique images, especially with abstract works and singular character images. The LoRA was trained using images in various styles and resolutions, but 576x1024 is recommended.2d3dactressalphaanimeanime irlartbeautifulbeautiful girlboyscutedarkfantasyfantasy artfemalegamegame charactergirlpackgirlsillustrationillustrationskawaiiloramanmemeneworiginalitypersonphotorealisticportraitsquality uprealisticrealisticlorasdxlsdxl 1,0sdxl animesdxl style lorasfwsharpstylestyle lorastyle mixstylemixstylesterrorvideo gamewomanxlxl1.0yamer

LoRA · SD

Guided Penetration | Test Sex Act Lora 445

341
This Lora is trained on guided penetration with varying results, particularly with hands and rear views. It aims to generate images involving the specified act and is reported to work with character Loras. Example prompts are provided for front and rear perspectives.animeposessexywoman

LoRA · SD

Breast Grab from Behind ++

041
This LoRA model generates images focused on the "grabbing from behind" pose, specifically breast grabbing. The model works best with a base model like Midnight Mixer Melt and can be enhanced using related embeddings such as "Watermelon Warrior." Use of WD VAE and setting CLIP skip to 2 is suggested for optimal results with the trigger keyword "melonstyle".breastconceptgrabtits

LoRA · IL

POV Missionary-Legs Together | LoRA

241
Weight : 0.7-1 Enjoy! If you like the model, I'd appreciate your review. Also, feel free to share your creations, I really like seeing everyone's results! :)girlshentaimissionarypornposeposessex

LoRA · SD

Hews Style | Goofy Ai

041
Hews Style | Goofy Ai is a model designed to emulate the artistic style of the original artist hews. Key features include the use of specific LoRA weights (0.7-1), the use of ADetailer for faces, and recommendations for upscaling via Img2Img and 4x-ultra sharp. The model is hosted on Tensor.art.animefemalegirlsstylestyleswoman

LoRA · SD

Crop Shirt + Underboob (anime+realistic) | Goofy Ai

340
This model generates images of characters, both anime and realistic, wearing crop shirts with underboob exposure. It works well with a Lora weight of 0.7-1 and benefits from a highres fix.animeclothclothingfemalegirlsoutfitrealisticsexywoman

LoRA · SD

Gyokai / ononoimoko (魚介 / おののいもこ) Art Style LoRA

340
Gyokai (ononoimoko) (https://www.pixiv.net/users/165192)'s art style.animeart stylecolorfulillustrationstylevideo gamevivid colors

LoRA · SD

female_pov and futanari_pov

240
This model generates images with a female point-of-view, sometimes incorporating futanari elements. Key triggers include female pov, pov breasts, pov crotch, and cunnilingus, though some triggers like female masturbation and fingering pov produce variable results. It prioritizes feminine presentation with occasional masculine attributes.animeconceptpov

LoRA · IL

Lesbian Facesitting

140
This model generates images of lesbian facesitting scenes. It can be used with different base models, with recommended strength adjustments for optimal results, and may require negative prompts to avoid unwanted earrings. The model is triggered by keywords such as facesitting, cunnilingus, 2girls, yuri, and on bed.animeconceptcunnilingusfacesittinglesbiansexy

LoRA · IL

Silhouette Sex | LoRA

140
This LoRA model generates silhouette images of sexual content. Use the trigger words "silhouette, sex" with a weight of ~0.6-1, and backgrounds like curtains or windows are recommended. It was trained on a small dataset, so flexibility may be limited.animeconceptnsfwsex

LoRA · SD

Mushoku Tensei (Jobless Reincarnation) Anime Style LoRA

140
This LoRA allows you to generate images in the style of the Mushoku Tensei (Jobless Reincarnation) anime. Using "mushoku tensei style" improves fidelity, while "anime coloring" produces flatter colors. It works best with AAM or AnyLoRA checkpoints, but remember it's a style LoRA, and character accuracy may require additional networks.animeanime styleboysfemalegirlsloramenmushoku tenseisexystylewoman

LoRA · Pony

Retro Game (CPS II) - Pixel Art - STYLE - | Illustrious XL | Pony XL | - By YeiyeiArt

140
This model generates images in the style of retro CPS II video game pixel art. It offers both a standard and a Pony XL version, with the latter providing improved prompt understanding and adjustable intensity. Key prompts include "Csp2Pixel" or "CspPixelArt_Style" and phrases like "fighting stance" or "dynamic pose" for creating Street Fighter-like images.animecartoonfantasygirlslorapixelartrealismrealisticretrostylevideo gamevideo game characterwoman

LoRA · IL

Ski Slope Breasts | Flux + Pony + ILL + SDXL

039
This model generates images of breasts with varying slopes and nipple puffiness, aiming to recreate the "Swooping Breasts" aesthetic. It offers multiple versions, including mixed, steep, and shallow slopes, as well as an XXL version for larger breasts. The SDXL version is best used with lower strength settings to avoid cropping the head.breastsconceptrealisticsexytitswoman

LoRA · IL

cum on eyes and nose

039
lora for facial cumshot, designed to describe 'cum on nose and eyes'. Modify the strength of the lora and other parameteres, depending on your checkpoint.bukkakeconceptcum on eyescum on nosecumshotfacialhentai

LoRA · SD

Hestia (DanMachi) LoRA

239
This was a request from someone. I think it turned out really good. What do you guys think? I'd love to see your images using my LoRA.animecharactergirls

LoRA · SD

Legs Together UP | Test Pose Lora 361

239
Lora trained on 361 images of legs together up. Reminder that ai sucks at feet so just inpaint and fix em or something. This was the best epoch of the 35 trained and had a 60% success rate compared to the others. Can kinda do sex, results may stray from the 60% rate. Should work with character loras. Trained on NAI gen'd on AOM2 nsfw.animefemaleposeposeswoman
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.