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 · Wan Video 2.2 I2V-A14B

Ultimate DeepThroat I2V Wan2.2 Video LoRa - K3NK

961
This LoRA model is designed for generating deepthroat blowjob scenes using Wan2.2 I2V. It was trained on a dataset of short clips and can handle various points of view in these scenes, though some positions may require specific prompting to avoid artifacts. The model aims to create realistic depictions of this act through text-to-video or image-to-video generation.69 blowjobactionblowjobdeepthroatnsfwpov blowjobsideview blowjob

LoRA · IL

ZH LoRA | Group Grab | Illustrious

060
extanimeconceptconcept loragirlsgrab breastgrabbinggroupgroup sexhentaimultiplensfwposesexywoman

LoRA · IL

legs lock with variants

360
Buy me coffee https://unfazedanomaly964.gumroad.com/l/buymeacoffee (https://unfazedanomaly964.gumroad.com/l/buymeacoffee) Trained on XL Best result with weight between : 0.3-0.8 and the CFG between 6-8 Reviews are really appreciated, i love to see the community use my work. If you like my work, please tip meanimegirlskissloralyingmating pressmissionarynsfwpornposessexsexysittingstandingstraddlestraddling,woman

LoRA · Pony

Sex Machine

160
Sex Machine is a model primarily triggered by the phrase "Sex Machine" to generate sexually explicit content often involving restraints, sex toys, and object insertion. The model is compatible with other models in the collection and has been updated to include Pony-style content.bdsmconceptdoldoobject insertionsex machinesex toystationary restraints

LoRA · Wan Video 14B t2v

Wan Cumshot (2.2 / 2.1)

1160
Wan 2.2 uses highnoise and lownoise LoRAs, while Wan 2.1 is tailored for Image-to-Video (I2V) and Text-to-Video (T2V) applications. Wan 2.1 (I2V) allows for origin points outside the frame, while T2V allows for the generation of specific scenarios and actions, including the generation of intimate acts.conceptcumshotsex

LoRA · SD

BBW style by CHfeels

059
This model, trained on a Rule34 dataset of voluptuous women in similar poses from artists like echosaber, aims to generate BBW style images. It was trained with a weight of 0.6-1.0 and performs well around epoch 8. The suggested prompt for image generation is "1 girl, bbw, venus body".style

LoRA · IL

Saimin Seishidou Style by Nyx for Illu

059
This Lora applies the Saimin Seishidou style to images, working best with Illustrious checkpoints using a weight around 0.8-1 and clip skip 2. It's triggered by the keyword "saimin" and includes styles for multiple characters from the series.animegirlssaimin seishidousexystyle

LoRA · SD

[Free] Breast Helper 1.2

558
This model helps generate images of breasts with specific attributes. It allows users to control breast size, shape, nipple color and style, and areola size using trigger words. The model includes fixes for face issues and improved stability for animation generation.big breastsbimbobreastsconcepthelpermedium breastsrealisticsmall breasttits

LoRA · SD

Female Masturbation [Fingering]

958
This model generates images of female masturbation, specifically fingering. It is designed for NSFW content and may require specific mixes or models like aom2 or defmix for optimal results. The model may occasionally produce inconsistent results.animeconceptfemalehentainudespornsexywoman

LoRA · IL

Bent Over Blowjob

258
This LoRA generates images of blowjob scenes with the subject bent over and displaying their ass. It works well with anime styles but can also produce 3D and realistic images, and is responsive to prompts for side views and POV shots. Use weights between 0.8 and 1.animeblowjobgirlsloraposeposeswoman

LoRA · SD

【Concept】Mechanical Stationary Restraints 机械四肢拘束

358
This model generates images of mechanical stationary restraints. It is trained exclusively on 2D anime-style data and may be incompatible with 3D models. It also suggests prompts relating to vaginal object insertion and sex machines.machine sexmechamechanicalmechanical_restraintssexsex machinesexy

LoRA · IL

Detailer: Plaijful ✨

158
Detailer: Plaijful enhances images with visual effects like glowing emotion, translucent movement, and soft flares, inspired by dances of light and imagination. It uses lightplay and effectplay to translate detailed prompts into artistic renderings with intentional lighting and focus. It aims to capture a unique artistic vision with a touch of cosmic magic and glossy surrealism.accentaffectcolorplayeffectplayillustriouslightplayloramotionposingreijlitastylestyle lora

LoRA · IL

Instant loss 2koma(即堕ち2コマ) / Concept LoRA / NoobAI

258
This LoRA is trained on the Instant loss 2koma(即堕ち2コマ). NoobAI-XL V-Pread 1.0 was used as the base model for training. Trigger2koma, comic, multiple views Prompt1girl, solo focus, explicit, 2koma, comic, multiple views, speech bubble, 1boy, sex, frown, ahegaoconceptinstant loss 2koma

LoRA · Pony

Dandadan - Momo Ayase [Pony + Illustrious]

058
This model generates images of Momo Ayase from Dandadan. It is designed for use with Illustrious-XL (Illustrious) and AutismPonyXL (Pony) and uses specific LoRAs for each. Key features include specific prompts for character appearance and outfits.animecharacterdandadanmomo ayase

LoRA · IL

Niji goth style | Goofy Ai

057
This model generates images in a Niji goth style. It is recommended to use a LoRA at 0.7-1 and ADetailer for faces, as well as img2img upscale with 4x-ultra sharp.animeconceptgothmechanijiniji journeyrealisticsemi-realisticwoman

LoRA · SD

(POV) Blowjob + Creampie LoRA

757
This LoRA generates "POV" and "side view" blowjob images, including cum-in-mouth and deepthroat depictions. It supports both POV and side perspectives and has improved anatomy in version 3. It is based on UberRealisticPornMerge.blowjobcum on facensfwphotorealisticpornposespov blowjobsexual activitywoman

LoRA · SD

Ancient Egypt Clothes

157
Ended up making it rather raunchy compared to the Greek version, hence why this is rated mature.clothingegypt clothesegyptian

LoRA · SD

Cyberhelmet | Wearable LoRA

257
Cyberhelmet is a LoRA model that generates images of characters wearing cyberpunk helmets. It offers two styles: a full cyborg appearance using "a cyborg in a cyberhelmet head" and a masked person look using "a person in a cyberhelmet". The model also supports a "fantastic" tag for crystal material effects.clothingcyberhelmetcyberpunkcyborghelmetmask

LoRA · Wan Video 2.2 T2V-A14B

WAN COWGIRL + REVERSE COWGIRL -- T2V & I2V LoRa

356
This LoRa model generates images and videos featuring the "cowgirl" and "reverse cowgirl" positions. It supports both text-to-video (T2V) and image-to-video (I2V) workflows and utilizes specific trigger words for each position. Camera angles and movements can also be specified in prompts.conceptcowgirlreverse cowgirlwan

LoRA · Pony

Medieval brothel Bedroom

056
This model generates images of medieval brothel bedrooms. Key features include settings with canopy beds, wooden floors/walls, candles, and options for dimmed lighting, particularly suited for rustic bedroom scenes. It also has a negative trigger to avoid blood in the generated images.backgroundbackground ponybedroomfantasyillustriousxlmedievalvintage

LoRA · SD

Film Grain Control SD15

056
Film Grain Control SD15 adds film grain to images generated by Stable Diffusion 1.5. This tool allows users to increase the graininess of their images, with suggested weights ranging from 0 to +5.camerafilmgrainyphotographyslidertooltools

LoRA · SD

Flashing Tits / Exhibitionism

156
Check images for prompting.actionboobsgirlsnsfwtits

LoRA · IL

Anilingus (Rimming, Rimjob) Femdom

056
The model, AniFemIL, generates images depicting anilingus and rimming scenarios. It includes femdom variations with heterosexual, lesbian, and pony themes. Key features involve different model versions (V3, V1 and Pony V1) focusing on specific kinks within this niche.anilingusconceptfemdomlicking ass

LoRA · SD

Dragon Ball Super Style LoRA

056
This LoRA applies the Dragon Ball Super anime style to images, trained on screenshots from DBS and Super Hero. It's designed for creating original characters in the DBS style and works best at a weight of 1 with the trigger word `dbsuper style`. It may not accurately depict non-human races.animeboysdragon balldragon ball superfemalegirlsmalemuscularsexystyle
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.