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

Erect Horse Penis - Concept LoRA

47
This LoRA generates erect horse penises on humanoid characters, primarily designed for anime models. It allows control over size, shape, and color through specific tags like "Erection," "Size Penis," and "Color Penis." Emphasis can be used to adjust penis size and various tags allow for customization of specific features.cockconceptdickdickgirlequine penisfutafutanarihorse penishorsecockpenisконский членпенисфутафутанаричлен

LoRA · IL

Suspended Congress - Concept

07
This model generates images containing the "suspended congress" concept. It includes triggers for specific appearances and poses, often depicting sexually suggestive situations with motion lines and blur. The weight is set at 1.0.concept

LoRA · IL

Covered Penetration | LoRA

17
This LoRA model generates images with implied sexual content. The trigger word "implied sex" activates the effect, and clothing tags like "oversized t-shirt" can enhance it. A weight of 0.8-1 is recommended.conceptgirlsnsfwpornpovsex

LoRA · IL

Prone Bone From Side - Concept

07
This model generates images featuring a prone character, viewed from the side, with a focus on nude, suggestive, and intimate scenes. Key elements include "prone bone," depiction of struggle, and visual effects like motion blur.concept

LoRA · SD

Jessie pokemon | Goofy Ai

17
This model generates images of Jessie from Pokemon in a Goofy AI style. It works best with a Lora weight of 0.7-1. Use the preview images for guidance.animecharacterfemalegirlsjessiepokemonwoman

LoRA · SDXL

Dogeza - Pose (Illustrious / SDXL)

07
The Dogeza - Pose (Illustrious / SDXL) model generates images of a female character in a "dogeza" pose (kneeling and bowing). It utilizes LoRA models, including "Dogeza," "illustrious_best_quality_v1," and "xmc_v0.3_noobai_cwhj," to achieve specific aesthetic qualities and character details. The model appears to support nude character generation.apologybeggingdogezaembarrassedhumiliationillustriousposeposessubmissive

LoRA · Wan Video 14B t2v

Mating Press (Wan)

17
You asked, Wan delivers! Trained the same way as my other LoRAs, I'd say this is a pretty solid setup. This one's more of a one-trick pony, but I concentrated on T2V this time. Wan 14B T2V, 40 epochs, 29 videos trimmed to 3 seconds and 480P / 24fps.concept

LoRA · IL

Upright Straddle - Concept

07
The model generates images of a character in an upright straddling position. It is trained with specific trigger words to depict sexual acts and poses, including nudity, kissing, and specific physical interactions. Its weight is 1.0.concept

LoRA · Wan Video 2.2 T2V-A14B

Cum on Face

4877
This model generates images of a woman's face covered in dripping semen, without depicting penises. It's trained on a dataset of 136 images and aims to enhance cum aesthetics when combined with other related LoRAs. The model description includes example prompts and workflow samples.conceptcumcum on facefacialsemen

LoRA · IL

Mating Press Holding Hands (NTR POV)

07
NTR POV of Mating Press. Man is holding hands of femaleconceptholding handsmating pressntrpov

LoRA · Pony

arm grab missionary (illustrious, pony)

17
lora to generate 'arm grab missionary' position. It works better for square(1024X1024) or landscape forms. It is NOT recommended to use vertical form (ex. 832X1246) to reproduce examples of images shown above.arm grabconceptmissionarysex

LoRA · IL

Penis shadow LoRa | Illustrious

07
This LoRa model generates penis shadows in anime-style images. It is trained on a large dataset and optimized for Illustrious models, but may not work well with realistic images. Use trigger words in your Stable Diffusion setup to activate it.big penisconceptpenis awepenis shadow

LoRA · IL

Extreme Spit Roast [With: Handjob/Choking/Dangling legs] | Shrekman Hentai Loras

07
Want to support me or request a model?Here is my ko-fi: https://ko-fi.com/renaissancegremlin (https://ko-fi.com/renaissancegremlin) My loras are also coming slowly to tensor art: https://tensor.art/u/836328663648595213 (https://tensor.art/u/836328663648595213)conceptcumcum zonehentaipornpornorough sexsexspit roast

LoRA · Wan Video

360 Degree Rotation (Microwave Rotation Wan2.1 I2V LoRA)

17
The 360 Degree Rotation (Microwave Rotation Wan2.1 I2V LoRA) model generates videos of objects rotating 360 degrees based on a given input image. It was trained on the Wan.21 14B I2V 480p model, using short clips of objects being rotated. The trigger word for this LoRA is 'r0t4tion 360 degrees rotation'.360concepteffectmicrowave effectrotationwanwan2.1

LoRA · SD

Sailor Moon——Sailor Jupiter

07
This model generates images of Sailor Jupiter (Makoto Kino) at a weight of 0.8-1. Key features include her signature bow, elbow gloves, neck ribbon, and long, ponytail hairstyle with bangs. The model also includes details like her circlet, jewelry and flower earrings.animecharacterfemalegirlsmakoto kinosailor jupitersailor moonsexywoman

LoRA · IL

Reverse upright straddle LoRa | Illustrious

07
The Reverse upright straddle LoRa model, also known as Illustrious, is designed for generating anime-style images. It's trained to minimize style impact while allowing for specific triggers; it's optimized for Illustrious models.legs togetherposespositionreverse cowgirlreverse upright straddle

LoRA · SD

Fried Egg Style [LoRA 1.5+SDXL]

07
Trigger: ral-friedegg ☕ Buy me a coffee: https://ko-fi.com/ralfingerai (https://ko-fi.com/ralfingerai) 🍺 Join my discord: https://discord.gg/g5Pb8qNUuP (https://discord.gg/g5Pb8qNUuP)eggfried eggstylestyles

LoRA · SD

Detail Tweaker LoRA (细节调整LoRA)

327
This LoRA enhances or diminishes image details while preserving the overall style and character. It is compatible with various base models, style LoRAs, and character LoRAs, and it supports a wide range of weights, including negative values to reduce details.animeconceptdetailedloraphotorealisticundetailed

LoRA · Pony

kiss glans handjob (illustrious, pony)

07
lora for handjob sex with kissing glans.conceptfellatiohandjobkiss glansoral sex

LoRA · SD

Chizuru-chan Kaihatsu Nikki - Hentai protagonist + style

07
This model focuses on generating content featuring a hentai protagonist. The model's key feature is its specific art style, likely associated with the "Chizuru-chan Kaihatsu Nikki" theme.character

LoRA · SD

Yukari Yukino (雪野 百香里) - The Garden of Words (言の葉の庭)

07
This model generates images of Yukari Yukino from The Garden of Words. It focuses on her appearance, including short black hair, blue eyes, and clothing such as a white shirt, peach blazer, and pencil skirt.animecharacterfemalegirlsmoviesenseiteacherwomanyukari yukino

LoRA · Flux.1 D

NSFW Flux Petite

37
NSFW Flux Petite generates photorealistic images of petite, often partially nude, white women with small to medium breasts. It was trained primarily on images without faces, so prompting may be needed to include facial details. It's designed for depicting nude women and should not be used to create images of children.conceptnsfwpetitephotorealisticwoman

LoRA · SD

Princess Eilonwy (The Black Cauldron)

06
I made this with Pixai: https://pixai.art/model/1668800121749700711 (https://pixai.art/model/1668800121749700711) The base model is Moonbeam 12/24/23: I've added a Hassaku base version to the filesblonde hairblue eyescharacterdisneyprincesswoman

LoRA · IL

アナルテイル/anal tail

06
The strength of Lora is recommended to be around 1.0.clothing
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.