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

【Pov】All Fours and From Above 爬向你

367
Anime lora trained on NAI. It's sfw(?), the girl won't eat something nsfw I think. 健全得很，我觉得她不会吃什么不健康的东西。 Following tags might help: top-down_bottom-up, from above, looking up 可能会有帮助的tag：top-down_bottom-up, from above, looking up And……remember to remove clothes. 以及……记得脱衣服。animeposes

LoRA · SD

Murky's - Cum on Tongue LoRA

1067
This LoRA enhances image generation related to the concept of cum on tongue and face (facial). It is triggered by keywords like "open mouth, cum in mouth, cum on tongue, tongue out, cum". It also includes keywords for cum dripping onto hands.animecumpornposessexual activitytongue

LoRA · Wan Video 14B t2v

Pussyjob Wan 2.1/2.2 14B T2V/I2V LoRA

36966
This LoRA, "Pussyjob" (or grinding), is designed for Wan 2.1 14B T2V but is also compatible with Wan 2.2 and I2V models. It generates animations of a woman rubbing her genitals on a penis, triggered by phrases like "pussy job, rubbing pussy on penis". Additional prompts control viewpoint and ejaculation aspects.actiongrindingpussyjob

LoRA · SD

Virgin killer sweater

566
This model generates images of characters wearing a "virgin killer sweater," with options for different sweater styles like ribbed or aran. It allows control over elements like sideboob exposure and color variations.clothingmeme attiresweater

LoRA · IL

Cheek Bulge LoRa | PonyXL

266
This Cheek Bulge LoRa model for PonyXL generates anime-style images with a visible bulge in the cheek caused by a penis in the mouth. It's optimized for PonyXL models and trained to not drastically alter artwork style.concept

LoRA · SD

Color fix and enhance realistic version

066
Simply enhance the colors of your model without changing it this version for photograph, anime version is here https://civitai.com/models/124819 (https://civitai.com/models/124819) Why is the file so big? Because it has 128 dimensions,you can adjust dims in "supermerge" tool as you liketool

LoRA · IL

Penis goes all the way through/anal threading/oral threading

066
This LoRa model generates images of a female character penetrated by a penis that goes completely through her body, either from mouth to anus or vice versa. It includes specific tags to control the direction of penetration, penis size, and related actions like grabbing the penis or deforming the character's body. The model may alter art styles and often works best with a weight of 0.8.all the way throughanalconceptdeep penetrationdeepthroatextreme penetrationfellatiohorse penishuge penislarge penetrationoralstomach bulgestomach deformationthroat bulgeweird fetishes

LoRA · SD

Slingshot Swimsuit v2

266
Slingshot Swimsuit v2 is a rebuilt model allowing specification of color, pattern, and pubic hair to generate swimsuit images. Animal patterns can be generated via prompts like "tiger print swimsuit," with adjustments possible to avoid unwanted animal features. The recommended version is AllLayer, with an experimental OUT version available for specific network arguments.clothing

LoRA · IL

0__11Xx | Shiiro's Styles | Niji

265
The model, 0__11Xx | Shiiro's Styles | Niji, generates images with surreal and glitch themes, using the trigger word "0__11Xx_illu". Effective sampling can be achieved with DPM++ 2M Karras (20-40 steps) or Euler a (25-40 steps), CFG Scale 1-7, and Clip Skip 2. Usable weight range is from 0.1 to 1.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman

LoRA · SD

POV Missionary-Raised Legs | LoRA

565
This LoRA model generates images with a missionary position and vaginal sex. Trigger words are "missionary, vaginal, sex", and a weight of 0.7-1 is recommended.animensfwpornposeposessexvaginal

LoRA · Pony

Nicole Demara (Pony, IL, XL, 1.5)

165
This Lora model generates images of Nicole Demara from Zenless Zone Zero, trained at 1024x1024 resolution and enhanced with 3D model data. The trigger prompt is "nicole demara", with additional prompts available to customize her default costume. It allows for easy costume modification or removal using specific prompts, with a recommended weight of 0.8~1.animecharacternicole demaravideo gamezenless zone zero

LoRA · SD

【Realistic & Anime】Genshin Impact AI Cosplayers Collection 原神 AI Coser合集

365
This model generates realistic and anime-style images of Genshin Impact cosplayers. It is recommended to use adetailer for face fixing. The model creator also suggests a hand-drawn LORA for anime checkpoint users.animebabaraclothingeulafaruzanfischlgenshingenshin impactgenshinimpactgirlshutaojeankamisato ayakakeqingkirara (genshin impact)luminelynettenilouningguangningguang (genshin impact)photorealisticraiden shogunrealisticsangonomiya kokomishenheyae mikoyoimiya

LoRA · SD

DDLC [sd1] Monika + Sayori + Natsuki + Yuri (Doki Doki Literature Club)

064
💌 All the dokis are here in a single small Lora! You can prompt the 4 girls by name as well as their school uniform, but you can use more specific tags if you need. Try putting the girls in different clothes, or putting a different character in the doki uniform. Hope you enjoy it! Works at weight 1. Made using my Lora guide (https://civitai.com/models/22530).animecharactercharacterpackddlcdoki doki literature clubgamegame charactergirlpack

LoRA · SD

Bursting Breasts | Goofy Ai

364
Bursting Breasts is a Lora model. It's designed for image generation and can be used with prompts and tools like Adetailer for faces and upscaling techniques.animebreastsbursting breastscleavageconceptfemalegirlswoman

LoRA · SD

Extended Downblouse | Clothing Lora 281

364
This Lora model is trained on 281 images to generate extended downblouse clothing styles. It can be prompted manually and works with various chest sizes. Key features include generating downblouse and extended downblouse styles on different characters.animeconceptwoman

LoRA · SDXL

0156 bubble bath（sd1.5,pdxl,sdxl）

263
This model, 0156 bubble bath (sd1.5, pdxl, sdxl), creates images of bubble baths that can be applied in various settings. It functions like a piece of clothing for characters and may require disabling breast repair settings. The WildcardX XL detail enhancer can be used to add detail to the soap bubbles.bubble bathclothing

LoRA · NAI

日焼け跡/tanline

063
The strength of Lora is recommended to be around 1.0. It was made with low steps, so it may not be stable. It is intended to leave a one-piece mark.concept

LoRA · IL

sexy details

163
This is a LORA trained on handpicked images of my personal preference. It is heavily nsfw based and enhances detalisation and facial expressions.enhancernsfwstyle

LoRA · Pony

Stealth Fellatio (under table) LoRa | PonyXL & Illustrious

162
This LoRa model generates anime-style images of a girl performing stealth fellatio under a table, optimized for side views. It is trained for PonyXL & Illustrious models and may not perform well with realistic art styles.animeconceptgirlssexywoman

LoRA · Pony

BDSM Cocksleeve - Undercarriage - Monsters (Pony & Illustrious)

062
Ties character to another character to be used as cocksleeve/onahole. For characters tied to centaurs or other 4 legged monsters, Landscape aspect ratio tends to work much better. Check examples for prompts.animebdsmbondageconceptrealisticwoman

LoRA · IL

Pixel Art LoRA [ Noob | IL ]

162
Pixel Art LoRA generates pixel art images, leveraging a multi-stage training process with fused LoRAs for enhanced generalization. It directly produces well-arranged pixel art due to SDXL's 1:8 latent-to-pixel ratio, and can be further refined with nearest-neighbor resampling for strict pixel alignment.animepixelstyle

LoRA · SD

ONArmor / Meat Shield

261
This Lora model generates images featuring a humanoid figure with a "meat shield," often in suggestive poses. It is trained on Anything v3 and activated using the keywords "onarmor," "meat shield," and "fanny packing." The model primarily focuses on the pose, and additional prompts may be needed for explicit actions.bondageconceptfanny packinghentaimeatshieldmonsternsfwonarmorwoman

LoRA · SD

Wedding Dress Extension | Clothing LoRA

361
This LoRA enhances the recognition of wedding dress features in AI models. It focuses on elements like tulle, suspenders, off-shoulder designs, V-necklines, lace patterns, and gemstone/pearl embellishments. The model includes a Champagne variation for specific dress styles.clothingevening dressunderwearweddingwedding dresswoman

LoRA · Pony

セクシーランジェリー/sexy lingerie(SD,ILL,pony)

161
The strength of Lora is recommended to be around 0.6.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.