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 · ZImageTurbo

[Z Image Turbo] Asian Mix Lora - EOL

3865K
The Z Image Turbo Asian Mix Lora is designed to enhance Asian image generation. It was trained on various datasets to improve details, lighting, body poses, and background representation, with adjustments for NSFW content. Recommended weight is 0.6-0.8.asianasian womanconceptwoman

Checkpoint · SDXL

LUSTIFY! [SDXL NSFW checkpoint]

184.8K
LUSTIFY! is a photorealistic SDXL checkpoint for generating images of women in sexual scenarios, trained to understand both danbooru tags and natural language prompts. It can also create SFW images if the NSFW bias is overcome. It is recommended to use specific samplers, schedulers, and CFG values for optimal results, and is not Pony or Illustrious based.base modelblowjobcheckpointdoggystylegeneral usegirlsnsfwphotophotorealisicpornsexsexywoman

LoRA · Pony

Takeda Hiromitsu style (illustrious/Pony/1.5) | Goofy Ai

104.8K
This model, named Takeda Hiromitsu style (illustrious/Pony/1.5), is hosted on Tensor.art. It can be used to generate images in the style of Takeda Hiromitsu. Use a Lora between 0.7 and 1 and Adetailer for faces to improve results.animehentaihentai stylemanga art styleportraitsrealisticstyletakeda hiromitsuvideo game

LoRA · SD

Feet XL + SD 1.5 + FLUX.1-dev + Pony + Illustrious

74.6K
The Feet XL model is trained on base model xl 1.0 with FLUX.1-dev and incorporates SD 1.5 enhancements. It also includes Pony and Illustrious versions, offering a range of stylistic outputs.assetsbodyfeetfemalefluxfootillustriouslegslegs uploraphotographyphotorealisticponyrealrealismrealisticsexytoeswomanxl

LoRA · NAI

Pony: People's Works v1-v6

84.6K
Pony: People's Works is a style LoCon trained on pony-based model images from Civitai, aiming to reflect community taste and visually appealing artwork rather than a specific artist style. It does not have specific trigger words for versions before V2, but V3 and later versions use positive tags like "masterpiece, best quality, very aesthetic" and negative tags like "worst quality, low quality, displeasing". The dataset has expanded over versions, with adjustments to tags and image selections to improve output quality and address issues like unwanted artifacts.animestyle

LoRA · Pony

Detail Slider LoRA | PonyXL SDXL

84.6K
This Detail Slider LoRA for PonyXL SDXL enhances image detail, particularly in backgrounds and scenery. It aims to be versatile across prompts without significantly altering the subject of the image. Recommended weighting is typically between 2 and 4.animebackgroundponyxlshedtheskinslider

LoRA · SDXL

Sinfully Stylish (dramatic lighting)

94.4K
Sinfully Stylish is a model designed to create dramatic, candlelight-like lighting with low-placed lights and long, warm shadows. It aims to enhance images with a stylish aesthetic suitable for various applications. The model has undergone several updates to improve its flexibility and performance.dramatic lightdramatic lightinghot soft lightlong shadowsmoodysinfully stylishsoft lightstylewarm light

LoRA · SDXL

DetailedEyes_XL

74.3K
use 0 images for finetune XLbase，should fit any XL model(even anime) add detailed eyes、detailed face and detailed skin including neg part and fixed bad hands Less effect over 75 tokensdetailed eyeseyestool

Checkpoint · IL

Mistoon_Anime

254.3K
Mistoon_Anime is a Stable Diffusion model blend designed to create cartoony anime-style images with thick borders and brighter colors. It's geared towards generating girl portraits, but newer versions can also create convincing male characters, and it supports both SFW and NSFW content. The model aims for a modern, colorful 2D anime aesthetic, producing realistic and expressive characters.animebase modelcartooncolorful

LoRA · Pony

Ass Size Slider - Pony / Illustrious

124.2K
New and custom content here: https://aicollective.ghost.io/ (https://aicollective.ghost.io/) Infinite Ass size control with this slider, can make more or less any size. Minimal picture impact from around 0.1 to 3. If you go lower or higher the image might change. Works for SDXL as well. Hope you enjoy! As always any feedback and submitted images are welcome, thanks :)ass,big assconceptsmall ass

Checkpoint · Wan Video 2.2 I2V-A14B

Smooth Mix Wan 2.2 (I2V/T2V 14B)

84.2K
Smooth Mix Wan 2.2 (I2V/T2V 14B) is a versatile image and text-to-video model based on Wan 2.2 A14B. It generates high-quality images and smooth animations with variety in styles, and is uncensored to allow for NSFW content. While focused on generating female characters, it also responds to prompts like 'SmoothMixAnime' and 'SmoothMixRealism'.base model

LoRA · SDXL

xl_more_art-full / xl_real / Enhancer

94.1K
The LoRa model enhances images to be more aesthetic, artistic, and detailed. It works with SDXL 1.0 and can produce photorealistic, anime, or illustrative styles. It also includes training for aerial photographs using the "Aerial" keyword.3d characteranimalsanimeartcreativedetaildetaileddetailed armordetailed texturedetailerenhancerillustrationlandscapephotorealisicphotorealismrealismrealisticrefinerstyle

Checkpoint · SD

Hardcore Hentai

234.1K
Hardcore Hentai is a model designed to generate high-quality hentai images that accurately follow prompts. It uses danbooru tags or sentence-based prompts, and achieves good results with a 1024x1024 resolution. Key features include strong prompt adherence and high-quality image generation for artistic and explicit content.animeartbase modelfemalegame charactergirlshardcorehentaiillustrationnsfwpornportraitssexsexywoman

LoRA · Pony

Hyper Girls

54.1K
Hyper Girls is a LoRA model focused on generating images of women with varying sizes and combinations of asses, thighs, bellies, and breasts. It relies heavily on specific tagging and canvas orientation for accurate results with larger sizes. The model is continuously being updated to improve consistency, face generation at larger sizes, and the functionality of various modifier tags.colossal asscolossal bellycolossal breastscolossal thighsconceptexpansiongigantic assgigantic bellygigantic breastsgigantic thighshuge asshuge bellyhuge breastshuge thighshyperhyper asshyper bellyhyper breastshyper thighsinflationpregnantshortstackstuffed belly

LoRA · IL

ExpressiveH V2 (Illustrious) エロアニメ

74K
Test of ExpressiveH for Illustrious Just testing something, updates coming soonanimeexpressivehsexystyle

LoRA · ZImageTurbo

Amateur nudes - FLUX, Wan 2.2, ZIT, (ZIB)

814K
This model generates amateur nude images, including selfies. Different versions are trained on various bases (Z-Image, ZIT, WAN) to improve genitalia accuracy, reduce cinematic color, and enhance compatibility with other LoRAs, though anatomy may not be perfect. It understands concepts like "nude selfie" and body shapes, but prompt following for body sizes is limited.conceptflux1.dnudesexywan2.2z image turbo

LoRA · IL

iwao style LoRA for PonyXL/Illustrious

73.9K
Will remove if requestedanimeartistsponyxlstyle

Checkpoint · IL

Plant Milk 🌿 - Model Suite

123.9K
Plant Milk is a multi-series model suite hosting various styles based on illustrious/noob model merges. It offers different 'flavors,' some of which are more Lora-heavy. It is recommended to use Euler or Euler a sampler with 3 cfg and ~28 steps.animebase modelboysgirlsplant milkstyled

LoRA · Pony

Pony Realism Slider

83.9K
The Pony Realism Detail Slider enhances image quality and realism in SDXL models by improving clarity, texture, and detail. It offers fine-tuned control over detail enhancements without requiring a specific activation prompt. The slider works best between +1.0 and +3.0 for clean, natural upgrades, while specific prompts may be needed for intricate details like eyes and teeth.add detaildetail enhancingdetailedenhancergirlsphotophotorealismphotorealisticrealrealisticskin detailsliderstylewoman

Checkpoint · SD

AnyLoRA - Checkpoint

193.8K
AnyLoRA is a model designed to ensure LoRA training compatibility with newer models, providing a style-neutral base for accurate style representation. It excels at training and inference, especially with anime styles, and consumes little VRAM; use pruned versions for training. It is recommended to use CLIP skip 2 and booru style tags when training, along with a good VAE for optimal image saturation.animeanyloraart stylebase modelbeautifulfemalegirlsillustrationmangasexywoman

LoRA · Pony

Cutesexyrobutts Style

143.7K
The Cutesexyrobutts Style model generates images in a distinctive art style. Key features include a focus on pastel colors and flexibility with Lora weights, with high-resolution fixes highly recommended.animeart styleembeddingfantasyfemalegame charactergirlsillustrationnudespersonphotorealisticpornportraitsrealisticsexystylevideo gamewoman

LoRA · IL

748cm | Style for Illustrious/NoobAI 0.75

83.7K
It works.animecutegirlsstylewoman

LoRA · SDXL

Midjourney mimic

63.7K
MJ52_v2.0 is a LoRa model that mimics the Midjourney style. Version 1.2 enhances color, background depth, and composition, while version 2.0 adds micro details. It is recommended to use both versions together, adjusting their weights for optimal results.midjourney v5midjourney v6style

LoRA · Pony

Pony Detail Tweaker

43.7K
The Pony Detail Tweaker model enhances image details like intricate lines and shading. It functions as a realism LoRA, increasing feature complexity at higher weights with minimal impact on composition. It allows controlled detail alteration and can achieve higher detail levels than prompt weighting alone.conceptdetailslider
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.