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 · Pony

CAT SS - Citron Secret Styles [Illustrious & NoobAI & Flux & Pony]

1135
Help fuel my passion! Even $1 makes a difference. ☕ https://ko-fi.com/citronlegacy Check out all the Art styles I’ve made: https://civitai.com/user/CitronLegacy/models?tag=style (https://civitai.com/user/CitronLegacy/models?tag=style)animeillustriousillustrious styleillustriousxlpony stylesexyspicystylestyleswomen

LoRA · SD

HD Horizon: The Resolution Frontier (Multi-Resolution / High Resolution Native Inferencing)

0135
HD Horizon enables multi-resolution image inferencing, ranging from 256x to 1536x. It achieves high-resolution inferencing natively, producing sharper images without needing extra fixes. This allows for detailed and clear digital imagery with fewer resolution limitations.resolutiontool

LoRA · Pony

Pepe (Jonasan) Style| Goofy Ai

1135
This model, named Pepe (Jonasan) Style| Goofy Ai, is inspired by the artist Jonasan. It generates images in a specific style that can be achieved by using the lora at 0.7-1 and ADetailer for faces. It is recommended to use Img2img upscale with 4x-ultra sharp for best results.animegirlslorasexystylestyleswoman

LoRA · SD

Undersized Bra (Outfit/Concept) LoRA

1134
This LoRA generates images featuring undersized bras. It is triggered by "undersized bra" and emphasizes large breasts with related features like cleavage and skin indentation. It offers options for both clothed and nude variations.animebrabreastsclothingfemalegame characterundersized clothesunderwearvideo gamewoman

LoRA · IL

rakugakingu

1134
Although the preview image may not show it, this LoRA is based on Katsuya Terada's LttP artwork. I always like to try to create preview pictures with empty prompts to see what the AI was taught, but of course there is a bias towards female characters. Feel free to experiment and create dark fantasy images. I would love to see your results.style

LoRA · SDXL

[XL + 1.5] Eyeshadow / Eyeliner / Freckles Enhancer

1134
This model enhances eyeliner, eyeshadow, freckles, and glitter effects in images. It includes an XL version (LoRA, 12 blocks) and a 1.5 version (LyCORIS, 27 blocks), and works best with the "EGirlMakeup" prompt along with specific keywords for each effect. The XL version is recommended for use with AlbedoBaseXL.charactereyelinerfacemakeup

LoRA · Pony

Breast Squeeze

1134
This LoRA model generates images of women squeezing their breasts together, primarily focusing on solo female subjects with medium to large breast sizes. It aims for consistent clothed/unclothed generation and improved hand quality, with ongoing development for varied breast sizes and squish levels.breast squeezebreasts squeezed togetherconceptdeep skingigantic breastsgrabbing breastsgrabbing own breasthuge breastslarge breasts

LoRA · Pony

Reverse upright straddle / sitting on lap

5134
This model generates images of a reverse upright straddle pose, typically featuring a character sitting on a lap. Key features include options for legs together or spread legs, and it is optimized for anime-style outputs. Recommended tags are provided for quality and negative tags for undesired elements.cowgirlhentaipornposeposesreverse upright straddlesexsex actsitting on lapstraddle

LoRA · Pony

Dragon Ball Style

1134
This model captures the art style of the original Dragon Ball anime. It was trained on early episodes and requires the activation tag "drgnbll" to function effectively. The model aims to replicate the style rather than specific characters.akira toriyamadragon ballstyle

LoRA · SD

EroPose - All fours

2132
EroPose - All fours is a Lora model that generates images of characters in the "all fours" pose, viewed from behind, using the trigger words "all fours, from behind." It may require specific face prompts to alter the default generated face. It works well with a recommended image ratio of 3:4, 3:2, 1:1, 2:3, and 3:4.all foursassposessexy

LoRA · SD

Urban Samurai | v0.14 | Clothing LoRA

5131
Urban Samurai LoRA dresses characters in Techwear style clothing suitable for 2D, 2.5D, and live-action models, and full body figures. Key prompts include "urbansamurai" and "techwear," while negative prompts should include "((mask))". It supports tags like "techwear jacket," "black cap and mask," and "tactical vest."clothingtechwear

LoRA · Pony

Doggystyle | All angles | Doggystyle sex

2130
Doggystyle | All angles | Doggystyle sex Trigger word: Palidoggy Suggest strength: 0.5-1 Front view: (frontal, from the front) Back view: (male POV, his POV) Side view: This is the most common, shouldn't need extra promptsanimeconceptdoggy styledoggystlegirlsheterolorapenetrationsexsexywoman

LoRA · IL

Zootopia_Art_Style (ALL IN ONE) 2D&3D [Illustrious]

1130
This LoRA applies the Zootopia art style to characters, drawing inspiration from characters like Judy Hopps and Nick Wilde. It allows users to imbue any character design with Zootopia's visual aesthetic in both 2D and 3D.animeanthrodisneyfoxfurryhentaijudy hoppsnick wildepolicerabbitstylezootopia

LoRA · Pony

Backless Panties - Pony | Goofy Ai

2129
This model generates images of backless panties. It is recommended to use a Lora weight of 1, Highres fix, and Adetailer for improved faces and resolution.animeanusbacklessclothinggirlspantieswoman

Checkpoint · SD

Clarity

11129
Clarity is a Stable Diffusion fine-tune for generating photorealistic images with an emphasis on human anatomy, capable of producing both NSFW and SFW content based on prompt tags. It uses a fine-tuned base model for realistic skin textures, improved fabric details, and enhanced lighting/shading.base modelckptfantasyfemalegame charactergeneral purposehardcoreinpaintingmennudespersonphotographyphotorealisticportraitsrealisticsexyvideo gamewoman

LoRA · IL

JAV HARD BDSM Generator (bondage wall ) Pony / IL XL | 拘束少女快楽拷問 アダルト ビデオ ジェネレーター

1128
This LORA model is designed to generate hentai anime based on JAV (Japanese Adult Video) content, specifically focusing on "bondage wall" scenes. It allows users to create images with a desired anime character within the learned BDSM context, but requires adjustments to negative prompts to avoid photorealistic outputs. The model captures restraints, character positions, and potentially explicit acts.animebdsmbondageconceptgirlsnsfworalpornsexvaginawoman

LoRA · SD

Oral sex - Sitting Blowjob LORA 👑

3127
This LORA model generates images of oral sex being performed in a sitting position. It is based on SD1.5 and uses the trigger word "oralsidesitQuiron". ADetailer with face_yolov8n.pt is recommended for face enhancement.blowjobcockconceptfellatiohardcorensfworalpenisphotophotorealisicpornrealisticwoman

LoRA · Pony

Mavis Dracula PonyDiffusionXL/illustriousXL

2127
Mavis Dracula PonyDiffusionXL/illustriousXL is a LoRA model for generating images of Mavis Dracula from the "Hotel Transylvania" series. It's recommended to use prompts like "m_d, 1girl, vampire, black hair, blue eyes, goth makeup" with a weight of 0.6-0.8 and the Fantasy Blend XL or Pony Diffusion XL models.charactergame charactergirlssexyvideo gamewoman

LoRA · SD

Gothic Punk Girl

2126
V.2 More flexible but you have to make sure to describe or put something about goth to trigger it. Less detail than V.1 weight recommend : 0.7 If you love My Model and want to support my workclothesclothingfashionfashion designgoth girlgothicgothic lolitagothicgirlpunkwoman

LoRA · IL

Pantyhose Enhancer/Fine Fabric (Illustrious)

0125
This model is intended to enhance images with fine fabric Trained on Illustrious V0.1 Tag: finefabricILL, fine fabric • Helpful tags: pantyhose, shiny pantyhose, textured pantyhose, high detail texture,conceptfabricfine fabricpantyhosetexture

LoRA · IL

mon (monmon2133) style | Illustrious [Commission]

1124
This model replicates the art style of MON (monmon2133). It was trained on WAI-IL-V7 and is best used with specific samplers, schedulers, and CFG values, ideally with hires fix enabled. Recommended Lora Weight 0.8-1.0.aestheticanimegirlshorrorstyletheme

LoRA · IL

乳首挿入/nipples fuck(pony)

0124
Lora strength of 1.0 or higher is recommended.concept

LoRA · SDXL

Big Breasts By Stable Yogi

0124
This model is designed to generate images of characters with large breasts. It requires specific positive and negative embeddings for optimal results. Refer to the provided comparison images to understand the difference when using the recommended embeddings.animebreastsconceptlarge breastsloraphotorealisticrealisticsexywoman

LoRA · SD

pose selfie

1124
A selfie LoRa, can make the effect of selfie in front of the mirror more stable effect, the current test generalization is good, you can copy the preview image tag magic change play, happy to use, welcome back to the picture 一个自拍的lora，可以让对着镜子自拍的效果更加稳定的出效果，目前测试泛化良好，可以抄写预览图tag魔改游玩，使用愉快，欢迎返图action
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.