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 · IL

Rapi (NIKKE) SDXL LoRA [Illustrious] | 4 Outfits

224
This SDXL LoRA generates images of Rapi from GODDESS OF VICTORY: NIKKE in various outfits. The model includes keywords for different versions and attires, such as Red Hood, default, and swimsuit variations. It focuses on replicating her visual characteristics and distinct costumes.animecharactergame charactergoddess of victory: nikkenikkewoman

LoRA · SDXL

[Illust&XL&Pony] iaidou / ready to draw / 居合い / 抜刀術 / シン・陰流簡易領域

124
This LoRA generates images of iaido poses, specifically drawing a sword from its scabbard (battoujutsu). Use the trigger word "iaidou" along with related terms like "katana," "sheathed," and "fighting stance," with a weight around 0.8. Different versions are trained for specific SDXL models like Illustrious-XL, Animagine XL and Pony Diffusion V6 XL, and may not function correctly with other modelsbattoujutsubattoujutsu stancejujutsu kaisenkatanaposesweapon

LoRA · Pony

Instant Loss 2 Koma Pony + Illustrious

024
Like and Follow! Comms always open.2komaconceptinstant loss

LoRA · IL

Cheating/Netorare | Prostitution | Concept version | Illustrious/NoobAI/Pony | Commission

124
This model is designed to generate images related to cheating/netorare and prostitution concepts, potentially improving image quality in these themes. Recommended settings include resolutions of 896x1152 or 1152x896 and a LoRA strength of 0.6-0.8. Use monochrome/greyscale for manga style images.cheating (relationship)conceptfingeringgrabbinggrabbing another's breastgropingimminet seximplied netorarenetorareprostitutionpussy object insertionresigned

LoRA · Hunyuan Video

Exotic Breast Massage (Yet Another Breast Massage Lora for Hunyuan and Wan2.1)

024
This Lora generates images of suggestive breast caressing and massage, designed for use with Hunyuan and Wan2.1 models. It is triggered by the word 'br38st-m8ss8g3' and benefits from prompts like "rubbing breasts" or "caressing breasts." When used with the "Exotic Dancer" Lora, lower strengths may be needed to maintain prompt characteristics.breasteroticmassagenuditystylewoman

LoRA · IL

Before & After corruption, bimbofication LoRa | Illustrious

224
This LoRa model generates anime-style images showing a before and after transformation, specifically corruption or bimbofication. It is designed for use with Illustrious models and utilizes trigger words to control the transformation.before and afterbimbobimboficationconceptcorruption

LoRA · IL

POV Lying on Viewer Handjob/Blowjob + Fingering - PONY / Illustrious

123
This LoRA model is trained to generate images of POV handjobs, blowjobs, and fingering. It has two versions: Pony and Illustrious, each with specific trigger words and prompting styles for generating the desired content. Illustrious is more dynamic and performs best with landscape resolutions.blowjobconceptfingeringhandjobpov

LoRA · IL

食い込み/Wedgie(XL,pony)

123
The strength of Lola is recommended to be around 1.0.concept

LoRA · Pony

Cooperative Paizuri LoRa | PonyXL & Illustrious

023
This LoRa model generates anime-style images depicting a titfuck scene with two girls and one boy. It is optimized for use with PonyXL & Illustrious models and trained to maintain the overall style of artwork while adding the specified subject matter. The model is for NSFW content generation.animeconceptgirlslorapaizurisexytitjobwoman

LoRA · IL

Mating Press Variations - IL&NAI&Pony | Shrekman Hentai Loras

123
The model generates images depicting mating press variations. It features characters from IL&NAI&Pony and includes elements from Shrekman Hentai Loras.concepthentaileglockmating presspornview from above

LoRA · IL

Kuroinu - All girls in one model! - Olga Discordia, Celestine Lucross, Alicia Arcturus, Chloe, Claudia Levantine, Kaguya, Luu Luu, Maia, Prim Fiorire

223
This model allows users to generate images of nine characters from Kuroinu. It includes an updated V2 version with improved training and dataset adjustments. Use the keyword "uncensored" to avoid mosaics.alicia arcturuscelestine lucrosscharacterchloeclaudia levantinekaguyakuroinuluu luumaiaolga discordiaprim fiorire

LoRA · IL

[Illustrious, SD1.5] Kirigaya Suguha 桐ヶ谷直葉 / Sword Art Online

123
This LoRA allows generating images of Kirigaya Suguha from Sword Art Online. It is designed for use with Illustrious SDXL checkpoints and a weight of 0.9~1 is recommended. The LoRA supports generating the character in various outfits, specified by tags.animeanime characteranime girlcharacterkirigaya suguhalorasword art online

LoRA · IL

NEW ANIME CORE - ILL - FLUX

022
NewAnimeCore is an anime LoRA designed to generate anime characters in a 3D-like fantasy and magic style, offering two variations: ILL for high magical energy and FLUX trained on anime character images. Both versions recommend a LoRA strength of 0.7-0.8 and share the "NewAnimeCore" trigger, with FLUX additionally using "Anime."concept

LoRA · IL

Street Fighter III / Pixel Art - (Retro Video Game) - STYLE - | Illustrious XL | - COMMISSION by YeiyeiArt

022
This model generates pixel art in the style of Street Fighter III. It was trained using high-quality images of the game's official sprites. Use the trigger word "SF3XL" and add prompts like "full body, fighting stance, from side" for optimal results.animeart stylescartoonfantasygame characterlorapixel artretrostylestylesvideo game

LoRA · IL

アナル舐め/anilingus(ill,pony)

022
The strength of Lora is recommended to be around 0.6.concept

LoRA · Pony

雌犬ポーズ/paw pose

122
The recommended Lola strength is around 1.0.poses

LoRA · Pony

Standing Doggystyle From Side - Concept

022
This model generates images of a "standing doggystyle from side" concept. Key features include the doggystyle pose, side view, and elements such as "ass ripple" and "hanging breasts." Trigger words are provided to influence the generated image.concept

LoRA · Flux.1 D

Flux Detailer

022
Flux Detailer enhances images with improved lighting, shadows, and colors. Version 1 can be used with or without a trigger, while Version 2 requires a trigger and stays closer to the original image. The model was trained on 385 images.detailerlorastylestyles

LoRA · Pony

Lesbian anal strap-on

022
Illustrious Version:Strength: 0.6-0.9 Trigger: Same as Pony Pony Version:Strength: 0.3-0.7 Trigger: lestraabed, yuri, on bed, sex, 2girls, strap-on, anal, moaning Optional: nudeanalbedconceptlesbianmoaningsexstrap-on

LoRA · SDXL

Escher Blend

022
EscherBlend is a model inspired by M.C. Escher's art, designed to generate optical illusions and impossible geometries. It allows artists to explore Escher's style and create mesmerizing, thought-provoking visuals, facilitating experimentation with Escher-like artwork.escherstylestyle art

LoRA · IL

Paizuri under clothes | LoRA

122
Trigger word: paizuri under clothes, penis, pov Weight: ~0.7-1 Enjoy! If you like the model, I'd appreciate your review. Also, feel free to share your creations, I really like seeing everyone's results! :)animeconcepthentainsfwpaizuriporn

LoRA · Pony

Tits Out Bounce XL

122
This model generates anime-style images of bouncing breasts resulting from a wardrobe malfunction. It's trained on PonyXL and responds to trigger words like "tits out bounce" along with tags for assisted exposure, clothing manipulation, and motion effects. Use a strength of ~1 for optimal results.bouncing breastsclothes pullconceptwardrobe malfunction

LoRA · SD

Murky's Cheek Bulge Fellatio LoRA

722
This LoRA enhances the "Cheek Bulge Fellatio" concept in images. Prompts such as fellatio, oral, and saliva may be needed to achieve the desired effect, with LoRA strength adjustable between 0.8 and 1.2. It was trained using 120 images.animeblowjobcharacterfellatiohentaisexual activitysexy

LoRA · NAI

婦警/female police(XL,ILL,pony)

122
The strength of Lora is recommended to be around 0.8clothing
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.