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 · SDXL

Dark Fantasy Art

022
💀 Trigger word is: dark fantasyA lightweight LoRA to help boost the gothic/dark art style.dark artgothgothic artstyle

LoRA · Wan Video

creampie (nakadashi/cum inside) concept WAN2.1 I2V

522
This model, a creampie concept WAN2.1 I2V, generates images involving vaginal penetration. It focuses on accurately depicting scenes of cum dripping from a vagina, although penis depiction may require prompt adjustments. It aims to improve text-to-video generation by understanding female anatomy better.conceptnsfwsex

LoRA · IL

Realisic Panties (Highly Detailed Panties) LoRA

021
女の子のパンツを花柄のレース付きのリアルな質感にします。 • トリガーワード: panties • 推奨重み: 0.4~1.0 -------------------------------------------------- This LoRA transforms a girl's panties into a realistic texture with floral lace details. • Trigger word: panties • Recommended weight: 0.4~1.0clothinglingeriepantiesunderwear

LoRA · IL

double handjob + paizuri (illustrious, pony)

121
lora for paizuri with double handjob,conceptdouble handjobpaizuri

LoRA · Flux.1 D

Nipples FLUX

221
Nipples FLUX is a model designed to enhance lewd image generation capabilities, focusing on realistic representation of nipples in various shapes and colors. It aims to improve realism, representation, and special flavors in generated images. Future versions will expand to include diverse nipple types.breastsconceptnipplesnsfwnudessexywoman

LoRA · Wan Video 2.2 I2V-A14B

Doggy slider T2V I2V Wan2.2 Video LoRa

1K21
This LoRa model is designed for generating videos of explicit sexual acts, primarily focusing on a doggy-style position. It can be used for both text-to-video (T2V) and image-to-video (I2V) generation, with square output resolutions recommended for better results. The model utilizes camera zoom effects to reveal the scene.conceptdoggydoggystylesexslider

LoRA · NAI

[costume]color changable Bodystocking/可换色连身丝袜 For SD1.5 pony & Illustrious

121
This model generates color-changeable bodystockings for SD1.5, Pony, and Illustrious characters. It allows users to specify the bodystocking color via prompts and suggests negative prompts to control unwanted clothing or NSFW elements. The Illustrious & Pony version does not have the shirt problem that SD1.5 has.bodystockingbodysuitclothingoutfitpantyhoseskin tight

LoRA · WAN_2_2_A14B_LOW_NOISE

Cumsh0t - LocalOptima

021
This is a pair of LoRAs trained on the WAN 2.2 I2V 14B low and high noise models. Together, these LoRAs model a mostly facial cumshot. The man doesn't have to be present in the first frame. Trigger Phrase: A man cums on her I recommend using a CFG of ~3.5 for high-noise sampling and 5-7 for low noise sampling. The examples in the showcase were generated using a constant CFG of 3.5 and 7 for the high and low noise sampling steps, respectively, 24 total sampling steps, a split step of 3, and a shift of 5 for both samplers. My full workflow is available on my Patreon . I noticed while I was generating samples that the cumshots appear to be bigger if the man is already in frame with his hand on his penis and the generated video has an aspect ratio close to 16:9. I think this quirk arises due to the nature of the dataset. If you like this model and want to support the creation of future models, please support my work by leaving positive reviews or posting your generations to the model page.

LoRA · SD

【Concept】Better Hair Censor 更好的头发遮胸

221
Checkpoints can not draw hair censor well so I made this lora. 大模型画不好头发遮胸所以我做了这个lora。 "topless" or "nude" is suggested to choose one to use if you want the character to wear certain clothes meanwhile. 如果你想要让角色同时还穿着特定的衣服建议配上topless或nude。 Can be viewed from behind/side. 可以从后面和侧边看。animeclothesconceptconcept artexposed clothingsexy

LoRA · Pony

Bowlegged Pose | Goofy Ai

121
This model generates images of bowlegged poses. Key features include prompts provided in the images, usage guidance like Lora strength (0.7-1) and ADetailer for faces, and recommendations for upscaling. It also encourages user feedback and requests.animebowlegged poseconceptgirlssexywoman

LoRA · SD

【Character】Celestine Lucullus

321
This LORA model generates images of Celestine Lucullus from Kuroinu. It performs best with 784mb VAEs and weights between 0.6 and 0.8, and benefits from use alongside an olga discordia LORA for high-quality NSFW results.animecharactergirls

LoRA · SDXL

sailor boys sd xl

021
Sailor Boys SD XL is a model created for testing SD XL LoRA functionalities. It performs best at resolutions such as 915x1144 and 886x1182, and at a strength of 0.8-1 in Blue Pencil SD XL lineups, with negative embeddings significantly improving output quality. The model was trained on 99 images and user feedback is appreciated.animecharactersailorsailor boyセーラーセーラー 男の子

LoRA · Pony

Cam Show (viewer perspective)

021
Illustrious Version:Strength: 0.5-0.8 Trigger: cagivp, livestream, chat log, user interface, sexually suggestive, gaming chair For more triggers, check out the cover images Pony Version:Strength: 0.7-1.1 Trigger: Same as Illustriousanimecam girlcam showconceptconceptsfingeringgirlslingerielivestreampornsexyundress

LoRA · Wan Video 2.2 I2V-A14B

(wan 2.2 experimental) WAN General NSFW model

1421
conceptnsfwsexvideowan

LoRA · Flux.1 D

FLUX_NSFW_Blowjob_FUCK_rimjob_Sevenof9

821
FLUX_NSFW_Blowjob_FUCK_rimjob_Sevenof9 is a model trained on handpicked, watermark-free images focused on specific adult themes. Optimal results are achieved around 25 steps using EULER with DDIM or SGM Uniform/Beta samplers, and it's suggested to increase resolution for noise reduction. The model provides various adult orientated poses, it's recommended users experiment with prompts and CFG values for ideal results.analblowjobcowgirlflux.1loramissionarynakednsfwnudeposespovpov bjrimjobside view

LoRA · Pony

Over The Edge Blowjob

120
This model appears to be a LoRA trained to generate images, possibly with a specific artistic style. The description contains a recipe for Old-Fashioned Sour Cream Doughnuts and a political statement against certain AI platforms and the Chinese government.blowjobposesupside down

LoRA · IL

Penis on Cheek LoRa | PonyXL & Illustrious

120
This LoRa model generates anime-style images featuring a penis playfully poking a girl's cheek. It's optimized for PonyXL and Illustrious models and uses trigger words to activate the specific action.animecheekconceptgirlswoman

LoRA · SD

[Experimental] Velociraptor (Dinosaur)

020
This Lora model generates images of Velociraptors, but may produce artifacts like bad hands or extra limbs. Use a weight of 0.7 and the trigger word "Velociraptor_Dino" for optimal results.animalanimalsdinodinosaurraptorvelociraptor

LoRA · SD

Non-humans (Concept)

120
This LoRA model generates images of various non-human species, including animals, creatures, monsters, and Pokemon, addressing the limitations of anime models in creating coherent, non-humanoid depictions. It was trained using the animefull-final-pruned checkpoint and is designed for use with anime-style models, using tags from e621 for prompting.animalanimecartooncutefantasyfurryhentaimonsterpokemonsanrio

LoRA · SD

Pinkie Pie | My Little Pony / Equestria Girls

020
This model generates images of Pinkie Pie from My Little Pony/Equestria Girls. Use the trigger word "mlppinkiepie" with a weight of 1.0. You may need to add "pink hair" and "blue eyes" for accurate results.characterequestria girlsmy little ponypinkie piewestern animation

LoRA · SD

Makoto Shinkai (Your Name + substyles) Style LoRA

320
This LoRA generates images in the style of Makoto Shinkai, triggered by "shinkai makoto." It includes substyles for Your Name ("kimi no na wa."), Weathering With You ("tenki no ko"), and The Garden of Words ("kotonoha no niwa"). It works best on AnyLoRA at 1 weight and is not a character-specific model.animeart styleartistartstylecutedigital illustrationfemalegirlshighly detailedillustrationmakoto shinkaimalemoviestylewoman

LoRA · Wan Video 14B i2v 720p

Bouncing Boobs - Wan 14B

619
This Lora model is designed to animate bouncing breasts using the Wan model. It was trained on short videos of breast movement with faces removed, using I2V-14B-720P as a base and Musubi-Tuner for training.boobsbouncingconcept

LoRA · SD

hanfu 汉服

1119
This model generates images of Hanfu, traditional Chinese clothing. It supports multiple styles based on different dynasties including Han, Tang, Song, Ming, and Jin. The model allows users to create images with specific Hanfu styles using corresponding tags.clothinghanfuhanstylejinstylemingstylesongstyletangstyle

LoRA · IL

Hentai Comic Random Generator (LastPage) (FinalPage) / Pony IL XL | エロ漫画ランダムジェネレーター（最終ページ）

119
This LORA specializes in generating last pages of hentai comics, specifically the climax and ending panels. It's designed for creating complete comic packages and works best with a width of 832 and height of 1216. Example prompts are provided to guide usage and can be combined with character LORAs with adjusted strengths.analanimeanuscomicconceptfellatiogangbanggirlsgroup sexhentaimasturbationnsfworalpornvaginawoman
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.