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

detaILeReij

1284
detaILeReij is a detailer model for images, enhancing them with artistic details. V2 adds more artistic flair at higher strengths, staging prompt settings like colors and lighting, while V1 adds subtle details up to strength 0.8 and becomes more creative from 0.9-1. It can be used without a trigger word, but "detailed" or "detailing" in the prompt can help.detailerilillustriouslorastylstyle

LoRA · Wan Video 2.2 I2V-A14B

Deepthroat, Blowjob - Wan 2.X I2V & T2V

19283
extblowjobconceptdeepthroatfellatioi2vimage to videooralt2v

LoRA · Pony

Hyper Breasts LoRa | PonyXL & Illustrious

1282
This LoRa model is trained to enhance breasts in anime-style images generated with PonyXL & Illustrious. It is triggered by specific keywords and is optimized for the aforementioned models; results with realistic images may vary.animebreastsconceptgirlssexywoman

LoRA · IL

Sinozick | Shiiro's Styles | Niji

3281
Sinozick is a style model that generates illustrations with gradient and spot color effects. It is triggered using the words "Sinozick_illu, gradient, spot color" with a weight between 0.1 and 1. Recommended samplers include DPM++ 2M Karras and Euler a, with CFG Scale ranging from 1 to 7, and a Clip Skip value of 2.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman

LoRA · Pony

Amateur Style - RawCam slider

1278
The RawCam slider adds a nostalgic, unpolished aesthetic to images, emulating film grain and amateur photography. It introduces character, warmth, and subtle imperfections without artificial gloss, and its intensity can be adjusted using a slider. The model may produce freckles and selfies, which can be mitigated with negative prompts.2000amateuramateur styleanalogbrightcamcorderconceptdisposable cameraflashflash photographygirlsinstainstagramnaturalnoiseoverexposurerawrawfullyselfieslidervsco

LoRA · SD

Elixir — Enhancer LoRA 🧪

1276
Elixir is a LoRA designed to enhance older models with renewed vitality and provide subtle improvements to newer ones. Created using the NinjaFix algorithm, it blends neurons from various neural networks to form a refined LoRA. It refines noise, lighting, styles, textures, details, and other elements.cinematicepicfashionillustrationmasterpiecephotorealisticstylestyleswoman

LoRA · Pony

Perfect Ass Slider - PONY

2274
This slider enhances the roundness and thickness of the female posterior in SDXL models. It offers precise control in 0.10 increments, avoids impacting male characters, breast size, or age, and requires no activation prompt. Results are strongest when used with relevant lower body tags.animebootybuttgirlshourglassillustriouxlponyxlsexysliderstylethickwoman

LoRA · IL

rizdraws style LoRA for PonyXL/Illustrious

0274
Will remove if requestedanimeartistsponyxlstyle

LoRA · SDXL

Finenude

3273
Finenude is a LoRA model, specifically trained to generate images of nude women. It's trained on a large dataset of high-quality photos, but the initial version is a proof-of-concept and improvements are planned, including dataset filtering and captioning. Future development aims to include male photos and improve anatomical accuracy.characterfemalensfwphotorealismphotorealisticsdxl

LoRA · IL

96yottea | Style LoRa

2272
This Style LoRa generates images in the style of 96yottea illustrations. Use a weight between 0.1 and 1, triggering with "69yottea_style_illu", and experiment with DPM++ 2M Karras or Euler a samplers.animecartoongamegame charactergirlsilluloramalemanpaintingphotorealisticrealisticstylestylesvideo gamewoman

LoRA · SD

Riding Sex Scene [SMF]

3271
This model generates explicit sexual content, intended for use with realistic checkpoints. It is recommended to use weights between 0.5 and 0.9 when mixing it with other LoRAs, and it works best with resolutions like 512x712 and 712x512.femalegirlsphotorealisticposeposesrealisticscenesex actsex posesexywoman

LoRA · Pony

Double Penetration LoRa | PonyXL & Illustrious

2270
This LoRa model generates anime-style artwork featuring double penetration. It is optimized for PonyXL & Illustrious models and designed to maintain the overall style of the artwork while reliably depicting the intended subject.animeconceptconceptsnsfwwoman

LoRA · SD

Pika's Super Realistic Detailed Eyes [SRDE]

0267
Hi everyone! This LORA takes ultra realistic macro photos of human eyes! You can use it directly in Prompt to take macro photos of eyes, or you can use it in inpaint. Share your generations, I will try to improve this LORA as I'm very interested in it!conceptconcept loraphotorealisticrealistic

LoRA · IL

Taretiti (sagging breasts) / 垂れ乳

3267
Taretiti are boobs that sag due to gravity!animeboobsconceptgigantic breastshentainagatiti

LoRA · IL

Sakimi Chan Style (Pony/Illustrious/FLUX)

2263
This Style-LoRA model replicates the art style of Sakimi Chan. It offers Pony, FLUX, and Illustrious versions, each with recommended weights and specific features like improved colors or tagless training. The model is optimized for resolutions around 1280x980 and often benefits from positive prompts to enhance detail and quality.animegame charactergirlslorasexystylewoman

LoRA · Flux.1 D

Xpenis Uncut Flux

1262
This is a flux model trained to generate images at resolutions like 1216x832, 832x1216, and 1536x1024. It is designed for realistic outputs and flexible generation, including chimera.concepterectionflaccidgayhomoeroticmalemannakednaked gaynudepenisphotorealisticpornuncut

LoRA · SD

Valbun Style

1262
The style of Valbun, a popular Mexican comic artist. If you like this style, please support the original artist!stylestylesvalbun

LoRA · Pony

Feminine body proportions slider/enhancer | Wider hips, narrow petite shoulders, softer hourglass or pear body shape

3261
This model enhances feminine body proportions, creating wider hips and narrower shoulders. It aims for softer hourglass or pear-shaped figures and can be activated with specific prompts to control the effect. It has been retrained and updated to improve quality, responsiveness, and compatibility with other LORAs.girlsponyxlsexystylewoman

LoRA · SD

Revealing dress

2261
This model generates images of characters wearing revealing dresses in various colors. It supports color-specific tags like "silver dress" or "red dress", which can be combined. Bonus characters from the training data may also appear.animecleavageclothesclothingcosplaydressfemalegirlsoutfitrealisticrevealing clothes

LoRA · SDXL

Breasts Out fashion clothing | 敞开胸怀时尚风格

3259
This model generates images of women's fashion, specifically clothing designed to reveal the chest area. It uses trigger words and descriptions of clothing and occupation to manipulate the image, creating strategic cutouts. The model aims to promote confidence and body positivity by celebrating freedom and empowerment.boobsbreast slipbreastsclothesconceptflashingsexywoman

LoRA · IL

MrPotatoParty [Illustrious] Style Lora

3259
MrPotatoParty [Illustrious] Style Lora generates images in a specific artistic style. Use trigger words "ytrprm" or "mrporty" and strength 1.0 for optimal results.animecartoonfemboyfurryfutafutanarigame charactergirlshentailoramalemanmr potato partymrpotatopartystylevideo gamevideogamewestern artwoman

LoRA · ZImageTurbo

NiceGirls UltraReal

19257
NiceGirls UltraReal is a model focused on generating images of realistic beauty, particularly of Asian women in the Z-Image edition. A Qwen version is also available for cleaner results, and it can be blended with other LoRAs typically using a weight around 0.6.beautycharacterphotorealistic

LoRA · Flux.1 D

Disney Renaissance Style

2255
This model generates images in the style of Disney Renaissance films (e.g., The Little Mermaid, Aladdin). It focuses primarily on replicating the visual style and characters from these movies, using specific tags for each film and character. The main tag is "DisneyRenstyle."disneyretrostyle

LoRA · Pony

Slimy / Fluid / Wet control

1255
This model generates a wet or clear liquid effect, allowing for "suggestive fluid" visuals instead of just "wet" or "cum" depictions. It's controlled via the "slimy [target]" tag, targeting specific body areas or objects, and can be refined with negative prompts like "wet".ambiguous fluidconceptcumdrippingfluidjuiceliquidpussy juicesexually suggestiveslimeslimystickysuggestive fluidwetwet panties
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.