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

Hug/kissing/breast press pov [remake]

339
This LoRA model generates POV images of hugging and kissing scenes. It offers customization options for kiss types, viewpoints, and levels of nudity/sexual activity. An SDXL version was tested but may produce poor results.animebreast presshentaihugkissloransfwposespovsexsexywoman

LoRA · Flux.1 D

Fractal Geometry Style [FLUX+SDXL+1.5]

039
This model generates images in a fractal geometry style. It is triggered by the keyword "ral-frctlgmtry" and is based on FLUX, SDXL, and 1.5 architectures.3ddepthfractalstyle

LoRA · Pony

Hug From Behind - Concept

039
Support me on facebook.com/Kaiseir (http://facebook.com/Kaiseir) patreon.com/Serkai (http://patreon.com/Serkai) https://ko-fi.com/kaiseir (https://ko-fi.com/kaiseir) Weight: 1.0 Trigger words: Appearance: , hug from behind, hug, sex from behind, hetero, penis, pussy, anal,concept

LoRA · IL

Ghibli style Illustrious & Flux & PDXL

139
This model generates images in the style of Studio Ghibli, trained on stills from movies like Mononoke, Arriety, and Spirited Away. Key features include Ghibli style rendering and character recognition for Totoro, San, and Kiki. ADetailer helps with image details, and the tags "source_anime, Ghiblistyle, anime coloring" are recommended.animeghiblistyle

LoRA · SDXL

Art Nouveau

039
The Art Nouveau model generates images in the Art Nouveau style, trained using MidJourney outputs with a personalized style. It works best with trigger words "ArsMJStyle, Art Nouveau" and features a V2 version based on a 250-image dataset containing portraits, landscapes, buildings, animals, and abstract paintings, with enhanced colors and composition compared to V1. The MJ7 version was rebuilt using MidJourney V7 and expands the range by including everyday objects, architectural details, and jewelry.arsmjstyleart nouveaumidjourneymidjourney v6style

LoRA · SDXL

SDXL MS Paint Portraits

139
This model generates images mimicking the style of MS Paint drawings, focusing on portraits but also applicable to other subjects. Expect low-quality, unexpected, and potentially humorous outputs when using the model with prompts like "MSPaint portrait of {subject}."computer graphicsmspaintstylestyles

LoRA · SD

Downblouse (for Boobs)

738
This LoRA model generates images of downblouse views, including extended downblouse perspectives. It was trained on images of people leaning forward and includes keywords like nip slip, visible nipple, and NSFW for prompting.animehentainudespornposessexywomanwomen

LoRA · IL

[Close-up] Facesitting - Facesit (POV) - Ass, Pussy

238
This Lora model generates images of facesitting poses, including POV shots. Poses can be controlled using specific tags related to viewing angle and body position, such as "looking_down_at_viewer" and "behind". It is recommended to use specific sampling methods and checkpoints for optimal results.animeass holebuttclitclose upcloseupconceptface in assfacesitfacesittingfemdomfetishfish eyehentaiillustriouslabianakednsfwnudeperspectivepornposepovsexysolovaginawoman

LoRA · Pony

Shego (Kim Possible) Pony + Illustrious

038
This model generates images of Shego from Kim Possible. It aims for character accuracy and incorporates Illustrious details.cartooncharacterkim possibleshegotv show

LoRA · IL

Lewd Expression Modifier

238
The Lewd Expression Modifier LoRA allows users to generate various lewd expressions such as ahegao, aroused, and moaning. Different versions offer varying approaches, with megapacks providing multiple expressions in a single LoRA and supplemental versions focusing on individual expressions, each requiring specific trigger words and weights. Users can mix and match expressions, but should be aware of potential concept bleeding and use negative prompts to refine results.ahegaoanimearousedaugmentconceptecstasyexpressionhentaihornylewdmoaningnsfwtorogao

LoRA · IL

Ka Marukogedago | Style LoRa

038
Ka Marukogedago is a style LoRa model that generates images with abstract, watercolor, or oil painting styles. The trigger word is k4_illu, and useful tags include abstract, watercolor, traditional media, scan, and blending. It is recommended to use a weight between 0.1 and 1, with samplers DPM++ 2M Karras or Euler a, CFG Scale between 1 and 7, and Clip Skip of 2.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman

LoRA · IL

[illustrious XL] 21 in 1,Yabuki Kentarou/矢吹健太朗 《To Love Ru》/《出包王女》- Artist Style

037
The illustrious XL model generates images in the style of Yabuki Kentarou (To Love Ru), supporting 21 characters. It offers three distinct styles: Yabuki Kentarou, traditional media (hand-drawn), and anime. The model was trained on over 2200 high-quality images from原画设定集,彩色漫画,TV动画 and OVA动画.haruna sairenjikonjiki no yamikotegawa yuilala satalin devilukemomo velia devilukenana asta devilukestyleto love ruyabuki kentarouyuuki mikan出包王女矢吹健太朗

LoRA · SD

Giantess

037
creates giantessescharacter

LoRA · IL

Knotting/Tugging | Dog dildo/penis | Concept version | Illustrious/NoobAI/Pony | Commission

137
This model generates images of knotting/tugging, specifically dog dildo/penis themes. It aims to produce high-quality images, and the creator recommends specific resolutions and Lora strengths for optimal results. The model also works well with monochrome and grayscale to create images with a manga style.analconceptdog dildofurryknottingobject insertionsextuggingvaginal

LoRA · SD

Deepthroat pov

737
This LoRA model generates deepthroat images from a first-person perspective. It can depict hands on the head and is triggered by the keyword "deepthroat". Other helpful tags include "pov hands", "head grab", and "fellatio".blowjobdeepthroatfellatiohentaiposespovpov handssucking

LoRA · SD

Millie (Helluva Boss)

237
Main Tags: • millie Reinforcement Tags: • demon, imp • red body/skin • black hair • yellow sclera • spade tailfurryhelluva bossimp

LoRA · Pony

Standing Doggystyle sex

237
This model generates images depicting the standing doggystyle sexual position. It's hosted and maintained on Tensor.art and can be used for free. Consider supporting development for early access and perks.animeconceptdoggystylegirlslorasexstanding doggystyle sexwoman

LoRA · Pony

Table humping

337
This model generates images tagged as "table humping." It recommends specific quality and negative tags for optimal results and suggests the AutismMix_confetti checkpoint.animeconceptconceptsfemale masturbationhentaihumpingmasturbationposetable humping

LoRA · IL

Hooters Uniform - Concept / Clothes - | Illustrious XL | - Waifus At Work! by YeiyeiArt

037
This model generates images of characters wearing a Hooters uniform. Use the trigger word "HootersUniform" along with prompts like "employee uniform, short shorts, orange shorts, tank top, white shirt, cleavage" to achieve the desired look.animeart stylescartoonclothesclothingfantasyloramangarealismrealisticsexystylesuniform

LoRA · IL

Bodycon (Illustrious)

037
This LoRA model generates images of tight-fitting dresses with cutouts and o-ring details. It is recommended to use a strength of 1, with the outfit tag 'bodycon' and extra details like 'fishnets' or 'clothing cutout'.animebodyconclothinggirlslorarevealing clothessluttywoman

LoRA · SD

Yor Briar (Spy x Family) LoRA

337
This LoRA generates images of Yor Briar from Spy x Family. Trigger words are "yor briar" plus descriptive terms, and it works with various models around a weight of 0.6. It can reproduce her different outfits with adjusted CFG scale or weight.animecharacterfemalegirlsmangasexyspy x familywomanyor briar

LoRA · SD

Cyberpunk Style

037
Cyberpunk Style is a model trained using the same data as SDXL. It was trained on the CivitAI trainer.animatedanimecyberpunkfemalefuturisticgame charactergirlsloramanpersonphotorealisticportraitspost apocalypticrealisticsexysexy attiresexy menstylestylesvideo gamewoman

LoRA · Wan Video 14B t2v

Side lying Sex - Wan I2V 14B

437
This LoRA model generates images and videos of side-lying sexual intercourse. It has two versions, one for text-to-video (t2v) and one for image-to-video (i2v), with the i2v version recommended for better performance. The i2v version can be triggered using "They are having side sex."conceptsex

LoRA · Pony

Heart Hands on Breast LoRa | PonyXL & Illustrious

136
This LoRA model generates anime-style images featuring a female character performing a heart hands gesture above the breast area. It is optimized for PonyXL and Illustrious models and trained to maintain the overall style of your artwork.animegirlsposessexywoman
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.