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 · SD

NEW ERA / LORA / PONY DIFFUSION

436
NEW ERA is a model designed to recreate retro anime styles, aiming to be a tool that fully recreates old anime rather than just imitating it. It incorporates artists from the 80s-00s and a wide array of characters, best used with specific models and settings for optimal results. Use booru tags for prompting.19801980 style1980's1980's style1980s1990's1990s1990s anime style80s90's90s90s styleaestheticanimeanime characteranime styleestheticretroretro animeretro artstyleretro stylestylevintage

LoRA · IL

Pov Bondage Chair [remake]

136
This LoRA generates images of characters bound to a chair in a point-of-view perspective. It allows customization of poses and integrates better with other LoRAs compared to the original version. Core prompts include specifying leg positions, while customization prompts offer control over subjects, restraints, angles, and sexual content.animebdsmbondagensfwposeposessexywoman

LoRA · SD

[SD 1.5] Modern Victorian fashion dress | 洛丽塔裙子 | ロリータ ドレス Vol.1

436
This model generates images of modern Victorian fashion dresses, also known as Lolita dresses. It was trained using realistic images and may not work well with anime models. The LORA weight is recommended to be around 0.7, and the creator welcomes feedback.clothingdressvictorian dress

LoRA · SD

No Panties under Pantyhose | Test Clothing Lora 824

336
This Lora is trained on pantyhose images (white, brown, and black) and can generate images with or without torn effects. It uses tags like "white1," "black1," "brown1," and "torn1" to influence the generation. The model is intended to generate images that may contain nudity or sexual content.animeclothinggirls

LoRA · SDXL

ボンデージ衣装/bondage outfit（XL,ILL,pony)

136
The strength of Lora is recommended to be around 0.8.clothing

LoRA · Wan Video 2.2 I2V-A14B

M4CROM4STI4 - Huge Natural Breasts Physics - Wan2.2 Video LoRa - K3NK

336
This LoRA model, M4CROM4STI4, generates images and videos featuring very large, natural-looking breasts. It was trained using a dataset of video clips and may occasionally produce unwanted artifacts like strange pubic hair. The model is designed for use with the WAN 2.2 workflow.big breastbouncing boobsbouncing breastsbreasts physicsgigantic breastsmarcomastianatural breastsnatural movementsstyle

LoRA · IL

Spooning Femdom (Handjob / Pegging): Pony & Illustrious

135
Spooning Femdom for Pony & Illustriousconceptcuddlingfemale dominationfemdomgirlshandjobhentaihugginglorapeggingpornsexyspooning

LoRA · IL

Painterly Fantasy by ChronoKnight - [FLUX & IL]

035
Painterly Fantasy by ChronoKnight is a LoRA model that generates images in a painterly fantasy style. Use the trigger word "in the style of ckpf" with a strength of 0.8-1.0 for local generation. Example prompts are included to get you started.animeartstylecartoonetherealethereal alienfantasticalfantasyfantasy artfantasy landscapefantasy landscapesfantasy stylegirlslandscapelandscapesloramagicmagicalmalepainterlypaintingscenerysorcerersorceressstylewhimsicalwoman

LoRA · Wan Video

Gangbang Missionary Sex WAN 2.1 I2V

235
This model generates images of gangbang scenarios with a focus on vaginal and anal penetration involving multiple partners. It supports realistic motion for penetration, and can depict related actions like penis stroking and facial expressions with varying degrees of success.conceptnsfwsex

LoRA · IL

Penis Pushing Panties

134
• You can see at the sample images for the prompt. • "peppan" trigger word is optional • Clothes : panties, leotard, slingshot swimsuit • Work with flaccid too • Slingshot swimsuit or sling bikini is hard to achieve, but add "panties, highleg panties" in negative prompt for better result.conceptfutafutanarimalensfwpantiespenis

LoRA · Pony

Anime Hentai Series Style

034
Made with 1000 screencaps of several episodes in different series.animestyle

LoRA · SD

Kitty Katswell (T.U.F.F. Puppy) Character Lora

034
This Lora generates images of Kitty Katswell from T.U.F.F. Puppy. Use the trigger word "kitty katswell" with a strength of 0.4-0.7.black haircartooncartoon charactercatcharacterfemalefurrygirlshairbandnicknickelodeonwoman

LoRA · Pony

takahegao (fucked silly face)

233
Takahegao is a Lora model trained to generate "fucked silly" ahegao faces, primarily based on monochrome datasets but functional with colors. It is biased towards Takatsu's art style, though this can be overridden, and is triggered using the "takahegao" tag along with related tags like "tongue" and "saliva".ahegaoanimeconceptexpressionillustriousponysexy

LoRA · SD

【Character】Akiryo's Mai

333
This LORA model allows users to generate images of Shiranui Mai using the trigger tags 'akiryo-mai' and 'shiranui mai', with weights between 0.6 and 0.8 recommended. A realistic version is available for use with realistic models; set clip skip to 2 for optimal results. The model has been updated with improved datasets and retraining, including adjustments to sampler settings for stable image generation.3dcharactergame character

LoRA · SD

WLOP Style LoRA

333
This LoRA allows users to apply the WLOP art style to images generated using Stable Diffusion. It is designed to be combined with existing models, particularly anime-based ones like AnyLoRA and Abyss Orange Mix V2, using a trigger word of "wlop". The LoRA modifies the image's aesthetic to resemble WLOP's distinctive style.animeart styleartistartstylecharacter artdigital artdigital illustrationfantasyfemalegirlshighly detailedportaitsportraitssexystylewlopwoman

LoRA · IL

Genshin Impact In-game Style (Illustrious and Pony)

033
This model replicates the visual style of Genshin Impact in-game screenshots. It's trained on a dataset of locations, characters, and poses using "G3NSHIN" as the trigger word. Increasing the LoRA strength or adding "3D" can enhance the style.3danimegamegenshinstyle

LoRA · IL

[Style] Mosouko [Illustrious-XL/NoobAI-XL]

033
The Mosouko model, designed for Illustrious-XL/NoobAI-XL, generates images in the style of the artist @mosouko. Use the trigger word MO85KO with a strength of 0.8-1.0.artstyleillustrationstyle

LoRA · SD

Breasts squeezed together

333
This LoRA generates images of characters squeezing their breasts together. It uses specific arm poses to achieve this effect, which is more visible on characters with larger breasts. Keywords like "breasts squeezed together," "v arms," and "hands on own chest" can help achieve the desired pose.animebreastbreastsbreasts squeezed togetherconceptsfemaleposeposessexy

LoRA · SD

Whale Tail (Clothing)| Goofy Ai

233
Whale Tail (Clothing) is a model hosted on Tensor.art. It offers both exclusive and public versions for free use. An upcoming NSFW Lora is available with early access through Patreon.animeclothingfemalewoman

LoRA · Wan Video 2.2 I2V-A14B

Slop Twerk WAN 2.2 I2V

433
Slop Twerk WAN 2.2 I2V is a LoRA trained on AI-generated videos of characters twerking, focusing on generating ass shaking and jiggling effects. It was trained using a modified Musubi Tuner GUI and the dataset includes manually tagged videos with descriptions of twerking actions. The LoRA is designed to be used with prompts related to twerking and ass shaking, with some breast jiggle also present.bouncebouncingbuttconceptsloptwerk

LoRA · IL

Bathing Together LoRa | PonyXL & Illustrious

132
This LoRa model generates anime-style scenes of a character bathing with the viewer. It's trained for PonyXL & Illustrious base models and designed to not significantly alter the underlying art style. It is intended for NSFW content creation.animebathingconceptgirlssexywoman

LoRA · Pony

Head Between Breasts Missionary (Motorboat / Size Difference): Pony & Illustrious

132
Missionary position w/ side difference and head between breasts Will update once dataset grows.animeconceptgirlsloramalemansexywoman

LoRA · IL

Pov bondage wall

132
This LoRA generates images of characters in a "pov bondage wall" scenario, focusing on characters restrained to a wall. Key features include different bondage positions such as legs up or down, customizable with various prompts for character, restraints, angles, and sexual acts.animebdsmbondageboundhentainsfwposessexsexywallwoman

LoRA · SD

30s Technicolor Movie

032
This LoRA creates images resembling 1930s technicolor movies. It's triggered with "ArsMovieStill, movie still from a 1930s technicolor movie," and newer versions focus on realism and period accuracy while others expand the dataset and include diverse themes.midjourneymidjourney v6moviemovie stillstillstyle
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.