Porn Factory AILogin

sex models for adult image and video generation

Compare 128 public adult AI checkpoints and LoRAs tagged sex. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

128 models available

LoRA · Hunyuan Video

HunyuanVideo Double Blowjob

21
This LoRA model generates images of two women performing oral sex from the viewer's perspective. It may not perfectly follow instructions, but produces decent results with a recommended strength of 0.7-1.0. Key phrases can help guide the image generation process.conceptoralsex

LoRA · Hunyuan Video

HunyuanVideo POV Missionary

10
HunyuanVideo POV Missionary is a model trained to generate videos of missionary-position intercourse from a point-of-view perspective. Later versions blur faces in the generated content and aim to improve compatibility with character LORAs. The model uses training data, configuration files, and captions to facilitate user training, with example prompts and workflows provided.conceptmissionarysex

LoRA · SD

POV Doggy Anal + Creampie LoRA

50
This LoRA model generates images focused on POV doggy-style anal and creampie scenes. Version 4 includes dataset and tagging improvements for better image quality and prompt responsiveness. Recommended strength is 0.7-0.8, and it is based on UberRealisticPornMerge.actionanalasscreampiecumhardcorephotorealisticpornsexsexual activitywoman

LoRA · Other

real spread pussy(experimental)

70
This experimental model generates detailed 2.5D images of spread genitalia. Newer versions offer improved accuracy but may negatively impact stylistic consistency; use lower weights or revert to older versions to preserve style. Trigger words and weight recommendations are provided, and the model is compatible with specific 2D models.2danimehentainakednudespornsemi-realisticsexvagina

LoRA · SD

M-Leg Gesture, Ultimate Edition

20
M-Leg Gesture, Ultimate Edition is a LoRA model focused on generating detailed images of female genitalia, specifically emphasizing pubic hair and labia appearance control. It was trained on over 2500 images and works best with specific base models and lower LoRA weights to avoid overfitting. The model allows users to control the level of pubic hair (hairy or shaved) and the appearance of the labia (everted) through prompting.nudessex

LoRA · SD

Standing Split Sex

50
This LoRA generates images of a male and female in a standing split sex position. It works best with anime models or those trained on NAI, using weights between 0.8-1.0, and includes the trigger words "ekstandsplit, 1boy, penis, sex, standing, standing split, standing sex." It's trained on 512x512 resolution, so generate at that size and upscale for higher resolution.animeconceptekuneloransfwsexstanding split sex

LoRA · Wan Video 14B t2v

WAN 2.1 - HairPulling DoggyStyle

30
The model generates images of a specific sexual position. It comprises two LoRAs, one trained on more videos and the other on fewer videos but with high-resolution images, designed to be used individually or combined. It is trained on 24 FPS videos and uses a base prompt describing the depicted act.conceptdoggydoggystylehair pullinghairpullingpornsex

LoRA · Other

breasts_on_glass

90
animegirlssex

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.