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.
Oral Insertion [WAN 2.2]
This LoRA model, trained on the WAN 2.2 I2V 14B, generates images of oral insertion scenarios where the man is not initially present. It is triggered by the phrase "A man appears and she sucks his penis," and optimized sampling requires adjusting the CFG based on the chosen noise model (high or low). The model is provided in a zip file containing LoRAs for both noise levels.
F4C3SPL4SH Cumshot - I2V Wan 2.2 Video LoRa - K3NK
This LoRa model is trained on a dataset of 391 clips to generate cumshot scenes for use with the Wan2.2 video model. It aims to create realistic and detailed adult content featuring male ejaculation onto a woman's face and chest. Specific lighting and secondary LoRAs are recommended for optimal results.
Wan 2.2 / 2.1 - Anal Reverse Cowgirl POV - t2v - i2v
Wan 2.2/2.1 is a text-to-video and image-to-video model trained on realistic videos. It generates high-quality animations, including depictions of sexual acts like anal sex, based on text prompts. Version 2.1 is compatible with both I2V and T2V models, trained using diffusion-pipe.
POV Insertion [WAN 2.X]
This LoRA is specifically trained to capture the moment of insertion when the penis is not initially in frame and can handle both missionary and doggystyle positions. Trigger Phrase: A man appears and inserts his penis into her pussyIf 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.
WAN DR34MJOB - Double/Single/Handy Blowjob
WAN DR34MJOB is a LoRA model designed to generate images of single and double blowjobs, including POV shots. It also produces images of handjobs. Using the specified triggers is necessary for desired outputs.
Ultimate DeepThroat I2V Wan2.2 Video LoRa - K3NK
This LoRA model is designed for generating deepthroat blowjob scenes using Wan2.2 I2V. It was trained on a dataset of short clips and can handle various points of view in these scenes, though some positions may require specific prompting to avoid artifacts. The model aims to create realistic depictions of this act through text-to-video or image-to-video generation.
WAN 2.2 I2V - Combo Handjob Blowjob
This model generates images of a woman performing simultaneous hand and mouth stimulation. It works well at strength 1, supporting both POV and third-person perspectives, and is best suited for live-action images due to potential blurring on animated fingers. The model was trained to prioritize image quality over smaller file size.
Ultimate Deepthroat - Wan2.1 Video LoRa
This LoRA model, "Ultimate Deepthroat - Wan2.1 Video LoRa," is trained to generate videos of deepthroat scenes using a 480p i2v model. It utilizes a dataset created from Hun deepthroat LoRAs and is intended for use with specific WAN2.1 workflows. The model is shared without warranties and users are responsible for its lawful and responsible use.
Facial Cumshot - Hun | Wan Video Lora
This LoRA model is designed to generate images or videos depicting facial cumshots. It was trained on a dataset of short video clips and can be used with specific workflows to create content featuring ejaculation onto a woman's face. The model is shared with the understanding that it will be used responsibly and lawfully.
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.