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.
Iwao178 (いわお) - Artist Style [Illustrious]
Iwao178 is a LoRA model that generates images in the style of the artist Iwao. Use the trigger word "1wa0" with a LoRA strength of 0.8 to 0.9, and "censored" as a negative tag is recommended.
Penis Real Diffusion - Illustrious - LORA 👑 realistic
This LORA, based on the Illustrious model, generates realistic images of penises in various positions and concept artworks. It utilizes the trigger word "PenisQuiron" and is designed for use with ADetailer and specific CFG/Lora strength settings.
BlackWhiplash (BWL) [Illustrious] Style LoRA
BlackWhiplash (BWL) [Illustrious] Style LoRA is a model for character and style generation. It is recommended to use a strength of 1.0, with the trigger word "blaash". Style 2 is trained on data from 2024-2025, while Style 1 is anything before.
ShadyFoxAlart - Art Style / [Illustrious/NoobAI]
ShadyFoxAlart is a Lora model designed to generate art in the style of ShadyFox. It works best with a weight between 0.8 and 1.0. The model is still being tested.
cunnystyle
Cunnystyle is a model for generating images, with different versions focusing on varying aspects of character likeness and image quality. Later versions aimed for clearer faces and eyes, while earlier versions experimented with different approaches. The model is not intended for commercial use.
Nudify XL: Better Bodies
Nudify XL is a LORA model for text-to-image generation that enhances nude female frontals and breast shapes. It's designed to remove censorship and works best with low weights and accompanying keywords like "naked" or "topless". The model uses a dataset of nude women and is intended for use with XL base models.
M4CROM4STI4 - Huge Natural Breasts Physics - Wan2.2 Video LoRa - K3NK
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.
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.