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.
WAI-illustrious-SDXL
WAI-illustrious-SDXL is a Stable Diffusion model, primarily focused on generating characters, especially from popular social games and anime. It incorporates character data up to around May 2025 and includes an integrated VAE. The model benefits from using specific settings like Euler a sampler with CFG scale 5-7, and users should be mindful of prompt length to maximize image quality.
Z Image Turbo
Z-Image-Turbo is a highly efficient 6B parameter image generation model, a distilled version of Z-Image. It offers sub-second inference, excels in photorealistic image generation and bilingual text rendering, and demonstrates strong instruction adherence while operating efficiently on consumer devices. Other variants include Z-Image-Base for fine-tuning and Z-Image-Edit specialized for instruction-based image editing.
Flux.2 Klein
The FLUX.2 Klein models are fast image models that unify generation and editing. They offer state-of-the-art image quality with end-to-end inference, designed for real-time applications.
Sex, Nudes, Other Fun Stuff (SNOFS)
SNOFS is a natural language trained model focused on generating images of sex, nudes, and related content. It excels at understanding full sentence prompts to create images with various sexual acts, positions, and scenarios. The model is flexible and can be used with other LoRAs for specific likenesses.
Instagramification
The Instagramification LoRA creates images of women resembling Instagram influencers. It enhances features like lips, skin tone, hair, and makeup, often adding large breasts, based on datasets from popular Instagram Baddies LoRAs and trained on Wan2.1-T2V-14B, working for both text-to-video (T2V) and image-to-video (I2V) applications.
[ZIT] Mystic XXX
The Mystic XXX model unlocks enhanced capabilities on Z Image Turbo. It provides specific improvements to the model's performance on the older ComfyUI version 0.3.75, with adjustments made for newer versions. V3 or bigger gives the most accurate results.
PornMaster-色情大师
PornMaster-色情大师 is a Stable Diffusion checkpoint model, with versions prior to v7 being based on the sd1.5 "Amateur Series". It allows for image generation under the Fair AI Public License, ensuring derivative works are also open source. The model creator offers customized LORAs and encourages users to support their work.
LUSTIFY! [SDXL NSFW checkpoint]
LUSTIFY! is a photorealistic SDXL checkpoint for generating images of women in sexual scenarios, trained to understand both danbooru tags and natural language prompts. It can also create SFW images if the NSFW bias is overcome. It is recommended to use specific samplers, schedulers, and CFG values for optimal results, and is not Pony or Illustrious based.
Smooth Mix Wan 2.2 (I2V/T2V 14B)
Smooth Mix Wan 2.2 (I2V/T2V 14B) is a versatile image and text-to-video model based on Wan 2.2 A14B. It generates high-quality images and smooth animations with variety in styles, and is uncensored to allow for NSFW content. While focused on generating female characters, it also responds to prompts like 'SmoothMixAnime' and 'SmoothMixRealism'.
Wan NSFW Posing Nude
This model generates NSFW nude portraits of standing, posing figures, focusing on anatomical accuracy and physics in a photoshoot setting. It was trained on a dataset designed to minimize bias toward specific facial features or accessories, allowing users to control details via prompts. It works best with specific aspect ratios and benefits from the use of lightning LoRAs for efficient generation.
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.
NSFW POV All In One SDXL (Realistic/Anime/WD14 - 74MB Version Available)
This NSFW model generates realistic and anime style POV images focusing on basic scenarios like blowjobs, butterfly sex, cumshots, doggy style, and others. It comes in two versions: a higher quality 1.78GB version and a smaller 74MB version. Watermarks may appear but can be avoided by adjusting LoRA weight or seed.
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.
Pov Blowjob + Titjob + Handjob [updated]
This LoRA model generates images with customizable combinations of fellatio, handjob, and paizuri. It is designed to be flexible, using prompts like 'pov, 1girl, 1boy' as a base and offering additional prompts for further customization and control. Users can adjust prompt strengths to achieve desired results for specific actions and perspectives.
Xpenis
Xpenis is a model trained with high-resolution material (832x1216 or 1216x832) focusing on penis imagery. It requires an external VAE and works best with SDXL base or low CFG settings. Key terms include flaccid and erect penis variations.
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.
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.
Hand in Panties - Masturbation - Wan 2.2 - Official Release!
Wan 2.2 is a specialized model for generating images depicting masturbation, specifically a hand in panties. It requires both high and low models and uses specific trigger phrases. The workflow is provided in the training data file.
Big Clit - WAN, Pony, IL, SDXL, Flux
This model generates images featuring a prominent clitoris, specifically an improved version (v2) built on the Pony model. It aims to create more realistic and aesthetically pleasing results compared to the original, addressing issues like unintentional penis-like features. The trigger words are "big clit" and "big clitoris".
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.
(CONCEPT) Fellatio gesture with finger circle / フェラ素振り(指で輪っか) (Illustrious)
エッッッッッッ🍄💦💦なジェスチャーを作りたかったので作りました。 This LoRA provides the fellatio gesture of making a circle with the fingers to seduce. Trigger word:fellatiogesturewithfingercircle, fellatio gesture, finger circle, oral invitation, hand on mouth, Strength:0.9
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.