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.
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.
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.
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.
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.
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.
(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
WAN DR34ML4Y - All-In-One NSFW
WAN DR34ML4Y is an all-in-one NSFW LoRA model designed to handle various specific concepts like double blowjobs, missionary position, reverse cowgirl, and doggy style. It accurately generates images based on specified keywords and positions. It is recommended to use both models to produce ideal outputs.
Wan POV Blowjob
The Wan POV Blowjob model generates images and videos of oral sex from a first-person perspective. It is capable of depicting cumshots and can handle images where the penis is not initially present. The model supports multiple angles and requires specific prompts to trigger certain actions, like the appearance of cum.
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.
WAN2.1 Facefuck
WAN2.1 Facefuck is a LORA model focused on generating images of a specific sexual act. It was trained on low-resolution videos to exaggerate movement and allows control over insertion speed and depth. The model aims for further refinement in future versions to improve realism and add scene variations.
FLUX_NSFW_Blowjob_FUCK_rimjob_Sevenof9
FLUX_NSFW_Blowjob_FUCK_rimjob_Sevenof9 is a model trained on handpicked, watermark-free images focused on specific adult themes. Optimal results are achieved around 25 steps using EULER with DDIM or SGM Uniform/Beta samplers, and it's suggested to increase resolution for noise reduction. The model provides various adult orientated poses, it's recommended users experiment with prompts and CFG values for ideal results.
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.
Wan 2.1 Deepthroat / Facefuck Entry - Blowjob, Fellatio, Oral, Lora, T2V 14B
This Lora generates videos of blowjobs, often starting with the penis outside the mouth and leaning towards facefucking. Video quality can be inconsistent but improves when used with other Loras at lower strengths, requiring multiple generations for optimal results. The action and details are generally good.
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.