Adult AI LoRAs with clear compatibility
LoRAs add a focused style, character, pose, motion, or visual concept to a compatible checkpoint. Choose one whose base model and generation mode match your checkpoint; each detail page shows its trigger words and supported workflows before you spend credits.
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.
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.
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.
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.
Choose a compatible adult AI LoRA
Match the checkpoint family
Select a LoRA built for the checkpoint's base model. Cross-family combinations are blocked instead of being submitted as an unreliable job.
Use trigger words deliberately
Model detail pages list available trigger words. Add only the terms needed for the intended style, subject, pose, or motion.
Look for workflow support
Image and video LoRAs are not interchangeable. A version appears in the generator only after its exact workflow mapping is validated.