Porn Factory AILogin

base model models for adult image and video generation

Compare 54 public adult AI checkpoints and LoRAs tagged base model. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

54 models available

Checkpoint · SD

Hardcore Hentai

234.1K
Hardcore Hentai is a model designed to generate high-quality hentai images that accurately follow prompts. It uses danbooru tags or sentence-based prompts, and achieves good results with a 1024x1024 resolution. Key features include strong prompt adherence and high-quality image generation for artistic and explicit content.animeartbase modelfemalegame charactergirlshardcorehentaiillustrationnsfwpornportraitssexsexywoman

Checkpoint · IL

Plant Milk 🌿 - Model Suite

123.9K
Plant Milk is a multi-series model suite hosting various styles based on illustrious/noob model merges. It offers different 'flavors,' some of which are more Lora-heavy. It is recommended to use Euler or Euler a sampler with 3 cfg and ~28 steps.animebase modelboysgirlsplant milkstyled

Checkpoint · SD

AnyLoRA - Checkpoint

193.8K
AnyLoRA is a model designed to ensure LoRA training compatibility with newer models, providing a style-neutral base for accurate style representation. It excels at training and inference, especially with anime styles, and consumes little VRAM; use pruned versions for training. It is recommended to use CLIP skip 2 and booru style tags when training, along with a good VAE for optimal image saturation.animeanyloraart stylebase modelbeautifulfemalegirlsillustrationmangasexywoman

Checkpoint · SD

RealCartoon3D

143.5K
RealCartoon3D is a Stable Diffusion model designed to produce diverse human characters with a cartoon look and a realistic touch, while working well with LoRAs. It aims to generate good results with minimal prompt attempts and has served as the basis for other RealCartoon variations. The model has a baked-in VAE and is intended for open access use, with some restrictions to prevent harmful or illegal outputs.2.5dafrican-americananimeart stylebase modelbeautifulcartoondigital artfantasyfantasy artfemalegirlsillustrationlandscapemanmechamixrealcartoonrealcartoon3drealisticscifisemirealisticstylesvariety

Checkpoint · Pony

Babes By Stable Yogi (Pony)

163.4K
Babes By Stable Yogi (Pony) is a model that generates images, with an enhanced pro version available. It is recommended to use specific positive and negative prompts for optimal results.animebase modelbeautiesfemalegame charactergirlsloramanpersonphotorealisticportraitsrealisticsexysexy posevideo gamewoman

Checkpoint · IL

NTR MIX | illustrious-XL | Noob-XL

143.1K
NTR MIX is a model that generates images with recommended settings for Comfyui. It provides specific configuration suggestions for various scenarios, including detailed scenery and character-focused images, using different samplers and settings based on the desired style. The model also suggests using quality and negative tags to improve image output.base model

Checkpoint · SD

ReV Animated

393.1K
ReV Animated is a checkpoint merge model designed for generating 2.5D images in styles like fantasy, anime, and semi-realistic scenes. It is LoRA-friendly and performs optimally at resolutions such as 512x512, 512x768, and 768x512, with emphasis on portrait generation.animebase modelcartoonfantasyillustrationportraits

Checkpoint · SDXL

epiCRealism XL

103K
Regards for all your love and support ❤ avoiding negatives can improve result on SDXLbase modelphotophotographyphotorealismrealisticwoman

Checkpoint · IL

✨ JANKU v5 Trained + NoobAI + RouWei Illustrious XL ✨

192.9K
JANKU v5 is a model designed for generating high-quality art with improved anatomy and details, especially for NSFW content. It offers vibrant colors, stable styles, and prompt responsiveness without requiring additional LoRAs. The model aims to eliminate watermarks and artifacts, following prompts accurately and providing good artist representation.animebase modelcharactershentaihigh qualitynsfwsexysfwwoman

Checkpoint · SDXL

RealVisXL V5.0

172.9K
RealVisXL V5.0 is a model designed for generating photorealistic images, capable of producing both SFW and NSFW content. It is recommended to use specific sampling methods and negative prompts for optimal results.base modelmannsfwphotorealisticrealisticsemi-realisticsfwwoman

Checkpoint · SD

MeinaHentai

302.8K
MeinaHentai is a model designed to generate NSFW illustrations without relying heavily on Loras. It recommends specific samplers, CFG scales, and resolutions for optimal image creation. Realistic results can be achieved by including "realistic" or "photo" in the prompt.animebase modelbreastserotic posegirlshentaiinpaintingnakednudessexsexy

Checkpoint · Other

Dark Sushi Mix 大颗寿司Mix

202.8K
Dark Sushi Mix is a Stable Diffusion checkpoint that integrates 2.5D elements into an anime style, improving body and face details with enhanced light and shadow effects. It's a fusion of multiple models, including the author's previous mixes and TmndMix, with a darker version incorporating noiseoffset for stronger light and shadow. It is recommended to use highres fix to improve quality.base model

Checkpoint · IL

Prefectious XL NSFW

102.7K
Prefectious XL NSFW is a new model merge, still under development and potentially containing bugs. It is designed for NSFW content generation and benefits from settings like CLIP skip 1, specific samplers/CFG values, and detail enhancement tools. Recommended prompts and negative prompts are provided for optimal image quality.animebase modelbase modelsgirlsillustrious xlstyleswoman

Checkpoint · SDXL

Animagine XL V3.1

172.7K
Animagine XL 3.1 is an open-source, anime-themed text-to-image model based on Stable Diffusion XL, designed to generate high-quality anime-style images. This version improves upon Animagine XL 3.0 with an optimized dataset, new aesthetic tags, and enhanced concept understanding, offering more detailed and accurate representations of anime characters. It is optimized for Danbooru-style tags and includes special tags for controlling quality, rating, creation date, and aesthetics.animebase model

Checkpoint · IL

Nova Anime XL

132.2K
Nova Anime XL is an SDXL checkpoint model for generating anime, 2.5D, and 3D style images. A "pony" version aims to replicate the look of both Nova Anime and Nova Domain. Recommended settings and prompts are provided for both Pony and Illustrious styles.2.5d2danimebase modelcolorfuldigital artfantasyillustrationlandscapemodelsdxlxl

Checkpoint · SD

PerfectDeliberate

182.1K
PerfectDeliberate is an image generation model. It is recommended to use resolutions such as 832x1216, 960x1440, 1024x1024, or 1024x1536 with a CFG scale of 5-8. Euler a or DPM++ 2M Karras sampling methods with 20-50 steps are also suggested.3danimebase modelfantasyhentaipornrealisticsexy

Checkpoint · Pony

Babes

112K
Babes is a Stable Diffusion model focused on generating semi-realistic images with refined faces and bodies, offering enhanced details, sharpness, and compositions. It includes adjustments to base styles, default faces, and often incorporates new training data and components to improve the overall image quality and feature set, especially regarding details like hand gestures. Different versions introduce improvements to aspects such as skin tones, lighting, and the incorporation of specific styles.animalsanimebabesbase modelbimbocarscartooncartoonishdigital artfantasyfemalegirlsgraphic designillustrationmalemidjourneyportraitportraitssemi-realisticsexystyle artsubjectwoman

LoRA · SDXL

SPO-SDXL_4k-p_10ep_LoRA_webui

31.9K
This model is a LoRA checkpoint fine-tuned from stable-diffusion-xl-base-1.0 using Step-by-step Preference Optimization (SPO) to improve image aesthetics. It was trained on 4,000 prompts for 10 epochs, enhancing fine-grained visual details without sacrificing image-text alignment.base model

Checkpoint · IL

iLustMix

101.8K
iLustMix is a model designed for semi-realistic image generation with exceptional detail, body proportions, and hand rendering. It uses ADetailer for improved face clarity and provides high quality outputs.base model

Checkpoint · IL

Illustrij

91.6K
Illustrij is a merged checkpoint model specializing in comic-anime-hybrid style images with digital art rendering and a touch of 3D on its way to semirealism. It focuses on elements like lighting, character design, and stylistic harmony, with versions offering various balances between anime and semi-realism, as well as support for both SFW and NSFW content. The model allows for the creation of images with detailed eyes, expressive characters, and tangible qualities, adaptable to different aesthetic preferences through prompt adjustments.animebase modelcheckpoint mergeillustriousmergemodel

Checkpoint · SDXL

CyberRealistic XL

71.3K
CyberRealistic XL is a model designed for generating clean, photo-realistic images. It produces sharp and detailed results and commonly needs negative prompts to avoid unwanted styles. The model offers recommended settings and optional tools to enhance generated images.base modelgirlsloramanphotorealisicphotorealisticrealisticwoman

Checkpoint · IL

Realism Illustrious By Stable Yogi

81.2K
Realism Illustrious By Stable Yogi is a model designed for generating realistic images. To achieve results similar to the creator's images, use the provided positive and negative embeddings at the beginning of your prompts. Check the "About this version" section for model details and settings.animebase modelgirlsillustriousxlmalephotorealisticrealisticsexywoman

Checkpoint · IL

One obsession

111K
This model is designed to create high-quality anime-style images, even for beginners without using LoRAs or complex tags. It aims for versatile outputs ranging from cute to mature and offers semi-realistic to 2D styles, with features like enhanced hands and feet in recent versions. The model provides recommendations for prompt keywords and resolutions for optimal results.animebase modelmy styleobsessiononesexy

Checkpoint · SD

Uber Realistic Porn Merge (URPM-SD1.5)

38516
URPM-SD1.5 is a model focused on generating realistic adult content. It aims to produce high-quality images and offers prompts to achieve desired results. The model also has SDXL and Pony-SDXL Hybrid versions available.base modelblendfantasygirlshardcorelewdnudespersonphotographyphotorealisticpornportraitsrealisticsexsexyvaginawomanwomen
Load more models

Showing 24 of 54

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.