Porn Factory AILogin

girls models for adult image and video generation

Compare 278 public adult AI checkpoints and LoRAs tagged girls. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

278 models available

LoRA · SD

薄塗り / USNR STYLE

72.7K
This is an online generation model. Recommended settings include DPM++ 2M SDE sampling method, SGM Uniform schedule type, and a CFG Scale of 6-4.animegirlsstyle

LoRA · Pony

Pony Realism Enhancer ✨

72.6K
Pony Realism Enhancer is a LoRA model trained to improve the realism and image quality of Pony Realism v2.2. It is recommended to use a strength of 0.5-0.9 and Clip Skip of 2.enhancergirlsphotophotorealismphotorealisticrealrealismrealisticsexystylewoman

LoRA · Pony

Real Skin Slider

52.5K
Real Skin Slider enhances images with photorealistic skin texture, subtle imperfections, and soft lighting. It refines details like pores and tones without altering the subject's structure, suitable for realism models and portraits. Use weights 2-3 for balanced results, increasing for more dramatic refinement.add detaildetail enhancingdetailedenhancergirlsphotophotorealismphotorealisticrealreal skinrealisticskinskin detailsliderstylewoman

LoRA · Flux.1 D

Niji semi realism

42.4K
Niji Semi-realism is a model fine-tuned on Niji v6 style images with a focus on pseudo-realistic and semi-realistic aesthetics. It produces high-quality images with distinct day/night styles, incorporating dark lighting and reflections. Use trigger words like "pseudo-realistic," "night," or "cartoon" to influence the output style.animegirlsloraphotorealisticrealisticstylewoman

LoRA · IL

Illustrious Realism Slider

72.1K
The Illustrious Realism Slider enhances image quality and realism, improving clarity and texture while preserving smaller details unless specifically prompted. It offers fine-tuned control through incremental adjustments, achieving natural, polished results with minimal effort. No activation prompt is needed, making it easy to use.add detaildetail enhancingdetailedenhancergirlsillustriousilxlphotophotorealismphotorealisticrealrealisticskin detailsliderstylewoman

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 · SD

Detailed Perfection style (Hands + Feet + Face + Body + All in one) XL + F1D + SD1.5 + Pony + Illu

42K
This model, trained on xl 1.0 + F1D, enhances images with detailed features for hands, feet, faces, and bodies. It has versions for SD1.5, Pony, and illustrative styles, and works well with other models, including Juggernaut and Realistic Stock Photo models. It can also be used as an extra layer without prompts when combined with other LoRA models.animecinematicdetaileddetailed eyesearearseyesfeetfingerfingersfootgilfgilfsgirlshairhaircuthandhandgunhandshyperrealismhyperrealistichyperrealistic character portraitshyperrealityillustriouslipslipstickloramalemanmaturemilfmilfsnosensfwperfectperfect bodyperfect boobsperfect eyesperfect handperfect skinperfect styleperfect titsperfectionpersonphotophotographyphotorealisiticphotorealismphotorealisticponyrealrealismrealistrealisticrealistic modelrealistic skinrealistic stylesexyskinskinsskintonestyletexturewomanwrinklexl

LoRA · Pony

Thicc (slider)

91.9K
The Thicc model generates images and requires no specific tags. It is recommended to use quality tags such as score_9, score_8_up, score_7_up, and score_6_up while avoiding tags like score_4 and score_5. The base model used will impact the output.assbody sizebootybuttconceptscurvyfemalegirlshourglassnarrow waistsexysliderstylethiccthickthick thighsthighswide hips

LoRA · IL

Fellatrix style (ILXL/PDXL/SD1.5) | GoofyAi

81.8K
The Fellatrix style model by GoofyAi (ILXL/PDXL/SD1.5) generates images. Example prompts are available and the Lora should be used at strength 1. Users can provide feedback, ideas, and requests.animebimbofellatrixfemalegirlsstylestyleswoman

LoRA · Pony

Uncensored PonyXL

61.8K
Uncensored PonyXL is a model trained on a dataset of anime-style images based on Pony XL. It focuses on generating images featuring explicit content and improves the shape of specific anatomical features. The model works better with style LORAs compared to previous versions, though image quality can be unstable.animecervixconceptfemalegirlslorapussy gapesexyspread pussywoman

LoRA · Pony

Breast Size Slider

11.5K
This slider model allows for precise control over breast size in SDXL models, from slight reductions to significant enhancements. It is designed to primarily affect breast size, with minimal impact on other body features, and offers broad compatibility across various SDXL bases. No specific activation prompt is needed; use the slider directly for immediate adjustments.breastsbustyconceptenhancergiganticgirlshuge breastspuffyrealisticslidersmall breastswoman

LoRA · IL

extreme insertion | ponyXL, illustriousXL

41.5K
extreme insertion or large insertion to generate anal content, lower the weight v2.0: added x-rayanimeconceptgirlssexsexyvaginawoman

LoRA · IL

BlackWhiplash (BWL) [Illustrious] Style LoRA

61.4K
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.animeblackwhiplashbwlcartoonfemboyfutafutanarigame charactergirlshentailoramalemanstylevideo gamevideogamewoman

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

LoRA · Pony

Osorubeshi Pony style LORAs

51.2K
These LORAs are trained to generate images in a Pony style. They can be mixed in reduced proportions and don't require special generation parameters. The Shonka model integrates three styles, selectable via specific keywords.animefemalegirlslorarealisticsemirealistsexystylewoman

LoRA · SDXL

Detailed nipples XL

11K
This Lora adds detailed skin texture to nipples, primarily for use with adetailer in SDXL. It's designed to enhance realism but may require adjustments based on pose and size, and is recommended with specific adetailer settings.adetailerbreastbreastsconceptdetailsfemalegirlsnipplenipplesphotorealisticrealisticsexyskinwoman

LoRA · IL

Nipple size slider - ILXL/PDXL | Goofy Ai

51K
The Nipple size slider model, ILXL/PDXL, allows users to adjust the nipple size in generated images. Key features include prompts in images, a sweet spot Lora range of -3 to 3, and recommendations for using Adetailer for faces and Img2img upscale with 4x-ultra sharp. It is maintained and hosted on Tensor.art.animeconceptgirlsillustriouxlnipplenipple sizeponysliderwoman

LoRA · IL

STYLES | Illustrious/Noob

51K
animegame charactergenshingirlskonosubalorasexystylestylesvideo gamewoman

LoRA · SD

Nyantcha / ThiccWithaQ style | Goofy Ai

4976
This model is designed to generate images in the style of Nyantcha/ThiccWithaQ. It offers a goofy aesthetic and requires specific prompts and settings like Adetailer for faces and upscaling techniques. The model is hosted on Tensor.art.animefemalegirlsstylestyleswoman

LoRA · IL

Krekkov Style | Goofy Ai

3938
Krekkov Style is a Goofy AI model hosted on Tensor.art. Prompts are available in the images, and the model is designed for use with Adetailer for faces and img2img upscaling. Use Lora at 0.7-1.animegirlskrekkov_stylelorasexystylestyleswoman

LoRA · Pony

Floox Style PDXL/illustrious | Goofy Ai

3936
Floox Style PDXL/illustrious is a model hosted on Tensor.art. Use the model with a Lora at 0.7-1 and ADetailer for faces. Consider img2img upscale and 4x-ultra sharp for optimal results.animeartflooxgirlsstylestyleswoman

LoRA · IL

T-Rex Studio V2 NEW!!- Hentai +18 - | STYLE | PONY XL | Illustrious XL | - COMMISSION - by YeiyeiArt

14894
T-Rex Studio V2 is a style model designed to generate artwork in the style of T-Rex Hentai Studio. It features Illustrious XL (trigger "TRexStyle") and PONY styles, with specific prompts recommended for each to achieve optimal results. The model is intended for creating +18 content.animecartoongirlsloransfwrealisticsexystylestylesvideo gamewoman

LoRA · Pony

Hentai Comic Random Generator (FULL COLOR) Pony / IL XL | フルカラーエロ漫画ランダムジェネレーター

6816
This model generates full-color hentai comics, particularly focusing on pony/IL XL styles. It adds noise and comic-style elements like frames and speech bubbles to images. It is designed to generate "infinite" erotic manga of preferred characters by using dynamic prompts and layering with other character LORAs.analanimeanuscomicconceptfellatiogangbanggirlsgroup sexhentaimasturbationnsfworalpornvaginawoman
Load more models

Showing 24 of 278

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.