Porn Factory AILogin

3d models for adult image and video generation

Compare 16 public adult AI checkpoints and LoRAs tagged 3d. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

16 models available

Checkpoint · Pony

Realism By Stable Yogi (Pony)

347.6K
Realism By Stable Yogi (Pony) is a model for image generation on Civitai. For optimal results, use specific positive and negative prompts available via linked resources.2d3danatomicalart styleasianbase modelcgidigital artdigital illustrationdreamlikearteuropean girlfantasyfantasy artgirlsillustrationindian womeninpainlandscapespaintingsphotorealisportraitsrealismrealisticscifiseni-realisvideo gamewoman

Checkpoint · SD

DreamShaper

576.7K
DreamShaper is a Stable Diffusion model designed to generate art and illustrations, aiming to be a versatile "swiss knife" model capable of producing a wide range of styles, including portraits, backgrounds, and anime-style characters. It has a distilled version (LCM) that runs much faster for video and real-time applications.2d3danimeart stylebase modeldigital artdigital illustrationfantasyfantasy artgirlsillustrationinpaintinglandscapespaintingsphotorealisticportraitsrealisticscifivideo gamewoman

Checkpoint · IL

Nova Furry XL

135.7K
Nova Furry XL is a 2D/2.5D furry checkpoint model designed to generate detailed images of fur, scales, and feathers. It aims to be an XL-fied version of Peaki Furry. The model has different versions like Illustrious and Pony that works well with the recommended setting provided.2.52d3danimalsanthrobase modelferalfurryfurry stylesdxlsexywomanxlyiff

Checkpoint · Other

Perfect World 完美世界

503.5K
Perfect World is a semi-realistic model designed to create beautiful, realistic faces with stylized bodies. It balances realism and anime aesthetics, with a focus on NSFW/hentai concepts and flexibility across various themes.3dartstylebreastsfantasyfantasy artgirlshentaimixpornsemi-realisticsexystyleulzzangwoman

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

LoRA · SDXL

3D rendering style

14742
This model is designed to achieve realistic CG 3D rendering effects, particularly excelling in producing high-quality, detailed 3D images. It is recommended to use with specific settings like DreamShaper XL Turbo, CFG scale 2, 8 sampling steps, and the DPM++ SDE Karras sampler.3d3d styleanimecgcute girlfemalegirlsmidjourneynijistyle

LoRA · Pony

Hyperrealistic [Pony | Illustrious]

3571
This Lora model generates hyperrealistic images, focusing on close-up, portrait, and upper body shots. It utilizes high-quality images and is responsive to positive and negative prompts.3danimecartoongame charactergirlslorarealisticstylevideo gamewoman

LoRA · Flux.1 D

(Detail Enhancer) 3D Blender Style

2424
The Detail Enhancer 3D Blender Style model aims to generate images with a high-quality, realistic look, similar to 3D renders produced in Blender. It supports trigger words like "ayn0_st", "realistic", and "3D" to control the level of detail and 3D elements, offering options ranging from photorealistic to stylized and themed renders. This model uses advanced techniques like ray tracing and ambient occlusion to achieve detailed textures, realistic lighting, and high-resolution output for a cinematic feel.3danimeartblenderepicgame charactermannsfwponyxlrealisticrendersfwstylestyleswoman

LoRA · SD

ReaLora/Realistic skin texture/

3296
ReaLora transforms art into realistic depictions of people with detailed skin texture, while also enhancing other image elements. It is recommended to use with a Lora strength between 0.1 and 0.7, a CFG scale of 7 or higher, and at least 24 steps.3daddaianatomicalanimeartcartooncinematicdetail facedetailsfantasyfemalefotorealismogame charactergirlsillustrationloramanmodelmonstersmore skinsnsfwpersonphotographyphotorealisticportraitsrealrealismrealisticrealorasexysfwskinstylestylesvideo gamewoman

LoRA · SDXL

SDXL YAMER'S STYLE 😍 Princeps Omnia LoRA

041
SDXL YAMER'S STYLE 😍 Princeps Omnia LoRA is a model designed to reinforce the creator's artistic style or inject it into other checkpoints. It excels at generating colorful, chaotic, and aesthetically unique images, especially with abstract works and singular character images. The LoRA was trained using images in various styles and resolutions, but 576x1024 is recommended.2d3dactressalphaanimeanime irlartbeautifulbeautiful girlboyscutedarkfantasyfantasy artfemalegamegame charactergirlpackgirlsillustrationillustrationskawaiiloramanmemeneworiginalitypersonphotorealisticportraitsquality uprealisticrealisticlorasdxlsdxl 1,0sdxl animesdxl style lorasfwsharpstylestyle lorastyle mixstylemixstylesterrorvideo gamewomanxlxl1.0yamer

LoRA · Flux.1 D

Fractal Geometry Style [FLUX+SDXL+1.5]

039
This model generates images in a fractal geometry style. It is triggered by the keyword "ral-frctlgmtry" and is based on FLUX, SDXL, and 1.5 architectures.3ddepthfractalstyle

LoRA · SD

【Character】Akiryo's Mai

333
This LORA model allows users to generate images of Shiranui Mai using the trigger tags 'akiryo-mai' and 'shiranui mai', with weights between 0.6 and 0.8 recommended. A realistic version is available for use with realistic models; set clip skip to 2 for optimal results. The model has been updated with improved datasets and retraining, including adjustments to sampler settings for stable image generation.3dcharactergame character

LoRA · IL

Genshin Impact In-game Style (Illustrious and Pony)

033
This model replicates the visual style of Genshin Impact in-game screenshots. It's trained on a dataset of locations, characters, and poses using "G3NSHIN" as the trigger word. Increasing the LoRA strength or adding "3D" can enhance the style.3danimegamegenshinstyle

LoRA · SD

M_Scene 卡通景景

31
M_Scene 卡通景景 generates cartoonish scenes in a toon or Pixar style with 3D elements. It's effective with the REV checkpoint and can create single buildings at smaller resolutions or sandbox environments at larger resolutions.3dbuildingscartoonfantasylandscapessencevideo game

LoRA · SD

Shenhe - LoRA Collection of Trauter's

40
This is a collection of anime LoRAs featuring characters from various series. It provides LoRAs for personal use with sample prompts and metadata, focusing on the creator's specific use cases. It contains guides and instructions on how to use LoRAs.2d3danimecharactergenshin impact

LoRA · SD

Hipoly 3D Model LoRA

150
This LoRA is trained on high-polygon 3D model images to generate clean, high-resolution skin, hair, and detailed clothing. It enhances 3D texture and depth without requiring a trigger word, and its style can be controlled using `3d` and `realistic` tags. The LoRA improves detail without eroding the base model's art style.3dfantasygame charactergirlsrealisticstylewoman

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.