Porn Factory AILogin

photorealistic models for adult image and video generation

Compare 132 public adult AI checkpoints and LoRAs tagged photorealistic. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

132 models available

LoRA · Pony

Better Bodies By Stable Yogi

1412
Better Bodies By Stable Yogi is a model that requires specific positive and negative embeddings at the beginning of your prompts for optimal results. Using the creator's negative embedding, detail sliders, and checkpoints is recommended for the best output.animeconceptgirlslarge breastsnudesphotorealisticrealisticsexyskinskin detaileswoman

LoRA · SD

Head Grab Blowjob/Fellatio - DarkMarauder

4402
A not perfect model of this pose, usually I generate a batch of 4 and select one or two good results. But anyway, it works.blowjobfellatiofemalegirlsphotorealisticpornposessexsex actsexywoman

LoRA · SDXL

Zavy's Dark Atmospheric Contrast - SDXL

2401
Zavy's Dark Atmospheric Contrast SDXL model enhances dark scenes by preserving tonal range and atmospheric depth. It addresses the limitations of other SDXL models, which often render dark scenes with an artificial effect. It brings out subtle details in shadows and allows for greater contrast adjustments in post-processing.atmosphericchiaroscurocontrastdarklow-keyphotographyphotorealisticstyle

LoRA · IL

Detail Tweaker Illustrious By Stable Yogi

1363
Detail Tweaker Illustrious By Stable Yogi is a model designed to work with specific negative embeddings and detail sliders for optimal results. It is intended to be used with related checkpoints created by the same author.conceptdetailerloraphotorealisticrealisticrealistic skinskinwoman

LoRA · SD

MengX girl_Mix

4348
MengX girl_Mix is an Asian female face model Lora that aims to make skin whiter and improve yellowing in images, sometimes adding a soft light effect, but potentially sacrificing skin texture. Optimal results are achieved with Asian models, ADetailer plugin use, and weights between 0.7 and 1.0. It produces expressive Asian female faces.characterfemalegirlspersonphotorealisticportraitsrealisticwoman

LoRA · IL

Jessica Rabbit -Disney- | Illustrious XL | PONY XL | SD 1.5 by YeiyeiArt

6317
This model by YeiyeiArt generates images of Jessica Rabbit in Illustrious XL, PONY XL, and SD 1.5 styles. Use the activation words "JessicaRabbitXLP" or "JessicaWaifu" along with specific prompts for desired results. The model supports generating images in the style of the original movie using the "Screencap" prompt.animeart stylecartoncharacterfantasyfemalegirlsloraphotorealisticrealisticsexywoman

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 · SD

Latex Dresses Collection By Stable Yogi

1292
This model is a collection focused on generating images featuring latex dresses. Refer to the model configuration for specific weight and trigger words. It is recommended to use a negative embedding and detail slider for optimal results.animeclothingfemalegirlsloraphotorealisticrealisticsexywoman

Checkpoint · Pony

iNiverse Mix(SFW & NSFW)

12287
iNiverse Mix is a realistic model optimized for generating images of Asian girls with intricate details, supporting various countries and styles. Different versions like Pony, Flux, and XL offer progressive updates, with some optimized for specific hardware. It also has versions to generate Chinese outfits.base modelchinesefemalegirlshanfunsfwphotorealisticrealisticsexysfwwoman

LoRA · IL

Sinozick | Shiiro's Styles | Niji

3281
Sinozick is a style model that generates illustrations with gradient and spot color effects. It is triggered using the words "Sinozick_illu, gradient, spot color" with a weight between 0.1 and 1. Recommended samplers include DPM++ 2M Karras and Euler a, with CFG Scale ranging from 1 to 7, and a Clip Skip value of 2.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman

LoRA · SD

Elixir — Enhancer LoRA 🧪

1276
Elixir is a LoRA designed to enhance older models with renewed vitality and provide subtle improvements to newer ones. Created using the NinjaFix algorithm, it blends neurons from various neural networks to form a refined LoRA. It refines noise, lighting, styles, textures, details, and other elements.cinematicepicfashionillustrationmasterpiecephotorealisticstylestyleswoman

LoRA · SDXL

Finenude

3273
Finenude is a LoRA model, specifically trained to generate images of nude women. It's trained on a large dataset of high-quality photos, but the initial version is a proof-of-concept and improvements are planned, including dataset filtering and captioning. Future development aims to include male photos and improve anatomical accuracy.characterfemalensfwphotorealismphotorealisticsdxl

LoRA · IL

96yottea | Style LoRa

2272
This Style LoRa generates images in the style of 96yottea illustrations. Use a weight between 0.1 and 1, triggering with "69yottea_style_illu", and experiment with DPM++ 2M Karras or Euler a samplers.animecartoongamegame charactergirlsilluloramalemanpaintingphotorealisticrealisticstylestylesvideo gamewoman

LoRA · SD

Riding Sex Scene [SMF]

3271
This model generates explicit sexual content, intended for use with realistic checkpoints. It is recommended to use weights between 0.5 and 0.9 when mixing it with other LoRAs, and it works best with resolutions like 512x712 and 712x512.femalegirlsphotorealisticposeposesrealisticscenesex actsex posesexywoman

LoRA · SD

Pika's Super Realistic Detailed Eyes [SRDE]

0267
Hi everyone! This LORA takes ultra realistic macro photos of human eyes! You can use it directly in Prompt to take macro photos of eyes, or you can use it in inpaint. Share your generations, I will try to improve this LORA as I'm very interested in it!conceptconcept loraphotorealisticrealistic

LoRA · Flux.1 D

Xpenis Uncut Flux

1262
This is a flux model trained to generate images at resolutions like 1216x832, 832x1216, and 1536x1024. It is designed for realistic outputs and flexible generation, including chimera.concepterectionflaccidgayhomoeroticmalemannakednaked gaynudepenisphotorealisticpornuncut

LoRA · ZImageTurbo

NiceGirls UltraReal

19257
NiceGirls UltraReal is a model focused on generating images of realistic beauty, particularly of Asian women in the Z-Image edition. A Qwen version is also available for cleaner results, and it can be blended with other LoRAs typically using a weight around 0.6.beautycharacterphotorealistic

LoRA · Wan Video 2.2 I2V-A14B

Pov_Blowjob

5246
This model generates images likely of explicit or sexual content. It utilizes Wan2.2 (High) v1.0 for denoising and Wan2.1 v1.0 for refinement.animebjblowjobgirlsloraphotorealisticposespovpov bjpov sexrealisticsexywoman

LoRA · SD

Onoff - On/Off LoRA

8245
The Onoff LoRA generates side-by-side images of a subject, with one version clothed and the other undressed. To use it, begin your prompt with "onoff" followed by a description of the subject and their clothing. Different versions of the LoRA are optimized for specific resolutions.conceptfemalenakednudephotorealisticsexyundress

LoRA · SD

GirlfriendMix_v1

3224
GirlfriendMix_v1 is a model that incorporates elements from koreanDollLikeness, aespaKarina, aliceNikke, JKuniform, and LORADilraba. It is recommended for use with XXMix_9 or majicMIX realistic base models. Recommended settings include VAE, specific samplers and steps, Clipskip, Upscaler, and CFG Scale values.femalegirlsphotorealisticrealisticsexywoman

LoRA · SDXL

Perfect Round Ass SD1.5/SDXL/FLUX | olaz

4218
This model generates images focused on round buttocks, specifically viewed from behind. It is available for SD1.5, SDXL, and FLUX, with recommended LoRA weights varying from 0.7 to 1.0 depending on the base model. It was created in response to user requests for a LoRA focused on ass roundness.assbody shapesconceptphotorealisticsexywoman

LoRA · Pony

Rembrandt (Low-Key) Lighting Style XL + SD1.5 + F1D + Illu + Pony

0196
This model generates images with a Rembrandt low-key lighting style. It's trained on the SDXL base model and incorporates F1D, Illu, Pony, and SD1.5 datasets.cinematiccinematic lightcinematic lightingcinematographyfilmfilmicfluxlightinglow-keymoviemovie dynamicmovie stillmovie stylephotophotographyphotorealisticphotoreallisticrealrealismrealisticrembrandtshadowstyle

LoRA · SDXL

Hidden SpyCam Changing Room XL/Pony

0188
More trigger words: Leg up / arms up Holding clothes from the side/ from behind Bent over/ leaning forward Underboob, Underbun, Sidewinders, Upshirt, upskirt, sideboob Ceiling light, yellow lighting, mirror, reflection Tried to make h15cvdr a trigger word but it just makes boats, planes, and cars lol.candidconceptcreepshotphotorealisticsexywoman

LoRA · SD

Yae Miko | Realistic Genshin LORA

14176
This model generates realistic images of Yae Miko from Genshin Impact, utilizing specific embeddings and VAE. It comes in mixed, standard, and full versions, each optimized for different levels of compatibility with other LORA models. Optimal weights for image generation vary depending on the version used.animecharactergame charactergenshin impactgirlslorapersonphotorealisticrealisticvideo gamewomanyae miko
Load more models

Showing 24 of 132

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.