Porn Factory AILogin

nsfw models for adult image and video generation

Compare 158 public adult AI checkpoints and LoRAs tagged nsfw. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

158 models available

LoRA · Pony

Krystal (dogzeela) / Star Fox - [Pony/Illu]

1107
KrystalSDXL is a Character Lora for generating images of Krystal from Star Fox in a pony style. It uses the trigger word "KrystalSDXL" and benefits from character and outfit tags, with a recommendation to use "3D" in the negative prompt to avoid 3D generations.animecharacterfurrynsfwsexwoman

LoRA · Pony

Pov Lying on Top [remake]

2103
This LoRA generates images of characters lying on top of or next to the viewer from a POV perspective. It offers customizable prompts to adjust elements like viewing angle, clothing, and intimate acts. Core prompts include "Lying on top" and "Lying next to viewer".animelying downnsfwposeposespovsexywoman

LoRA · IL

Suoiresnu - NSFW Style - Illustrious XL

499
The Suoiresnu - NSFW Style - Illustrious XL model recreates the artistic style of Suoiresnu. It is compatible with both SFW and NSFW content. Use the trigger word "suoirensu" with a model strength of ~1.0 for best results.animehentailoransfwstyle

LoRA · IL

(IL+Pony) Rear Naked Choke / 裸絞め

197
This model generates images of the "rear naked choke" submission hold. It addresses the issue of base models often depicting incorrect choking techniques when prompted with "choke hold." Use the trigger word "choke hold (rnc)" with a recommended weight of 1.conceptnsfw

LoRA · SD

(SDXL/Pony/SD1.5) Sono Bisque Doll wa Koi wo Suru - Marin Kitagawa

196
This LoRA model generates images of Marin Kitagawa from "Sono Bisque Doll wa Koi wo Suru," trained on original anime images. It supports multiple outfits and hairstyles, including school uniform, bikini, gothic dress, and demon-themed attire. Use the provided trigger words to generate specific looks.animecharacterkitagawakitagawa marinloramarin kitagawamy dress up darlingnsfw

LoRA · SDXL

LEAKCORE (LEAKED NUDES STYLE, Realism, Amateur)

696
LEAKCORE produces images in the style of amateur, realistic photographs reminiscent of "leaked" content, without using any actual leaked photos. It's trained primarily on the LUSTIFY OLT model and uses the trigger word "amateur photo" to achieve the desired aesthetic, often enhanced with "film grain."girlsnsfwnudepornsexystyle

LoRA · SD

Public Exposure, Embarrassed, Uterus Drawing

285
This model generates images featuring specific poses and concepts like shocked faces, spread legs while sitting, uterus drawings on the body, standing with raised arms, and sitting with arms around knees. Version 2 adds poses such as sitting while covering the face and an embarrassed spread pussy pose. The model is available for both SD1.5 and SDXL, though the uterus drawing concept may require inpainting in SDXL.nsfwnudeposesuterus

LoRA · IL

Areolae size slider

083
Areolae size sliderareolaeconceptnipplensfw

LoRA · IL

Hentai Comic Random Generator (START STORY) (1Page to 3Page) Pony / IL XL | エロ漫画ランダムジェネレーター（ストーリ序盤 ）1ページ～3ページ

183
This LORA generates 1 to 3 page prologues for hentai comics, allowing specification of the number of pages. It focuses on creating basic characters, backgrounds, and suggestive situations typical of comic introductions. Width 832 Height 1216 is recommended.analanimeanuscomicconceptfellatiogangbanggirlsgroup sexhentaimasturbationnsfworalpornvaginawoman

LoRA · Wan Video 14B i2v 720p

Eye contact blowjob

280
This model generates images and videos of women performing blowjobs while maintaining eye contact with the viewer. It utilizes Pony and Flux LORAs, with the "Eye contact blowjob" keyword suggested for the Pony version, and works with various styles and detailed depictions. The model can also be used to generate videos with guided eye movements.1man1womanactionblowjobdeepthroateye contacteye contact blowjobeyesmouthnsfwone manone womanoralpenissex

LoRA · SD

POV Paizuri-Twisted Breasts | LoRA

377
This LoRA model generates images of paizuri scenes. Use the trigger word "paizuri" with a weight of 0.8-1, optionally including "breasts squeezed together" and "penis" for desired results.animeconcepthentainsfwpaizuri

LoRA · SD

Yuri kiss

172
not convinced with controlnet for kissing, so I'm testing with loraskissnsfwrealistic

LoRA · IL

0__11Xx | Shiiro's Styles | Niji

265
The model, 0__11Xx | Shiiro's Styles | Niji, generates images with surreal and glitch themes, using the trigger word "0__11Xx_illu". Effective sampling can be achieved with DPM++ 2M Karras (20-40 steps) or Euler a (25-40 steps), CFG Scale 1-7, and Clip Skip 2. Usable weight range is from 0.1 to 1.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman

LoRA · SD

POV Missionary-Raised Legs | LoRA

565
This LoRA model generates images with a missionary position and vaginal sex. Trigger words are "missionary, vaginal, sex", and a weight of 0.7-1 is recommended.animensfwpornposeposessexvaginal

LoRA · IL

sexy details

163
This is a LORA trained on handpicked images of my personal preference. It is heavily nsfw based and enhances detalisation and facial expressions.enhancernsfwstyle

LoRA · SD

ONArmor / Meat Shield

261
This Lora model generates images featuring a humanoid figure with a "meat shield," often in suggestive poses. It is trained on Anything v3 and activated using the keywords "onarmor," "meat shield," and "fanny packing." The model primarily focuses on the pose, and additional prompts may be needed for explicit actions.bondageconceptfanny packinghentaimeatshieldmonsternsfwonarmorwoman

LoRA · Wan Video 2.2 I2V-A14B

Ultimate DeepThroat I2V Wan2.2 Video LoRa - K3NK

961
This LoRA model is designed for generating deepthroat blowjob scenes using Wan2.2 I2V. It was trained on a dataset of short clips and can handle various points of view in these scenes, though some positions may require specific prompting to avoid artifacts. The model aims to create realistic depictions of this act through text-to-video or image-to-video generation.69 blowjobactionblowjobdeepthroatnsfwpov blowjobsideview blowjob

LoRA · IL

ZH LoRA | Group Grab | Illustrious

060
extanimeconceptconcept loragirlsgrab breastgrabbinggroupgroup sexhentaimultiplensfwposesexywoman

LoRA · IL

legs lock with variants

360
Buy me coffee https://unfazedanomaly964.gumroad.com/l/buymeacoffee (https://unfazedanomaly964.gumroad.com/l/buymeacoffee) Trained on XL Best result with weight between : 0.3-0.8 and the CFG between 6-8 Reviews are really appreciated, i love to see the community use my work. If you like my work, please tip meanimegirlskissloralyingmating pressmissionarynsfwpornposessexsexysittingstandingstraddlestraddling,woman

LoRA · SD

(POV) Blowjob + Creampie LoRA

757
This LoRA generates "POV" and "side view" blowjob images, including cum-in-mouth and deepthroat depictions. It supports both POV and side perspectives and has improved anatomy in version 3. It is based on UberRealisticPornMerge.blowjobcum on facensfwphotorealisticpornposespov blowjobsexual activitywoman

LoRA · SD

Flashing Tits / Exhibitionism

156
Check images for prompting.actionboobsgirlsnsfwtits

LoRA · IL

Fondled

255
The Fondled model produces images, with best results using a weight of 0.5-0.8 and CFG of 6-8. It currently has known issues with hands, which the next version aims to address.animebreast grabgirlsgrabbinggropegropingmanmultiple menmultiple_boysnsfwposessexywoman

LoRA · IL

Facesit / Facesitting POV (Illustrious)

251
This model is intended to enhanced images where the POV is an imminent facesit Trained on Illustrious V0.1 Tag: facesitpovILL, face sit pov • Helpful tags: impending facesit, imminent facesitting, facesitting pov, from below, standing over viewerconceptfacesittingnsfwpov

LoRA · IL

Dancer Lingerie

348
.clothesclothingdancerlingeriensfwnsfw clothes
Load more models

Showing 24 of 158

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.