Porn Factory AILogin

AI porn models for adult image and video generation

Browse the building blocks behind the factory. Filter checkpoints and LoRAs by image or video support, base model, and tags, then open any version directly in the unified generator.

1487 models available

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 · IL

Ass Implants - IllustriousXL

2188
This LoRA model enhances images with the appearance of ass implants, creating a perfectly round or bubble butt effect, primarily in anime/2D style. It is designed to work within a weight range of 0.8 to 1, and can be used for both SFW and NSFW images with appropriate prompting.ass implantsbubble buttconcepthuge asswoman

LoRA · Pony

マン汁/pussy juice

3186
The strength of Lora is recommended to be around 1.0. It is assumed that it is in a drooping state.concept

LoRA · Pony

X-ray (vaginal, anal & oral) LoRa | PonyXL & Illustrious

4184
This model creates anime-style images depicting visible penetration (vaginal and oral) through bodies. It's designed for PonyXL & Illustrious models. It is NSFW content and should be used responsibly.animeconceptgirlswomanxray

LoRA · Pony

Ingrid (Taimanin Series, Hell Knight Ingrid) NoobAI-XL (Eps / V-pred) / PonyXL / SD 1.5

3183
Ingrid (Taimanin Series, Hell Knight Ingrid) is a character model for PonyXL, NoobAI-XL, and Stable Diffusion 1.5. It generates images of the character Ingrid in various outfits like Hell Knight, business woman, secretary, and bride. The model leverages V-pred and Epsilon techniques for improved image generation and has specific quality settings for optimal results.animeart stylecharacterfemalegame charactergirlshentaiingridlorapersonrealisticsexyvideo gamewoman

LoRA · SDXL

Crying - sliders / ntcai.xyz

0182
This model generates crying expressions based on slider inputs. It was trained on 6000 instances using a batch size of 12, over 500 steps. The training was based on the TurboXLLCM Super Mario Merge model.charactercrycryingemotionssliders

LoRA · Pony

マンスジ/cameltoe

2182
The strength of Lora is recommended to be around 1.0. Without Lora, it's modest, so I made it. There are other similar ones. I don't think there's anything particularly good about it.concept

LoRA · IL

Create Concept - Concept (Illustrious | Pony | Flux.1 Dev)

0181
This model generates unique concepts, particularly focusing on digital paintings, character and animal focus, and scenery. It works best with the Add Micro Details model and various keywords like artwork, digital painting, and character focus. Results vary significantly depending on the checkpoint used.animeartworkconceptconcept artdigitalink workpaintingponystyle loratraditional

LoRA · Pony

Exploding Clothes / Torn Clothes for Pony+IL

2180
This model generates images of characters with exploding or torn clothing, suitable for Pony and Illustrious models. It utilizes tags like "exploding clothes," "torn clothes," and "surprised" to achieve the effect. The model can also produce related imagery like censoring and wardrobe malfunctions.clothingclothing loraconcept loraexploding clothesexplosionwardrobe malfunction

LoRA · SDXL

Multiple XL Sliders - Age, weight, Hands, etc

2179
This model provides a collection of sliders, including age, brightness, and nose size, for image generation using SDXL and PONY models. The sliders were originally created by Rohit Gandikota and converted to safetensor files for easier use. These sliders allow for more granular control over generated image attributes.tooltoolkittools

LoRA · NAI

裂けた服/torn clothes(ill,pony)

2179
The strength of Lora is recommended to be around 1.0. It is also produced without Lora. The degree of tearing changes slightly. In particular, I think the crotch part will change.clothing

LoRA · SD

cowgirl with hands on knees

2179
襲われた感じにしたかった。 prompt : pov,astride Recommended option : thrustingconceptcowgirlnsfwpovsex

LoRA · Pony

Bara Juice (Pony/ILXL)

1178
A bara style based on a checkpoint from Skumerz that its not available here on civit. Hope u guys enjoy. Feed Back is appreciated.style

LoRA · IL

Shortstack

0177
conceptshortstacksmall waistthick thighs

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

LoRA · Pony

Second Skin - Ultra Skin Tight

1176
This model modifies clothing rendering to be tighter and more revealing. It enhances anatomical detail visibility through clothes and can be used with specific tags for further control. It's recommended to use negative prompts like "Nude" to avoid unwanted nudity.animeclothesconcepthentainsfwsexywoman

LoRA · Pony

Lola Bunny (Space Jam) Pony + Illustrious

1175
This model recreates Lola Bunny from the 1996 Space Jam movie. It aims for character accuracy and includes an illustrious version.cartooncharacterfurrylola bunnylooney tunesmoviespace jam

LoRA · SD

penis on face concepts

2174
This model generates images depicting penises on faces in various configurations. It was trained on tags such as "penis on face," "penis on mouth," and "cheek press," and can produce images with multiple female subjects. The output quality may vary.animeconceptnsfwpenis on face

LoRA · SD

EnhancedDetail Slider

0174
Weight 3~-3 Sweet point 1~2 如果你喜歡我的工作可以幫我買杯咖啡，謝謝 If you like what I do, you can buy me a cup of coffee. Thanks. 私の仕事を気に入っていただけたら、コーヒーを一杯おごってください。 ありがとうございます。 https://ko-fi.com/vicentma

LoRA · Pony

Perfect Ass - Pony/Illustrious

1173
New and custom content here: https://aicollective.art (https://aicollective.art/) Pony V3 Weight 0.6-1, you can download the model for free on my webpage listed above Create perfect bubble butt asses with this LoRA, weight 0.4-0.8 Hope you enjoy! As always any feedback and submitted images are welcome, thanks :)ass,bubble buttconceptperfect assround ass

LoRA · SDXL

Upright straddle sex - standard side view

2170
This model generates images of upright straddle sex from a side view, based on the XL 1.0 architecture. It's recommended to use a weight of 1.0, and previous versions were tested on various models with a weight range of 0.7-0.8.animeanime styleposessexstraddle

LoRA · IL

Ass front view - Lying on stomach pose | Updated to SDXL Illustrious

2170
This model generates images focusing on the rear view, specifically the "ass front view" pose, and lying on the stomach. The activation prompt is "assview" (previously "assfrontview"), and it works best with prompts including terms like "ass," "lying," and "on stomach."assconceptlyingpose

LoRA · SD

【Character / Art Style】Fashion Girl

14170
The Fashion Girl model generates images of fashionable girls, trained on a dataset of realistic and photorealistic images. It includes LyCORIS and LoRA versions, and the trigger tag is 'fashi-girl' for some versions. The model is continuously updated to improve image quality and fix issues.animeconceptgirlsrealistic

LoRA · Flux.1 D

FLUX [pro] 1.1 Style Lora - Extreme Detailer for [FLUX + ILLUSTRIOUS]

3168
FLUX [pro] 1.1 Style Lora is an extreme detailer trained using FLUX pro 1.1 images. It can significantly enhance image details, and its strength can be adjusted depending on the desired effect, offering both "strong" and "light" versions. The recommended strength is between 0.4 and 1.0, and the trigger word is aidmafluxpro1.1.animalsdetailsfluxflux proflux pro 1.1flux.1menphotophotographyprorealismscenerystylewoman
Load more models

Showing 24 of 1487

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.