Porn Factory AILogin

game character models for adult image and video generation

Compare 69 public adult AI checkpoints and LoRAs tagged game character. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

69 models available

LoRA · IL

T-Rex Studio Style (Illustrious/Pony)

2202
This Style-LoRA is based on the style of T-Rex Studio, known for hentai animation featuring distinctive heart-shaped pupils. Use prompts like "source_anime, anime studio" or "illustrioustrexxx" for optimal results, and the tag "trexxx" may also improve outcomes. For explicit content, utilize specific positive and negative prompts to control censoring.animegame charactergirlshentailorasexystylewoman

LoRA · SD

【Art Style】Sakimichan Style

3200
The Sakimichan Style LoRA model generates images in the art style of Sakimichan. It is trained on a dataset of approximately 800 images and works best with 784mb VAEs at weights between 0.6 and 0.8, with a maximum generation resolution of 1024x1024. To improve results, the trigger tag 'sakimichan' should be used.animeart stylegame charactersexystyle

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 · 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 · SD

Real Mechanical Parts

3167
This model, Real Mechanical Parts version, generates images featuring mechanical parts integrated with organic bodies, primarily humanoids. To achieve intended results, users should use "cable, wires, reelmech and mechanical parts" in the positive prompt and "animal" in the negative prompt. The model is currently in alpha and trained on 768x768 resolution, requiring upscaling for best face clarity.animegame charactermechanicalphotorealisticrealisticstylewoman

LoRA · IL

Aosiai123 | Shiiro's Styles

2152
The Aosiai123 model, part of Shiiro's Styles, generates images in a traditional media style using the trigger words "traditional media,aosiai123_illu." It's optimized with samplers like DPM++ 2M Karras and Euler a, a CFG Scale between 1-7, and a Clip Skip of 2, with a weight range of 0.1 to 1.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman

LoRA · SD

Tifa Lockhart/ティファ・ロックハート (Final Fantasy VII) LoRA | 11 Outfits

2142
This LoRA model generates images of Tifa Lockhart from Final Fantasy VII in eleven different outfits. It was trained on NAI and tested at 0.8-1.0 strength. Prompts are provided for each outfit, including her original and remake appearances, dresses, and Ever Crisis outfits.animecharacterfemalefinal fantasyfinal fantasy viifinal fantasy vii remakegame charactervideo gamewoman

LoRA · IL

Marvel Rivals - GAME STYLE - | PONY XL | Illustrious XL |- by YeiyeiArt

1136
This model generates artwork in the style of the game Marvel Rivals. Use the trigger word "MarvelRivals" along with "cartoon, dutch angle" for optimal results. The Illustrious XL version can be further refined with "Semi realistic."animecartooncomicfantasyfurrygame characterloramalemanmarvelphotorealisticrealisticstylevideo gamewoman

LoRA · SD

Undersized Bra (Outfit/Concept) LoRA

1134
This LoRA generates images featuring undersized bras. It is triggered by "undersized bra" and emphasizes large breasts with related features like cleavage and skin indentation. It offers options for both clothed and nude variations.animebrabreastsclothingfemalegame characterundersized clothesunderwearvideo gamewoman

Checkpoint · SD

Clarity

11129
Clarity is a Stable Diffusion fine-tune for generating photorealistic images with an emphasis on human anatomy, capable of producing both NSFW and SFW content based on prompt tags. It uses a fine-tuned base model for realistic skin textures, improved fabric details, and enhanced lighting/shading.base modelckptfantasyfemalegame charactergeneral purposehardcoreinpaintingmennudespersonphotographyphotorealisticportraitsrealisticsexyvideo gamewoman

LoRA · Pony

Mavis Dracula PonyDiffusionXL/illustriousXL

2127
Mavis Dracula PonyDiffusionXL/illustriousXL is a LoRA model for generating images of Mavis Dracula from the "Hotel Transylvania" series. It's recommended to use prompts like "m_d, 1girl, vampire, black hair, blue eyes, goth makeup" with a weight of 0.6-0.8 and the Fantasy Blend XL or Pony Diffusion XL models.charactergame charactergirlssexyvideo gamewoman

LoRA · IL

Smooth Styles (Illustrious/NoobAI)

0120
Smooth Styles provides various artistic styles and effects when used with Illustrious and NoobAI models. These styles offer diverse visual outputs depending on the checkpoint and prompts used, encouraging experimentation. The model family includes a newly added "Lambda" style.animeanime characterscyberpunkfantasygame charactergirlshdillustriousrealisticscience fictionsemi-realisticsexystylestylesvideogame

LoRA · SD

【Character】alice (nikke)

7114
This LoRA model generates images of Alice from Goddess of Victory: NIKKE. It utilizes tag dropout to prevent overfitting and offset noise for better image lighting. The model is optimized for size and quality, and the NAI's VAE is recommended with weights between 0.6 and 0.8.animecharactergame charactergirls

LoRA · SD

Dark Magician Girl LoRA

6106
This LoRA generates images of Dark Magician Girl. It works best on anime models with a weight of around 1 (0.6-0.7 for older versions) and is triggered using "dark magician girl" along with the desired outfit description.animecharacterconsistent characterdark magician girlfemalegame charactergamesgirlsmangasexytcgyu-gi-oh!

LoRA · IL

Kinu Nishimura - (CAPCOM) - STYLE - | Illustrious XL | - COMMISSION by YeiyeiArt

1103
This model replicates the art style of Kinu Nishimura, utilizing the activation keyword "NishimuraXL". It's designed to produce images in Nishimura's style and can be further adjusted for strength.animeart stylecartooncharactersfantasygamegame charactergirlslorarealisticretrosexystylestylesvideo gamewoman

LoRA · SD

Purah (The Legend of Zelda: Tears of the Kingdom) LoRA

3102
This LoRA generates images of Purah from The Legend of Zelda: Tears of the Kingdom, trained on NAI. Use the trigger word "purah" and suggested prompts for her common appearance. Recommended strength is 0.7-0.9.animecharacterfemalegame characterthe legend of zeldavideo gamewoman

LoRA · NAI

Mai Shiranui (illustrious, NoobAI-vPred & PonyXL)

481
Mai Shiranui (illustrious NoobAI-vPred PonyXL)This was a requested one thank you! Nothing really to add really, the testing was pretty simple and fun to do. I've always liked this character...for reasons >.>animecharactergame characterillustriousloramai shiranuiponysexyvideo gamewoman

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

DDLC [sd1] Monika + Sayori + Natsuki + Yuri (Doki Doki Literature Club)

064
💌 All the dokis are here in a single small Lora! You can prompt the 4 girls by name as well as their school uniform, but you can use more specific tags if you need. Try putting the girls in different clothes, or putting a different character in the doki uniform. Hope you enjoy it! Works at weight 1. Made using my Lora guide (https://civitai.com/models/22530).animecharactercharacterpackddlcdoki doki literature clubgamegame charactergirlpack

LoRA · IL

Evelyn Chevalier 伊芙琳・舒瓦利耶 | Zenless Zone Zero [IllustriousXL]

154
This model generates images of Evelyn Chevalier from Zenless Zone Zero. Key features include blonde hair, purple eyes, and detailed descriptions for her default outfit and an alternate version. The recommended weight is 1.0.animecharacterevelyn chevaliergame charactergirlswomanzenless zone zero

LoRA · SD

2B (YoRHa No.2 Type B) / Nier: Automata

453
This model generates images of 2B from Nier: Automata, with weight 0.7 recommended. It includes outfits with and without her blindfold, which swaps between black blindfold/covered eyes and blue eyes. The model also enables switching between her dress and a leotard outfit, specifying details such as clothing cutouts, sleeves, and gloves.2bandroidcharactergamegame characterloranier automatayorha no.2 type b

LoRA · IL

[ILLUST] Lillie | Pokémon Sun & Moon

051
This model generates images of Lillie from Pokémon Sun & Moon. It focuses on her appearance, including her hairstyles (twin braids, ponytail) and eye color, and can depict her in various outfits like her white dress or white shirt and skirt. Recommended weight is 0.7~1.0.animecharactergame characterlilliepokemonvideo 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 · IL

Ka Marukogedago | Style LoRa

038
Ka Marukogedago is a style LoRa model that generates images with abstract, watercolor, or oil painting styles. The trigger word is k4_illu, and useful tags include abstract, watercolor, traditional media, scan, and blending. It is recommended to use a weight between 0.1 and 1, with samplers DPM++ 2M Karras or Euler a, CFG Scale between 1 and 7, and Clip Skip of 2.abstract paintinganimeartart styleartistartstylebackground platebackground ponybackgroundscartooncolordetailflowersgame charactergeometrygirlsloramalemanmangamanga artistnsfwpaintphotorealisticrealisticshapesshiirostylestyleswoman
Load more models

Showing 24 of 69

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.