Porn Factory AILogin

dark models for adult image and video generation

Compare 15 public adult AI checkpoints and LoRAs tagged dark. Review each model's versions, base-model family, trigger words, previews, and validated image or video workflows before you create.

15 models available

LoRA · SD

epi_noiseoffset

122.8K
darkhigh contrastnoise offsettool

LoRA · IL

Lighting / darkness slider

22.2K
This model is a lighting intensity slider that adjusts the brightness of light sources in an image for natural control. To use it effectively, add lighting descriptors to your prompt, like "blue hour" or "late night," and be mindful that dark-related keywords will significantly darken the image. Specifying eye color may be necessary to avoid unintended blue eye effects in dark scenes.brightnessdarklightingslidertoolwomen

LoRA · Pony

Sinozick Style | Style Lora | Pony

31.7K
This LoRA replicates the art style of the AI artist Sinozick, best suited for original characters. Activate it using the prompt "sinozick style" and consider adding "dark theme, flat color" for better results.darkstyle

LoRA · IL

Darker Than Dark

2491
Darker Than Dark is a Lora model designed to add darkness or contrast to images, particularly anime-style pictures. It works well with base Pony/Illustrious models and can be controlled using tags like "dark," "night," or "day."conceptdarkdarknessnightnoctnoise offsetoffset

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

BBC Thug

1395
Trained on the BBC men of 'The Pitt' Prompts: BBC_TP, BBC, dark skin, dark skinned male, gold chain, grey sweatpantsbarabbcblackblackedcharacterdarkdark skingaythug

LoRA · Pony

LUT Color Grading - Slider

0299
The LUT Color Grading Slider applies film-like color grading to images, adjusting tone, mood, and color balance without affecting structure. It shifts color temperature, contrast, and shadows, creating diverse atmospheres and working across various styles. It is compatible with SDXL, ILXL, and Pony models.animecolordarkgradientilxllutponyrealismrealisticsdxlsliderstyle

LoRA · IL

HL's Styles - WAI | ILLUSTRIOUS

1235
HL's Styles - WAI | ILLUSTRIOUS is a LoRA model offering a WAI/ILLUSTRIOUS version of styling options. Information about each specific LoRA within the model can be found in the "About this version" section.darkstylestyles

LoRA · SD

Gloomifier slider LECO

1157
The Gloomifier slider LECO modifies images, making them gloomier with positive weights and happier with negative weights. Different versions offer variations in intensity and response to positive/negative weights, allowing for diverse results. Trigger words are not required, but descriptors like "dark" or "glowing" can enhance the effect.conceptdarklightslider

LoRA · SD

NoiseOffset_By_Stable_Yogi

0154
NoiseOffset_By_Stable_Yogi is a LoRA model designed to enhance contrast and produce darker images. It works best with specific keywords like "dark," "rim lighting," and "low key," and the weight should be adjusted based on the sampler used. It improves the image's overall contrast and darkness.darkdarkenlowranoise injectionnoise offsettool

LoRA · Flux.1 D

Retro Anime Flux - Style

3107
This LoRA captures a retro anime style, trained using FLUX. It's recommended to use a strength of 0.8-1.2, and detailed descriptions of the desired retro anime style are encouraged for best results. Future updates will focus on better grain control and dataset expansion.80s80s scifi80s style90s90s anime90s styleanimeartstyleartworkcharacterscinematiccomiccontrastcyberpunkcyborgdarkdigitaldigital artdrawingepicevangelionfantasyfuturisticgirlsglowillustrationlandscapelineloramanmangamechamechanicalmidjourneymidjourney animemidjourney v6mythicalnijiniji6outlineoutlinespersonretroretro animerobotsci-fiscience fictionstylestylesvibrantvibrant colorsvintagevintageanimevividwoman

LoRA · Chroma

Dark Art Style Chroma/illustriousXL

191
Chroma version : weight between [0.8,1.2], best at 1 trigger word : dark_art_style Illustrious version : weight between [0.7 ,1], best at 1 trigger word : dark_art_styledarkdark artdark fantasyhorrorstyle

LoRA · IL

Dark / Dim lighting / Dark Background

043
This LoRA strengthens darkness in images and improves directional lighting, stabilizing light sources. Use 'dark', 'dim lighting', or 'dark background' to trigger the effect, adjusting LoRA weight for intensity. It's also useful for dark shading and controlling light sources.conceptdarkdarknessdim lightinglow lightnight

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

Dark Side of Light

013
Dark Side of Light generates images, with showcased examples created using Fluxmania. It is recommended to use Clip L with the Fluxmania model, and all licensing conditions for the Flux Dev model apply.darkexperimental photofaded colorslow-keyphotogrphyphotorealimstyle

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.