PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generate
Models
Studio
Contest
Mio.2

Conversational creation

AI Tools
Guide

User LoRA

XL
Background

[Liminal Backrooms] Backrooms Style Background

#Scenery#Creepypasta

AI Tools

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
[Liminal Backrooms] Backrooms Style Background - AI Model cover image
Uploaded at
Jul 27, 2025, 12:57 AM
Uses
4.6k
Reviews
Dissatisfied
Trigger Words

backrooms

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

real sexy pose nude fullbody - AI Model cover image

User LoRA

real sexy pose nude fullbody
3
polish 1.0 - AI Model cover image

User LoRA

polish 1.0
124
One piece swimsuit - AI Model cover image

User LoRA

One piece swimsuit
6
[illu v0.1] Rinna Mayfield リンナ・メイフィールド | Shining Resonance - AI Model cover image

User LoRA

[illu v0.1] Rinna Mayfield リンナ・メイフィールド | Shining Resonance
8

Description

https://civitai.com/models/563476/liminal-backrooms-backrooms-style-background

Trained from screenshots I took in Gmod from the map Backrooms (Horror Map) and The Backrooms https://steamcommunity.com/sharedfiles/filedetails/?id=2812585895 https://steamcommunity.com/sharedfiles/filedetails/?id=2732733089

Works similar to the other BG LORA I've uploaded, so not much new to add there... Still a messy model, but with proper care can do good stuff. This time the tagging process was way simplified since the map looks almost the same everywhere, so just pick between an empty space or a hallway or both. Light can also be manipulated.

It doesn't have a specific trigger, but backrooms appears at the beginning of all the images in the dataset. Weight: It works well between 0.8 and 1.0. I didn't test it lower than 0.8 but overall seems more stable in regards of weight.

Hi-Res Fix: Same as prior models. Don't use Hi-Res fix, use ImgtoImg with the same parameters you used in TxtToImg but make sure to use a low denoising strength (0.3-0.5) and use DPM++ 2M Karras as the sampler to avoid deformations. If you're still getting weird stuff happening to the image, try lowering the LORA weight to 0.7 or lower on the ImgtoImg process.

Sometimes it’s difficult to get a character to appear in the scene, so it’s recommended to put the following in the negative tags:

scenery, no humans Important tags for the model:

backrooms (creepypasta), brown carpet floor, yellow wall, argyle wall, tile ceiling, ceiling light, indoors, General tags to use with the model:

hallway, empty space, blue door, dark, dim lightning

Other LORAS used on the preview pics:

Albinauric Monster: https://civitai.com/models/395351?modelVersionId=440953

Strange World: https://civitai.com/models/499581?modelVersionId=555311

Styles for Pony Diffusion V6 XL (Not Artists styles) - Concept Art DarkSide: https://civitai.com/models/264290?modelVersionId=446346

Comments