Cockpit 360 Diffusion LoRA for FLUX.1-dev

Prompt
360 degree equirectangular view, photo from the driver's seat of a family car driving on a countryside highway under a blue sky, with steering wheel in the center
Prompt
360 degree equirectangular view, View from the pilot's seat in a boeing passenger plane cockpit, sunrise across the clouds visible through front windows
Prompt
360 degree equirectangular view, photo from the driver's seat of a sports car driving on a race track under a blue sky, with steering wheel in the center
Prompt
360 degree equirectangular view, View from the pilot's seat in a boeing passenger plane cockpit, dark night with lights in the distance

Model description

This LoRA was trained for 27,250 iterations with rank 64 on a diverse dataset of around 300 images, for the purpose of creating 360 degree panorama images of cockpits and vehicle interiors.

The seam and polar distortion artifacts should be minimal, but some careful editing or in-painting may be required to make the image appear seamless.

Usage

There is no trigger phrase, but as with all 360° Flux LoRAs, you should include some variation of '360 degree equirectangular view' in your prompt to improve output quality.

  • Generally the word 'cockpit' and 'pilot's seat' can be used for aircraft, including planes & helicopters.
  • Terms like 'driver's seat' can be useful for creating views from inside cars, trucks, buses, and trains.

When rendering images, it's recommended that you choose a 2:1 aspect ratio, like 1024x512, 1536x768, or 2048x1024. Afterwards, you can use an upscaler of your choosing to make the resolution high enough for skyboxes, VR, and 2D/3D environments.

Additional Tools

HTML 360 Viewer

To make the viewing and sharing of 360 images & video easier, I built a web browser based HTML 360 viewer that runs locally on your device.

Recommended ComfyUI Nodes

If you are a user of ComfyUI, then these sets of nodes can be useful for working with 360 images & videos.

For diffusers and other libraries, you can make use of the pytorch360convert library when working with 360 media.

Limitations

The dataset was weighted towards aircraft cockpits and the front seats of cars.

Citation Information

BibTeX

@software{Egan_Cockpit_360_Diffusion_2025,
author = {Egan, Ben},
license = {MIT},
month = aug,
title = {{Cockpit 360 Diffusion LoRA for FLUX.1-dev}},
url = {https://huggingface.co/ProGamerGov/cockpit-360-lora-flux-dev},
year = {2025}
}

APA

Egan, B. (2025). Cockpit 360 Diffusion LoRA for FLUX.1-dev [Computer software]. https://huggingface.co/ProGamerGov/cockpit-360-lora-flux-dev

Please refer to the CITATION.cff for more information on how to cite this model.

Download model

Download them in the Files & versions tab.

Downloads last month
16
Inference Providers NEW
Examples

Model tree for ProGamerGov/cockpit-360-lora-flux-dev

Adapter
(36368)
this model