|
|
--- |
|
|
language: |
|
|
- en |
|
|
thumbnail: "https://huggingface.co/ProGamerGov/sdxl-360-diffusion/resolve/main/examples/gallery_grid.jpg" |
|
|
base_model: |
|
|
- stabilityai/stable-diffusion-xl-base-1.0 |
|
|
pipeline_tag: text-to-image |
|
|
tags: |
|
|
- '360' |
|
|
- '360°' |
|
|
- 360-degree |
|
|
- 360-image |
|
|
- equirectangular |
|
|
- equirectangular-projection |
|
|
- image-generation |
|
|
- text-to-image |
|
|
--- |
|
|
# SDXL 360 Diffusion |
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
## General |
|
|
|
|
|
SDXL 360 Diffusion is a 3.5 billion parameter model designed to generate 360 degree spherical images from text descriptions. |
|
|
|
|
|
The model was trained from the [SD-XL 1.0-base model](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) on an extremely diverse dataset composed of tens of thousands of equirectangular images, depicting landscapes, interiors, humans, animals, and objects. All images were resized to 2048x1024 before training. |
|
|
|
|
|
Given the right prompt, the model should be capable of producing almost anything you want. |
|
|
|
|
|
|
|
|
## Usage |
|
|
|
|
|
The trigger phrase is "equirectangular 360 view", "360 panorama", or some variation of those words in your prompt. |
|
|
|
|
|
When rendering images, it's recommended that you choose a 2:1 aspect ratio, such as 1024x512, 1536x768, or 2048x1024. Afterwards, you can use an upscaler of your choosing to make the resolution high enough for sky-boxes, backgrounds, VR, VR therapy, and 3D worlds. |
|
|
|
|
|
|
|
|
## 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. |
|
|
|
|
|
* You can try it out here on Github Pages: https://progamergov.github.io/html-360-viewer/ |
|
|
* Github code: https://github.com/ProGamerGov/html-360-viewer |
|
|
* You can append '`?url=`' followed by a link to your image in order to automatically load it into the 360 viewer, making sharing your 360 creations extremely easy. |
|
|
* Example: https://progamergov.github.io/html-360-viewer/?url=https://upload.wikimedia.org/wikipedia/commons/7/76/Dauderi.jpg |
|
|
|
|
|
|
|
|
### Recommended ComfyUI Nodes |
|
|
|
|
|
If you are a user of [ComfyUI](https://github.com/comfyanonymous/ComfyUI), then these sets of nodes can be useful for working with 360 images & videos. |
|
|
|
|
|
* ComfyUI_preview360panorama |
|
|
* For viewing 360s inside of ComfyUI (may be slower than my web browser viewer). |
|
|
* Link: https://github.com/ProGamerGov/ComfyUI_preview360panorama |
|
|
|
|
|
* ComfyUI_pytorch360convert |
|
|
* For editing 360s, applying circular Conv2d padding, and masking potential artifacts. |
|
|
* Link: https://github.com/ProGamerGov/ComfyUI_pytorch360convert |
|
|
|
|
|
For diffusers and other libraries, you can make use of the [pytorch360convert](https://github.com/ProGamerGov/pytorch360convert) library when working with 360 media. |
|
|
|
|
|
### LoRA Training |
|
|
|
|
|
Due to the relative scarcity of 360 images, it is often easier to produce your own 360s to teach the model new concepts. There are a number of ways that you can produce your own 360 images for training LoRAs: |
|
|
|
|
|
1. Blender Renders |
|
|
- There are tons of free models and scenes available, and you can pose characters exactly how you want. |
|
|
- Blender's [Cycles rendering engine with panoramic equirectangular setting](https://docs.blender.org/manual/en/latest/render/cycles/object_settings/cameras.html) generates 360 degree renders. |
|
|
2. Video Game Screenshots |
|
|
- Example: Using Nvidia Ansel. |
|
|
3. 360 Cameras |
|
|
- Public Libraries: 360 Cameras can sometimes be borrowed from libraries. |
|
|
- Purchasing: 360 Cameras can also be purchased. |
|
|
4. Digital illustration, Painting, & Drawing Tools |
|
|
- Some tools used for creating digital illustrations, drawings, paintings, and other mediums by hand also have the ability to help you create seamless 360 images. |
|
|
|
|
|
|
|
|
## Limitations |
|
|
|
|
|
Due to the nature of SDXL, multiple attempts may be required to achieve a desirable output based on a given prompt. |
|
|
|
|
|
|
|
|
## Contributors |
|
|
|
|
|
- [Ben Egan](https://github.com/ProGamerGov) |
|
|
- [XWAVE](https://twitter.com/XWAVEart) |
|
|
- [Jimmy Carter](https://huggingface.co/jimmycarter) |
|
|
|
|
|
|
|
|
## Citation Information |
|
|
|
|
|
BibTeX |
|
|
|
|
|
``` |
|
|
@software{Egan_SDXL_360_Diffusion_2025, |
|
|
author = {Egan, Ben and {XWAVE} and {Jimmy Carter}}, |
|
|
license = {MIT}, |
|
|
month = aug, |
|
|
title = {{SDXL 360 Diffusion}}, |
|
|
url = {https://huggingface.co/ProGamerGov/sdxl-360-diffusion}, |
|
|
year = {2025} |
|
|
} |
|
|
``` |
|
|
|
|
|
APA |
|
|
|
|
|
``` |
|
|
Egan, B., XWAVE, & Jimmy Carter. (2025). SDXL 360 Diffusion [Computer software]. https://huggingface.co/ProGamerGov/sdxl-360-diffusion |
|
|
``` |
|
|
|
|
|
Please refer to the [CITATION.cff](https://huggingface.co/ProGamerGov/sdxl-360-diffusion/blob/main/CITATION.cff) for more information on how to cite this dataset. |
