---
license: mit
tags:
  - pytorch
  - diffusers
  - unconditional-image-generation
---
# City Diffusion Model

This is a diffusion model trained to generate cities.

The model will output a 256x256 image of a city where blue pixels represent buildings, red pixels represent roads, and white pixels represent empty space.

## Frontend
[City Generator Web Interface](https://github.com/bart1259/CityDiffusion)

![frontend](https://raw.githubusercontent.com/bart1259/CityDiffusion/refs/heads/main/images/frontend.gif)

## Sample training data

![sample_data](https://raw.githubusercontent.com/bart1259/CityDiffusion/refs/heads/main/images/train_samples.png)