Hugging Face's logo

bart1259
/
CityDiffusion

Unconditional Image Generation
Diffusers
Safetensors
PyTorch
DDPMPipeline
Model card Files
xet
 Community
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("bart1259/CityDiffusion", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

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

frontend

Sample training data

sample_data

Downloads last month
-
Inference Providers NEW
Unconditional Image Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support