import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("aycaduran/ddpm-facade-128", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]DDPM-Façade-128
A denoising diffusion probabilistic model (DDPM) trained to generate 128×128 building façade images.
This model can be used for synthetic façade generation, data augmentation, or exploratory work in façade-related research.
Example Output
Below is a sample generated by the model:
Model Description
This model learns façade structures (windows, floor patterns, façade grids) from the training dataset and generates synthetic 128×128 images with similar architectural characteristics.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support