Dummy diffusion model following architecture of https://github.com/lucidrains/denoising-diffusion-pytorch
Run the model as follows:
from diffusers import UNetModel
import torch
model = UNetModel.from_pretrained("fusing/ddpm_dummy")
batch_size, num_channels, height, width = 1, 3, 32, 32
dummy_noise = torch.ones((batch_size, num_channels, height, width))
time_step = torch.tensor([10])
image = model(dummy_noise, time_step)