elif last_image is None:
# video_condition = torch.cat(
# [image, image.new_zeros(image.shape[0], image.shape[1], num_frames - 1, height, width)], dim=2
# )
video_condition = torch.cat(
[image, image.new_zeros(image.shape[0], image.shape[1], num_latent_frames - 1, height, width)], dim=2
)
print("video_condition shape:", video_condition.shape) # torch.Size([1, 3, 21, 720, 544])
else:
last_image = last_image.unsqueeze(2)
# video_condition = torch.cat(
# [image, image.new_zeros(image.shape[0], image.shape[1], num_frames - 2, height, width), last_image],
# dim=2,
# )
video_condition = torch.cat(
[image, image.new_zeros(image.shape[0], image.shape[1], num_latent_frames - 2, height, width), last_image],
dim=2,
)
