Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices into

Runs the given method on all workers.

Wait for futures returned from _run_workers() with async_run_remote_workers_only to complete.

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

Center cropping implementation from ADM. https://github.com/openai/guided-diffusion/blob/8fb3ad9197f16bbc40620447b2742e13458d2831/guided_diff

Args: clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W)

Decode a batch of images. Args: z (`torch.Tensor`): Input batch of latent vectors. return_dict (`bool`, *opt

Run video-to-world generation demo. This function handles the main video-to-world generation pipeline, including: - Setting up the random see

Run text-to-world generation demo. This function handles the main text-to-world generation pipeline, including: - Setting up the random seed

r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev

Encode a batch of images into latents. Args: x (`torch.Tensor`): Input batch of images. return_dict (`bool`,

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Args: prompt (`str` or `List[str]`, *optional*): prompt to be encoded prompt_2 (`str` or `List[s

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):