get activation layer Args: act_type (str): the activation type Returns: torch.nn.functional: the activation layer

Decode a batch of images/videos. Args: z (`torch.FloatTensor`): Input batch of latent vectors. return_d

AI is creating summary for apply_gate Args: x (torch.Tensor): input tensor. gate (torch.Tensor, optional): gate tensor. Defaults

Args: batch_encoding (dict): Batch encoding from tokenizer. use_attention_mask (bool): Whether to use attention mask.

Initialize the Inference pipeline. Args: pretrained_model_path (str or pathlib.Path): The model path, including t2v,

Compute the noise coefficient along the path

modulate by shift and scale Args: x (torch.Tensor): input tensor. shift (torch.Tensor, optional): shift tensor. Defaults to None.

Function to reshape time t to broadcastable dimension of x Args: t: [batch_dim,], time vector x: [batch_dim,...], data point

We always output sde according to score parametrization;

Compute the data coefficient along the path

the fucntion to load the 3D VAE model Args: vae_type (str): the type of the 3D VAE model. Defaults to "884-16c-hy". vae_precision

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m

Tokenize the input text. Args: text (str or list): Input text.

Perform QKV self attention. Args: q (torch.Tensor): Query tensor with shape [b, s, a, d], where a is the number of heads. k

Get the normalization layer. Args: norm_layer (str): The type of normalization layer. Returns: norm_layer (nn.Module):

load hunyuan video model Args: args (dict): model args in_channels (int): input channels number out_channels (int): outpu

Take the mean over all non-batch dimensions.

Sampling x0 & t based on shape of x1 (if needed) Args: x1 - data point; [batch, *dim]

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`)

align hight, width according to alignment Args: value (int): height or width alignment (int): target alignment factor Return

Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query 'xq' a

Apply text to template. Args: text (str): Input text. template (str or list): Template string or list of cha

r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and

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

RIFLEx: Precompute the frequency tensor for complex exponentials (cis) with given dimensions. This function calculates a frequency tensor wi

get the closest ratio in the buckets Args: height (float): video height width (float): video width ratios (list): video a

This is a n-d version of precompute_freqs_cis, which is a RoPE for tokens with n-d structure. Args: rope_dim_list (list of int): Dim

Reshape frequency tensor for broadcasting it with another tensor. This function reshapes the frequency tensor to have the same shape as the

Create a directory (or the parent directory of a file) if it does not exist. Args: path (str or Path): Path to the directory. R

Create the parent directory of a file if it does not exist. Args: path (str or Path): Path to the file. Returns: path (

forward loop of sde

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor`

r""" Decode a batch of images/videos using a tiled decoder. Args: z (`torch.FloatTensor`): Input batch of latent vect

r"""Encode a batch of images/videos using a tiled encoder. When this option is enabled, the VAE will split the input tensor into tiles to c

TODO: generalize here by adding all private functions ending with steps to it

Get the last step function of the SDE solver

Apply the RMSNorm normalization to the input tensor. Args: x (torch.Tensor): The input tensor. Returns:

generate a black image Args: width (int): image width height (int): image height Returns: _type_: a black image

Collect the information of the running environments. Returns: dict: The environment information. The following fields are contained.