Augment: horizontal flips OR rotate (0, 90, 180, 270 degrees). We use vertical flip and transpose for rotation implementation. All the images

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 = [

Build model from options. Args: opt (dict): Configuration. It must contain: model_type (str): Model type.

Calculate metric from data and options. Args: opt (dict): Configuration. It must contain: type (str): Model type.

Compute the ratio between d_alpha and alpha

Compute the diffusion term of the SDE Args: x: [batch_dim, ...], data point t: [batch_dim,], time vector form: s

Compute the mean of time-dependent density p_t

Compute the vector field corresponding to p_t

Sample xt from time-dependent density p_t; rng is required

Compute the mean for the previous step, given a function cond_fn that computes the gradient of a conditional log probability with res

Compute the mean for the previous step, given a function cond_fn that computes the gradient of a conditional log probability with res

function for creating Transport object **Note**: model prediction defaults to velocity Args: - path_type: type of path to use; default to

Sample x_{t-1} from the model using DDIM. Same usage as p_sample().

Sample x_{t-1} from the model using DDIM. Same usage as p_sample().

Generate samples from the model using DDIM. Same usage as p_sample_loop().

Use DDIM to sample from the model and yield intermediate samples from each timestep of DDIM. Same usage as p_sample_loop_prog

Use DDIM to sample from the model and yield intermediate samples from each timestep of DDIM. Same usage as p_sample_loop_prog

Initialize network weights. Args: module_list (list[nn.Module] | nn.Module): Modules to be initialized. scale (float): Scale init

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

Encodes texts into embeddings and returns the last hidden state and pooled output.

Finds a pre-trained Latte model, downloading it if necessary. Alternatively, loads a model from a local path.

Applies the flow color wheel to (possibly clipped) flow components u and v. According to the C++ source code of Daniel Scharstein Accordi

Generate Gaussian kernel used in `duf_downsample`. Args: kernel_size (int): Kernel size. Default: 13. sigma (float): Sigma of the

This is the deprecated API for creating beta schedules. See get_named_beta_schedule() for the new library of schedules.

This is the deprecated API for creating beta schedules. See get_named_beta_schedule() for the new library of schedules.

member function for obtaining the drift of the probability flow ODE

Generates embeddings for a list of image file paths.

Get the input video from the input_path. params: input_path: str, the path of the input video. devices: str,

Get the position from a period list. It will return the index of the right-closest number in the period list. For example, the cumulative_per

member function for obtaining score of x_t = alpha_t * x + sigma_t * eps

Wrapper function: transfrom velocity prediction model to score Args: velocity: [batch_dim, ...] shaped tensor; velocity model outp

Get target label. Args: input (Tensor): Input tensor. target_is_real (bool): Whether the target is real or fake.

Generates embeddings for a list of text prompts.

deprecation