r"""Index tensor using t and format the output according to x.

r"""Download OSS [file or folder] to the cache folder. Only the 0th process on each node will run the downloading. Barrier all proce

Compute sigma_t of a given continuous-time label t in [0, T].

Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].

Compute log(alpha_t) of a given continuous-time label t in [0, T].

Convert the model to the noise prediction model or the data prediction model.

Expand the tensor `v` to the dim `dims`. Args: `v`: a PyTorch tensor with shape [N]. `dim`: a `int`. Returns: a

r"""Distribution of p(x_{t-1} | x_t).

Compute alpha_t of a given continuous-time label t in [0, T].

Compute the intermediate time steps for sampling. Args: skip_type: A `str`. The type for the spacing of the time steps. We suppor

Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t.

r"""Distribution of p(x_{t-1} | x_t).

r"""Distribution of q(x_{t-1} | x_t, x_0).

Zero out the parameters of a module and return it.

python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_fil

r"""Sample from q(x_t | x_0).

Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`. =========================================

DPM-Solver-1 (equivalent to DDIM) from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time. For discrete-time DPMs, we convert `t_continuou

r"""Distribution of q(x_{t-1} | x_t, x_0).

Singlestep solver DPM-Solver-2 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means y

Return the data prediction model (with thresholding).

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

A piecewise linear function y = f(x), using xp and yp as keypoints. We implement f(x) in a differentiable way (i.e. applicable for autograd).

Multistep DPM-Solver with the order `order` from time `t_prev_list[-1]` to time `t`. Args: x: A pytorch tensor. The init

Return the noise prediction model.

r"""Sample from q(x_t | x_0).