Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

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.

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

Apply the model to get p(x_{t-1} | x_t), as well as a prediction of the initial x, x_0. :param model: the model, which takes

Zero out the parameters of a module and return it.

Get a term for the variational lower-bound. The resulting units are bits (rather than nats, as one might expect). This allows

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

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

Generate the mesh grid, centering at zero. Args: kernel_size (int): Returns: xy (ndarray): with the shape (kernel_size, ke

Generate samples from the model. :param model: the model module. :param shape: the shape of the samples, (N, C, H, W).

Compute the mean and variance of the diffusion posterior: q(x_{t-1} | x_t, x_0)

Calculate the rotated sigma matrix (two dimensional matrix). Args: sig_x (float): sig_y (float): theta (float): Radian

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

Convert tensor data type from uint8 to float, divide value by 255.0 and permute the dimensions of clip tensor Args: clip (torch.t