Compute what the p_mean_variance output would have been, should the model's score function be conditioned by cond_fn. See con

Return the data prediction model (with corrector).

Return the data prediction model (with corrector).

Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization.

Downloads a pre-trained PixArt model from the web.

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

Flush written text to both stdout and a file, if open.

Forward pass of PixArt. x: (N, C, H, W) tensor of spatial inputs (images or latent representations of images) t: (N,) tensor

Forward pass of PixArt. x: (N, C, H, W) tensor of spatial inputs (images or latent representations of images) t: (N,) tensor

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

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/

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

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

Get relative positional embeddings according to the relative positions of query and key sizes. Args: q_size (int): size of qu

Compute the intermediate time steps for sampling.

Initialize random seed. If the seed is not set, the seed will be automatically randomized, and then broadcast to all processes to prevent som

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).

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).

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

Thanks to DPM-Solver for their code base

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.

Return the noise prediction model.

Compute the KL divergence between two gaussians. Shapes are automatically broadcasted, so batches can be compared to scalars, among other

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

Set random seed. Args: seed (int): Seed to be used. deterministic (bool): Whether to set the deterministic option for

Singlestep solver DPM-Solver-3 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma

Constructs the noise schedule of Karras et al. (2022).

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep

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 = [

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

End DDP training.

Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).

Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).

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

Convert the model output to the corresponding type the DPMSolver/DPMSolver++ algorithm needs. DPM-Solver is designed to discretize an

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

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

Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization.

Report whether the tensor contains any `nan` or `inf` entries. This is useful for detecting overflows/underflows and best to call rig

Compute the log-likelihood of a Gaussian distribution discretizing to a given image. :param x: the target images. It is assumed that this

The adaptive step size solver based on singlestep DPM-Solver. Args: x: A pytorch tensor. The initial value at time `t_T`

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