Compute the log-likelihood of a continuous Gaussian distribution. :param x: the targets :param means: the Gaussian mean Tensor. :para

Convert the torso of the model to float16.

Convert the torso of the model to float32.

Create a ScheduleSampler from a library of pre-defined samplers. :param name: the name of the sampler. :param diffusion: the diffusion ob

Sample x_{t+1} from the model using DDIM reverse ODE.

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

Take a list of samples (as dictionary) and create a batch, preserving the keys. If `tensors` is True, `ndarray` objects are combined into ten

Forward pass for the flow model

Args: x (torch.Tensor): In shape of (B, C, H, W)

Args: x (torch.Tensor): In shape of (B, C, H, W)

Apply the module to `x` given `emb` timestep embeddings.

Apply the block to a Tensor, conditioned on a timestep embedding. :param x: an [N x C x ...] Tensor of features. :param emb:

Apply QKV attention. :param qkv: an [N x (H * 3 * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor afte

Apply QKV attention. :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor afte

Apply the model to an input batch. :param x: an [N x C x ...] Tensor of inputs. :param t: a 1-D batch of timesteps. :

Function to include sampling with Classifier-Free Guidance (CFG)

Args: x: source minibatch (bs, *dim) sample_kwargs: dict, additional sampling arguments for the solver

Args: x: source minibatch (bs, *dim) sample_kwargs: dict, additional sampling arguments for the solver

Create a schedule with a constant learning rate preceded by a warmup period during which the learning rate increases linearly between 0 and t

Create a schedule with a learning rate that decreases following the values of the cosine function between the initial lr set in the optimizer

Apply the model to an input batch and return the features from the middle block. :param x: an [N x C x ...] Tensor of inputs.

Get a pre-defined beta schedule for the given name. The beta schedule library consists of beta schedules which remain similar in the limi

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

Returns: torch.Tensor: Unconditional conditioning information for text of shape (1, max_length, d_model), e.g. (1

Returns: torch.Tensor: Unconditional conditioning information for text of shape (1, max_length, d_model), e.g. (1

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

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

Function to reshape the vector by the number of dimensions of x. E.g. x (bs, c, h, w), v (bs) -> v (bs, 1, 1, 1).