Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices into

Take the mean over all non-batch dimensions.

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

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

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

r""" Set the attention processor to use. Args: processor (`AttnProcessor`): The attention processor to us

r""" Reshape the tensor from `[batch_size, seq_len, dim]` to `[batch_size, seq_len, heads, dim // heads]` `heads` is the number of hea

Diffuse the data for a given number of diffusion steps. In other words, sample from q(x_t | x_0). :param x_start: the initial

Compute pairwise distances between two batches of feature vectors.

A fast approximation of the cumulative distribution function of the standard normal.

r""" Copy from torch.nn.utils.clip_grad_norm_ Clips gradient norm of an iterable of parameters. The norm is computed over all gradients

Compute image features for downstream evals. :param batches: a iterator over NHWC numpy arrays in [0, 255]. :return: a tuple

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

Evaluate precision and recall efficiently. :param features_1: [N1 x D] feature vectors for reference batch. :param radii_1:

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

Compute the Frechet distance between two sets of statistics.

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

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).

Evaluate pairwise distances between two batches of feature vectors.

Importance-sample timesteps for a batch. :param batch_size: the number of timesteps. :param device: the torch device to save

This function disables printing when not in master process

Step the EMA model towards the current model.

Step the EMA model towards the current model.

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

Copied from: https://github.com/numpy/numpy/blob/fb215c76967739268de71aa4bda55dd1b062bc2e/numpy/lib/format.py#L788-L886 Read from file-like

在指定路径的文件中追加一行文本。 :param file_path: 文件的完整路径 :param line_to_append: 要追加的文本行

r""" Reshape the tensor from `[batch_size, seq_len, dim]` to `[batch_size // heads, seq_len, dim * heads]`. `heads` is the number of h

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

Center cropping implementation from ADM. https://github.com/openai/guided-diffusion/blob/8fb3ad9197f16bbc40620447b2742e13458d2831/guided_diff

End DDP training.

End DDP training.

将给定路径中的图片横向拼接

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

Builds a single .npz file from a folder of .png samples.

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

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

r""" Args: prompt (`str` or `List[str]`, *optional*): prompt to be encoded prompt_2 (`str` or `List[s

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

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/

r""" Compute the attention scores. Args: query (`torch.Tensor`): The query tensor. key (`torch.Tensor`): The

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