Convert a numpy image to a pytorch tensor

Modifies the UNet (`unet`) to perform Pix2Pix Zero optimizations.

Process a batch of samples from HuggingFace Dataset

Updates paths inside attentions to the new naming scheme (local renaming)

Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the

r""" Parameters: `processor (`dict` of `AttentionProcessor` or `AttentionProcessor`): The instantiated processo

Sets the noise scales used for the diffusion chain. Supporting function to be run before inference. The sigmas control the weight

This function disables printing when not in master process

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

Correct the predicted sample based on the output model_output of the network. This is often run repeatedly after making the predict

Step function propagating the sample with the linear multi-step method. This has one forward pass with multiple times to approximat

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to b

Serializes this instance to a JSON string. Returns: `str`: String containing all the attributes that make up this co

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size,

Zero out the parameters of a module and return it.

the segmentation stage splits K: chunks of length P: hop size input: [B, N, L] output: [B

Initialization. INPUT: - in_features: shape of the input - alpha: trainable parameter alpha

Iterate over sampler. Returns: python iterator

x: [b, h, l, l] ret: [b, h, l, 2*l-1]

Bias for self-attention to encourage attention to close positions. Args: length: an integer scalar. Returns: a Tensor with sha

Computes the maximum attention value for each of the tokens we wish to alter.

Replace image_unet's `Transformer2DModel` blocks with `DualTransformer2DModel` that contains transformer blocks from both `image_un

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

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

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

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

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

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

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