r"""Move internal buffers of the ExponentialMovingAverage to `device`. Args: device: like `device` argument to `torch.Tensor.t

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

Initialize a Linear or Convolutional layer.

This is a helper function that allows to create random tensors on the desired `device` with the desired `dtype`. When passing a list of generator

Sets the discrete timesteps used for the diffusion chain. Supporting function to be run before inference. Args: num_

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

Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion process from the learned

Convert a numpy image or a batch of images to a PIL image.

Initialize a Batchnorm layer.

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep.

Resize a PIL image. Both height and width will be downscaled to the next integer multiple of `vae_scale_factor`

Args: Compares the current Accelerate version to a given reference with an operation. operation (`str`): A string rep

r""" Maybe convert a prompt into a "multi vector"-compatible prompt. If the prompt includes a token that corresponds to a multi-vect

r""" Args: Loads the ExponentialMovingAverage state. This method is used by accelerate during checkpointing to save the ema

Function invoked when using the prior pipeline for interpolation. Args: images_and_prompts (`List[Union[str, PIL.Ima

r""" Returns the state of the ExponentialMovingAverage as a dict. This method is used by accelerate during checkpointing to save the

Mixup x of even indexes (0, 2, 4, ...) with x of odd indexes (1, 3, 5, ...). Args: x: (batch_size * 2, ...) mixup_lambda: (b

`torch.device`: The device on which the module is (assuming that all the module parameters are on the same device).

Args: Compares the current PyTorch version to a given reference with an operation. operation (`str`): A string repres

Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].

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

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

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

Create a 1D, 2D, or 3D convolution module.

Create a 1D, 2D, or 3D convolution module.

Convert the model to the noise prediction model or the data prediction model.

r""" Disable sliced VAE decoding. If `enable_slicing` was previously invoked, this method will go back to computing decoding in one

r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in s

Root Mean Square Layer Normalization :param d: model size :param p: partial RMSNorm, valid value [0, 1], default -1.0

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and ta

Initialize a Linear or Convolutional layer.

Create a linear module.

Normalize an image array to [-1,1]