Retrieves exactly 'data_len' items (per key) from output_queue by merging batches. If 'data_len' == 'all_available', returns ALL item

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`,

A helper function to create random tensors on the desired `device` with the desired `dtype`. When passing a list of generators, you can seed each

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m

r""" Function that offloads all components, removes all model hooks that were added when using `enable_model_cpu_offload` and then app

r""" Processes prompts that include a special token corresponding to a multi-vector textual inversion embedding to be replaced with mu

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

Adjust the weightage given to the LoRA layers of the model. Args: model (`torch.nn.Module`): The model to scale.

Removes the previously passed weight given to the LoRA layers of the model. Args: model (`torch.nn.Module`): The model t

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

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

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

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

Preprocess an image or batch of images. Args: images (`ImageInput`): Image to preprocess. Expects a sing

Returns a dict of object names and values in a module, while skipping private/internal objects Args: module (ModuleType):

Args: t0: start time has shape [batch_size, *shape, 1] t1: finish time has shape [batch_size, *shape, 1]

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

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

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

Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize.

Prepares the perturbed attention guidance for the PAG model. Args: cond (torch.Tensor): The conditional input tensor.

Retrieves exactly 'data_len' items (per key) from output_queue by merging batches. If 'data_len' == 'all_available', returns ALL item

Resize image. Args: image (`PIL.Image.Image`, `np.ndarray` or `torch.Tensor`): The image input, can be a

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

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

r""" Prepare the attention mask for the attention computation. Args: attention_mask (`torch.Tensor`): The

Check whether the module was compiled with torch.compile()

r""" Normalize the encoder hidden states. Requires `self.norm_cross` to be specified when constructing the `Attention` class.

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

r""" Get the attention processor in use. Args: return_deprecated_lora (`bool`, *optional*, defaults to `False`):

Helper function to get activation function from string. Args: act_fn (str): Name of activation function. Returns: nn.Module:

The name of the task file (without the .py extension). :return: The name of the task.

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

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

r""" Instantiate a pretrained MultiControlNet model from multiple pre-trained controlnet models. The model is set in evaluation mode

Fetches all the values from the specified state column, and filter out empty values.

Returns true if can add and adds it rotation_limits: how mush we allow it to rotate from its original position

Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query or key

r""" Load a model or scheduler configuration. Parameters: pretrained_model_name_or_path (`str` or `os.PathLike`, *optiona

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

Check if variable is empty, explicitly handling None, common containers, NumPy arrays, PyTorch tensors, and avoiding accidental handling of s

r""" Converts a video tensor to a list of frames for export. Args: video (`torch.Tensor`): The video as a tensor.

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

r""" Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to `enable_sequenti

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