r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: device: (`torch.device`): torch device

r""" Encodes the prompt into text encoder hidden states. Args: device: (`torch.device`): torch device

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

Parameters: - args: Arguments. - results: Results to evaluate. - eval_method: The evaluation method. either "openai".

Get the imports a given module makes. Args: module_fname (`str`): The name of the file of the module where we want to lo

Fourier filter as introduced in FreeU (https://arxiv.org/abs/2309.11497). This version of the method comes from here: https://github.com/hugg

r""" Instantiates a text-to-image Pytorch diffusion pipeline from pretrained pipeline weight. The from_pretrained() method takes care

Packs benchmarking data into a dictionary for latter serialization.

Precompute the frequency tensor for complex exponentials (cis) with given dimensions. This function calculates a frequency tensor with compl

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

Walks the `tests` folder to return a list of files/subfolders. This is used to split the tests to run when using paralellism. The split is:

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

Divides an iterable into chunks of specified size or based on a given function. Useful for batching Parameters: - it

Extracts a class from a module file, present in the local folder or repository of a model. <Tip warning={true}> Calling this function w

Simple helper method to retrieve class object of module as well as potential parent class objects

Get image and phrases embedding by using CLIP pretrain model. The image embedding is transformed into the phrases embedding space thr

Get the diff between a base commit and one or several commits. Args: repo (`git.Repo`): A git repository (for instance t

Get the diff in doc examples between a base commit and one or several commits. Args: repo (`git.Repo`): A git repository