Get dummy components with x8 VAE downscaling and 3 UNet down blocks. These dummy components are intended to fully-exercise the T2I-Adapter

Args: original_image (np.ndarray): an image of shape (H, W, C) (in BGR order). Returns: features (dict):

See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298 Args: w (`tor

Calculates the input preconditioning factor c_in, which is used to scale the U-Net image input.

r""" Map label strings from ImageNet to corresponding class ids. Parameters: label (`str` or `dict` of `str`):

Takes in random seed and returns corresponding noise vector

Calculates the noise preconditioning function c_noise, which is used to transform the raw Karras sigmas into the timestep input for the U-Net

Computes the solver order at each time step. Args: num_inference_steps (`int`): The number of diffusion

Get the index (e.g. 2) from the prediction (e.g. 'C')

Get the index (e.g. 2) from the prediction (e.g. 'C')

r""" Tokenize a list of prompts and return its tokens with weights of each token. No padding, starting or ending token is included.

r""" Tokenize a list of prompts and return its tokens with weights of each token. No padding, starting or ending token is included.

Creates a torch.Generator based on the random seed of this region

Get the list of modules that are relatively imported in a module file. Args: module_file (`str` or `os.PathLike`): The module file t

Get sample rate. Returns: `int`: Sample rate of audio.

Args: append_path: optional path to append to the tests dir path Return: The full path to the `tests` dir, so that the tests

Get a list of mapping: prompt index to str (prompt in a list of token str)

When the length of tokens is a multiple of the capacity of the text encoder, it should be split into chunks and sent to the text encoder indi

When the length of tokens is a multiple of the capacity of the text encoder, it should be split into chunks and sent to the text encoder indi

Reads the current version in the __init__.