slerps batches b1, b2 according to ratio r, batches should be flat e.g. NxC

Takes a prompt and converts it to a list of (token, weight, word id) elements. Tokens can both be integer tokens and pre computed CLI

Checks the prompt to see if the style text is wrapped around it. If so, returns True plus the prompt text without the style text. Otherwise,

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

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

Args: windows: (num_windows*b, window_size, window_size, c) window_size (int): Window size h (int): Height of image

Args: med_config (str): path for the mixture of encoder-decoder model's configuration file image_size (int): input im

Return an activation function given a string

Load weights from .npz checkpoints for official Google Brain Flax implementation

Helper method that segments an image into superpixels using slic. Parameters: x: base64 representation of an image

Takes a potential embedding name and tries to retrieve it. Returns a Tuple consisting of the embedding and any leftover string, embed

Adaptive instance normalization. Adjust the reference features to have the similar color and illuminations as those in the degradate features.

kohya-ss hash for safetensors from https://github.com/kohya-ss/sd-scripts/blob/main/library/train_util.py

Align and crop face with landmarks. The output_size and transform_size are based on width. The height is adjusted based on shrink_ratio_h/shr

Performs all_gather operation on the provided tensors. Graph remains connected for backward grad computation.

Create a 1D, 2D, or 3D average pooling module.

Create a 1D, 2D, or 3D average pooling module.

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: b_loc (tensor):

Decode landm from predictions using priors to undo the encoding we did for offset regression at train time. Args: pre (tensor): landm

Arguments: frames: a list of PIL.Image, or torch.Tensor(shape=[n, h, w, c], type=np.float32, BGR format).

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

Partitions the tokens into src and dst and merges r tokens from src to dst. Dst tokens are partitioned by choosing one randomy in each (sx, s