Prepare latent variables for a U-Net model. :param img: The image to process. :return: A concatenated tensor of latents for U

Calculate the similarity between sets of facial landmarks and return the indices of the most similar faces. Parameters: landmarks_list (

Decode latent variables back into an image. :param latents: The latent variables to decode. :return: A NumPy array representi

Calculate GAN loss weight based on training step

将裁剪的面部图像粘贴回原始图像，并进行一些处理。 Args: image (numpy.ndarray): 原始图像（身体部分）。 face (numpy.ndarray): 裁剪的面部图像。 face_box (tuple): 面

Generate and affine transformation matrix. Given a set of points, a center, a scale and a targer resolution, the function generates and affin

Specify how to select the next token, based on the current trace and logits Parameters ---------- tokens : Tensor, shape = (n

Return dataset based on configuration Args: cfg: Configuration dictionary Returns: Dataset: Combined dataset

3x3 convolution with padding

Apply any filtering or masking to logits in-place Parameters ---------- logits : Tensor, shape = (n_batch, vocab_size)

Returns the names of available models

3x3 convolution with padding

3x3 convolution with padding

Crop and resize image Args: img: Input image bbox: Bounding box crop_type: Type of cropping

Encode an image into latent variables. :param image: The image tensor to encode. :return: The encoded latent variables.

Convert any audio (mp3/ogg/m4a/wav/…) to 16kHz mono PCM WAV via ffmpeg. Returns path to the converted .wav (original if already correct).

对图像进行面部解析，生成面部区域的掩码。 Args: image (PIL.Image): 输入图像。 Returns: PIL.Image: 面部区域的掩码图像。

Generate random value Returns: float: Generated random value

Get sliced features based on a given index :param feature_array: :param start_idx: the start index of the feature :p

Load a Whisper ASR model Parameters ---------- name : str one of the official model names listed by `whisper.available_model

Perform a forward pass on the decoder and return per-token logits

Preprocess an image for the VAE. :param img_name: The image file path or a list of image file paths. :param half_mask: Wheth

Save a list of strings to a file, each string on a new line. Parameters: file_path (str): The path to the file where the list will be sa

Create cheek area mask (1/4 area on both sides)

Convert video files to a specified format and save them to the destination path. Parameters: org_path (str): The directory containing th

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

Clean up any resources or hooks after decoding is finished