Execute a forward pass and store the order of execution of specific sub-modules. - `module`: The module to trace. - `args`:

Unpack the positional and keyword arguments passed to a module.

Align and warp faces with face template.

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you

Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to t

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

3x3 convolution with padding

Takes a bounding box in the form [x1,y1,x2,y2] and returns z in the form [x,y,s,r] where x,y is the centre of the box and s is the scale/area and

Takes a bounding box in the centre form [x,y,s,r] and returns it in the form [x1,y1,x2,y2] where x1,y1 is the top left and x2,y2 is the bottom

A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and

Provide a singleton of FaceRestoreHelper. FaceRestoreHelper loads a model internally so we need to cache it or we end up with a memory l

Patch group_norm to cast the weights to the same type as the inputs. From what I can understand all the other repos just switch to full prec

https://github.com/CompVis/stable-diffusion/issues/25#issuecomment-1221416526.

Formats the filename based on the provided template and variables.

Range but handles floats.

Generates a video from a single image or multiple images, conditioned on the provided input_path. Args: input_path (str): Path to an

:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])

Get the next file number in a directory.

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

Function: ---------- get reference 5 key points according to crop settings: 0. Set default crop_size: if default_

Function: ---------- Find Similarity Transform Matrix 'trans': u = src_pts[:, 0] v = src_pts[:, 1]