Support OrderedDict for yaml. Returns: yaml Loader and Dumper.

r""" Enable sliced attention computation. When this option is enabled, the attention module splits the input tensor in slices to comp

Set models to evaluation mode.

Tool function to split the image into tiles @param h: height of the image @param w: width of the image @return: tile_

summarize the mean and var and return a function that apply group norm on each tile

r""" Decode a batch of images using a tiled decoder. Args: z (`torch.FloatTensor`): Input batch of latent vectors.

r"""Encode a batch of images using a tiled encoder. When this option is enabled, the VAE will split the input tensor into tiles to compute en

Decode a latent vector z into an image in a tiled manner. @param z: latent vector @return: image

Apply wavelet blur to the input tensor.

Apply wavelet decomposition, so that the content will have the same color as the style.

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Args: img_size (int, tuple): input image size patch_size (int, tuple): patch size in_chans (int): number

r""" Tag2Text inference module, both captioning and tagging are included. Tag2Text is an efficient and controllable vision-language pre-traini

r""" The Recognize Anything Model (RAM) inference module. RAM is a strong image tagging model, which can recognize any common category with hi

r""" Tag2Text inference module, both captioning and tagging are included. Tag2Text is an efficient and controllable vision-language pre-traini

r""" The Recognize Anything Model (RAM) inference module. RAM is a strong image tagging model, which can recognize any common category with hi

Initialize the weights

Initialize the weights