The connection class for face landmarks.

The face landmarks detection result from FaceLandmarker, where each vector element represents a single face detected in the image. Attributes:

A 2D Transformer model for image-like data. Parameters: num_attention_heads (`int`, *optional*, defaults to 16): The number of heads

r""" A basic Transformer block. Parameters: dim (`int`): The number of channels in the input and output. num_attention_heads

Convert any spelled-out numbers into arabic numbers, while handling: - remove any commas - keep the suffixes such as: `1960s`, `274th`,

Applies British-American spelling mappings as listed in [1]. [1] https://www.tysto.com/uk-us-spelling-list.html

Options for the face landmarker task. Attributes: base_options: Base options for the face landmarker task. running_mode: The running mode o

Select the sample with the highest log probabilities, penalized using either a simple length normalization or Google NMT paper's length penal

A thin wrapper around `GPT2TokenizerFast` providing quick access to special tokens

The output of [`Transformer2DModel`]. Args: sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` or `(ba

The output of [`UNet2DConditionModel`]. Args: sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):

A 2D UNet mid-block [`UNetMidBlock2D`] with multiple residual blocks and optional attention blocks. Args: in_channels (`int`): The n

Tiny Autoencoder block used in [`AutoencoderTiny`]. It is a mini residual module consisting of plain conv + ReLU blocks. Args: i

The 52 blendshape coefficients.

Class that performs face landmarks detection on images.

The connections between face landmarks.

r""" A conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample shaped output. This mo