Args: pixel_values (`torch.FloatTensor`): Pixel values of shape (num_patches, num_channels * temporal_patch_size

Input shape: Batch x Time x Channel

Args: hidden_states (`torch.FloatTensor`): Input to the layer of shape `(batch, seq_len, embed_dim)`.

r""" Args: inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Optionally,

r""" spatial_shapes (`torch.LongTensor` of shape `(batch_size, 2)`): Tensor containing the spatial dimensions (height, width) of t

r""" pixel_attention_mask (`torch.Tensor` of shape `(batch_size, image_size, image_size)`, *optional*): Mask to avoid performing a

Resize positional embeddings to image-specific size and pad to a fixed size. Args: positional_embeddings (`torch.Tensor`

Run single model inference.

Update UI status when generation starts.

Toggle visibility of image and video input components.