r""" Instantiate a pretrained PyTorch model from a pretrained model configuration. The model is set in evaluation mode - `model.eval(

Compute the decay factor for the exponential moving average.

member function for obtaining the drift of the probability flow ODE

member function for obtaining score of x_t = alpha_t * x + sigma_t * eps

Wrapper function: transfrom velocity prediction model to score Args: velocity: [batch_dim, ...] shaped tensor; velocity model outp

Return function over iterator that groups key, value pairs into samples. :param keys: function that splits the key into key and extension (base_p

:param image_ids: :param video_ids: :return:

This method allows to interpolate the pre-trained position encodings, to be able to use the model on higher resolution images. This m

Take a conditioning sequence of indices idx (LongTensor of shape (b,t)) and complete the sequence max_new_tokens times, feeding the p

Take a conditioning sequence of indices idx (LongTensor of shape (b,t)) and complete the sequence max_new_tokens times, feeding the p

Standard multivariate normal prior Assume z is batched

Process an image with variable resolutions. Args: image (PIL.Image.Image): The input image to be processed. processor: The i

Used for CC12M

Resize and pad an image to a target resolution while maintaining aspect ratio. Args: image (PIL.Image.Image): The input image.

Args: Helper function for reproducible behavior to set the seed in `random`, `numpy`, `torch`. seed (`int`): The seed to set.

(batch_size, seq_len) t2i sequence = [ [pad][pad][t2i][sot][text][text][eot][soi][image][image][eoi]

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma

Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distribution :

x: (N, T, patch_size**2 * C) imgs: (N, H, W, C)