Initialize the weights

Initialize the weights

Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base class PreTrainedModel

Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base class PreTrainedModel

r""" Returns: `dict` of attention processors: A dictionary containing all attention processors used in the model with

r""" Returns: `dict` of attention processors: A dictionary containing all attention processors used in the model with

Disables the FreeU mechanism.

r""" Disable sliced VAE decoding. If `enable_slicing` was previously enabled, this method will go back to computing decoding in one st

r""" Disable tiled VAE decoding. If `enable_tiling` was previously enabled, this method will go back to computing decoding in one step

r"""Enables the FreeU mechanism from https://arxiv.org/abs/2309.11497. The suffixes after the scaling factors represent the stage blocks wher

r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev

just do any calculation with pytorch layers - the first time this is done it allocaltes about 700MB of memory and spends about 2.7 seconds do

Forward pass for inference.

r""" Args: sample (`torch.FloatTensor`): Input sample. sample_posterior (`bool`, *optional*, defaults to `False`):

r""" The [`UNet2DConditionModel`] forward method. Args: sample (`torch.FloatTensor`): The noisy input ten

r""" encoder_hidden_states (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`): Seq

r""" encoder_hidden_states (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`): Seq

call function as forward Args: image: type: torch.Tensor shape: batch_size * 3 * 384 * 384 caption: type: l

Parameters ---------- x: input logits y: targets (multi-label binarized vector)