Ë ¢Ùbiãó\—ddlmZddlmZeGd„de««ZeGd„de««Zy) é)Ú dataclassé)Ú BaseOutputcó—eZdZUdZded<y)ÚAutoencoderKLOutputa@ Output of AutoencoderKL encoding method. Args: latent_dist (`DiagonalGaussianDistribution`): Encoded outputs of `Encoder` represented as the mean and logvar of `DiagonalGaussianDistribution`. `DiagonalGaussianDistribution` allows for sampling latents from the distribution. ÚDiagonalGaussianDistributionÚ latent_distN©Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú__annotations__©óú\/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/models/modeling_outputs.pyrrs…ñð0Ô/rrcó—eZdZUdZded<y)ÚTransformer2DModelOutputa¤ The output of [`Transformer2DModel`]. Args: sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` or `(batch size, num_vector_embeds - 1, num_latent_pixels)` if [`Transformer2DModel`] is discrete): The hidden states output conditioned on the `encoder_hidden_states` input. If discrete, returns probability distributions for the unnoised latent pixels. z torch.TensorÚsampleNr rrrrrs…ñð ÔrrN)Ú dataclassesrÚutilsrrrrrrúrsAðÝ!åð ô 0˜*ó 0ó ð 0ð ô ˜zó ó ñ r