§ òwŠiãóv—ddlmZddlmZeGd„de¦«¦«ZeGd„de¦«¦«ZdS) é)Ú dataclassé)Ú BaseOutputcó—eZdZUdZded<dS)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__©óúq/root/.openclaw/workspace/chatterbox_venv_py311/lib/python3.11/site-packages/diffusers/models/modeling_outputs.pyrrs*€€€€€€ððð0Ð/Ð/Ñ/Ð/Ð/rrcó—eZdZUdZded<dS)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*€€€€€€ððð ÐÐÑÐÐrrN)Ú dataclassesrÚutilsrrrrrrúrsŸðØ!Ð!Ð!Ð!Ð!Ð!àÐÐÐÐÐð ð 0ð 0ð 0ð 0ð 0˜*ñ 0ô 0ñ „ð 0ð ð ð ð ð ð ˜zñ ô ñ „ð ð ð r