r""" Instantiate a Python class from a config dictionary Parameters: pretrained_model_name_or_path (`str` or `os.Path

r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and

Returns the tokenized representation of given input string(s) Parameters ---------- texts : Union[str, List[str]] An i

Zero out the parameters of a module and return it.

Construct a layernorm module in the T5 style. No bias and no subtraction of mean.

r""" Disable tiled VAE decoding. If `enable_vae_tiling` was previously invoked, this method will go back to computing decoding in on

Initialize a Batchnorm layer.

Initialize a Linear or Convolutional layer.

Args: Compares the current Transformers version to a given reference with an operation. operation (`str`): A string r

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward p

Args: x: (batch_size , ...) mixup_lambda: (batch_size,) Returns: out: (batch_size, ...)

Check whether the module was compiled with torch.compile()

Updates paths inside resnets to the new naming scheme (local renaming)

Save a configuration object to the directory `save_directory`, so that it can be re-loaded using the [`~ConfigMixin.from_config`] c

Shuffle sampler indices.

Encode an event to an index.

Compute the intermediate time steps for sampling. Args: skip_type: A `str`. The type for the spacing of the time steps. We sup

Interpolate data in time domain. This is used to compensate the resolution reduction in downsampling of a CNN. Args: x: (batch_size

Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t.

Removes segments. Positive values shave the first segments, negative shave the last segments.

Convert self to a tuple containing all the attributes/keys that are not `None`.

Sampler initialisation.

r""" Combines a latent iamge img_vae of shape (B, C, H, W) and a CLIP-embedded image img_clip of shape (B, 1, clip_img_dim) into a s

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

Args: Compares a library version to some requirement using a given operation. library_or_version (`str` or `packaging.version.Vers