r""" Performs Pipeline dtype and/or device conversion. A torch.dtype and torch.device are inferred from the arguments of `self.to(*arg

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`,

A helper function to create random tensors on the desired `device` with the desired `dtype`. When passing a list of generators, you can seed each

r""" Args: Loads the ExponentialMovingAverage state. This method is used by accelerate during checkpointing to save the ema st

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. A

Creates a random float32 tensor

Loads `image` to a PIL Image. Args: image (`str` or `PIL.Image.Image`): The image to convert to the PIL Image format.

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m

r""" Enable sliced attention computation. When this option is enabled, the attention module splits the input tensor in slices to compu

r""" Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to `enable_sequenti

Helper function for reproducible behavior during distributed training. See - https://pytorch.org/docs/stable/notes/randomness.html for pytorc

Resize image. Args: image (`PIL.Image.Image`, `np.ndarray` or `torch.Tensor`): The image input, can be a

Load LoRA weights specified in `pretrained_model_name_or_path_or_dict` into `self.unet` and `self.text_encoder`. All kwargs

r"""Move internal buffers of the ExponentialMovingAverage to `device`. Args: device: like `device` argument to `torch.Tensor.to`

r""" Function that offloads all components, removes all model hooks that were added when using `enable_model_cpu_offload` and then app

Convert a NumPy image or a batch of images to a PIL image.

r""" Processes prompts that include a special token corresponding to a multi-vector textual inversion embedding to be replaced with mu

Disables custom attention processors and sets the default attention implementation.

r""" Returns the state of the ExponentialMovingAverage as a dict. This method is used by accelerate during checkpointing to save the e

Checks if the LoRA layers are correctly set with peft

r""" Adds a new adapter to the current model for training. If no adapter name is passed, a default name is assigned to the adapter to

r""" Reshape the tensor from `[batch_size, seq_len, dim]` to `[batch_size, seq_len, heads, dim // heads]` `heads` is the number of hea

r""" Offloads all models to CPU using 🤗 Accelerate, significantly reducing memory usage. When called, the state dicts of all `torch.nn

Resize an image to `(size["height"], size["width"])`. Args: image (`np.ndarray`): Image to resize.

Adjust the weightage given to the LoRA layers of the model. Args: model (`torch.nn.Module`): The model to scale.

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

`torch.device`: The device on which the module is (assuming that all the module parameters are on the same device).

Removes the previously passed weight given to the LoRA layers of the model. Args: model (`torch.nn.Module`): The model t

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

Save a configuration object to the directory specified in `save_directory` so that it can be reloaded using the [`~ConfigMixin.from_c

Args: Returns a dict of object names and values in a module, while skipping private/internal objects module (ModuleType):

Preprocess an image or batch of images. Args: images (`ImageInput`): Image to preprocess. Expects a sing

r""" Instantiates a text-to-image Pytorch diffusion pipeline from another instantiated diffusion pipeline class. The from_pipe() meth

Args: t0: start time has shape [batch_size, *shape, 1] t1: finish time has shape [batch_size, *shape, 1]

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

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

Function invoked when using the prior pipeline for interpolation. Args: images_and_prompts (`List[Union[str, PIL.Image.I

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

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take

r""" Fuses the LoRA parameters into the original parameters of the corresponding blocks. <Tip warning={true}> This is an exp

Preprocess the image input. Accepted formats are PIL images, NumPy arrays or PyTorch tensors.

Loads `image` to a PIL Image. Args: image (`str` or `PIL.Image.Image`): The image to convert to the PIL Image format.

r""" Set the attention processor to use. Args: processor (`AttnProcessor`): The attention processor to us

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

Prepares a pair (image, mask) to be consumed by the Stable Diffusion pipeline. This means that those inputs will be converted to ``torch.Tens

Postprocess the image output from tensor to `output_type`. Args: image (`torch.FloatTensor`): The image

Helper function to get activation function from string. Args: act_fn (str): Name of activation function. Returns: nn.Module:

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

r""" Instantiate a pretrained MultiControlNet model from multiple pre-trained controlnet models. The model is set in evaluation mode

r""" Load a model or scheduler configuration. Parameters: pretrained_model_name_or_path (`str` or `os.PathLike`, *optiona