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

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

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

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

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

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

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

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

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

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

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

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

Predict the sample at the previous timestep by reversing the ODE. Core function to propagate the diffusion process from the learned m

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

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

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

Creates a random float32 tensor

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

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

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

Disables custom attention processors and sets the default attention implementation.

r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`): The p

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

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""" Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/). When this option is enabled, yo

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

Runs `command` with `subprocess.check_output` and will potentially return the `stdout`. Will also properly capture if an error occurred while

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

Checks if the LoRA layers are correctly set with peft

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

r""" Create a new pipeline from a given pipeline. This method is useful to create a new pipeline from the existing pipeline components

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

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

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

r""" Instantiate a [`DiffusionPipeline`] from pretrained pipeline weights saved in the `.ckpt` or `.safetensors` format. The pipeline

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

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

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

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

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

Args: Helper function for reproducible behavior to set the seed in `random`, `numpy`, `torch`. seed (`int`): The seed to set.

Return a logger with the specified name. This function is not supposed to be directly accessed unless you are writing a custom diffusers mod

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

Unified API to get any scheduler from its name. Args: name (`str` or `SchedulerType`): The name of the scheduler to use.

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

Activates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or *checkpoint activations*

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

r""" Converts a state dict to new diffusers format. The state dict can be from previous diffusers format (`OLD_DIFFUSERS`), or PEFT format (`P

r""" Set the attention processor for the PAG layers.