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

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

Resize a PIL image. Both height and width are downscaled to the next integer multiple of `vae_scale_factor`.

Sets the discrete timesteps used for the diffusion chain. Supporting function to be run before inference. Args: num_infe

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

Creates a random float32 tensor

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

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

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

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

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

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

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

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

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

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

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

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

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

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

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

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

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

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

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

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

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

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

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

r""" Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet, text_encoder, vae and safety

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

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

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

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

Disables custom attention processors and sets the default attention implementation.

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

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

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

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