Downsamples the provided mask tensor to match the expected dimensions for scaled dot-product attention. If the aspect ratio of the ma

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

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

Prepares a single grid of images. Useful for visualization purposes.

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

r"""Disable the FreeNoise sampling mechanism.

r""" Instantiate a [`ControlNetModel`] from [`UNet2DConditionModel`]. Parameters: unet (`UNet2DConditionModel`):

Finds a rectangular region that contains all masked ares in an image, and expands region to match the aspect ratio of the original im

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

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

Forward process in flow-matching Args: sample (`torch.FloatTensor`): The input sample. times

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

Optionally removes offloading in case the pipeline has been already sequentially offloaded to CPU. Args: _pipeline (`Dif

Applies the FreeU mechanism as introduced in https: //arxiv.org/abs/2309.11497. Adapted from the official code repository: https://github.com/Chen

Disables the active LoRA layers of the underlying model. Example: ```py from diffusers import AutoPipelineForText2I

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

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

Precompute the frequency tensor for complex exponentials (cis) with given dimensions. This function calculates a frequency tensor with compl

This function return the height and width that are downscaled to the next integer multiple of `vae_scale_factor`. Args:

r""" Load pretrained attention processor layers into [`UNet2DConditionModel`]. Attention processor layers have to be defined in

This will load the LoRA layers specified in `state_dict` into `text_encoder` Parameters: state_dict (`dict`):

Convert a NumPy image to a PyTorch tensor.

r""" Preprocesses input video(s). Args: video (`List[PIL.Image]`, `List[List[PIL.Image]]`, `torch.Tensor`, `np.array`, `L

Upload model, scheduler, or pipeline files to the 🤗 Hugging Face Hub. Parameters: repo_id (`str`): The n

r""" Removes all hooks that were added when using `enable_sequential_cpu_offload` or `enable_model_cpu_offload`.