Convert a PyTorch tensor to a NumPy image.

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

To run a test in a subprocess. In particular, this can avoid (GPU) memory issue. Args: test_case (`unittest.TestCase`):

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

Gets scaled timesteps from the Karras sigmas for input to the consistency model. Args: sigmas (`float` or `np.ndarray`):

Correct the predicted sample based on the `model_output` of the network. This is often run repeatedly after making the prediction for

Uploads all files in `working_dir` to `repo_id`.

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

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

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

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

Parameters: pretrained_model_name_or_path_or_dict (`str` or `os.PathLike` or `dict`): Can be either:

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

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

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

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

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

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

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

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

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

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

r""" Checks if the version of PEFT is compatible. Args: version (`str`): The version of PEFT to check against.

Copy current averaged parameters into given collection of parameters. Args: parameters: Iterable of `torch.nn.Parameter`

Encode an event to an index.

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

Normalize an image array to [-1,1].