Restores the original order of elements from the reordered list. Parameters: - newarr (List): The reordered array.

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 `unet`. Parameters: state_dict (`dict`): A

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

Draw the first `n` samples in order from the specified split. Used for tasks with "canonical" ordered fewshot examples, such as MMLU

r""" Save attention processor layers to a directory so that it can be reloaded with the [`~loaders.UNet2DConditionLoadersMixin.load_at

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

Construct a layernorm module in the T5 style. No bias and no subtraction of mean.

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

Args: img_tensor: should be a batch of torch tensors in the shape of [B, C, H, W] prompt: the prompt to use, a string

r""" Instantiate a pretrained MultiAdapter model from multiple pre-trained adapter models. The model is set in evaluation mode by def

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

Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona

Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona

Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona

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

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

Aggregate the results of the screenspot evaluation task using the specified metric. Args: - results (list of dict): List of result dicti

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

:return: Iterable[obj] A iterable of any object, that doc_to_text can handle

r""" Reverses the effect of [`pipe.fuse_lora()`](https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraLoade

:return: Iterable[obj] A iterable of any object, that doc_to_text can handle