Create a single 'user'-role OpenAI message with one prompt followed by N media items. Emits `image_url` for images and `video_url` fo

r""" Applies an overlay of the mask and the inpainted image on the original image. Args: mask (`PIL.Image.Image`):

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

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

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

Convert a batch of per‑frame PIL images to BxTxCxHxW float tensors. pipe_images : List[List[PIL.Image]] Outer list over batch, inner

r""" Convert a NumPy image to a PyTorch tensor. Args: images (`np.ndarray`): The NumPy image array to con

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

Save an image (RGB, RGBA, depth, or semantic) to the specified path. Args: img (torch.Tensor or np.ndarray): The image data. Accepted

If the task is currently successful. :return: Tuple containing 2 bools: first specifies if the task is currently successful, seco

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

Build the *complete* message list in a readable, linear flow.

Compares a library version to some requirement using a given operation. Args: library_or_version (`str` or `packaging.version.Versio

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""" Converts a state dict from UNet format to diffusers format - i.e. by removing some keys

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

format eta and time elapsed

Take the mean over all non-batch dimensions.

r""" Safety checker that arguments are correct - also replaces some NoneType arguments with their default values.

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

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

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

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

Cleans up the history for the specified key by set all the values to pd none in the column.

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

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

r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and en

Encode an event to an index.

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

Expand a tensor or array to a specified number of images.

Gets a 1D array of all the low-dimensional obseervations. :return: 1D array of observations.

This matches the implementation in Denoising Diffusion Probabilistic Models: Create sinusoidal timestep embeddings. Args timesteps (

Recovers the depth values from an image. Reverses the depth to image conversion performed by FloatArrayToRgbImage or FloatArrayToGrayImage. Th

Convert a NumPy image to a PyTorch tensor.

Process the input_dict to extract b_action, save_dirs, return_objects, txt_list, img_list.

Convert a PyTorch tensor to a NumPy image.