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

r""" Pad the tokens (with starting and ending tokens) and weights (with 1.0) to max_length.

r""" Pad the tokens (with starting and ending tokens) and weights (with 1.0) to max_length.

Partitions t0 and t1 into n_samples intervals. Args: ts: [batch_size, *shape, n_samples, 1] Return:

Convert a PIL image or a list of PIL images to NumPy arrays.

latents = self.prepare_latents( batch_size * num_images_per_prompt, 1 num_channels_latents, 4 height, 153

Modifies the UNet (`unet`) to perform Pix2Pix Zero optimizations.

This function is to be called from `conftest.py` via `pytest_addoption` wrapper that has to be defined there. It allows loading both `confte

Generate multiple reports at the end of test suite run - each report goes into a dedicated file in the current directory. The report files ar

Read the init and extracts PyTorch, TensorFlow, SentencePiece and Tokenizers objects.

Perform volumetric rendering over a partition of possible t's in the union of rendering volumes (written below with some abuse of not

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 attentions to the new naming scheme (local renaming)

Here, we replace the placeholder tokens in text recorded in token_map so that the text_encoder can encode them vector_shuffle

Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and Sample Steps are Flawed](http

Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and Sample Steps are Flawed](http

Args: image: RGB-like depth image Returns: depth map

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

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`)

Find the interpolation point between the 'low' and 'high' values for the given 'val'. See https://en.wikipedia.org/wiki/Slerp for more details on

Split `code` into its indented blocks, starting at `indent_level`. If provided, begins splitting after `start_prompt` and stops at `end_promp

Step function propagating the sample with the linear multi-step method. This has one forward pass with multiple times to approximate