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

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

r""" Returns the device on which the pipeline's models will be executed. After calling `pipeline.enable_sequential_cpu_offload()` the

r""" Returns the device on which the pipeline's models will be executed. After calling `pipeline.enable_sequential_cpu_offload()` the

r""" Disable sliced VAE decoding. If `enable_vae_slicing` was previously invoked, this method will go back to computing decoding in on

r""" Disable sliced VAE decoding. If `enable_vae_slicing` was previously invoked, this method will go back to computing decoding in on

r""" Disable tiled VAE decoding. If `enable_vae_tiling` was previously invoked, this method will go back to computing decoding in one

r""" Disable tiled VAE decoding. If `enable_vae_tiling` was previously invoked, this method will go back to computing decoding in one

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

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

r""" Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet, text_encoder, vae and safety

r""" Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet, text_encoder, vae and safety

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

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

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

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

Evaluate spherical harmonics at unit directions using hardcoded SH polynomials. Works with torch/np/jnp. ... Can be 0 or more batch d

Get ray directions for all pixels in camera coordinate. Reference: https://www.scratchapixel.com/lessons/3d-basic-rendering/ r

replace background pixel with white color

replace background pixel with white color

replace background pixel with white color; the main difference with load_im_masked is that the mask is passed as a numpy array

replace background pixel with white color; the main difference with load_im_masked is that the mask is passed as a numpy array

sample points along the rays Inputs: rays: () Returns:

Reads an HDR map from disk. Args: path (str): Path to the .hdr file. Returns: numpy.ndarray: Loaded (float) HDR map with RGB

input: pos, [3,] camera location, point to the origin output: elevation, azimuth, distance

depth: (H, W)