Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The LatentCutToBatch node takes a latent representation and splits it along a specified dimension into multiple slices. These slices are then stacked into a new batch dimension, effectively converting a single latent sample into a batch of smaller latent samples. This is useful for processing different parts of a latent space independently.

Inputs

ParameterData TypeRequiredRangeDescription
samplesLATENTYes-The latent representation to be split and batched.
dimCOMBOYes"t"
"x"
"y"
The dimension along which to cut the latent samples. "t" refers to the temporal dimension, "x" to the width, and "y" to the height.
slice_sizeINTYes1 to 16384The size of each slice to cut from the specified dimension. If the dimension’s size is not perfectly divisible by this value, the remainder is discarded. (default: 1)

Outputs

Output NameData TypeDescription
samplesLATENTThe resulting latent batch, containing the sliced and stacked samples.