Skip to main content
The LatentCutToBatch node splits a latent representation along a chosen dimension into multiple slices and stacks them into a new batch. This allows you to process different parts of a latent sample independently.

Inputs

ParameterDescriptionData TypeRequiredRange
samplesThe latent representation to be split and batched.LATENTYes-
dimThe dimension along which to cut the latent samples. "t" refers to the temporal dimension, "x" to the width, and "y" to the height.COMBOYes"t"
"x"
"y"
slice_sizeThe 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)INTYes1 to 16384 (max resolution)

Outputs

Output NameDescriptionData Type
samplesThe resulting latent batch, containing the sliced and stacked samples.LATENT
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 565fd1e72a1353050cf8c32c6ab8dade475afb2e8ee13ba323d30a8467204201