Skip to main content
The RebatchLatents node is designed to reorganize a batch of latent representations into a new batch configuration, based on a specified batch size. It ensures that the latent samples are grouped appropriately, handling variations in dimensions and sizes, to facilitate further processing or model inference.

Inputs

ParameterDescriptionData Type
latentsThe ‘latents’ parameter represents the input latent representations to be rebatched. It is crucial for determining the structure and content of the output batch.LATENT
batch_sizeThe ‘batch_size’ parameter specifies the desired number of samples per batch in the output. It directly influences the grouping and division of the input latents into new batches.INT

Outputs

ParameterDescriptionData Type
latentThe output is a reorganized batch of latent representations, adjusted according to the specified batch size. It facilitates further processing or analysis.LATENT
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub