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 EmptyCosmosLatentVideo node creates an empty latent video tensor with specified dimensions. It generates a zero-filled latent representation that can be used as a starting point for video generation workflows, with configurable width, height, length, and batch size parameters.

Inputs

ParameterData TypeRequiredRangeDescription
widthINTYes16 to MAX_RESOLUTIONThe width of the latent video in pixels (default: 1280, must be divisible by 16)
heightINTYes16 to MAX_RESOLUTIONThe height of the latent video in pixels (default: 704, must be divisible by 16)
lengthINTYes1 to MAX_RESOLUTIONThe number of frames in the latent video (default: 121)
batch_sizeINTNo1 to 4096The number of latent videos to generate in a batch (default: 1)

Outputs

Output NameData TypeDescription
samplesLATENTThe generated empty latent video tensor with zero values