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 EmptyLTXVLatentVideo node creates an empty latent tensor for video processing. It generates a blank starting point with specified dimensions that can be used as input for video generation workflows. The node produces a zero-filled latent representation with the configured width, height, length, and batch size.

Inputs

ParameterData TypeRequiredRangeDescription
widthINTYes64 to MAX_RESOLUTIONThe width of the latent video tensor (default: 768, step: 32)
heightINTYes64 to MAX_RESOLUTIONThe height of the latent video tensor (default: 512, step: 32)
lengthINTYes1 to MAX_RESOLUTIONThe number of frames in the latent video (default: 97, step: 8)
batch_sizeINTNo1 to 4096The number of latent videos to generate in a batch (default: 1)

Outputs

Output NameData TypeDescription
samplesLATENTThe generated empty latent tensor with zero values in the specified dimensions