EmptyCosmosLatentVideo - ComfyUI Built-in Node Documentation - ComfyUI

EmptyCosmosLatentVideo creates an empty latent video tensor with the 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

Parameter	Description	Data Type	Required	Range
`width`	The width of the latent video in pixels (default: 1280, increments of 16)	INT	Yes	16 to MAX_RESOLUTION
`height`	The height of the latent video in pixels (default: 704, increments of 16)	INT	Yes	16 to MAX_RESOLUTION
`length`	The number of frames in the latent video (default: 121, increments of 8)	INT	Yes	1 to MAX_RESOLUTION
`batch_size`	The number of latent videos to generate in a batch (default: 1)	INT	No	1 to 4096

Note: The latent tensor is spatially downsampled by a factor of 8 in both height and width, and contains 16 channels. The number of latent temporal frames is calculated as ((length - 1) // 8) + 1.

Outputs

Output Name	Description	Data Type
`samples`	The generated empty latent video tensor with zero values	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): 7ee194324b02367ed853f6d36bc51742081bac6a9469c4a619586e0560a1b33b