EmptyHunyuanLatentVideo - ComfyUI Built-in Node Documentation

The EmptyHunyuanLatentVideo node is similar to the EmptyLatentImage node. You can consider it as a blank canvas for video generation, where width, height, and length define the properties of the canvas, and the batch size determines the number of canvases to create. This node creates empty canvases ready for subsequent video generation tasks.

Inputs

Parameter	Description	Comfy Type
`width`	Video width, default 848, minimum 16, maximum `nodes.MAX_RESOLUTION`, step size 16.	`INT`
`height`	Video height, default 480, minimum 16, maximum `nodes.MAX_RESOLUTION`, step size 16.	`INT`
`length`	Video length, default 25, minimum 1, maximum `nodes.MAX_RESOLUTION`, step size 4.	`INT`
`batch_size`	Batch size, default 1, minimum 1, maximum 4096.	`INT`

Outputs

Parameter	Description	Comfy Type
`samples`	Generated latent video samples containing zero tensors, ready for processing and generation tasks.	`LATENT`

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

EmptyHunyuanImageLatent - ComfyUI Built-in Node Documentation

EmptyHunyuanVideo15Latent - ComfyUI Built-in Node Documentation

​Inputs

​Outputs

Inputs

Outputs