Skip to main content
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

ParameterComfy TypeDescription
widthINTVideo width, default 848, minimum 16, maximum nodes.MAX_RESOLUTION, step size 16.
heightINTVideo height, default 480, minimum 16, maximum nodes.MAX_RESOLUTION, step size 16.
lengthINTVideo length, default 25, minimum 1, maximum nodes.MAX_RESOLUTION, step size 4.
batch_sizeINTBatch size, default 1, minimum 1, maximum 4096.

Outputs

ParameterComfy TypeDescription
samplesLATENTGenerated latent video samples containing zero tensors, ready for processing and generation tasks.