Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

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

Overview

The EmptyARVideoLatent node creates a blank, empty latent representation for video generation. It is used to initialize a video generation process by providing a tensor of zeros with the specified dimensions, aspect ratio, and length.

Inputs

ParameterData TypeRequiredRangeDescription
widthINTYes16 to 8192 (step: 16)The width of the video frames in pixels (default: 832)
heightINTYes16 to 8192 (step: 16)The height of the video frames in pixels (default: 480)
lengthINTYes1 to 1024 (step: 4)The number of frames in the video (default: 81)
batch_sizeINTYes1 to 64The number of videos to generate in a single batch (default: 1)

Outputs

Output NameData TypeDescription
LATENTLATENTA latent tensor filled with zeros, representing an empty video latent space with the specified dimensions, length, and batch size. The tensor shape is [batch_size, 16, lat_t, height/8, width/8], where lat_t is calculated from the length.

Source fingerprint (SHA-256): b36c40d768e846bc67ed6a7bfb4145c6e2a4ca55824296250a88f52d5ae305cf