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

Generates temporally-correlated noise for the second pass of the VOID video refinement process. It takes the output video from Pass 1 and warps Gaussian noise along optical flow vectors, creating noise that moves consistently with the video content. This warped noise is used as the starting latent for Pass 2, which improves temporal consistency in the final output.

Inputs

ParameterData TypeRequiredRangeDescription
optical_flowOPTICAL_FLOWYes-Optical flow model from OpticalFlowLoader (RAFT-large).
videoIMAGEYes-Pass 1 output video frames [T, H, W, 3].
widthINTYes16 to MAX_RESOLUTION (step 8)Width of the output latent (default: 672).
heightINTYes16 to MAX_RESOLUTION (step 8)Height of the output latent (default: 384).
lengthINTYes1 to MAX_RESOLUTION (step 1)Number of pixel frames. Rounded down to make latent_t even (patch_size_t=2 requirement), e.g. 49 → 45 (default: 45).
batch_sizeINTYes1 to 64Number of identical noise sequences to generate (default: 1).
Note on length parameter: The length value is automatically rounded down to the nearest valid value that produces an even latent_t dimension. This is required by the CogVideoX-Fun-V1.5 model’s patch_size_t=2 constraint. A warning is logged when rounding occurs.

Outputs

Output NameData TypeDescription
warped_noiseLATENTA 5D tensor (B, C, T, H, W) containing optical-flow warped Gaussian noise, ready for use as the initial latent in VOID Pass 2.

Source fingerprint (SHA-256): fa7f08bd5e050324d1d9681243e82d66b1613b8694a5b69a5949b39974c6bddb