Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The LTXVSeparateAVLatent node takes a combined audio-visual latent representation and splits it into two distinct parts: one for video and one for audio. It separates the samples and, if present, the noise masks from the input latent, creating two new latent objects.

Inputs

ParameterData TypeRequiredRangeDescription
av_latentLATENTYesN/AThe combined audio-visual latent representation to be separated.
Note: The input latent’s samples tensor is expected to have at least two elements along the first dimension (batch dimension). The first element is used for the video latent, and the second element is used for the audio latent. If a noise_mask is present, it is split in the same way.

Outputs

Output NameData TypeDescription
video_latentLATENTThe latent representation containing the separated video data.
audio_latentLATENTThe latent representation containing the separated audio data.