This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe 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
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
av_latent | LATENT | Yes | N/A | The combined audio-visual latent representation to be separated. |
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 Name | Data Type | Description |
|---|---|---|
video_latent | LATENT | The latent representation containing the separated video data. |
audio_latent | LATENT | The latent representation containing the separated audio data. |