This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThis node adjusts the first few frames of a video latent to make them look more like the frames that come after. It calculates the average and variation from a set of reference frames later in the video and applies those same characteristics to the starting frames. This helps create a smoother and more consistent visual transition at the beginning of a video.
Inputs
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
latent | LATENT | Yes | - | The video latent representation to process. |
start_frame_count | INT | No | 1 to 16384 | Number of latent frames to normalize, counted from the start (default: 4). |
reference_frame_count | INT | No | 1 to 16384 | Number of latent frames after the start frames to use as reference (default: 5). |
reference_frame_count is automatically limited to the number of frames available after the starting frames. If the video latent is only 1 frame long, no normalization is performed and the original latent is returned unchanged.
Outputs
| Output Name | Data Type | Description |
|---|---|---|
latent | LATENT | The processed video latent with the starting frames normalized. |