ReplaceVideoLatentFrames - ComfyUI Built-in Node Documentation

The ReplaceVideoLatentFrames node inserts frames from a source latent video into a destination latent video, starting at a specified frame index. If the source latent is not provided, the destination latent is returned unchanged. The node handles negative indexing and will issue a warning if the source frames do not fit within the destination.

Inputs

Parameter	Description	Data Type	Required	Range
`destination`	The destination latent where frames will be replaced.	LATENT	Yes	-
`source`	The source latent providing frames to insert into the destination latent. If not provided, the destination latent is returned unchanged.	LATENT	No	-
`index`	The starting latent frame index in the destination latent where the source latent frames will be placed. Negative values count from the end (default: 0).	INT	Yes	-MAX_RESOLUTION to MAX_RESOLUTION

Constraints:

The index must be within the bounds of the destination latent’s frame count. If it is not, a warning is logged and the destination is returned unchanged.
The source latent frames must fit within the destination latent frames starting from the specified index. If they do not, a warning is logged and the destination is returned unchanged.

Outputs

Output Name	Description	Data Type
`output`	The resulting latent video after the frame replacement operation.	LATENT

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

Source fingerprint (SHA-256): c70eb5f907964e00babcee66a98d1bf382c3bc704f920d61598a4a03f4d686f8

​Inputs

​Outputs

Inputs

Outputs