RunwayAleph2VideoToVideoNode - ComfyUI Built-in Node Documentation

This node edits a video using a text prompt with Runway’s Aleph2 model. It transforms your footage by restyling, relighting, adding or removing elements, or changing the viewpoint while preserving the original motion and timing. The output resolution matches the input video.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	Describes what should appear in the output (1-1000 characters).	STRING	Yes	1-1000 characters
`video`	Input video to edit. Must be 2-30 seconds at 30 fps or lower.	VIDEO	Yes	2-30 seconds duration, 30 fps max
`seed`	Random seed for generation (default: 0).	INT	Yes	0 to 4294967295
`public_figure_threshold`	Content moderation for recognizable public figures (default: “low”).	COMBO	Yes	”auto" "low”
`keyframes`	Guidance images anchored to the input video, from Aleph2 Keyframe nodes (up to 5). Use keyframes or prompt images, not both.	KEYFRAME	No	Up to 5 items
`prompt_images`	Guidance images anchored to the output video, from Aleph2 Prompt Image nodes (up to 5). Use keyframes or prompt images, not both.	PROMPT_IMAGE	No	Up to 5 items

Important constraints:

The input video must be between 2 and 30 seconds long and have a frame rate of 30 fps or lower.
You can use either keyframes or prompt_images for guidance, but not both at the same time.
Each guidance input (keyframes or prompt images) supports a maximum of 5 items.
Keyframe timestamps and prompt image timestamps must not exceed the input video duration.

Outputs

Output Name	Description	Data Type
`video`	The edited video generated by the Aleph2 model.	VIDEO

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): bda4d0f49843c1a8f311ddbce5911a2a157cae798a26f7a183b31fe41686d0b7

​Inputs

​Outputs

Inputs

Outputs