GrokVideoReferenceNode - ComfyUI Built-in Node Documentation

The Grok Reference-to-Video node generates a video based on a text prompt, using up to seven reference images to guide the style and content of the output. It connects to an external API to create the video, which is then downloaded and returned.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	Text description of the desired video.	STRING	Yes	N/A
`model`	The model to use for video generation.	COMBO	Yes	`"grok-imagine-video"`
`model.reference_images`	Up to 7 reference images to guide the video generation.	IMAGE	Yes	1 to 7 images
`model.resolution`	The resolution of the output video.	COMBO	Yes	`"480p"` `"720p"`
`model.aspect_ratio`	The aspect ratio of the output video.	COMBO	Yes	`"16:9"` `"4:3"` `"3:2"` `"1:1"` `"2:3"` `"3:4"` `"9:16"`
`model.duration`	The duration of the output video in seconds (default: 6).	INT	Yes	2 to 10
`seed`	Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0).	INT	No	0 to 2147483647

Note: The model parameter is a group containing reference_images, resolution, aspect_ratio, and duration. You must provide at least one reference image, and you can provide up to seven.

Outputs

Output Name	Description	Data Type
`video`	The generated video file.	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): df50e80ca403d05469881e1c456ca4777d70989d8950c5e3844271c3ff8df85a

​Inputs

​Outputs

Inputs

Outputs