> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-chore-sync-comfy-api-v2-spec.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# GrokVideoReferenceNode - ComfyUI Built-in Node Documentation
> The Grok Reference-to-Video node generates a video from a text prompt, using up to seven reference images to guide the style and content of the output.
The Grok Reference-to-Video node generates a video from a text prompt, using up to seven reference images to guide the style and content of the output. With the `grok-imagine-video-1.5` model, you can also attach up to three preset voice references and refer to images and voices directly in the prompt using `@ImageN` and `@AudioN` tags. The node sends the request to an external API, waits for the generation to complete, and downloads the resulting video.
## Inputs
### Common Inputs
| Parameter | Description | Data Type | Required | Range |
| --------- | ------------------------------------------------------------------------------------------------------------- | -------------- | -------- | ------------------------------------------------------ |
| `model` | The model to use for video generation. | DYNAMIC\_COMBO | Yes | `"grok-imagine-video-1.5"`
`"grok-imagine-video"` |
| `prompt` | Text description of the desired video. Must be a non-empty string. | STRING | Yes | N/A |
| `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0). | INT | Yes | 0 to 2147483647 |
### Grok Imagine Video 1.5 Inputs
Available when `model` is set to `grok-imagine-video-1.5`.
| Parameter | Description | Data Type | Required | Range |
| -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | -------- | --------------------------------------------------------------------------------------- |
| `voice_1` | Optional preset voice reference; refer to it in the prompt as @Audio1. The API supports only these preset voices, not custom audio (default: none). | COMBO | No | Preset voice options, including `"none"` |
| `voice_2` | Optional second voice reference; @Audio2 in the prompt (default: none). | COMBO | No | Preset voice options, including `"none"` |
| `voice_3` | Optional third voice reference; @Audio3 in the prompt (default: none). | COMBO | No | Preset voice options, including `"none"` |
| `resolution` | The resolution of the output video. | COMBO | Yes | `"480p"`
`"720p"` |
| `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"` |
| `duration` | The duration of the output video in seconds (default: 6). | INT | Yes | 1 to 15 |
### Grok Imagine Video Inputs
Available when `model` is set to `grok-imagine-video`.
| Parameter | Description | Data Type | Required | Range |
| -------------- | --------------------------------------------------------- | --------- | -------- | --------------------------------------------------------------------------------------- |
| `resolution` | The resolution of the output video. | COMBO | Yes | `"480p"`
`"720p"` |
| `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"` |
| `duration` | The duration of the output video in seconds (default: 6). | INT | Yes | 2 to 10 |
### Reference Inputs
| Parameter | Description | Data Type | Required | Range |
| ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | -------- | ------------- |
| `reference_images` | Growable slot: connect 1 to 7 reference images to guide the video generation. With `grok-imagine-video-1.5`, refer to them in the prompt as @Image1 ... @Image7, numbered in input order; a batched input counts once per image. | IMAGE | Yes | 1 to 7 images |
**Note:** The sub-parameters shown depend on the selected `model`; `grok-imagine-video-1.5` adds the `voice_1`, `voice_2`, and `voice_3` inputs. At least one reference image is required, and the total is capped at 7 (a batched input counts once per image). With `grok-imagine-video-1.5`, the prompt can reference connected images as `@Image1` ... `@Image7` and voice slots as `@Audio1`, `@Audio2`, `@Audio3`; an unnumbered `@image` or `@audio` refers to the first one. `@AudioN` refers to the `voice_N` widget, not the order of enabled voices. Referencing an image that is not connected or a voice slot set to `none` causes an error. The API supports only preset voices, not custom audio.
## 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](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoReferenceNode/en.md)
***
**Source fingerprint (SHA-256):** `e584c450563eaa7fcb7751d2325f9ef847fa34a4342df01f2bd9ce2e4ff8f2c3`