> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Vidu3StartEndToVideoNode - ComfyUI Built-in Node Documentation

> Complete documentation for the Vidu3StartEndToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage.

> 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/Vidu3StartEndToVideoNode/en.md)

This node generates a video by interpolating between a provided start frame and an end frame, guided by a text prompt. It uses the Vidu Q3 model to create a seamless transition between the two images, producing a video of a specified duration and resolution.

## Inputs

| Parameter          | Data Type | Required | Range                                | Description                                                                                                                                           |
| ------------------ | --------- | -------- | ------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model`            | COMBO     | Yes      | `"viduq3-pro"`<br />`"viduq3-turbo"` | The model to use for video generation. Selecting an option reveals additional configuration parameters for `resolution`, `duration`, and `audio`.     |
| `model.resolution` | COMBO     | Yes      | `"720p"`<br />`"1080p"`              | Resolution of the output video. This parameter is revealed after selecting a `model`.                                                                 |
| `model.duration`   | INT       | Yes      | 1 to 16                              | Duration of the output video in seconds (default: 5). This parameter is revealed after selecting a `model`.                                           |
| `model.audio`      | BOOLEAN   | Yes      | `True` / `False`                     | When enabled, outputs video with sound (including dialogue and sound effects) (default: False). This parameter is revealed after selecting a `model`. |
| `first_frame`      | IMAGE     | Yes      | -                                    | The starting image for the video sequence.                                                                                                            |
| `end_frame`        | IMAGE     | Yes      | -                                    | The ending image for the video sequence.                                                                                                              |
| `prompt`           | STRING    | Yes      | -                                    | A text description guiding the video generation (maximum 2000 characters).                                                                            |
| `seed`             | INT       | No       | 0 to 2147483647                      | A seed value for controlling the randomness of the generation (default: 1).                                                                           |

**Note:** The `first_frame` and `end_frame` images should have similar aspect ratios for optimal results.

## Outputs

| Output Name | Data Type | Description               |
| ----------- | --------- | ------------------------- |
| `video`     | VIDEO     | The generated video file. |