# Vidu2 Start/End Frame-to-Video Generation

This node generates a video by interpolating between a provided start frame and an end frame, guided by a text prompt. It uses a specified Vidu model to create a smooth transition between the two images over a set duration.

## Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `model` | The Vidu model to use for video generation. | COMBO | Yes | `"viduq2-pro-fast"`<br>`"viduq2-pro"`<br>`"viduq2-turbo"` |
| `first_frame` | The starting image for the video sequence. Only a single image is allowed. | IMAGE | Yes | - |
| `end_frame` | The ending image for the video sequence. Only a single image is allowed. | IMAGE | Yes | - |
| `prompt` | Prompt description (max 2000 characters). | STRING | Yes | - |
| `duration` | The length of the generated video in seconds (default: 5). | INT | No | 2 to 8 |
| `seed` | A number used to initialize the random generation for reproducible results (default: 1). | INT | No | 0 to 2147483647 |
| `resolution` | The output resolution of the generated video. | COMBO | No | `"720p"`<br>`"1080p"` |
| `movement_amplitude` | The movement amplitude of objects in the frame. | COMBO | No | `"auto"`<br>`"small"`<br>`"medium"`<br>`"large"` |

**Note:** The `first_frame` and `end_frame` images must have similar aspect ratios. The node validates that their aspect ratios are within a relative range of 0.8 to 1.25. Only one image is allowed for each input.

## Outputs

| Output Name | Description | Data Type |
|-------------|-------------|-----------|
| `output` | 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/Vidu2StartEndToVideoNode/en.md)

---
**Source fingerprint (SHA-256):** `01316d15f95f264cadfb33978565fc320a9f42917693faa87c1367c0f31ca400`