# Google Veo 3 First-Last-Frame to Video

The Veo3FirstLastFrameNode uses Google's Veo 3 model to generate a video based on a text prompt, with a provided first and last frame that define the start and end of the video sequence.

## Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `prompt` | Text description of the video (default: empty string). | STRING | Yes | N/A |
| `negative_prompt` | Negative text prompt to guide what to avoid in the video (default: empty string). | STRING | No | N/A |
| `resolution` | The resolution of the output video. | COMBO | Yes | `"720p"`<br>`"1080p"`<br>`"4k"` |
| `aspect_ratio` | Aspect ratio of the output video (default: "16:9"). | COMBO | No | `"16:9"`<br>`"9:16"` |
| `duration` | Duration of the output video in seconds (default: 8, step: 2). | INT | No | 4 to 8 |
| `seed` | Seed for video generation (default: 0). | INT | No | 0 to 4294967295 |
| `first_frame` | The start frame for the video. | IMAGE | Yes | N/A |
| `last_frame` | The end frame for the video. | IMAGE | Yes | N/A |
| `model` | The specific Veo model to use for generation (default: "veo-3.1-generate"). | COMBO | No | `"veo-3.1-generate"`<br>`"veo-3.1-fast-generate"`<br>`"veo-3.1-lite"` |
| `generate_audio` | Generate audio for the video (default: True). | BOOLEAN | No | N/A |

**Note:** The `veo-3.1-lite` model does not support 4K resolution. If you select `veo-3.1-lite` and `4k` resolution, an error will occur.

## 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/Veo3FirstLastFrameNode/en.md)

---
**Source fingerprint (SHA-256):** `2fe55d2a1d018e58fd290c901c596708898acda835d2358adf36ed80103aeb6e`