This node generates a video featuring a person or object based on provided reference materials. It uses the Wan 2.7 model to create videos from a text prompt, supporting single-character performances and multi-character interactions. You must provide at least one reference video or image for the generation to work.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `model` | The specific model to use for video generation. | COMBO | Yes | `"wan2.7-r2v"` |
| `model.prompt` | Prompt describing the video. Use identifiers such as 'character1' and 'character2' to refer to the reference characters. | STRING | Yes | - |
| `model.negative_prompt` | Negative prompt describing what to avoid in the generated video (default: empty). | STRING | No | - |
| `model.resolution` | The resolution of the output video. | COMBO | Yes | `"720P"`<br>`"1080P"` |
| `model.ratio` | The aspect ratio of the output video. | COMBO | Yes | `"16:9"`<br>`"9:16"`<br>`"1:1"`<br>`"4:3"`<br>`"3:4"` |
| `model.duration` | The length of the generated video in seconds (default: 5). | INT | Yes | 2 to 10 |
| `model.reference_videos` | A list of reference videos. You can add up to 3 videos. | VIDEO | No | - |
| `model.reference_images` | A list of reference images. You can add up to 5 images. | IMAGE | No | - |
| `seed` | Seed to use for generation, which helps control the randomness of the output (default: 0). | INT | No | 0 to 2147483647 |
| `watermark` | Whether to add an AI-generated watermark to the result (default: False). This is an advanced setting. | BOOLEAN | No | - |

**Important Constraints:**
*   You must provide at least one reference video or reference image in the `model.reference_videos` or `model.reference_images` inputs.
*   The total combined number of reference videos and images cannot exceed 5.

## 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/Wan2ReferenceVideoApi/en.md)

---
**Source fingerprint (SHA-256):** `83550e1193a13c3686506a279c0a8469be93be564dd27867e31b8b2724e7025d`