# Kling 3.0 Omni Edit Video Node

The Kling Omni Edit Video (Pro) node uses an AI model to edit an existing video based on a text description. You provide a source video and a prompt, and the node generates a new video of the same length with the requested changes. It can optionally use reference images to guide the style and keep the original audio from the source video.

## Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `model_name` | The AI model to use for video editing (default: `"kling-v3-omni"`). | COMBO | Yes | `"kling-v3-omni"`<br>`"kling-video-o1"` |
| `prompt` | A text prompt describing the video content. This can include both positive and negative descriptions. | STRING | Yes |  |
| `video` | Video for editing. The output video length will be the same. | VIDEO | Yes |  |
| `keep_original_sound` | Determines if the original audio from the input video is kept in the output (default: True). | BOOLEAN | Yes |  |
| `reference_images` | Up to 4 additional reference images. | IMAGE | No |  |
| `resolution` | The resolution for the output video (default: `"1080p"`). | COMBO | No | `"1080p"`<br>`"720p"` |
| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed (default: 0). | INT | No | 0 to 2147483647 |

**Constraints and Limitations:**

* The `prompt` must be between 1 and 2500 characters long.
* The input `video` must be between 3.0 and 10.05 seconds in duration.
* The input `video` dimensions must be between 720x720 and 2160x2160 pixels.
* A maximum of 4 `reference_images` can be provided when a video is used.
* Each `reference_image` must be at least 300x300 pixels.
* Each `reference_image` must have an aspect ratio between 1:2.5 and 2.5:1.

## Outputs

| Output Name | Description | Data Type |
|-------------|-------------|-----------|
| `video` | The edited video generated by the AI model. | 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/KlingOmniProEditVideoNode/en.md)

---
**Source fingerprint (SHA-256):** `4aa7779a30183c80f025e15ae693ba23021013c68d247753e7e9a4c3a64762da`