This node uses the latest Kling AI model to generate a video from a start frame, an optional end frame, or reference images. It can create a single video or a multi-shot storyboard with individual prompts and durations for each segment. The node processes these inputs to produce a video of a specified length and resolution, with optional audio generation.
## Inputs
| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `model_name` | The specific Kling AI model to use for video generation. | COMBO | Yes | `"kling-v3-omni"`
`"kling-video-o1"` |
| `prompt` | A text prompt describing the video content. This can include both positive and negative descriptions. Ignored when storyboards are enabled. | STRING | Yes | - |
| `duration` | The desired length of the generated video in seconds (default: 5). | INT | Yes | 3 to 15 |
| `first_frame` | The starting image for the video sequence. | IMAGE | Yes | - |
| `end_frame` | An optional end frame for the video. This cannot be used simultaneously with `reference_images`. Does not work with storyboards. | IMAGE | No | - |
| `reference_images` | Up to 6 additional reference images. | IMAGE | No | - |
| `resolution` | The output resolution for the generated video (default: "1080p"). | COMBO | No | `"4k"`
`"1080p"`
`"720p"` |
| `storyboards` | Generate a series of video segments with individual prompts and durations. Only supported for `kling-v3-omni`. When enabled, each storyboard requires a prompt and duration input. | DYNAMIC_COMBO | No | `"disabled"`
`"1 storyboard"`
`"2 storyboards"`
`"3 storyboards"`
`"4 storyboards"`
`"5 storyboards"`
`"6 storyboards"` |
| `generate_audio` | Generate audio for the video (default: False). Only supported for `kling-v3-omni`. | BOOLEAN | No | True / False |
| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed (default: 0). | INT | No | 0 to 2147483647 |
**Important Constraints:**
* The `end_frame` input cannot be used at the same time as the `reference_images` input.
* The `end_frame` input cannot be used simultaneously with storyboards.
* The `kling-video-o1` model does not support durations greater than 10 seconds, audio generation, 4k resolution, or storyboards.
* If you do not provide an `end_frame` or any `reference_images` with the `kling-video-o1` model, the `duration` can only be set to 5 or 10 seconds.
* All input images (`first_frame`, `end_frame`, and any `reference_images`) must have a minimum dimension of 300 pixels in both width and height.
* The aspect ratio of all input images must be between 1:2.5 and 2.5:1.
* A maximum of 6 images can be provided via the `reference_images` input.
* The `prompt` text must be between 1 and 2500 characters in length (0 characters allowed when storyboards are enabled).
* When storyboards are enabled, the total duration of all storyboard segments must equal the global `duration` value.
* Each storyboard prompt must be between 1 and 512 characters in length.
## 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/KlingOmniProFirstLastFrameNode/en.md)
---
**Source fingerprint (SHA-256):** `caa8c321124c70cb9cbeedee13cdde4c37c7e107c04265b4baf2dd8864a1fc65`