> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# kling-video-o1

> Use kling-video-o1 through the Kling Legacy Omni Video API for multimodal video generation and editing.

Kling O1 is Kling's unified multimodal video model. One Legacy Omni endpoint supports text-to-video, image-to-video, image and element references, video editing, video continuation, and first/end-frame generation.

## Core capabilities

* **Text to video** — Generate a 3–10 second video from a text prompt
* **Image and element reference** — Preserve characters, objects, scenes, and style with images or Legacy element IDs
* **Video editing** — Add, remove, or modify elements and change composition, viewpoint, style, color, or weather
* **Video reference** — Reference content, motion, style, or camera movement to create a previous or next shot
* **First/end frames** — Guide a transition with a first frame or with both first and end frames

<Note>
  Use `model_name: "kling-o1"`. Kling O1 supports 3–10 seconds, 720p (`std`), and 1080p (`pro`). It does not support multi-shot generation or 4K.
</Note>

## Quick example

```bash cURL theme={null}
curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/omni-video \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model_name": "kling-o1",
    "prompt": "A traveler walks through a rain-soaked Tokyo street with cinematic camera movement",
    "mode": "pro",
    "aspect_ratio": "16:9",
    "duration": "7"
  }'
```

## Multimodal prompts

Use `<<<image_1>>>`, `<<<element_1>>>`, and `<<<video_1>>>` in `prompt` to reference items in the corresponding arrays. Numbering starts at 1 and follows array order.

```json theme={null}
{
  "model_name": "kling-o1",
  "prompt": "Make the person in <<<image_1>>> wave to the camera, using the style of <<<image_2>>>",
  "image_list": [
    {"image_url": "https://example.com/character.png"},
    {"image_url": "https://example.com/style.png"}
  ],
  "mode": "pro",
  "aspect_ratio": "16:9",
  "duration": "5"
}
```

## Video editing and reference

* `refer_type: "base"` edits the input video. It cannot be combined with first/end frames, and `duration` is ignored because output duration follows the input.
* `refer_type: "feature"` references content, action, style, or camera movement and can generate a previous or next shot.
* Set `keep_original_sound` to `yes` or `no`.
* Set `sound` to `off` whenever `video_list` is present.

## Media limits

* Images accept URL or raw Base64 without a data URI prefix. Use JPG/JPEG/PNG up to 10 MB, at least 300 px per side, and an aspect ratio from 1:2.5 to 2.5:1.
* An end frame requires a first frame. Kling O1 does not support first/end-frame mode when `image_list` contains more than two images.
* First/end-frame mode cannot use elements.
* Videos must use an accessible MP4/MOV URL, at least 3 seconds, dimensions 720–2160 px, 24–60 fps, at most one file up to 200 MB, and aspect ratio 1:2.5 to 2.5:1.
* Without a reference video and with only multi-image elements, images plus elements cannot exceed 7; with a reference video, the total cannot exceed 4.

<Card title="API Reference" icon="code" href="/api-reference/model-api/kuaishou/kling-video-o1">
  View the complete Legacy schema, scenario examples, and task query responses.
</Card>

<script src="/feedback.js" />