About Kling O3 Pro - Reference to Video
Part of the Kling 3.0/o3 family, this reference-to-video model transforms static reference images into dynamic video sequences. It excels at preserving image details like identity, layout, and text while adding realistic motion, camera movements, and scene progression based on cinematic prompts. Supports multi-shot generation, explicit motion instructions, flexible durations up to 15 seconds, and native audio when specified. Optimized for advertising, branded content, and realistic scene extensions with smooth transitions and narrative continuity.
Ready to build with Kling O3 Pro - Reference to Video?
Try Kling O3 Pro - Reference to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "kling-video-o3-pro-reference-to-video",
"negative_prompt": "blur, distort, and low quality",
"generate_audio": true,
"aspect_ratio": "16:9",
"duration": 5
}'Request parameters
Every field Kling O3 Pro - Reference to Video accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
start_image_url | stringuri · nullable | No | — | The first frame of the video. The model will try to extend the contents of this frame. |
tail_image_url | stringuri · nullable | No | — | The last frame of the video. Requires start frame to be configured. The model will try to fill in between the frames. |
input_image | array<string>nullable | No | — | Reference images for style/appearance. Use @Image1, @Image2, etc. in the prompt to refer to them. Maximum 4 total (elements + reference images) when using video. |
elements | array<object> | No | — | Optional element references. Use @Element1, @Element2, etc. in the prompt to refer to them. |
negative_prompt | string | No | — | Text describing what to avoid in the generated video. |
generate_audio | boolean | No | true | Whether to generate native audio for the video. Supports Chinese and English voice output. |
aspect_ratio | string | No | "16:9" | 9:161:116:9 |