About Kling O3 4K - Reference to Video
Part of the Kling 3.0/o3 family, this 4K reference-to-video model generates native 4K (3840x2160) video from reference images and text prompts with no upscaling step. It excels at preserving identity, layout, and stylistic detail while adding cinematic motion, camera movement, and scene progression. Supports element and style references (combined limit of 7), optional start and end frame anchoring, multi-shot generation up to 15 seconds, and optional native synchronized audio in English and Chinese. Optimized for advertising, branded content, and production-grade scene work where 4K detail is required.
Ready to build with Kling O3 4K - Reference to Video?
Try Kling O3 4K - 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-o3-4k-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 4K - 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 |