Try Kling O3 Edit - Video to Video in the Workbench
Run this model interactively, tune parameters, and compare outputs.
kling-video-o3-pro-video-to-video-edit
Kling Video 3.0 Video to Video is an all-in-one generative video model that unifies high-quality video creation and editing into a single workflow, letting you input text, images, or reference characters to produce cinematic, multi-shot sequences with coherent motion, physics-informed camera behavior, and synchronized audio.
Example request
- Sync
- Async
- Async with SSE
This blocks until the video is ready (typically 5-15 minutes). Prefer Async or Async with SSE for anything beyond quick experimentation.See the video generation reference for more details.
- Minimal
- Basic parameters
- All parameters
Fetch model details
The models endpoint returns the full model object, including itsjson_request_schema.
Request parameters
Required parameters
| Field | Type | Default | Description |
|---|---|---|---|
prompt | string | "A red bird flies in and lands in-between the two birds on the wire. They fight for positioning before settling in their spots." | Text description of what you want to generate, or the instruction on how to edit the given image. |
input_video | string | "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/birds_on_telephone_wire.mp4" | Video to use as reference. Format: uri. |
Optional parameters
| Field | Type | Default | Description |
|---|---|---|---|
input_image | array<string> | [] | Optional reference images. Use @Image1, @Image2, etc. in the prompt to refer to them. |
elements | array<object> | — | Optional element references. Use @Element1, @Element2, etc. in the prompt to refer to them. |
keep_audio | boolean | false | Whether to keep the original audio from the video.. |