Written scene briefs
turn an explicitly described action into a clip.
Video generation
Kling O3
Build a video scene directly from a written brief.
Loading model settings…
Your prompt, settings, and references stay together in a new Canvas.
01 / Meet the model
What can Kling O3 do?
Kling O3 is offered as a text-to-video model in WeGen. It suits a prompt-led workflow where the subject, environment, action, and camera direction are described in words. Native audio is optional, and the supported resolution range includes a larger output for detailed review.
02 / Choose it for
Where Kling O3 fits best
Audio choice
compare the visual sequence with or without generated sound.
Delivery sizing
choose a supported frame size for the intended use.
03 / Before you create
Kling O3 specifications
Model settings. Availability, input mode, and references can narrow the choices offered in Canvas.
- Inputs on this page
- Text prompt
- Aspect ratios
- 16:9 · 9:16 · 1:1
- Resolution
- 720p · 1080p · 4K
- Duration
- 3–15 seconds
- Audio
- Optional generated audio
- Default output
- 720p · 5s · 16:9
04 / A closer look
Questions about Kling O3
Can I upload a starting image to Kling O3 here?
No. The current WeGen integration is text-to-video and does not expose frame or visual-reference inputs for Kling O3. Choose a frame-capable model if an existing image must define the starting composition.
What can I use as input for Kling O3?
Text prompt. The input controls above show the options available for your selected mode.
Which formats does Kling O3 support?
16:9 · 9:16 · 1:1. 720p · 1080p · 4K.
How do I choose settings for Kling O3?
Start with the format you intend to publish, then choose the available output settings. Changing inputs can change the choices. Review the current Gem estimate before Generate; availability and cost can vary.