Kling O3 (Kling 3.0 Omni) reference-to-video casts up to 7 reference images, such as a person, an outfit or a place, together in one new shot. Clips run 3 to 15 seconds at 720p, 1080p or 4K, with optional native audio.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
sealed-letter-named-refs Three references, three jobs: <<<image_1>>> the man (coat, turtleneck, stubble), <<<image_2>>> the 1930s dining car (walnut paneling, brass lamps), <<<image_3>>> the wax-sealed letter. All three carried through into a shot none of the source photos showed on their own. The requested train and rain sound came back almost silent in the mix - describe ambience plainly and expect it to be a minor layer, not the loudest element.
- audio
- Output5s
sealed-letter-night-train Three references, three jobs: Image 1 the man (coat, turtleneck, stubble), Image 2 the 1930s dining car (walnut paneling, brass lamps), Image 3 the wax-sealed letter. All three carried through into a shot none of the source photos showed on their own. The requested train and rain sound came back almost silent in the mix - describe ambience plainly and expect it to be a minor layer, not the loudest element.
- audio
This example starts at $0.067 per output second. The Playground updates the estimate when you change the settings.