Now on Runway
Kling O3
Kling's multi-modal video model, on Runway. Generate from text or images, guide motion with keyframes, and produce multi-shot sequences with audio at up to 4K.
How to use Kling O3 on Runway
Bring text, images or both
Start from a prompt, an image, or a combination — Kling O3 is multi-modal, so you can mix inputs to describe exactly what you want.
Guide the motion with keyframes
Place timed keyframe images along your video to steer composition and action at specific moments, instead of leaving the in-between to chance.
Generate up to 4K
Choose Standard, Pro or 4K output and generate multi-shot video with audio, ready to download and share.
What you can do with Kling O3
Keyframe-guided motion
Timed keyframes let you direct what happens at specific points in the clip — a control most video models don't offer.
Up to 4K output
Generate at Standard or Pro quality for iteration, then step up to 4K for delivery-ready footage.
Multi-shot with audio
Produce multi-shot sequences with generated audio in a single pass.
Direct your first Kling O3 video on Runway.
Try nowMore models on Runway
Runway gives you access to the world's leading video, image and audio models — Runway's own frontier models plus the best from Google, OpenAI, Kling, ByteDance and more — all in one workspace.
Kling 3.0
Video generation with native audio and speech, from text or images.
Explore the model
Veo 3.1
Google's cinematic video generation with native audio and speech.
Explore the model
Seedance 2.0
Multi-modal video generation with sound from text, images, video or audio.
Explore the model
Gemini Omni Flash
Google's newest video model — generate new clips or edit existing footage.
Explore the model
Try Kling O3 on Runway today.
Keyframe-directed, multi-modal video at up to 4K — in the same workspace as every other leading model.
Try now
