Sample
Kuaishouvideo model
Kling O1
An image-driven Kling tier. It has no text-to-video mode at all: a source image is required, and the model animates it with native audio at a flat per-second rate whether or not audio is generated.
280 cr/secReference image
Excels at
- Purpose-built for animating an existing still image
- Native audio at no extra per-second cost
- Clip lengths from 5 to 10 seconds
Signal
Speed
Realism
Creativity
Control
Use when
- Bringing a generated or photographed still into motion
- Product or character shots where the first frame is already art-directed
Avoid when
- Text-to-video — this model cannot generate without a source image
- Clips beyond 10 seconds (use Kling o3 Pro or v3)
Prompt used for this sample
A paper boat drifting down a rain-slicked city street at dusk, gentle camera follow, cinematic
Also available
Kling v3 — Supports both text-to-video and image-to-video.