"From the first frame to the last frame: [what happens]. Camera [move]."
A start and an end frame pin both ends of the shot.
Kling 2.6 — Kuaishou’s model with strong motion adherence, in 5 or 10 second clips. It takes a text prompt, a start frame, or a start and an end frame. It makes no sound; for a Kling clip with audio, use Kling 3.0.
Video models start at Starter.

Made on FlowPix on Nov 17, 2026: the clip came back in 297 s.
"A dancer in a flowing pale dress leaps across wet sand at sunset as a wave breaks behind her; the camera tracks sideways at her speed; spray catches the low sun. Text to video, no starting image. The dancer is an invented person."
Spray rises behind the dancer as she moves, but the sky is grey daylight rather than a sunset, and the call took the longest of our clips: about five minutes.
Example prompts stay in English, which is what the models handle best.
"From the first frame to the last frame: [what happens]. Camera [move]."
A start and an end frame pin both ends of the shot.
Kling 3.0 is the newer model and can add native sound. Kling 2.6 is silent; choose it when you will add your own audio.
When your request plays to Kling 2.6's strengths. Name it in your message or pick it in the composer; FlowPix never switches models on its own, and uses its default video model when you choose none.
Yes. The model picker in any chat lets you pin per-turn or per-session. Set as default in /settings.