"From the first frame to the last frame: [what changes]. Smooth, continuous motion."
Give both frames to control exactly where the clip starts and ends.
PixVerse V6 — stylised video in four sizes, from 360p up to 1080p, and 1 to 15 seconds long. It animates a start frame, joins a start and an end frame, or fuses up to seven reference pictures into one clip, with sound on by default.
Video models start at Starter.

Made on FlowPix on Nov 17, 2026: the clip came back in 73 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."
The scene is daylight rather than a sunset, and the dancer's legs and dress lose their shape in the last seconds as she turns.
Example prompts stay in English, which is what the models handle best.
"From the first frame to the last frame: [what changes]. Smooth, continuous motion."
Give both frames to control exactly where the clip starts and ends.
"Combine the subjects of the reference pictures: [who or what] in [scene], [action]."
Up to seven references are fused into a single shot.
Yes, by default: each size has a version with native audio, and that is the one made unless you ask for a silent clip, which costs less.
When your request plays to PixVerse V6'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.