"Animate this still: [motion description]. The camera [holds steady / pushes in slowly]. Subject stays in frame."
Separate what MOVES from what the CAMERA does. H3 follows both when they are named apart.
MiniMax H3 — the step up from Hailuo 2.3 in the same family. Native 2K output and long-prompt following, with up to five reference images to carry a subject across shots. Clips run 4 to 15 seconds.
Video models start at Starter.

Made on FlowPix on Nov 17, 2026: the clip came back in 120 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."
Every part of the prompt is in the clip: the high leap, the breaking wave, the spray at her feet and the low sun, with sound.
Example prompts stay in English, which is what the models handle best.
"Animate this still: [motion description]. The camera [holds steady / pushes in slowly]. Subject stays in frame."
Separate what MOVES from what the CAMERA does. H3 follows both when they are named apart.
"Use the product in the reference images as the subject. [Scene and motion]."
Up to five references, and the first five cost nothing — this is the model to reach for when a subject has to survive across shots.
"[Scene]. — then set duration to 8-10s for a full beat rather than a loop."
Several models here stop at 5 to 8 seconds. H3 takes any length from 4 to 15, which is long enough for a shot to actually resolve.
Same family, different tier. H3 outputs native 2K where Hailuo 2.3 tops out at 1080p, takes any length from 4 to 15 seconds where Hailuo 2.3 takes 6 or 10, and takes up to five reference images. Hailuo 2.3 is the value pick; H3 is the one to use when the prompt is long or the subject has to stay consistent.
The provider builds a 4-second clip regardless of what you ask for below that, so a shorter request would pay for four seconds and receive one. The floor is enforced on our side instead.
When your request plays to MiniMax H3'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.