A quiet tracking shot
A paper boat drifts across a quiet pond in soft morning light. Track slowly at water level. One continuous shot, no text.
Have a scene in mind, or a picture you want to move? Choose the starting point, describe one action and check the available video models. Build a short clip around a clear idea.
The selected preset guides the new scene. The example and your render can differ in timing, sound and appearance.
A paper boat drifts across a quiet pond in soft morning light. Track slowly at water level. One continuous shot, no text.
A ceramic cup sits on a wooden table beside a window. A thin ribbon of steam rises. Slow push-in, natural light, no added text.
These source-gallery examples illustrate different visual possibilities. They were not generated by this site and do not establish which model created them.
Reference media from the source site shows the creative direction. It is not a result generated by this service; your output may differ.
A short AI video is easier to direct when it has one main subject and one visible action. Describe what changes during the shot, then add a camera instruction only if it helps. A text prompt creates the scene; a photo anchors the starting appearance.
Subject: name what the viewer should pay attention to.
Action: describe a visible movement rather than an abstract mood.
Camera: choose a steady frame, a slow track or a gentle push-in.
Make the settings match the shot, then inspect the result before expanding the idea.
Choose Text for a new composition, or Image for a visual starting point.
Review the model name, duration, resolution, aspect ratio and quote. Different models offer different settings.
Inspect the subject, movement and audio. Save the result, or revise one detail for a new request.
A short clip cannot reliably carry several locations, a chase and a final reveal.
Ask for a small change if preserving the original photo’s details matters.
Hold the brief steady when changing a model or output setting so the difference is meaningful.
MiniMax H3 starts at 5 seconds and 768P for this scene. Change duration or quality to update the general-credit quote, and review it before submitting.
MiniMax H3 · 480P / 768P / 1080P: 4–30 whole seconds · 2K: 4–15 seconds.
| Resolution | Duration | credits |
|---|---|---|
| 480P | 5s | 6 |
| 768P | 5s | 8 |
| 1080P | 5s | 13 |
| 2K | 5s | 14 |
The quote updates with duration and quality. For 16–30 seconds, the whole video fee doubles, including any video-reference reserve. Up to five photos and audio add no extra fee. Standard queue is used.
Trial and video-pack units cover only five-second outputs at their matching quality, without a video reference. Other settings use general credits.
1 video · 5s · 768P
Try one freeUse general credits for other durations or qualities and after your matching five-second allowance is used. Confirmed generation failures restore the allowance or credits.
View credit plansYes. Choose Text, describe a scene and submit with a model that supports that workflow. No photo is required in text mode.
This scene uses MiniMax H3 through Metaso. Happy Wan is the page name. The generator shows the selected duration, quality and credit quote before submission.
Yes. Switch to Image, upload a permitted reference and describe the desired movement. The model may change details, so inspect the result.
No. Supported settings vary by model and current configuration. The editor shows the available choices; exact content, sound and visual fidelity can vary.
The editor shows the HiHD credit quote for your selected model and output settings before you generate. The Pricing page lists the available plans and credit packs.
Start with a sentence or a picture.
Start creating