Skip to main content

MiniMax H3

Start with a scene or a still. Give it motion and sound.

Function

Choose an image-based function above to add images, or continue with a text prompt.

Describe what you want to create.
Runs on

MiniMax H35–15 s · 4K

Aspect ratio
Duration
Resolution
Prompt enhancement
Try a prompt:
Record Haul — Pick One
Record Haul — Pick One

Candid vertical phone video, 9:16. A young white British man, clearly an adult in his mid-twenties (around 24), stands waist-up facing the camera in a small sunlit independent record shop. Short dark-brown curly hair, clean-shaven, warm expressive brown eyes, natural skin texture. He wears a moss-green overshirt over a plain cream T-shirt. Soft natural daylight from a window off-camera left. Background: warm wooden shelves softly blurred, golden-hour shop tone — the look of a real candid phone shot. [Static shot] He holds three 12-inch vinyl record sleeves: in his left arm, two sleeves lightly fanned — one cobalt blue, one cream — resting against his lower chest. In his right hand, one vivid orange sleeve with a single bold abstract blue geometric shape; no text, no lettering, no recognisable album artwork on any sleeve. All sleeves remain flat, solid and distinct; his fingers grip them naturally. He starts with a small pleased smile and makes friendly, relaxed eye contact — the energy of sharing a good find with a friend. Then, smoothly and naturally, he brings the orange sleeve forward toward the camera with his right hand into the lower foreground, as if offering the viewer first pick. The sleeve grows naturally in perspective as it approaches. He stops it just below his chin so his full face stays visible throughout. He gives a brief playful eyebrow raise and a warm grin, then holds that moment. Throughout, there is a gentle, subtle phone-camera sway — the natural micro-movement of a handheld phone. No cuts, no dramatic camera moves, no slow motion, no beauty filter. No other people in the foreground. No text overlays, captions, logos or watermarks. Sound: soft cardboard sleeve rustle as the orange record slides forward, quiet shop room tone — ambient hum of a small record shop. No speech, no music, no background conversation.

MiniMax H3 · 5 s

Very quiet ambient audio accompanies this record-shop motion study.

How it works

Try it now
  1. 01

    Say what you want

    A sentence or two is enough.

  2. 02

    Use MiniMax H3

    Choose the settings that fit what you want to make.

  3. Record Haul — Pick One
    03

    Make it

    Start creating, then keep working with HowWorks.

Explore the possibilities

Record Haul — Pick One
Very quiet ambient audio accompanies this record-shop motion study.MiniMax H3

MiniMax H3 at a glance

Good at
Best at changing one thing and keeping the rest. Native audio. 5–15s, up to 4K.
Modes
Text to Video, Image to Video, First & Last Frame, Reference to Video
Length
5–15 s (presets 5, 10, 15 s)
Resolution
480p, 720p, 2K, 4K
Aspect ratios
16:9, 9:16, 1:1, 4:3, 3:4, 21:9
Image-led framing
May follow the input image; check the output frame
Sound
Always on
Reference images
Up to 9

About

For creators planning a scene for a landscape screen, a vertical feed or a square placement, MiniMax H3 offers several output formats and includes audio with the picture. Start from a written scene or animate an image. In Image to Video, the output follows the source image’s aspect, so prepare the composition before uploading. This page keeps H3 selected while you explore the shot and review its available settings.

Questions

Can MiniMax H3 start from text or an image?

Yes. Describe a scene for Text to Video, or add a start image and describe its movement for Image to Video.

Can I make both vertical and landscape clips?

Yes. Choose an available aspect ratio before framing the scene. Plan separate compositions when a subject needs to work in substantially different screen shapes.

Should I choose H3 or H3 Max for a larger output?

Compare their resolution options directly. Their catalogs differ, and the word Max does not by itself tell you the output size. Use the model whose available settings match your delivery requirement.

Can I turn off the generated audio?

H3’s current model configuration includes audio automatically. It does not use the Seedance audio on/off setting. Review the generated audio alongside the picture before using it.

What happens to my image’s aspect ratio?

In Image to Video, H3 follows the source image’s aspect. Prepare the image for the composition you want, then compare the opening and later frames with the original.