Describe it. MiniMax H3 shoots it.

Write a scene and MiniMax H3 generates it as video — motion, camera and sound composed together in one pass. Start from a sentence, bring a photo to life, or feed it reference images to steer the look. Vertical clips, ready to post.
Try MiniMax H3 →

50 credits per video.

✍️ Any scene you can write 🎭 Multiple reference images 🎞️ First & last frame control 🔊 Native audio in the same pass

Three ways to start

From nothing, from a photo, or from your own material.

Text to Video

Start from a sentence

No upload needed. Describe the scene, the camera move and the sound you want, and H3 composes all three together.

Image to Video

Animate a photo

Bring a still image to life. Add a second image and it becomes the closing frame, so you control where the shot begins and where it lands.

Reference to Video

Give each image a job

Feed in several references and say what each one is for: this one for the talent, this one for the product, this one for the mood. They all land in the same shot.

Why creators picked it up

It stopped being a slot machine and started taking direction.

✍️

Anything you can write

The place, the action, the mood, the sound. H3 reads all of it as one instruction and composes the shot around it, so the range of what you can make is the range of what you can describe.

🎬

Direction, not dice

Write the clip as beats — what the camera does at the start, what it lands on by the end — instead of re-rolling a one-line prompt and hoping something usable falls out.

🎭

Your own material

Drop in reference images and tell the model what each is for — your face, your product, your street — and they carry into the scene you wrote.

🔊

Ready to post

Vertical, and the sound is generated with the picture rather than added afterwards — so a clip comes out finished instead of silent and waiting on an edit.

Write your first scene

A sentence is enough to start. Add a photo or reference images when you want more control.

Try MiniMax H3 →

50 credits per video.