TRStart creating
Menu

MiniMax H3 Max

H3 Max Multi Angle turns a single image into a video with precise, keyframe-based control over the camera's orbit, elevation, and distance in 3D space

Input

Fields marked * are required. Review the price before generating.

Text prompt for video generation. When omitted or blank, defaults to preserving the frozen reference scene while only the camera moves.

Video length in seconds. The output can run up to about 0.7 s longer than requested.

The native generation resolution, or 1080P latent refinement from a native 768P source.

Tips and requirements

How much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'balanced' returns in about a second. 'quality' spends up to ~30s on a richer prompt.

URL of the image to use as the first frame.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Additional settings

Random seed. A random seed is selected when omitted.

Tips and requirements

Ordered camera keyframes. The first pose is held before its time and the final pose is held for the remainder of the video. Signed full turns are preserved, with at most 32 turns of total azimuth travel.

Tips and requirements

A fixed free-camera move. Truck, pedestal, and dolly slide the camera; pan, tilt, and roll turn it in place. The path is not editable. When this is set, camera_trajectory is ignored. Each move is one training-scale step: one near-depth unit, 30 degrees of pan, or 20 degrees of tilt or roll.

Starting price$0.08 / second

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use MiniMax H3 Max

Getting started

Choose the mode for the material you already have. Start with text for a new scene, image-to-video for an opening photo, or a video-editing mode for an existing clip. The default endpoint on this page creates video from text; the other modes have their own model IDs.

Example prompt

A cyclist rides along a quiet riverside path in warm morning light. The camera follows from the side at a steady distance. Keep the rider and bicycle consistent in one continuous shot.

Review your result

Watch the whole clip and listen to the soundtrack. Check the bicycle wheels, body movement, background continuity and any requested speech. Keep the original input and selected settings when comparing another mode.

Inputs and settings

Describe the subject, one main action and camera movement in prompt. Choose duration, resolution and aspect_ratio from the current schema before requesting a quote.

prompt_expansion_mode controls whether the prompt is rewritten. When comparing your own instructions, keep the same expansion setting and record any expanded prompt returned with the result.

An optional target_audio_url can supply a soundtrack. Review the supported file constraints and video duration first; listen for trimming, silence or a mismatch with the visual action.

We use analytics cookies. Privacy policy