MiniMax H3 Max

Transform Blender renders and 3D previs into photorealistic video. H3 Max uses the source clip to guide scene layout, camera movement, and timing, with optional image references for appearance.

Input

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

Video *

Blender video, up to 15 seconds and 32 shots, at a public HTTPS URL.

Uploading a file needs an account. Create accountMP4, WebM · up to 100 MB

Scene Intent

Optional clarification of what your proxies represent or how they move, for example: 'The moving block represents a running person.' Camera, trajectories, timing and object count remain defined by the video.

Reference Images

Optional environment, subject, interior or detail references. When supplied, uses these images directly without visual planning or generating new images; Scene Intent is optional. Without references, automatically creates appearance references within your new-image limit. Camera and movement always come from the video.

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

Quality

Output quality. Duration is taken automatically from the video.

Additional settings

Maximum New References

Tips and requirements

Maximum NEW images to generate when no reference images are supplied. Ignored when reference images are supplied. Uses fewer when enough views are covered. Uncovered shots stay in the video.

Starting price$0.0793 / 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.