Available now

MiniMax H3: video from references

By MiniMax

MiniMax H3 makes videos of 5 to 15 seconds from a written scene, a first or last frame, or up to 9 reference images, at sizes up to 4K.

Model ID
Maker
MiniMax

Input

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

Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on.

Example prompt. Edit it or write your own.

The duration of the video in seconds.

480P and 768P are native generation modes; 2K and 4K upscale a 768P base result.

The subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB · 0/9

Additional settings

Random seed. A random seed is selected when omitted.

Uploading a file needs an account. Create account

MP3, WAV · up to 50 MB

Price$1.03 / run

You sign up first. Your settings are kept.

About this model

Overview

MiniMax H3 renders natively at 480P or 768P; the 2K and 4K options upscale a 768P render. Clips run 5 to 15 seconds in six aspect ratios from 21:9 to 9:16. Before rendering it can rewrite your prompt; you choose how much effort that takes, or turn it off.

Start from text, from a first frame, a last frame or both, or from up to 9 reference images for a subject or a style, named in the prompt as Image 1, Image 2 and so on. You can also pin your own audio clip as the soundtrack.

What you can build

  • Ad and social clips in shapes from 21:9 to 9:16
  • A product photo used as the first frame and set in motion
  • Shots that land on a final frame you choose
  • Scenes that keep a character or a look from reference images
  • Clips timed to your own music or voice-over

Prompting tips

  • 2K and 4K are upscaled from a 768P render, so try ideas at 768P and pick the larger size for the final.
  • Turn prompt expansion off when the model must follow your exact words; pick quality for a one-line idea.
  • In the reference mode, name each image by its place in the list, for example "the jacket from Image 2".
  • Your own audio replaces the generated soundtrack, so set the clip length close to the audio length.

What to check

Watch for changing identities, disappearing objects and sound that misses the action.

Inputs

  • Prompt (required): Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on.
  • Duration (optional): The duration of the video in seconds. From 5 to 15.
  • Resolution (optional): The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result. Options: 480P, 768P, 2K, 4K.
  • Seed (optional): Random seed. A random seed is selected when omitted.
  • Prompt Expansion Mode (optional): How much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'fast' returns in about a second. 'balanced' picks per request. 'quality' spends up to ~30s on a richer prompt.
  • Aspect Ratio (optional): The aspect ratio of the generated video. Options: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
  • Reference Images (optional): URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files.
  • Target Audio (optional): Optional URL of an audio clip at least 2 seconds long (maximum 15 MB) to pin to the generated soundtrack. Cannot be combined with reference audio. Longer clips are trimmed to the generated video's length, keeping the beginning; shorter clips are padded with silence. The clip is resampled to 32 kHz stereo and replaces the output soundtrack without changing playback speed. Accepts an HTTP(S) URL or a base64 data URI.

Output and limits

  • Length: 5 seconds to 15 seconds.
  • Resolutions: 480P, 768P, 2K, 4K.
  • Aspect ratios: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to, default options: $1.03 / run