MINIMAX H3

One model. Three ways to direct motion.

Minimax Motion gives H3 a focused workspace for text-to-video, frame-guided animation, and reference-led production.

Create an H3 video arrow_forward

Choose the input that fits the shot

movie_edit

TEXT · START FRAME · END FRAME

Standard mode

Start with text alone, or attach a first frame and optional end frame. Minimax Motion selects the matching H3 generation path automatically.

hub

IMAGES · VIDEO · AUDIO

References mode

Use images and short video or audio references to communicate identity, action, camera language, timing, and sound.

5s · 10s · 15s

Output options

Generate 5, 10, or 15-second clips at 768p or 2K. Text generations support concrete aspect ratios; frame-led generations follow the source framing.

768p

Standard

2K

High detail

9 IMAGES · 3 VIDEOS · 3 AUDIO

Reference limits

Use up to 9 images, 3 videos, and 3 audio files. Reference videos and audio may total up to 15 seconds per media type. The creator validates formats, dimensions, duration, and file size before generation.

JPG / PNG / WebP / HEICMP4 / MOVWAV / MP3
MiniMax H3 is developed by MiniMax. Minimax Motion is an independent service and is not affiliated with or endorsed by MiniMax.
MiniMax H3 AI Video Generator | Minimax Motion