MiniMax H3

Video Models

generateanimatetext to videoimage to videostart frameend frameaudio

Overview

Generate 2K video with native stereo audio from a text prompt or from a first frame. Supports text-to-video and image-to-video, 5-15 seconds, with an optional end frame to control where the shot lands.

Accepts up to 2 image inputs: first frame and end frame.

First frame
End frame