MiniMax H3

Omni-modal 2K video with native stereo sound

MiniMax H3, the successor of Hailuo, reads text, images, video and audio together and returns up to 15 seconds at up to 2K with native stereo sound. Strong at following instructions, motion transfer and editing.

• Up to 2K resolution, 5–15 s
• Native stereo audio
• First/last frame + image, video and audio references
• Great instruction following

Min. credits

80

Typical time

~190s

Max resolution

768p