MiniMax H3
New

Generate high-resolution AI videos from text, images, or references with stable motion, sound, and cinematic control.

Describe the video to generate, including motion, camera, and audio direction.

Token cost updates automatically by duration and resolution. 2K and 4K upscale a 768P render and cost more per second.

5

Choose any whole-second duration from 5 to 15 seconds.

Choose the output frame for Text-to-Video. Image-to-Video follows the uploaded image automatically.

Sign in to spend tokens

Prompt is required

Your generated video will appear here