MiniMax H3 Text to Video

Design a complete MiniMax H3 shot from text alone. Stay prompt-only and never submit a generation job.

Confirm this workflow

Use this skill only when no uploaded media is meant to control the result. If an image is an exact first frame, use ../minimax-h3-frame-to-video/SKILL.md. If any asset supplies identity, style, motion, voice, or editing rhythm, use ../minimax-h3-reference-to-video/SKILL.md.

Recommend a 5–15 second clip, 768P for iteration or 2K for a final pass when the active workflow and hardware support it, and a fixed aspect ratio such as 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16. Treat these as starting settings and let the executor validate the installed workflow.

Build the prompt

1. State duration, aspect ratio, format, and whether the clip is one continuous shot or a short sequence.
2. Describe the subject and environment with only details that matter on screen.
3. For more than one beat, allocate timecoded actions whose durations add up correctly.
4. Choose one principal camera behavior per beat.
5. Describe lighting, palette, texture, and production language.
6. Direct dialogue, ambience, effects, and music with timing when relevant.
7. Finish with a short list of concrete continuity and exclusion constraints.