---
name: musicvideo-shots
description: "Write and run the parts of an AI music video on MiniMax H3 Max reference-to-video — Image 1 the character's 5-angle face board, Image 2 the look sheet, then 4 replaced film frames; 8 shots a part (2 per frame: two angles), cuts on beats with a different H01 transition each, and for every shot camera, light, action, acting, head movement, emotion and constant lip-sync; 16:9, 768P, enhance disabled. Part of the musicvideo reference set."
---

These creative references describe source experiments with external tools. Use your own supported account and tools; this download installs no automation. Settings and timings are experimental observations, not current FlashBoards availability. Use only media and voices you have permission to use.

# musicvideo-shots · the prompt structure for every part

> **Alternative external route:** Seedance 2.5 reference-to-video (`bytedance/seedance-2.5/reference-to-video`, references as @Image1… / @Audio1…, 4–30 s, native sound) was preferred in the source experiments. The measured side-by-side comparison was a product commercial, not every format; compare it with the H3 method below for your material.

**Write every prompt fresh for this track and story; the example prompts are for reading only.** References are the person's own `{face board}`, `{look sheet}` and the frames replaced for this story.

## Request

`minimax/h3-max/reference-to-video` · `duration` = part rounded up · `resolution: 768P` · `aspect_ratio: 16:9` · `prompt_expansion_mode: disabled` · `reference_image_urls`: [`{face board}`, `{look sheet}`, frame 1.4] · `reference_audio_urls`: [the part of `{track}`]. Generation took 21–30 s per part. Run all parts in parallel.

## Prompt structure (JSON)

- `output`: "A cinematic 16:9 music video told as a short film in three acts, part N of M ({act} and what happens). 8 shots with cuts and transitions on the beat at the given times, D seconds, then the video ends."
- `style`: cinematic and natural, moving camera, the real light of each place, natural skin and sweat, real acting; no text, no screens, **no phones**, no slow motion.
- `references`: Image 1 "only {character}'s face and hair, seen from five sides so they can turn their head freely; never on screen"; Image 2 "only their outfit [and prop]"; Image k "the place of shots 2j+1 and 2j+2: place, light, atmosphere and the people around; never its framing"; Audio 1 "the soundtrack… only {character} [raps/sings] the words".
- `character`: "never frozen: their head, eyes and face move all the time and their expression changes with every moment".
- `rules`: framing new every time; everyone around exactly like the images, no new crowds; each transition done in camera on the beat; no split screen.
- `shots[]`: `cut_at` (on beats from `beats.json`), `transition`, `camera`, `light`, `action`, `acting`, `head`, `performance` ("[raps/sings] every word in sync with Audio 1… nodding their head and shoulders on every beat"), `lyrics` (the words in that shot, from the Scribe word times).

Picture roles only — never describe the person's looks; the face board and look sheet carry them. If the person cast another of their characters, name who performs the words in Audio 1.

## Shots and transitions

- 2 shots per frame: A — close to the frame's idea; B — another angle (dolly-in, low tracking, crane, over the shoulder, circling, extreme close-up of eyes and lips, Dutch angle, push-in through the crowd).
- Within one place: match on action, arc, crash cut, jump cut, roll, match motion. Between places: whip, object portal [an opening in the set, e.g. a porthole, a furnace mouth], wipe, shape, frame portal (door), lap dissolve, flash cut, seamless (behind steam or a pillar), superimposition, smash cut. **No transition twice in a part.**
- Write light per shot from the real sources of each place [e.g. furnace orange, a torch's blue-white, red alarm, a green flooded room, moonlight] and acting as eyes, lips, breath, a gesture.

## What to expect

- Cuts land a little early (0.1–0.5 s); the edit trims each part to its length.
- Some transitions come out as plain cuts.
- With a frontal face as Image 1 the head freezes; the 5-angle board fixes it.

## Example run (reference only — never reuse its files, prompts, faces or frames for a person)

«The Welder» (demo character Mara Vale, *Titanic*, 7 parts): Image 2 was "only her outfit and torch"; Audio 1 "only Mara raps the words"; light per shot: furnace orange, the torch's blue-white, red alarm, green flooded saloon, moonlight; object portals: porthole, furnace mouth.