---
name: animate-prompt-enhance
description: Choose H3 prompt expansion — disabled for any scripted scene, balanced or quality for a loose idea the model should pace, and read the expandedPrompt that comes back, because the video follows the rewrite, not your words.
---
# Prompt expansion — disabled, balanced or quality

FlashBoards user skill, version 1.2.3 (2026-10-13).

On the board, read these guides with `list_skills` and `get_skill` when the assistant exposes them; otherwise use the hosted index through an available read-only retrieval tool. Use that runtime’s actual model discovery, current page context and guarded board actions for execution. Keep native readiness, approval and cost gates; do not claim a guide was read when retrieval is unavailable.

Read related guides with `get_skill({skillId:"<id>"})` or the [hosted index](https://pub-78da82d51ed14147ac554d38094b0c0b.r2.dev/user-skills/1.2.3/index.html). Reading a guide does not start or authorize a paid generation.

Read `animate` for the shared rules. `promptExpansion` tells H3 whether to rewrite the prompt before filming: **disabled** films the prompt as written, **balanced** rewrites it in about a second, **quality** spends up to about 30 s on a richer prompt. The rewrite the model actually used comes back as `expandedPrompt` in the result of `generate_video` / `get_generation`.

## Which models take which modes

| Model | Modes | Default |
|---|---|---|
| `minimax-h3-max-turbo` | disabled, balanced, quality | disabled |
| `minimax-h3-max` (image-to-video) | balanced, quality | balanced |
| `minimax-h3-max-reference-to-video` | always disabled | disabled |

## Choose

| Priority | Mode | When |
|---|---|---|
| Scripted | **disabled** | any JSON scene with shots, `cut_at`, "Image N is shot 3" |
| One-line idea | **balanced** | the model should pace the action and add camera and sound; read `expandedPrompt` — that is what gets filmed |
| Slow idea | **quality** | the same with more detail, when you can wait and retry; the strictest about references |

## Measured A/B (5 s, 480P, the same three images and two sentences)

| | Disabled | Balanced | Quality |
|---|---|---|---|
| Prompt the model got | 58 words, as written | 350 words | 517 words |
| Shots | one | **two — a hard cut at exactly 3.0 s** | one |
| The action | only starting at the end | done | done |
| Invented in the text | — | a scar moved to another cheek | a new prop detail, a synth drone |

- **Balanced planned "[Shot 2] At 00:03.000 …" and the video cut at 3.0 s** — the model follows the rewrite, not your words.
- Both rewrites fixed the pacing (a timestamp for each beat), and both got details wrong.
- Quality checks references harder: it refused a reference set that disabled and balanced accepted.

## Steps

1. A scripted scene → `promptExpansion: "disabled"` on Turbo (H3 Max Reference to Video is always disabled).
2. A loose idea → balanced; open `expandedPrompt` and check shots, cuts and the character's details before judging the video — the rewrite describes the person's character in its own words.
3. A refusal only on quality → retry on balanced or disabled.

## Never

- Balanced or quality on a JSON scene — the rewrite replaces your structure with its own.
- Trust a surprise cut without reading `expandedPrompt` (and `detect_video_cuts`).

## Execute through MCP or on the board

Use the person's FlashBoards account; never ask for a personal provider key or run the source's local scripts. Discover `get_account`, `list_generation_models` and the tools of this client first: a published guide does not prove a feature is deployed.

**Headless, no open board.** Quote with `estimate_generation_cost` (skill models: `estimate_skill_model`), then run `generate_image`, `generate_video`, `generate_audio` or `run_skill_model` with one stable `generationAttemptId` per logical attempt. Pass `maxCostUsd` only when the current operation and selected model support it; otherwise use the quoted cost and the person's explicit approval with the supported controls. Never silently ignore an unsupported spending cap; make one `get_generation` check after `retryAfterSeconds`. Pass the person's own results by `generationId`: images in `referenceGenerationIds`, `firstFrameUrl` and `endFrameUrl`, audio in `referenceAudioUrls` or `targetAudioUrl`, videos in `referenceVideoGenerationIds`. They are read on the server; signed result links do not work as public URLs. Every `generationId` a tool returns stays valid: a later read of the same result gives a different string, and both work. Film frames and gallery pictures go in by `previewHandle`: `referencePreviewHandles` of the generation tools, a `{previewHandle}` source of `arrange_images`, `crop_image` and `pad_image`, and `describe_media`. New files come from `show_media_upload_picker` as receipts. The person's character comes in as its sheet, by `generationId` or as an upload; there is no search by name. If the person names a character without the sheet, ask for it or make one with `character-sheet`; do not scan recent results for it. Free server steps: `trim_video`, `concat_videos`, `conform_video`, `replace_video_audio`, `extract_video_frame`, `extract_video_audio`, `detect_video_cuts`, `crop_image`, `pad_image`, `arrange_images`, `cut_audio_span`, `concat_audio_tracks`, `mix_audio_tracks`, `fit_audio_duration`, `add_audio_reverb`. Check every result with `describe_media` (a question about an image; `model`, `mode` and `sourceRange` only for a video) and `transcribe_media` for speech. Both checks are paid: `describe_media` costs a fraction of a cent for an image and about 2–4 ¢ for a short video (more for a long one), `transcribe_media` under 1 ¢ a minute — count the checks you plan in the price you name before the first paid step. `describe_media` is not reliable about sound: it misses effects mixed under music and can hear voices or instruments that are not there. Check speech with `transcribe_media` and ask the person to listen for effects and music. Never repay an uncertain submission; reuse an attempt ID only for the identical request. Make each new `requestId` or `generationAttemptId` unique, for example the task, the date and a short random suffix: an ID used before, even in another chat, replays that earlier request or answers `REQUEST_ID_CONFLICT`.

**On the board.** Inspect with `list_board_sessions` and `get_board_snapshot` and carry the same `sessionId` and a fresh `activeBoardId` as `expectedBoardId`. Native cards: `execute_board_action` (`listNativeModels`, `setModel`), `prepare_board_generation` with ordered board items or owned outputs, then one `generate_on_board` within the authorized budget. Board media tools: `list_media_tools` → `start_media_tool` → `get_media_tool_run`. Put headless results on a board with `add_media_to_board`.

Keep mandatory safety settings and the live limits of each model. Prices, timings, endpoints and "free retry" claims in the sources are historical, not FlashBoards contracts. If a step this guide needs is not available or is refused (a tool error, `audio_not_configured`, a missing model or input), keep the finished assets, tell the person which step is blocked and why, and ask how to go on. A single generation that ends `failed` is not a blocked step: submit it once more with a new `generationAttemptId` (reworded if it may have hit the content checker), and stop to ask only if it fails again. A failed attempt is not always refunded, so the retry may be paid again and `maxCostUsd` caps each request on its own: count both against the budget the person approved. Never swap in another route on your own: no image model redrawing a layout or a frame, no `describe_media` in place of the frames it should check, no clip generated only to take its sound, no picture drawn where the guide takes a film frame.

## Source and related guides

- [Original Learn guide](https://flashboards-h01.vercel.app/learn/acting/animate-ai-character/skills/animate-prompt-enhance.md)
- Updated from the owner's skill sources of 2026-10-11.

Read: `animate`, `animate-multi-image`. Source experiments and demo materials are historical; use the person's own approved media.