--- name: animate-video-ref description: Make the person's character do the motion of a clip with the clip's camera — H3 Max Reference to Video with the sheet as Image 1 and a short silent clip as Video 1, conformed to exactly 16:9 or 9:16, 24 fps and 2, 5, 10 or 15 s; for Turbo, the motion in words. --- # Motion and camera from a clip 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:""})` 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. {character sheet} as Image 1 + a short clip (sound removed) as Video 1 → {character} doing the clip's motion with the clip's camera. > **Quality route:** Seedance 2.5 (`seedance-2-5`) does this job much better; quote both. On the cheap Turbo route, describe the motion in words instead of passing a clip. ## Steps 1. **The clip**: one of the person's own video results (`generationId`) or a joined/trimmed result (`videoFinishingTaskId`), cut to the moves they need. 2. **Conform it**: `conform_video` with `fps: 24`, `aspect: "16:9"` (or `"9:16"`), `removeAudio: true`, `startSeconds`/`endSeconds` for exactly 2, 5, 10 or 15 s. The video tariff takes only those shapes and lengths, and an H3 result (1344 × 768) is not exactly 16:9 until it is cropped. A clip from elsewhere must already have that shape to go in as a public HTTPS URL (`referenceVideoUrls`). 3. **Request**: `generate_video` with `minimax-h3-max-reference-to-video`, `referenceGenerationIds: []`, `referenceVideoGenerationIds: []`, `duration` at least as long as the clip, `resolution: "480P"` (768P for the final), `aspectRatio` of the output. Quote first: a reference video is billed by its frames and costs more than it looks. 4. **Prompt** — one job per reference, blind, the action in words: ``` Image 1 is only the look of {character}: exactly their face, hair and outfit from Image 1, nothing added. Image 1 never appears on screen. Video 1 is the motion and camera reference only: copy its {motion} - every {move}, {move}, {move}, the timing - and its camera, {the clip's camera: framing, angle, movement}. Live-action film scene, one continuous shot: {character}, exactly as in Image 1, {action} in {place}, exactly like the person in Video 1. Exactly one person is in the frame: {character}. Sound: {sound}. ``` 5. **Compare** with the clip: `describe_media` on both with the same question about the moves and the camera. ## What transfers - Every step, the arm swings, the kicks, the timing; the camera — framing, angle, a still or moving camera. - Not the performer's face, hair, make-up or costume — the character keeps their own outfit from Image 1. - H3 may add speech to a silent motion shot: write "no dialogue, no speech" and check with `transcribe_media`; speech that still comes back → `conform_video` with `removeAudio: true` (free), then `replace_video_audio` with the intended sound. ## Never - Expect the clip to dress or cast the character — the look comes only from Image 1. - A long clip "just in case" — every second of reference video is billed. ## 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-video-ref.md) - Updated from the owner's skill sources of 2026-10-11. Read: `animate`, `character-sheet`, `animate-multi-image`. Source experiments and demo materials are historical; use the person's own approved media.