---
name: toon-turbo
description: "Generate a 15 s cartoon episode from one 3×3 storyboard on MiniMax H3 Max Turbo image-to-video with native voices and sound — the board as image_url only (480P, 15 s, enhance disabled, no end image, no target audio), the prompt that keeps the board off screen, nine shots with seconds, cartoon acting, the lines in quotes, voices described in words; trim the board flash. Generation took 2.5–6 s. Part of the toon 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.

# toon-turbo · one request, native sound

> **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.

Request: `minimax/h3-max-turbo/image-to-video` · `image_url` = the board · `duration: 15` · `resolution: 480P` · `prompt_expansion_mode: disabled`. **No `end_image_url`, no `target_audio_url`.**

Prompt (prose, the source example):
1. `A 15-second animated short, "{title}", in the style of {style}. Expressive, funny, heartfelt cartoon acting: big emotions on every face, squash and stretch, snappy comic timing. 16:9, nine shots with cuts at the given times.`
2. `The given first image is NOT a shot: it is the storyboard for this film, nine numbered frames in three rows of three on black. It never appears on screen; the film starts directly inside frame 1, and every shot looks exactly like its storyboard frame enlarged to the full screen … The screen is never split into a grid.`
3. Characters with **voices in words**: `MARA … a warm, low, playful voice. PIP … a tiny, high, squeaky cartoon voice, fast and excitable.`
4. Nine lines `Shot k (frame k, a–b s): {action with emotion}. {Who}: "{line}"` — about 1.7 s a shot.
5. `Sound: generated with the picture — the voices, {music and sounds of the style}, and cartoon foley for every action, all quieter than the voices. Each character speaks only their own lines, lips in sync. No subtitles, no text, no live action.`

What to expect (13 episodes): the board shows for 1–7 frames at the start (trim from the first cut + 1 frame) and never comes back; all lines spoken, roughly on time; sometimes an extra word or a sound that is not what was asked (a hiccup heard as a raspberry, a sneeze as a scream); a comic-book style may add a speech bubble despite "no text".