SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsseedance-storyboard

seedance-storyboard

General & other

View repository

Updated 10-15 17:32

About this skill

seedance-storyboard

Plot → multi-shot storyboard. Seedance internally decouples time and space,The ideal form for complex video is a timeline-based storyboard。

When not to use this skill

  • Single shot, single action → use seedance-prompter
  • 5/10/15 second compact short film (HappyHorse's main battlefield) → use happyhorse-prompter
  • Want to make a looping video → single shot + loop-ready motion with seamless start and end frames

Core Rules

See methodology/03-分镜时序.md。

  1. Use 镜头1、镜头2、镜头3 and other markers,in the order events occurorganize (primary first, secondary after)
  2. Do not force a duration limit on each segment(a notation like "00-03s" is unstable; let the model generate the rhythm naturally)
  3. Seedance is at most 15 seconds, sokeep the number of shots to 3-5most stable
  4. Organize each shot by 4 dimensions:
    • Camera movement or shot transition method(e.g., "wide shot slowly pushing in", "fixed camera position", "cut to...")
    • Subject action and expression(key actions and expression changes of the core character/object)
    • Position or spatial change(the scene, position, or spatial relationship the subject is in)
    • Audio information(sound effects, voice, or background music)

Workflow

Step 1: Parse the plot

Split the user's plot into 3-5 key beats. Each beat corresponds to one shot. Ask yourself:

  • What is the most critical image at this moment?
  • What action/expression is the emotional anchor at this moment?
  • How do adjacent shots connect (action inertia / scene cut / time jump)?

Step 2: Determine asset roles

If the user mentions using reference images/videos, clarify the "functional role" of each asset:

Role Purpose
Character anchoring Lock character appearance (recommended: headshot + full-body shot)
Scene tone-setting Lock environment and style
Camera movement reference Lock camera language and action rhythm
Rhythm and atmosphere Use audio to control emotion and timbre

Recommended configuration: 4-5 assets,do not use the maximum(too many will cause style conflicts).

Step 3: Assemble with the template

[素材分配 + 主体定义]，参考 @视频X 的运镜方式（如有）。

镜头 1：[运镜] + [主体@素材N 的动作与表情] + [位置/空间] + [音频]。
镜头 2：[运镜切换] + [主体@素材N 的动作变化] + [位置变化] + [音频]。
镜头 3：[运镜] + [主体动作] + [位置] + [音频]。

[整体约束：风格/色调/质量/稳定性]

Step 4: Check

  • For each shot,specify only 1 type of camera movement(do not push + pan at the same time)
  • Multi-subject scenes: use astable labelfor each character ("police officer"/"thief", to avoid referential confusion)
  • When subjects are involved,make references explicit("@图片N" or "<主体N>"), do not omit
  • Actions should be specific to body parts (slowly raising a hand, pushing hard against the ground), avoiding abstract verbs like "running" or "fighting"
  • Concretize and externalize emotions (refer to Emotion Externalization Table）

Step 5: Output Format

## 分镜脚本

\`\`\`
[完整分镜提示词]
\`\`\`

**镜头数**：N 个 · **推荐时长**：10-15 秒 · **比例**：[X:Y]

**镜头节拍分析**：
- 镜头 1（建立）：[简述]
- 镜头 2（发展）：[简述]
- 镜头 3（结尾）：[简述]

**素材建议**：[告诉用户准备哪些参考素材]

Practical Example

User Input: "The female lead breaks down after receiving bad news at the hospital"

Beat Breakdown：

  1. Calm before answering the phone (setup)
  2. The moment of freezing upon receiving the news (turning point)
  3. Breakdown when alone in private (release)

Output：

将@图片1的中年女性定义为主角，故事场景设定在@图片2的医院走廊。整体运镜参考@视频1
的中景跟拍。

镜头 1：医院走廊白炽灯下，主角@图片1 靠在墙边低头看手机，肩膀放松，嘴角带着浅
        浅的微笑回复信息。中景平稳跟拍，从侧面缓慢推近。窗外傍晚柔光，画面
        色调温暖。<远处护士站的低语声和脚步回声>。

镜头 2：手机响起，她抬手接听，镜头切到面部特写。瞳孔瞬间放大，下颌线绷紧，呼吸
        屏住三秒。她的手指无意识地攥紧手机壳。固定机位，焦点锁定在眼神变化上。
        背景虚化，色调变冷。<电话听筒里隐约的机械嗓音 + 心跳声渐强>。

镜头 3：她快步走进走廊尽头的洗手间，背靠门缓慢滑坐到地上，双手抱住膝盖，肩膀
        开始无声颤抖。镜头从上往下缓慢拉远，最后定格在她蜷缩成一团的全景。
        荧光灯白光与瓷砖冷调。【背景音】只剩水龙头滴水声和压抑的抽泣。

全程画面高清电影纪实风，色调由暖转冷，光影柔和；人物面部稳定不变形，动作自然
流畅，无卡顿无闪烁；不要生成水印、Logo、字幕。

Number of shots: 3 · Recommended duration: 12-15 seconds · Aspect ratio：16:9

Shot Beat Analysis：

  • Shot 1 (setup): warm, relaxed, creating contrast as groundwork
  • Shot 2 (turning point): fixed camera position + facial close-up + sudden sound effect change, locking the emotion in the pupil changes
  • Shot 3 (release): pull back the camera + curled-up posture + dripping water sound, letting sadness "be seen" rather than be told

Material Suggestions: 1 headshot of the female lead + 1 full-body photo of the female lead (maintain consistent ID) + 1 hospital corridor scene image + 1 medium shot tracking reference video. 4 materials in total, do not add more.

Reference Resources