muapi-storyboard

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Storyboard Generator

故事板生成器

Generate N keyframes for a short story or scene sequence (image only, no video).
Estimated credits: ~24 per run.
为短篇故事或场景序列生成N个关键帧(仅生成图片,不生成视频)。
预估积分消耗: 每次运行约24积分。

Inputs

输入参数

NameTypeRequiredDefaultDescription
premise
textyesOne-line story premise (e.g. "lonely robot finds a tiny mechanical bird friend").
scenes
intno6Number of keyframes to produce.
style
textnocinematic, photoreal, soft lighting, 16:9Visual style tags applied to every keyframe.
名称类型是否必填默认值描述
premise
文本一行式故事前提(例如:“孤独的机器人找到了一个小小的机械鸟朋友”)。
scenes
整数6要生成的关键帧数量。
style
文本cinematic, photoreal, soft lighting, 16:9应用于每个关键帧的视觉风格标签。

Steps

步骤

Use the plan to dispatch all N keyframes in a single parallel layer.
  1. Decompose
    premise
    into
    {{scenes}}
    story beats with a clear arc: setup → inciting moment → escalation → climax → resolution.
    • Each beat gets a one-paragraph visual description.
    • Maintain character / object continuity across beats (same character appearance, same world).
  2. For each beat, create a
    muapi image generate
    node (model=nano-banana-2, aspect_ratio=16:9):
    • Prompt =
      "<beat description>. {{style}}"
      .
    • Tier: balanced (these are reference keyframes, not finals).
    • Aspect ratio: 16:9.
  3. Run the plan in parallel (no
    depends_on
    between keyframes).
  4. Return the asset ids in beat order with a one-line caption per scene.
使用规划在单个并行层中调度所有N个关键帧。
  1. premise
    分解为
    {{scenes}}
    个具有清晰叙事弧的故事节拍: 铺垫 → 触发事件 → 升级 → 高潮 → 结局。
    • 每个节拍对应一段视觉描述。
    • 在各个节拍间保持角色/物体的连贯性(相同的角色外观、相同的世界设定)。
  2. 为每个节拍创建一个
    muapi image generate
    节点(model=nano-banana-2, aspect_ratio=16:9):
    • 提示词 =
      "<beat description>. {{style}}"
    • 层级:balanced(这些是参考关键帧,而非最终成品)。
    • 宽高比:16:9。
  3. 并行执行规划(关键帧之间无
    depends_on
    依赖)。
  4. 按节拍顺序返回资产ID,并为每个场景添加一行说明文字。

Notes

注意事项

  • Don't animate, upscale, or add audio — this skill is keyframes only. If the user wants video, suggest the
    music-video
    skill afterward.
  • For consistency, repeat character description verbatim in every prompt ("a small rusty humanoid robot with…") rather than relying on the model to remember.
  • 不要进行动画制作、放大或添加音频——本技能仅生成关键帧。如果用户需要视频,后续可推荐
    music-video
    技能。
  • 为保证一致性,在每个提示词中逐字重复角色描述(例如:“一个小型生锈类人机器人,拥有……”),而非依赖模型记忆。

Trigger Keywords

触发关键词

storyboard
,
keyframes
,
scene sequence
,
story panels

storyboard
,
keyframes
,
scene sequence
,
story panels

Notes for the Executing Agent

执行Agent注意事项

  • This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call
    muapi
    CLI commands. Use
    muapi auth configure
    first if
    MUAPI_API_KEY
    is unset.
  • For model IDs without a CLI alias yet, fall back to the raw endpoint via
    curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'
    and poll with
    muapi predict wait <request_id>
    .
  • Substitute
    {{input_name}}
    placeholders with the user's actual inputs before issuing each call.
  • 本流程由LLM编排:阅读每个阶段,向用户收集缺失的输入,然后调用
    muapi
    CLI命令。如果
    MUAPI_API_KEY
    未设置,先使用
    muapi auth configure
    进行配置。
  • 对于尚未有CLI别名的模型ID,可通过原始端点回退,使用
    curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'
    ,并通过
    muapi predict wait <request_id>
    进行轮询。
  • 在发出每个调用前,将
    {{input_name}}
    占位符替换为用户的实际输入。