用 n8n 将文本提示自动转为多场景电影级视频

输入 Google Sheets 行数据 → GPT-4o 生成叙事与分镜 → Fal.AI Seedance 逐场景渲染 → 合并为带环境音的 MP4

给谁

内容创作者、短视频营销人员、教育工作者、有 n8n 基础的用户

你会得到

从一行表格数据自动生成多场景电影级视频（MP4），可自动上传 YouTube

你需要

n8n · fal-ai · google-sheets · youtube

步骤

1. 准备输入并触发工作流

   在 Google Sheets 创建包含以下列的表格：story（简短提示词）、number_of_scene（场景数）、duration（单片段时长）、aspect_ratio、resolution、model。在 n8n 中手动点击「Execute workflow」或设置 Sheet 更新触发。

2. 生成完整叙事

   AI Agent 节点调用 GPT-4o-mini，根据 story 字段生成沉浸式、有情绪弧的完整短视频叙事。输出为长文本故事，受 Structured Output Parser 约束为 {story: string} 格式。

   运行提示词 · 来源原文。AI Agent 节点 'Generate Full Narrative from Prompt' 的 text 参数

   复制提示词

   =Instructions:
   
   Create a captivating, vivid, and detailed short video story based on the idea provided below. The story should feel immersive, emotional, and cinematic — suitable for visual storytelling.
   Please ensure the following:
   
   Include a rich, visually descriptive setting (lighting, weather, architecture, colors).
   
   Describe the main characters clearly: their appearance, mood, clothing, and motivations.
   
   Build a sense of mood, tension, or emotional arc.
   
   Keep the tone aligned with the theme of the original idea.
   
   Format your output as long-form narrative text.
   
   Idea: {{ $json.story }}

3. 拆分叙事为场景并验证数量

   第二个 AI Agent 节点（GPT-4o-mini）将叙事拆分为恰好 number_of_scene 个场景，输出受 Structured Output Parser 约束为 {scenes: string[]}。随后 Code 节点验证 sceneCount 是否达标；若不足则循环回拆，达标后进入下一步。

   运行提示词 · 来源原文。AI Agent 节点 'Break Narrative into {{n}} Scenes' 的 text 参数

   复制提示词

   =<Instructions>
   
   Break down the following story into a script (for short video) with exacly {{ $('Get Data').item.json.number_of_scene }} scenes.
   
   </Instructions>
   
   <Story>
   {{ $json.output.story }}
   </Story>

4. 逐场景生成结构化视频描述

   Split Out 节点将 scenes 数组拆分为单条。每条进入 AI Agent 节点（GPT-4o），结合完整故事上下文，输出结构化场景描述：角色列表、场景背景、镜头运动、物体运动、音效设计。输出受 Structured Output Parser 约束为 {characters, scene_description, camera_movement, object_movements, sound_effects}。

   运行提示词 · 来源原文。AI Agent 节点 'Describe Each Scene for Video' 的 text 参数

   复制提示词

   =Prompt Template: Generate Detailed Scene (5s Clip)
   
   Instructions:
   Create a detailed visual breakdown of the following scene.
   Use the full story context to ensure continuity, tone, and emotional flow.
   
   For this scene, include:
   
   1. Characters in the Scene:
   - List all characters present
   - Describe their age, attire, appearance, posture, emotion, and current action
   
   2. Scene Background & Environment:
   - Describe the setting in detail (lighting, background elements, color palette, time of day)
   - Mention any objects in the environment that affect mood or action
   
   3. Camera Direction:
   - Describe camera angle, motion (e.g. dolly, pan, zoom), perspective, or transitions during the 5s scene
   
   4. Object & Character Movement:
   - Describe how characters or objects move within this 5-second clip
   - Use dynamic motion where appropriate
   
   5. Sound Effects & Ambience:
   - Describe background sound, music, or specific SFX
   - Include emotional tone and pacing of sound
   
   Scene Input:
   {{ $json.scenes }}
   
   
   Full Story Reference:
   {{ $('Generate Full Narrative from Prompt').item.json.output.story }}
   
   Output Format Example:
   
   Characters:
   - Anya (17): Wears a tattered blue coat. Snow clings to her hair. She breathes heavily, face flushed from the cold. Her eyes are locked ahead, determined.
   - The Old Man (60s): Frail, cloaked in furs, holding a lantern that flickers with a weak flame.
   
   Scene Background: A narrow trail carved through pine trees covered in frost. The sky is turning orange. In the distance, the silhouette of a crumbling tower. Mist coils low to the ground.
   
   Camera Movement: Slow push-in from behind Anya’s shoulder, transitioning to a side dolly as she steps forward and the tower comes into view.
   
   Movement in Scene: Snowflakes fall steadily. Anya trudges forward. The Old Man stops, raises his lantern slightly, casting light across the branches. A raven flutters from a tree.
   
   Sound Design:
   - Soft wind whistling through trees
   - Crunching snow with each step
   - Distant echo of a bell
   - Faint strings rise in tension as the tower is revealed

5. 调用 Seedance 生成视频并轮询状态

   HTTP Request 节点向 https://queue.fal.run/fal-ai/{model} 发送 POST，body 包含 XML 格式的 Characters、SceneDescription、CameraMovements、ObjectMovements，以及 aspect_ratio、resolution、duration。随后通过 SplitInBatches 逐条处理，Wait 节点延时后 HTTP 轮询 status_url，Switch 节点判断状态：COMPLETED 则获取视频，IN_PROGRESS/IN_QUEUE 则继续等待。

   运行提示词 · 来源原文。HTTP Request 节点 'Call Fal.ai API (Seedance)' 的 bodyParameters.prompt 字段

   复制提示词

   =<Characters>
   {{ $json.output.characters.map(character => `<Character>
     <Name>${character.name}</Name>
     <Description>${character.description}</Description>
   </Character>`).join('\n') }}
   </Characters>
   
   <SceneDescription>
   {{ $json.output.scene_description }}
   </SceneDescription>
   
   <CameraMovements>
   {{ $json.output.camera_movement }}
   </CameraMovements>
   
   <ObjectMovements>
   {{ $json.output.object_movements }}
   </ObjectMovements>

6. 为视频添加环境音频

   HTTP Request 节点向 https://queue.fal.run/fal-ai/mmaudio-v2 发送 POST，传入 video_url（上一步输出）和 prompt（来自场景描述的 sound_effects）。通过 SplitInBatches 逐场景循环，Wait+HTTP 轮询音频完成状态，获取带音频的视频片段。

   运行提示词 · 本站建议版本。HTTP Request 节点 'Start adding audio to the video' 的 bodyParameters；需替换为实际 n8n 表达式

   复制提示词

   video_url: {{ $json.video.url }}
   prompt: {{ $('Describe Each Scene for Video').item.json.output.sound_effects }}

7. 合并片段为最终视频

   Aggregate 节点汇总所有带音频的视频片段。HTTP Request 节点向 https://queue.fal.run/fal-ai/ffmpeg-api/compose 发送 POST，jsonBody 构造 tracks 数组，每个片段 6000ms 依次拼接。随后 Wait+HTTP 轮询合并状态，最终获取 merged video URL。

   运行提示词 · 来源原文。HTTP Request 节点 'Start merging videos' 的 jsonBody 字段

   复制提示词

   ={
     "tracks": [
       {
         "id": "1",
         "type": "video",
         "keyframes": {{ JSON.stringify($json.data.map((item, index) => ({ url: item.video.url, timestamp: index * 6000, duration: 6000 }))) }}
       }
     ]
   }

8. 可选：自动上传 YouTube

   若配置了 YouTube OAuth2，最终视频可通过 YouTube 节点自动上传，标题取自 Sheets 的 story 字段，分类 ID 28（Science & Technology），地区码 TH。

你正在搭建一个 n8n 工作流，将 Google Sheets 中的一行文本提示自动转为多场景电影级视频。请先确认你已准备好：n8n 实例、Fal.AI Header Token、OpenAI API Key、Google Sheets OAuth2 凭证。然后按步骤导入模板、配置凭证、准备表格列（story, number_of_scene, duration, aspect_ratio, resolution, model），最后运行并观察队列轮询状态。