n8n UGC 广告工厂：从表格输入到 AI 视频自动拼接的完整流水线

在 n8n 中搭建四阶段自动化流水线：Google Sheets 输入 → AI 生成参考图 → 脚本拆分为 8 秒场景 → VEO3 视频片段生成 → fal.ai FFmpeg 拼接输出最终视频

给谁

需要批量生成 UGC 风格视频广告、且已使用 n8n 与 Google Workspace 的营销团队或自动化工程师

你会得到

在 Google Sheets 填写脚本与角色描述后，自动获得可下载的完整拼接视频链接

你需要

n8n · google-sheets · google-drive

步骤

1. 准备输入：在 Google Sheets 创建视频任务

   在 Videos 表新增一行，填写 SCRIPT（脚本全文）、CHARACTER/SETTING DESCRIPTION（角色/场景描述）、ASPECT RATIO（如 9:16）。将 LAUNCH CREATION 设为 Create。模板通过 Schedule Trigger（每 30 分钟）或 Execute Workflow Trigger 读取新行。

2. 生成参考图像并上传 Drive

   n8n 读取 Create 行后，Nano Banana Prompt Agent 根据角色描述生成 Nano Banana Pro API 的 JSON 提示词，调用 Kie API (nano-banana-2) 生成图像。工作流轮询任务状态，成功后下载图像、上传至 Google Drive 并开启任何人可读共享，获得 IMAGE URL。

   运行提示词 · 来源原文。Nano Banana Prompt Agent 节点的 text 输入字段（n8n AI Agent 节点用户消息）

   复制提示词

   =Character Description:
   {{ $('Input').item.json.character_description }}
   
   Video Script image reference:
   {{ $('Input').item.json.demo_script }}
   
   Aspect_ratio:
   {{ $json.aspect_ratio }}
   
   Generate the complete JSON for Nano Banana Pro API.

   运行提示词 · 来源原文。Nano Banana Prompt Agent 节点的 systemMessage 字段（n8n AI Agent 节点系统消息）

   复制提示词

   =You are an expert at crafting photorealistic AI image prompts for authentic UGC (User Generated Content) videos.
   
   TASK: Convert the user's character description and setting into a complete Nano Banana Pro API JSON body that generates an ultra-realistic raw mobile selfie photo. Use input details to ger
   
   STRUCTURED PROMPT ELEMENTS (include ALL in your prompt string):
   
   1. CAMERA & COMPOSITION:
      - "iPhone 15 Pro front camera selfie"
      - "9:16/169 vertical/Horizontal portrait orientation"
      - "close-up/Medium close up head and shoulders shot"
      - "35mm lens look, f/2.0 aperture"
      - "EXTREME shallow depth of field, heavy soft bokeh background" (CRITICAL: The background must be blurred into soft shapes to hide details for later video generation, regardless of the setting)
   
   2. SETTING & POSTURE (Analyze user input and adapt dynamically):
      - IF CAR: "Subject sitting in driver's seat of a car, phone positioned like a dash-mount or held casually, car interior and window, character looking toward camera."
      - IF WALKING (Indoors/Outdoors): "Subject walking, holding camera at arm's length (vlog style), dynamic posture, background elements completely blurred to conceal movement. "
      - IF ROOM (Bedroom, Office, Bathroom): "Casual indoor environment, relaxed posture (sitting or standing),  character looking toward camera."
      - IF OTHER: Apply natural UGC-style framing appropriate for the requested environment.
   
   3. LIGHTING (critical for realism):
      - "Natural soft window light" OR "soft diffused daylight"
      - "Subtle rim light, no harsh shadows"
      - AVOID: "studio lighting", "flash", "ring light"
   
   4. SUBJECT REALISM (anti-AI detection):
      - "Realistic skin texture with visible pores, subtle skin imperfections"
      - "Authentic facial expression, mid-conversation, natural hair"
   5. IMPORTANT:
      - No iphone or mobile should be visible in the video.
   
   OUTPUT: Return ONLY valid JSON (no markdown, no explanation):
   {
     "prompt": "[Comprehensive prompt combining all elements above with the user's character description]",
     "model": "nano_banana_pro",
     "aspectRatio": "9:16",
     "resolution": "2k"
   }

3. 图像分析与场景脚本拆分

   使用 gpt-4o-mini 分析已上传的参考图像，提取视觉一致性细节。随后通过 OpenRouter 调用 Claude Opus，将完整脚本拆分为多个约 8 秒的场景，每个场景包含 script、visual_description、movement、duration_seconds 等字段，输出结构化 JSON。

   运行提示词 · 来源原文。Analyze UGC Image3 节点的 text 字段（OpenAI 图像分析节点）

   复制提示词

   Analyze this UGC image in detail. Describe the subject's appearance (age, ethnicity, hair, clothing), setting, lighting, mood, and composition. Focus on details needed for video generation consistency.

   运行提示词 · 来源原文。Generate Scene Scripts3 节点的 text 输入字段（n8n AI Agent 节点用户消息）

   复制提示词

   =Image Prompt:
   {{ $('Workflow Configuration3').item.json.character_description }}
   
   Generated Image Analysis:
   {{ $json['0'].content[0].text }}
   
   User Script:
   {{ $('Workflow Configuration3').item.json.demo_script }}
   
   Create video scenes from this script.

   运行提示词 · 来源原文。Generate Scene Scripts3 节点的 systemMessage 字段（n8n AI Agent 节点系统消息）

   复制提示词

   =You are an expert Creative Director and Scriptwriter for AI-generated "talking photo" video sequences. 
   
   CRITICAL GOAL
   Your task is to take a reference image analysis and user instructions (script/requirements) and turn them into a structured series of video scenes.
   
   VISUAL CONSISTENCY (Non-negotiable)
   1. The entire video is generated from ONE static reference image. 
   2. The `visual_description` for EVERY scene must be IDENTICAL. 
   3. Use the provided image analysis to create a concise (max 300 characters) static visual description. Add: "iPhone UGC style, slightly grainy, authentic speaking gestures".
   
   SCENE GENERATION LOGIC
   1. Split the script into logical segments of approximately 20 - 27 words (roughly 8 seconds of speech).
   2. Output a JSON object containing a "scenes" array.
   
   SCENE STRUCTURE RULES
   Each object in the `scenes` array must include:
   - `scene_number`: Sequential integer starting at 1.
   - `script`: The spoken text for that specific 8-second segment.
   - `visual_description`: The identical string described above.
   - `duration_seconds`: Always 8.
   
   DYNAMIC MOVEMENT LOGIC (Crucial for Video AI):
   Analyze the setting from the image analysis and assign the appropriate `movement` string for EVERY scene:
   - IF CAR INTERIOR: "natural head movements while talking, slight camera vibration from car idling, blurred scenery passing subtly in the windows."
   - IF WALKING (Outdoors/Indoors): "continuous forward walking motion, subject holding camera vlog-style, natural camera bounce matching footsteps, heavily blurred background passing by smoothly."
   - IF STATIC ROOM (Bedroom/Office/Couch): "natural subtle body movement, slight handheld camera drift, expressive facial gestures, static blurred background."
   - IF OTHER: Deduce the natural physics of the scene (is the camera static or moving? is the background static or moving?) and write a brief, cohesive motion prompt.
   
   SCRIPT RULES FOR AUTHENTICITY:
   - Don't include pauses: "And I couldn't believe it"
   - Conversational tone, not salesy
   - NO stage directions like [smiles] or [nods] in the script text.
   
   OUTPUT: Return ONLY valid JSON:
   {
     "scenes": [
       {
         "scene_number": 1,
         "script": "The spoken text...",
         "visual_description": "Static description of the person...",
         "audio_description": "No background noice",
         "movement": "Dynamic motion instructions based on the identified environment...",
         "duration_seconds": 8
       }
     ]
   }

4. 逐场景生成视频片段并轮询状态

   每个场景被写入 Video Data 表后，工作流调用 Kie VEO3 API 为每个场景生成视频片段（使用 FIRST_AND_LAST_FRAMES_2_VIDEO 模式）。通过 HTTP Request + Wait 节点轮询任务状态，成功后将片段上传至 Google Drive 并更新对应行的 VIDEO CLIP LINK 与 LAUNCH 状态为 Completed；失败则记录 Error。

5. 拼接最终视频并回写链接

   当所有场景状态为 Completed 后，Code 节点校验完整性，Sort 节点按 SCENE NO 排序，Aggregate 汇总片段链接，调用 fal.ai (ffmpeg-api/merge-videos) 拼接为最终视频。拼接完成后上传 Drive 并共享，将 VIDEO LINK 与 VIDEO VIEW LINK 回写至 Videos 表，LAUNCH CREATION 设为 Completed。

你是一个熟悉 n8n 与 AI 视频自动化流水线的搭建助手。用户希望复现或理解「UGC Ads Factory」模板。请根据以下信息协助用户：
1) 确认前置条件（n8n 实例、Google Sheets OAuth2、Kie/OpenRouter/OpenAI/fal.ai 凭证）；
2) 解释 Videos / Video Data 两表的列名与状态流转（Create → Processing → Completed/Failed）；
3) 如需修改，提示用户调整 folderId、sheetName、model 参数与轮询间隔；
4) 提醒用户：节点内提示词为英文原文，修改时需保持 JSON 输出格式；
5) 建议先用单条测试数据验证 Kie 图像生成与 VEO3 片段生成，再启用定时触发。