用 n8n 自动把 Google Sheets 产品表转成 UGC 视频（DALL·E + GPT-4 Vision + Sora）

输入：Google Sheets 产品列表；处理：DALL·E 3 生成图像 → GPT-4 Vision 分析视觉风格 → Sora 生成视频 → 上传 Google Drive；输出：带公开链接的完成行。

给谁

已有 n8n 实例、熟悉 OAuth 凭证配置的营销运营或自动化工程师

你会得到

自动为每个标记为 Pending 的产品生成 AI 图像与短视频，回写公开链接到表格

你需要

n8n · google-sheets · google-drive · dalle-3

步骤

1. 触发与读取待处理产品

   在 n8n 中配置 Schedule Trigger 按设定间隔运行。添加 Google Sheets 节点读取 Products 工作表全部行，再用 Code 节点过滤出 Status = "Pending" 的行，并记录每行的 sheetRowNumber（i + 2，含表头偏移）。若无 Pending 行，工作流自然结束。

   搭建指导 · 来源原文。n8n Schedule Trigger + Google Sheets 节点配置说明

   复制提示词

   ## Stage 1 — Trigger & data fetch. 
   
   A schedule trigger fires on a set interval. It reads all rows from a Google Sheets "Products" tab, then a code node filters down to only rows where Status = "Pending", tracking each row number for later updates.

2. 用 DALL·E 3 生成产品图像

   对每个待处理产品，Code 节点（AI Prompt Builder1）拼接 UGC 风格提示词，调用 OpenAI Images Generations API（model: dall-e-3, size: 1024x1024, quality: hd, style: natural）。下游 Code 节点（Extract DALL-E URL1）从响应中提取 imageUrl 并携带全部产品数据继续传递。

   运行提示词 · 来源原文。n8n Code 节点 AI Prompt Builder1 的 JS Code 字段

   复制提示词

   // Build a UGC-style image generation prompt from product data
   const item = $input.first().json;
   
   const productName = item.productName || 'product';
   const description = item.description || '';
   const targetAudience = item.targetAudience || 'young adults';
   
   // Construct a detailed DALL-E 3 prompt with UGC aesthetic
   const prompt = [
     `A lifestyle photograph of ${productName} being used by ${targetAudience}.`,
     description ? `The product is ${description}.` : '',
     'Shot on iPhone, natural window lighting, casual home or cafe setting.',
     'UGC aesthetic: authentic, unposed, relatable feel.',
     'Warm color grading, shallow depth of field, genuine emotion.',
     'No text overlays, no logos, no watermarks.',
     'Photorealistic, editorial quality, candid moment.'
   ].filter(Boolean).join(' ');
   
   return [{
     json: {
       ...item,
       imagePrompt: prompt
     }
   }];

   运行提示词 · 来源原文。n8n HTTP Request 节点 DALL-E 3 Generate Image1 的 JSON Body 字段

   复制提示词

   ={{ JSON.stringify({
     model: "dall-e-3",
     prompt: $json.imagePrompt,
     n: 1,
     size: "1024x1024",
     quality: "hd",
     style: "natural"
   }) }}

   运行提示词 · 来源原文。n8n Code 节点 Extract DALL-E URL1 的 JS Code 字段

   复制提示词

   // Extract the DALL-E image URL directly and carry forward all product data
   const response = $input.first().json;
   const prevData = $('AI Prompt Builder1').first().json;
   
   const imageUrl = response.data?.[0]?.url || response.data?.[0]?.revised_url || '';
   
   if (!imageUrl) {
     throw new Error('No image URL returned from DALL-E 3: ' + JSON.stringify(response));
   }
   
   return [{
     json: {
       ...prevData,
       imageUrl: imageUrl,
       dalleRevisedPrompt: response.data?.[0]?.revised_prompt || ''
     }
   }];

3. GPT-4 Vision 分析图像并构建 Sora 视频脚本

   HTTP Request 节点调用 GPT-4o（model: gpt-4o）进行视觉分析：system 提示词要求返回 JSON（含 mood / dominantColors / composition / lighting / subjectExpression / settingDetails / suggestedCameraMovements / emotionalTone），user 消息携带产品名与 imageUrl（detail: high）。下游 Code 节点（Parse Vision Analysis1）清洗并解析 JSON，再传入 Video Script Builder1 拼接成 Sora 优化格式的视频提示词。

   运行提示词 · 来源原文。n8n HTTP Request 节点 GPT-4 Vision Analysis1 的 JSON Body 字段

   复制提示词

   ={{ JSON.stringify({
     model: "gpt-4o",
     messages: [
       {
         role: "system",
         content: "You are a visual analyst for UGC video production. Analyze the image and return a JSON object with these fields: mood (string), dominantColors (array of strings), composition (string describing layout), lighting (string), subjectExpression (string), settingDetails (string), suggestedCameraMovements (array of strings for video), emotionalTone (string). Be specific and cinematic in your descriptions."
       },
       {
         role: "user",
         content: [
           {
             type: "text",
             text: "Analyze this UGC product image for video production planning. Product: " + $json.productName + ". Return structured JSON only, no markdown."
           },
           {
             type: "image_url",
             image_url: {
               url: $json.imageUrl,
               detail: "high"
             }
           }
         ]
       }
     ],
     max_tokens: 1000,
     temperature: 0.3
   }) }}

   运行提示词 · 来源原文。n8n Code 节点 Parse Vision Analysis1 的 JS Code 字段

   复制提示词

   // Parse GPT-4 Vision analysis and carry forward
   const input = $input.first().json;
   const prevData = $('Extract DALL-E URL1').first().json;
   
   const content = input?.choices?.[0]?.message?.content || '{}';
   
   let visionAnalysis;
   try {
     // Strip markdown code fences if present
     const cleaned = content.replace(/```json\n?/g, '').replace(/```\n?/g, '').trim();
     visionAnalysis = JSON.parse(cleaned);
   } catch (e) {
     // If JSON parsing fails, use raw text
     visionAnalysis = {
       mood: 'warm and authentic',
       dominantColors: ['warm tones'],
       composition: content,
       lighting: 'natural',
       subjectExpression: 'genuine',
       settingDetails: 'casual setting',
       suggestedCameraMovements: ['slow zoom in', 'pan across product'],
       emotionalTone: 'relatable'
     };
   }
   
   return [{
     json: {
       ...prevData,
       visionAnalysis: visionAnalysis
     }
   }];

   运行提示词 · 来源原文。n8n Code 节点 Video Script Builder1 的 JS Code 字段

   复制提示词

   // Build a structured UGC video script for OpenAI Sora
   const item = $input.first().json;
   
   const product = item.productName || 'this product';
   const description = item.description || '';
   const audience = item.targetAudience || 'young adults';
   const vision = item.visionAnalysis || {};
   
   const mood = vision.mood || 'warm and authentic';
   const colors = (vision.dominantColors || ['warm tones']).join(', ');
   const lighting = vision.lighting || 'natural lighting';
   const setting = vision.settingDetails || 'casual everyday setting';
   const emotion = vision.emotionalTone || 'relatable';
   const cameraMovements = (vision.suggestedCameraMovements || ['slow zoom in']).join(', ');
   
   // Build a concise video prompt optimized for Sora
   // Sora works best with clear, descriptive scene prompts rather than screenplay-style scripts
   const videoScript = [
     `UGC-style smartphone video of ${audience} authentically using ${product} in ${setting}.`,
     description ? `The product is ${description}.` : '',
     `Visual style: ${mood} mood, ${colors} color palette, ${lighting}.`,
     `Camera: ${cameraMovements}, handheld smartphone feel.`,
     `The person picks up ${product} with genuine curiosity, uses it naturally, and reacts with authentic satisfaction.`,
     `Emotional tone: ${emotion}, relatable, candid.`,
     'Natural ambient lighting, shallow depth of field, no text overlays or logos.'
   ].filter(Boolean).join(' ');
   
   return [{
     json: {
       ...item,
       videoScript: videoScript
     }
   }];

4. Sora 异步生成视频并轮询结果

   先 Wait 60 秒限速，再 HTTP POST 到 https://api.openai.com/v1/videos（model: sora-2, seconds: 8, size: 720x1280）。Sora 返回 job ID 而非直接 URL。Code 节点提取 videoId 后进入轮询：Wait 30 秒 → GET /v1/videos/{videoId} → Check Sora Status1 判断 isDone（status === 'completed'）。最多 40 次轮询（约 20 分钟超时）。完成后 Fetch Sora Video Content1 获取视频二进制。

   运行提示词 · 来源原文。n8n HTTP Request 节点 Sora Generate Video1 的 JSON Body 字段

   复制提示词

   ={{ JSON.stringify({
     model: "sora-2",
     prompt: $json.videoScript,
     seconds: '8',
     size: "720x1280"
   }) }}

   运行提示词 · 来源原文。n8n Code 节点 Extract Sora Job ID1 的 JS Code 字段

   复制提示词

   const raw = $input.first().json;
   const prevData = $('Video Script Builder1').first().json;
   const response = Array.isArray(raw) ? raw[0] : raw;
   
   if (!response || !response.id) {
     throw new Error('Could not extract video job ID from Sora response: ' + JSON.stringify(raw).substring(0, 500));
   }
   
   return [{
     json: {
       productName: prevData.productName,
       description: prevData.description,
       targetAudience: prevData.targetAudience,
       sheetRowNumber: prevData.sheetRowNumber,
       imageUrl: prevData.imageUrl,
       videoId: response.id,
       videoStatus: response.status,
       progress: response.progress || 0,
       pollCount: 0
     }
   }];

   运行提示词 · 来源原文。n8n Code 节点 Check Sora Status1 的 JS Code 字段

   复制提示词

   const raw = $input.first().json;
   const response = Array.isArray(raw) ? raw[0] : raw;
   
   // Get carried data from the job ID node
   const carried = $('Extract Sora Job ID1').first().json;
   
   const status = response.status || '';
   const progress = response.progress || 0;
   const pollCount = (carried.pollCount || 0) + 1;
   const maxPolls = 40; // 20 minutes max
   
   if (response.error) {
     throw new Error('Sora video generation failed: ' + JSON.stringify(response.error));
   }
   
   if (pollCount >= maxPolls) {
     throw new Error('Sora video generation timed out after ' + maxPolls + ' polls (20 minutes)');
   }
   
   return [{
     json: {
       productName: carried.productName,
       description: carried.description,
       targetAudience: carried.targetAudience,
       sheetRowNumber: carried.sheetRowNumber,
       imageUrl: carried.imageUrl,
       videoId: carried.videoId,
       videoStatus: status,
       progress: progress,
       pollCount: pollCount,
       isDone: status === 'completed'
     }
   }];

5. 上传视频到 Google Drive 并回写表格

   Fetch Sora Video Content1 获取 MP4 二进制，经 Google Drive 节点上传到指定文件夹，再 HTTP POST 设置 anyone/reader 公开权限。Code 节点（Build Public Drive URL1）构造分享链接，最后 Google Sheets 节点更新对应 row_number 的 Status=Done、Image URL、Video URL 等字段。Loop Over Items 处理下一行。

   运行提示词 · 来源原文。n8n Code 节点 Build Public Drive URL1 的 JS Code 字段

   复制提示词

   const driveFile = $('Upload Video to Google Drive1').first().json;
   const carried = $('Check Sora Status1').first().json;
   
   const fileId = driveFile.id;
   // Direct shareable link format
   const videoUrl = `https://drive.google.com/file/d/${fileId}/view?usp=sharing`;
   
   return [{
     json: {
       productName: carried.productName,
       description: carried.description,
       targetAudience: carried.targetAudience,
       sheetRowNumber: carried.sheetRowNumber,
       imageUrl: carried.imageUrl,
       videoUrl: videoUrl,
       videoId: carried.videoId,
       driveFileId: fileId
     }
   }];

6. 配置错误处理工作流

   主工作流失败时，Error Trigger 启动错误处理流：Parse Error Details 从执行数据中提取 sheetRowNumber 与错误信息；若已知行号则更新 Google Sheets Status=Error 并写入 Error Message；否则仅日志记录。需在主工作流设置中将此工作流设为 Error Workflow。

   搭建指导 · 来源原文。n8n 错误处理工作流 Sticky Note 说明；主工作流设置中绑定 Error Workflow

   复制提示词

   ## ERROR HANDLER WORKFLOW
   This workflow is triggered when the main UGC pipeline fails.
   It extracts the error details and row number, then updates
   the Google Sheet with Status = "Error" and the error message.
   
   SETUP: In the main workflow settings, set this workflow
   as the "Error Workflow".

你是一个 n8n 工作流搭建助手。用户希望复现「从 Google Sheets 自动生成 UGC 视频」的模板。请按以下顺序协助：1) 确认用户已拥有 n8n 实例、Google Sheets/Drive OAuth 凭证、OpenAI API Key；2) 指导导入 workflow.json 并替换硬编码的 documentId、folderId；3) 解释每个 Code 节点的输入变量与输出格式；4) 建议先用单行 Pending 数据测试，观察 DALL·E → Vision → Sora 链路是否返回预期字段；5) 提醒 Sora 访问限制与按量计费风险。不要替用户执行 API 调用。