用 n8n 从参考图自动生成产品照片与营销视频

用户提交产品图与描述 → GPT-4.1 改写提示词 → OpenAI 生成新图 → RunwayML 生成视频 → Gmail 自动发送结果

给谁

电商运营、内容创作者、营销团队

你会得到

提交一张参考产品图后，自动获得 AI 生成的新产品图与 5 秒营销视频

你需要

n8n · google-drive · gmail · runwayml · imgbb

步骤

1. 配置表单触发器

   在 n8n 中添加「A.I Stunning Generator Interface」表单触发节点（Form Trigger）。设置表单标题为「Stelo Link Studio」，添加四个必填字段：Image File（文件，接受 .jpeg/.jpg/.png/.webm）、Product Image Name（文本，占位符「Name of New Image」）、Prompt A.I（多行文本，占位符「Explain your Vision. Think [Background, Content and Styles]」）、Email（邮箱，占位符「[email protected]」）。工作流激活后 n8n 自动生成公开表单 URL，可直接分享给提交者。

2. 备份原图到 Google Drive

   表单提交后，先将原图上传至 Google Drive 备份。添加「Upload to Google Drive」节点，使用 Google Drive OAuth2 凭证；文件名字段设为「={{ $json['Product Image Name'] }} (original)」；folderId 替换为你自己的 Google Drive 文件夹 ID（从文件夹 URL 中复制）；inputDataFieldName 设为「Image_File」。随后用「Download from Google Drive」节点按上传返回的 id 下载该文件，供后续步骤使用。

3. AI 改写提示词并生成新图

   添加「AI Agent」节点，连接「Chat GPT 4.1」语言模型（模型选 gpt-4.1）。AI Agent 的输入文本设为：「=Product : {{ $('A.I Stunning Generator Interface').item.json['Product Image Name'] }}\nDescription : {{ $('A.I Stunning Generator Interface').item.json['Prompt A.I'] }}」。在 AI Agent 的 System Message 中粘贴以下提示词（来源 workflow.json 节点原文），使 GPT-4.1 将用户描述改写为专业图像生成提示词。随后添加「OpenAi Create Image」节点，调用 https://api.openai.com/v1/images/edits，使用 HTTP Header Auth（Bearer YOUR_OPENAI_API_KEY），multipart/form-data 格式提交：image 字段接前一步下载的文件 data，prompt 字段接 AI Agent 输出「={{ $('AI Agent').item.json.output }}」，model 设为 gpt-image-1。最后用「Convert to File」节点将返回的 data[0].b64_json 转为二进制文件。

   运行提示词 · 来源原文。AI Agent 节点的 System Message 字段

   复制提示词

   =# Overview
   You are a world-class marketing strategist and an expert text-to-image prompt engineer
   specializing in creating hyper-realistic, high-quality product photography prompts for AI image
   generation models.
   ## Your Objective:
   When given a product description, your task is to craft a detailed, professional prompt that
   results in a hyper-realistic, clean, and visually stunning product image suitable for marketing
   material, advertising campaigns, or e-commerce platforms.
   ## Key Requirements:
   - Focus on hyper-realistic, professional studio photography.
   - Maintain a clean, minimalistic, and elegant visual style.
   - Highlight the product as the main subject with sharp detail and perfect lighting.
   - Use backgrounds that complement but do not overpower the product (e.g., soft gradient,
   light-colored, or pure white).
   - Include professional lighting details such as "softbox lighting"
   ,
   "studio lights"
   , or "natural soft
   shadows"
   .
   - Emphasize realism, texture, and color accuracy.
   - Maintain a high-end, premium look and feel.
   - If applicable, suggest a subtle setting that enhances the product's story (e.g., a luxury kitchen
   counter for a high-end blender).
   ## Output Format:
   - Write a single text-to-image prompt optimized for a professional AI image model.
   - Be direct and descriptive without using excessive words.
   - Avoid unnecessary repetition or adjectives that do not enhance the image quality.
   - Ensure the prompt is complete and ready for direct input into an AI model.
   ## Tone:
   Professional, precise, clean, and optimized for maximum realism and marketing impact.
   # Example Input:
   "A premium wireless Bluetooth speaker in matte black, cylindrical shape, modern design.
   "
   # Example Output:
   "Hyper-realistic product photo of a premium matte black wireless Bluetooth speaker with a
   cylindrical modern design, centered on a clean white studio background, softbox lighting with
   natural shadows, sharp focus on texture and material, minimalistic, professional advertising
   shot.
   "

4. 上传图像获取公开 URL

   添加「Get URL」节点，调用 ImgBB 上传 API（https://api.imgbb.com/1/upload），使用 HTTP Query Auth（参数名 key，值 YOUR_IMGBB_API_KEY）。请求类型 multipart/form-data，body 参数 image 设为 formBinaryData，inputDataFieldName 为「data」（接前一步 Convert to File 的输出）。上传成功后，ImgBB 返回的 data.url 将用于下一步视频生成。

5. 提交视频生成并轮询结果

   添加「Create Video」节点，向 https://api.dev.runwayml.com/v1/image_to_video 发送 POST 请求，HTTP Header Auth（Bearer YOUR_RUNWAYML_API_KEY）。Header 必须包含 X-Runway-Version: 2024-11-06（不可更改）。Body 参数：promptImage 为前一步 ImgBB 的 data.url，model 为 gen4_turbo，promptText 为固定视频描述（见下方提示词），duration 为 5，ratio 为 720:1280。随后添加「60 Seconds」等待节点（60 秒），再添加「HTTP Request」轮询节点，URL 为「=https://api.dev.runwayml.com/v1/tasks/{{ $('Create Video').item.json.id }}」，同样带 X-Runway-Version: 2024-11-06 头。接着用「If」节点判断返回 status 是否为「SUCCEEDED」或「RUNNING」：若为 SUCCEEDED 则进入发送邮件步骤；否则进入「Wait」节点等待 30 秒后再次轮询（Wait 节点接回 HTTP Request 形成循环）。

   运行提示词 · 来源原文。Create Video 节点的 bodyParameters.promptText 字段

   复制提示词

   =Create a highly professional marketing video from the provided product photo. Simulate a smooth 360 rotation, realistic 3D turntable rotation around the product, as if the product is slowly rotating in place. The movement should be continuous, slow, and elegant — no sudden pans, jerks, or camera cuts. Always keep the entire product fully in frame, centered, and clearly visible at all times. Avoid zooming in or cropping. Focus on a premium, clean, and modern aesthetic that feels suitable for commercial marketing materials. No flashy effects, transitions, or overlays — only a subtle, realistic 3D rotation that highlights the product in the most polished way possible.

6. 发送结果邮件

   添加「Send a message」Gmail 节点，使用 Gmail OAuth2 凭证（发送账户即授权账户）。收件人设为「={{ $('A.I Stunning Generator Interface').item.json.Email }}」，主题设为「=Marketing Material : {{ $('A.I Stunning Generator Interface').item.json['Product Image Name'] }}」，邮件类型 text，内容如下（来源 workflow.json 节点原文）。关闭 appendAttribution。

   运行提示词 · 来源原文。Send a message 节点的 message 字段

   复制提示词

   =Hey!
   
   Here is your photo: {{ $('Get URL').item.json.data.url_viewer }}
   
   and your video: {{ $json.output[0] }}
   Cheers
   Thank you for choosing Stelo Link

7. 配置凭证与权限

   按来源说明配置以下五类凭证，全部在 n8n 的 Credentials 页面完成：1) OpenAI — HTTP Header Auth，Header name: Authorization，Value: Bearer YOUR_OPENAI_API_KEY，连接到 Chat GPT 4.1 和 OpenAi Create Image 节点；2) Google Drive — Google Drive OAuth2，按 OAuth 流程授权，然后在 Upload to Google Drive 节点更新 Folder ID；3) ImgBB — HTTP Query Auth，Parameter name: key，Value: YOUR_IMGBB_API_KEY，免费注册于 imgbb.com，连接到 Get URL 节点；4) RunwayML — HTTP Header Auth，Header name: Authorization，Value: Bearer YOUR_RUNWAYML_API_KEY，连接到 Create Video 和 HTTP Request 轮询节点；5) Gmail — Gmail OAuth2，按 OAuth 流程授权，连接到 Send a Message 节点。

你正在搭建一个 n8n 工作流：用户提交产品参考图与描述，系统自动生成 AI 产品图和营销视频并邮件发送。请先确认你已准备好 n8n 实例、OpenAI API Key（开通 gpt-image-1 权限）、Google Drive 文件夹、ImgBB Key、RunwayML Key 和 Gmail OAuth 账户，然后按步骤导入 workflow.json 或手动重建节点。