HumationHuman + Automation
Back to Catalog

Generate marketing ad banners with LINE, Gemini, and Nano Banana Pro

Masaki GoMasaki Go
5189 views
2/3/2026
Product UpdateTag ManagementInventory ManagementShopifyE-commerce Automation
Official Page

About This Template

This workflow creates high-quality, text-rich advertising banners from simple LINE messages.

It combines Google Gemini (for marketing-focused prompt engineering) and Nano Banana Pro (accessed via Kie.ai API) to generate images with superior text rendering capabilities. It also handles the asynchronous API polling required for high-quality image generation.

How It Works

  1. Input: Users send a banner concept via LINE (e.g., "Coffee brand, morning vibe").
  2. Prompt Engineering: Gemini optimizes the request into a detailed prompt, specifying lighting, composition, and Japanese catch-copy placement.
  3. Async Generation: The workflow submits a job to Nano Banana Pro (Kie API) and intelligently waits/polls until the image is ready.
  4. Hosting: The final image is downloaded and uploaded to a public AWS S3 bucket.
  5. Delivery: The image is pushed back to the user on LINE.

Who It’s For

  • Marketing teams creating A/B test assets.
  • Japanese market advertisers needing accurate text rendering.
  • Developers looking for an example of Async API Polling patterns in n8n.

Requirements

  • n8n (Cloud or Self-hosted).
  • Kie.ai API Key (for Nano Banana Pro model).
  • Google Gemini API Key.
  • AWS S3 Bucket (Public access enabled).
  • LINE Official Account (Messaging API).

Setup Steps

  1. Credentials: Configure the "Header Auth" credential for the Kie.ai nodes (Header: Authorization, Value: Bearer YOUR_API_KEY).
  2. AWS: Ensure your S3 bucket allows public read access so LINE can display the image.
  3. Webhook: Add the production webhook URL to your LINE Developers console.

Generate Marketing Ad Banners with n8n, Gemini, and Nano Banana Pro

This n8n workflow is designed to automate the generation and storage of marketing ad banners. It acts as an API endpoint, receiving a request, processing it with AI, and then storing the output.

What it does

This workflow performs the following key steps:

  1. Receives a Webhook Trigger: The workflow starts by listening for incoming HTTP POST requests to its unique webhook URL.
  2. Generates Content with Google Gemini: It uses the Google Gemini node to process the incoming data, likely generating text or ideas for ad banners based on the input.
  3. Processes Data with Custom Code: A Code node is included, suggesting custom JavaScript logic is applied to transform or prepare the data, potentially for the next steps.
  4. Makes an HTTP Request: An HTTP Request node indicates an external API call is made. This could be to a banner generation service (like Nano Banana Pro, as hinted by the directory name, although not explicitly in the JSON), or another service to retrieve or send data.
  5. Waits for a specified duration: A Wait node is included, which pauses the workflow for a configurable amount of time. This might be used to allow an external service to process a request or to rate-limit subsequent actions.
  6. Stores Data in AWS S3: Finally, the workflow stores the generated output (likely the banner images or related data) into an AWS S3 bucket.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Google Gemini Credential: An API key or credential for Google Gemini to enable AI content generation.
  • AWS S3 Credential: AWS credentials with permissions to write to an S3 bucket.
  • External API Access: If the HTTP Request node points to a specific banner generation service (e.g., Nano Banana Pro), you will need the necessary API key or authentication for that service.

Setup/Usage

  1. Import the workflow: Import the provided JSON into your n8n instance.
  2. Configure Webhook:
    • Activate the "Webhook" node. n8n will provide a unique URL. This URL is where you will send your incoming requests to trigger the workflow.
    • Ensure the Webhook is set to the correct HTTP method (e.g., POST) and authentication if required.
  3. Configure Google Gemini:
    • Set up your Google Gemini credential in the "Google Gemini" node.
    • Adjust the prompt or parameters within the "Google Gemini" node to align with your desired ad banner content generation.
  4. Customize Code Node:
    • Review and modify the JavaScript code in the "Code" node to fit your specific data transformation needs.
  5. Configure HTTP Request:
    • Update the "HTTP Request" node with the correct URL, headers, body, and authentication details for the external API you intend to call (e.g., a banner generation service).
  6. Adjust Wait Time:
    • Modify the duration in the "Wait" node as needed.
  7. Configure AWS S3:
    • Set up your AWS credential in the "AWS S3" node.
    • Specify the S3 bucket name, region, and object key (file path) where you want to store the generated banners or data.
  8. Activate the workflow: Once all nodes are configured, activate the workflow. You can then trigger it by sending a POST request to the Webhook URL.

Related Templates

Auto-create TikTok videos with VEED.io AI avatars, ElevenLabs & GPT-4

💥 Viral TikTok Video Machine: Auto-Create Videos with Your AI Avatar --- 🎯 Who is this for? This workflow is for content creators, marketers, and agencies who want to use Veed.io’s AI avatar technology to produce short, engaging TikTok videos automatically. It’s ideal for creators who want to appear on camera without recording themselves, and for teams managing multiple brands who need to generate videos at scale. --- ⚙️ What problem this workflow solves Manually creating videos for TikTok can take hours — finding trends, writing scripts, recording, and editing. By combining Veed.io, ElevenLabs, and GPT-4, this workflow transforms a simple Telegram input into a ready-to-post TikTok video featuring your AI avatar powered by Veed.io — speaking naturally with your cloned voice. --- 🚀 What this workflow does This automation links Veed.io’s video-generation API with multiple AI tools: Analyzes TikTok trends via Perplexity AI Writes a 10-second viral script using GPT-4 Generates your voiceover via ElevenLabs Uses Veed.io (Fabric 1.0 via FAL.ai) to animate your avatar and sync the lips to the voice Creates an engaging caption + hashtags for TikTok virality Publishes the video automatically via Blotato TikTok API Logs all results to Google Sheets for tracking --- 🧩 Setup Telegram Bot Create your bot via @BotFather Configure it as the trigger for sending your photo and theme Connect Veed.io Create an account on Veed.io Get your FAL.ai API key (Veed Fabric 1.0 model) Use HTTPS image/audio URLs compatible with Veed Fabric Other APIs Add Perplexity, ElevenLabs, and Blotato TikTok keys Connect your Google Sheet for logging results --- 🛠️ How to customize this workflow Change your Avatar: Upload a new image through Telegram, and Veed.io will generate a new talking version automatically. Modify the Script Style: Adjust the GPT prompt for tone (educational, funny, storytelling). Adjust Voice Tone: Tweak ElevenLabs stability and similarity settings. Expand Platforms: Add Instagram, YouTube Shorts, or X (Twitter) posting nodes. Track Performance: Customize your Google Sheet to measure your most successful Veed.io-based videos. --- 🧠 Expected Outcome In just a few seconds after sending your photo and theme, this workflow — powered by Veed.io — creates a fully automated TikTok video featuring your AI avatar with natural lip-sync and voice. The result is a continuous stream of viral short videos, made without cameras, editing, or effort. --- ✅ Import the JSON file in n8n, add your API keys (including Veed.io via FAL.ai), and start generating viral TikTok videos starring your AI avatar today! 🎥 Watch This Tutorial --- 📄 Documentation: Notion Guide Need help customizing? Contact me for consulting and support : Linkedin / Youtube

Dr. FirasBy Dr. Firas
39510

Automate invoice processing with OCR, GPT-4 & Salesforce opportunity creation

PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive ➜ Download PDF ➜ OCR text ➜ AI normalize to JSON ➜ Upsert Buyer (Account) ➜ Create Opportunity ➜ Map Products ➜ Create OLI via Composite API ➜ Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content → the parsed JSON (ensure it’s an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id ➜ build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total ➜ per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger → Download File From Google Download File From Google → Extract from File → Update File to One Drive Extract from File → Message a model Message a model → Create or update an account Create or update an account → Create an opportunity Create an opportunity → Build SOQL Build SOQL → Query PricebookEntries Query PricebookEntries → Code in JavaScript Code in JavaScript → Create Opportunity Line Items --- Quick setup checklist 🔐 Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. 📂 IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) 🧠 AI Prompt: Use the strict system prompt; jsonOutput = true. 🧾 Field mappings: Buyer tax id/name → Account upsert fields Invoice code/date/amount → Opportunity fields Product name must equal your Product2.ProductCode in SF. ✅ Test: Drop a sample PDF → verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep “Return only a JSON array” as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields don’t support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your org’s domain or use the Salesforce node’s Bulk Upsert for simplicity.

Le NguyenBy Le Nguyen
942

Automated weekly security audit reports with Gmail delivery

🔒 N8N Security Audit Report - Automated Weekly Email 🎯 What does this workflow do? This workflow automatically generates and emails a comprehensive security audit report for your N8N instance every week. It identifies potential security risks related to: Credentials 🔑 : Exposed or insecure credentials Nodes 🧩 : Sensitive nodes (Code, HTTP Request, SSH, FTP, etc.) Instance settings 🏢 : Global security configuration Community nodes 📦 : Third-party nodes that may pose risks The report includes direct links to affected workflows, execution statuses, and actionable recommendations. --- ✨ Key Features 📊 Smart Risk Assessment Calculates overall risk level: 🟩 Low / 🟧 Moderate / 🟥 High Tracks unique credentials (not just total occurrences) Provides detailed breakdown by node type 🔗 Direct Workflow Links Clickable links to each workflow mentioned Shows last execution status (🟢 success / 🔴 failed) Displays execution timestamps 🌍 Bilingual Support Full support for French and English Switch language with a single variable 📧 Beautiful HTML Email Clean, professional formatting Color-coded risk levels Emoji icons for easy scanning --- 🚀 Quick Setup (5 minutes) 1️⃣ Configure Credentials N8N API: Generate an API key in your N8N settings Gmail OAuth2: Set up OAuth2 for Gmail sending 2️⃣ Set Your Variables Edit the "Set Config Variables" node: javascript { "email_to": "your.email@domain.com", "project_name": "My-N8N-Project", "server_url": "https://n8n.yourdomain.com", // NO trailing slash! "Language": "EN" // or "FR" } 3️⃣ Test & Activate Click "Execute Workflow" to test Check your email inbox Activate for weekly automation --- 📧 Example Report Output Subject: 🔒 Audit Report My-Project – Risk 🟧 Moderate Content: 📊 Summary • Credentials involved: 8 (5 unique) • Nodes involved: 12 💻 code: 4 🌐 httpRequest: 3 🔐 ssh: 2 • Community nodes: 1 • Overall risk level: 🟧 Moderate 🔐 Credentials Risk Report 🔹 Credentials with full access 🔑 My AWS Credentials 🔑 Database Admin 📋 Workflow: Data Processing Pipeline 🟢 (25-10-2024 06:15 → 06:16) 💻 Process Data 🌐 API Call 🧩 Nodes Risk Report [...detailed node analysis...] --- 🎨 Customization Options Change Schedule Modify the "Schedule Trigger" node to run: Daily at 8 AM Monthly on the 1st Custom cron expression Add Recipients Add multiple emails in the Gmail node's toList parameter Adjust Risk Thresholds Edit the JavaScript in "Format Audit Report" nodes to customize when risk levels change Use Different Email Service Replace Gmail node with: SMTP Microsoft Outlook SendGrid Any email service N8N supports --- 💡 Use Cases ✅ Compliance Monitoring: Track security posture for audits ✅ Team Awareness: Keep your team informed of security status ✅ Change Detection: Notice when new risky nodes are added ✅ Best Practices: Get recommendations to improve security ✅ Multi-Environment: Run separate instances for dev/staging/prod --- 🔧 Technical Details Nodes Used: 8 Credentials Required: 2 (N8N API + Gmail OAuth2) External Dependencies: None N8N Version: Compatible with latest N8N versions Execution Time: ~10-20 seconds --- 📋 Requirements N8N instance with API access Gmail account (or other email service) N8N API key with audit permissions Valid SSL certificate for workflow links (recommended) --- 🐛 Troubleshooting Empty report? → Check your N8N API key has audit permissions Workflow links don't work? → Verify server_url is correct and has no trailing slash No execution status shown? → Workflows must have been executed at least once Wrong language displayed? → Set Language to exactly "FR" or "EN" (uppercase) --- 🌟 Why This Template? Unlike basic monitoring tools, this workflow: ✅ Provides context-aware security analysis ✅ Links directly to affected workflows ✅ Shows real execution data (not just theoretical risks) ✅ Calculates unique credential exposure (not just counts) ✅ Supports bilingual reports ✅ Delivers actionable recommendations --- 🤝 Feedback & Support Found this helpful? Please rate the template! Have suggestions? Drop a comment below. Pro tip: Combine this with N8N's native alerting for real-time incident response! --- Tags: security audit monitoring compliance automation email reporting credentials governance --- 📜 License MIT - Feel free to modify and share!

MatthieuBy Matthieu
389