Workflow Templates

This workflow provides automated access to the Black Forest Labs Flux Krea Dev AI model through the Replicate API. It saves you time by eliminating the need to manually interact with AI models and provides a seamless integration for image generation tasks within your n8n automation workflows. Overview This workflow automatically handles the complete image generation process using the Black Forest Labs Flux Krea Dev model. It manages API authentication, parameter configuration, request processing, and result retrieval with built-in error handling and retry logic for reliable automation. Model Description: An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism. Creates images that avoid the oversaturated "AI look". Key Capabilities High-quality image generation from text prompts** Advanced AI-powered visual content creation** Customizable image parameters and styles** Text-to-image transformation capabilities** Tools Used n8n**: The automation platform that orchestrates the workflow Replicate API**: Access to the Black Forest Labs/flux-krea-dev AI model Black Forest Labs Flux Krea Dev**: The core AI model for image generation Built-in Error Handling**: Automatic retry logic and comprehensive error management How to Install Import the Workflow: Download the .json file and import it into your n8n instance Configure Replicate API: Add your Replicate API token to the 'Set API Token' node Customize Parameters: Adjust the model parameters in the 'Set Image Parameters' node Test the Workflow: Run the workflow with your desired inputs Integrate: Connect this workflow to your existing automation pipelines Use Cases Content Creation**: Generate unique images for blogs, social media, and marketing materials Design Prototyping**: Create visual concepts and mockups for design projects Art & Creativity**: Produce artistic images for personal or commercial use Marketing Materials**: Generate eye-catching visuals for campaigns and advertisements Connect with Me Website**: https://www.nofluff.online YouTube**: https://www.youtube.com/@YaronBeen/videos LinkedIn**: https://www.linkedin.com/in/yaronbeen/ Get Replicate API**: https://replicate.com (Sign up to access powerful AI models) #n8n #automation #ai #replicate #aiautomation #workflow #nocode #imagegeneration #aiart #texttoimage #visualcontent #aiimages #generativeart #flux #machinelearning #artificialintelligence #aitools #automation #digitalart #contentcreation #productivity #innovation

Automate Drafts From Google Drive This workflow automates the end-to-end process of extracting and summarizing information from PDFs stored in a specific Google Drive folder. When a new PDF or any binary data is added, the workflow is triggered and begins by downloading and processing the PDF to extract all available text. If multiple PDFs are detected, their content is aggregated into a single, combined dataset. This automation eliminates the time consuming task of manually reading, taking notes, and drafting documents. By removing this burden, users can focus on more meaningful tasks while the workflow handles the repetitive, tedious work. The extracted content is then passed through an AI-powered information extractor that identifies key details such as names, dates, addresses, and any other structured data points the user wants to extract from the PDF. This step is highly customizable, allowing the user to define exactly what type of information should be extracted. While the workflow is designed to extract all available content from the PDF, specifying additional structured data points ensures that critical details are accurately captured. A second OpenAI Node uses the extracted information to draft a professional, formal summary suitable for documentation. This is the most important part of the workflow and can be fully customized to meet the user's specific needs. By editing the prompts, users can tailor the workflow to generate a wide variety of draft formats based on the extracted content. The workflow then generates a new Google Document containing the full draft and composes an email summarizing the key points in 3 to 5 bullet points. This email is automatically sent to the designated recipient along with a direct link to the Google Doc. This solution is ideal for insurance, legal, or administrative use cases where timely, accurate extraction and reporting from incoming PDFs is essential. How To Use The Workflow Step 1 - Place any binary data (e.g., PDF files) into the designated Google Drive folder. Step 2 - The workflow will automatically download each PDF, extract the text, and if multiple PDFs are present combine them into a single dataset for analysis. Step 3 - The OpenAI Draft Agent will analyze the extracted information, generate a formal draft, and create a Google Document. This document will be updated with the draft content and saved back into the same Google Drive folder. Step 4 - An email will be sent to the designated recipient(s), including a summary of the draft and key extracted information, along with a link to view the Google Document. Need Help? Have Questions? For consulting and support, or if you have questions, please feel free to connect with me on LinkedIn or email michael.gullo@outlook.com.

Description This powerful n8n automation template enables seamless synchronization between Zoho Inventory and Supabase—keeping your product database up to date with zero manual effort. Whether you’re running an eCommerce store, inventory dashboard, or product catalog app, this workflow ensures your data pipeline stays clean, consistent, and fully automated. What This Template Does: 🔁 Runs on a schedule to fetch inventory data from Zoho 🔓 Authenticates via OAuth using refresh token for secure API access 📦 Fetches products & variants with complete metadata 🔄 Splits each item and maps it into Supabase row-by-row 📊 Pushes rich product data, including name, SKU, unit, tags, stock levels, dimensions, and up to 3 custom attributes Fields Included in Sync: Product ID, Variant ID, Variant Name, Brand, SKU Returnability, Item Type, Unit, Attributes (1–3) Tags, Stock on Hand, UPC/EAN/ISBN, Status Reorder Level, Dimensions, Created Time, and more Requirements: Zoho Inventory API access (with Refresh Token) Supabase account & API key Target table (e.g., Fairy Frills) set up in Supabase Optional: Custom field mapping for additional use cases Perfect For: Inventory managers syncing Zoho to custom dashboards D2C brands and eCommerce platforms powered by Supabase Internal tooling teams needing a real-time product database sync Startups replacing spreadsheets with a production-grade backend

Important: This workflow uses the Autype community node and requires a self-hosted n8n instance. This workflow downloads a fillable PDF form from a URL, extracts all form field names and types using Autype, sends the field list to an AI Agent (OpenAI) together with applicant data, and uses the AI response to fill the form automatically. The AI is instructed to return raw JSON only, and a Code node validates the response before filling. The filled PDF is flattened (non-editable) and saved to Google Drive. Who is this for? Companies that regularly submit the same types of PDF form applications -- permit renewals, tax filings, compliance questionnaires, insurance claims, customs declarations, or any recurring government/regulatory paperwork. Instead of manually filling the same form fields every quarter or year, the AI reads the form structure and fills it with the correct data automatically. Concrete example: A manufacturing company must renew its operating permit every year by submitting a multi-page PDF application to the local regulatory authority. The form asks for company name, registration number, address, contact person, business type, employee count, and more. With this workflow, the company stores its data once in the AI Agent prompt, and every renewal period they simply run the workflow to get a completed, flattened PDF ready for submission. This also works as an additional skill for an AI agent. Instead of a manual trigger, connect the workflow to a webhook or chat trigger so an agent can call it when a user asks "fill out the permit renewal form for Q2 2026." What this workflow does On manual trigger, the workflow fetches a fillable PDF from a URL (e.g. a government portal, internal document server, or S3 bucket). It uploads the PDF to Autype and calls Get Form Fields to extract every field name, type (text, checkbox, dropdown, radio), current value, available options, and read-only status. The field list is passed directly to an AI Agent via an inline expression (no separate prompt-building Code node needed). The AI's system message instructs it to return only raw JSON. A Code node validates and parses the response before Autype fills the form, flattens it, and the result is saved to Google Drive. Showcase How it works Run Workflow -- Manual trigger starts the pipeline. Download PDF Form -- An HTTP Request node fetches the fillable PDF from a URL (the sample uses a registration form with 7 fields). Upload PDF Form -- Uploads the PDF binary to Autype Tools to get a file ID. Get Form Fields -- Autype extracts all form fields and returns them as metadata. Each field includes: name, type (text/checkbox/dropdown/radio/optionlist), value (current), options (for dropdowns/radio), and isReadOnly. No output file is created. AI Agent -- Receives the field list and applicant data directly in its prompt via an n8n expression. The system message instructs the AI to return only a raw JSON object mapping field names to values (strings for text/dropdown/radio, booleans for checkboxes). Prepare Fill Data -- A Code node parses and validates the AI JSON response (strips markdown fences if present), then pairs it with the Autype file ID. Fill PDF Form -- Autype fills every form field with the AI-generated values. Fields are flattened (non-editable) so the output is a clean, final PDF. Save Filled PDF to Drive -- The completed form is uploaded to Google Drive as filled-form-YYYY-MM-DD.pdf. Setup Install the Autype community node (n8n-nodes-autype) via Settings > Community Nodes. Create an Autype API credential with your API key from app.autype.com. See API Keys in Settings. Create an OpenAI API credential with your key from platform.openai.com. Create a Google Drive OAuth2 credential and connect your Google account. Import this workflow and assign your credentials to each node (including the OpenAI Chat Model sub-node). The sample form URL is pre-configured. To use your own form, replace the URL in the "Download PDF Form" node. Edit the applicant data directly in the AI Agent node prompt (the "Prompt (User Message)" field). Set YOUR_FOLDER_ID in the "Save Filled PDF to Drive" node to your target Google Drive folder. Click Test Workflow to run the pipeline. Note: This is a community node, so you need a self-hosted n8n instance to use community nodes. Requirements Self-hosted n8n instance (community nodes are not available on n8n Cloud) Autype account with API key (free tier available) n8n-nodes-autype community node installed OpenAI API key (gpt-4o-mini or any chat model) Google Drive account with OAuth2 credentials (optional, can replace with other output) How to customize Change applicant data:** Edit the prompt text directly in the "AI Agent" node. Replace the example person/company info with your own. Use a different AI model:** Swap the OpenAI Chat Model sub-node for Anthropic Claude, Google Gemini, or any LangChain-compatible chat model. Connect to an AI agent:** Replace the Manual Trigger with a Webhook or Chat Trigger so an AI agent can call this workflow as a tool (e.g. "fill the Q2 permit renewal form"). Skip flattening:** Set flatten to false in the "Fill PDF Form" node if you want the fields to remain editable after filling. Add watermark:** Insert an Autype Watermark step after Fill Form to stamp "DRAFT" or "SUBMITTED" on every page before saving. Add password protection:** Insert an Autype Protect step after filling to encrypt the PDF before uploading to Drive. Change output destination:** Replace the Google Drive node with Email (SMTP), S3, Slack, or any other n8n output node. Pull data from a database:** Instead of hardcoding data in the AI Agent prompt, query a database (Postgres, MySQL, Airtable) or CRM (HubSpot, Salesforce) to dynamically fill different forms for different entities.

Who's it for This workflow is ideal for AI developers running multi-agent systems in n8n who need to quantitatively evaluate tool usage behavior. If you're building autonomous agents and want to verify their decisions against ground-truth expectations, this workflow gives you plug-and-play observability. What it does This template uses n8n's built-in Evaluation Trigger and Evaluation nodes to assess whether an AI agent correctly used all the expected tools. It supports: Dataset-driven testing of agent behavior Logging actual tools to compare them with the expected tools Assigning performance metrics (tool_called = true/false) Persisting output back to Google Sheets for further debugging The workflow can be triggered by either the chat input or the dataset row evaluation. It routes through a multi-tool agent node powered by the best LLMs. The agent has access to tools such as web search, calculator, vector search, and summarizer tools. The workflow then aims to validate tool use decisions by extracting the intermediate steps from the agent (i.e., action + observation) and comparing the tools that were called with the expected tools. If the tools that were called during the workflow execution match, then it's a pass; otherwise, it's documented as a fail. The evaluation nodes take care of that process.  How to set it up Connect your Google Sheets OAuth2 credential. Replace the document with your own test dataset. Set your desired models and configure the different agent tools, such as the summarizer and vector store. The default vector store used is Qdrant, so the user must create this vector store with a few samples of queries + web search results. Run from either the chat trigger or the evaluation trigger to test. Requirements Google Sheets OAuth2 credential OpenRouter / OpenAI credentials for AI agents and embeddings Firecrawl and Qdrant credentials for web + vector search How to customize Edit the Search Agent system message to define tool selection behavior Add more metric columns in the Evaluation node for complex scoring Add new tool nodes and link them to the agent block Swap in your own summarizer

🔥 Automated Daily Firecrawl Scraper with Telegram Alerts Get structured insights scraped daily from the web using Firecrawl’s AI extraction engine — then send them directly to your Telegram chat. 🧰 What this workflow does: This workflow automatically scrapes specific structured data from any webpage every day at a scheduled time using the Firecrawl API, checks if results are returned, and then sends the formatted results to Telegram. For step-by-step video tutorials of n8n builds, check out my channel: https://www.youtube.com/@Automatewithmarc 🧭 How It Works: 🕐 Schedule Trigger (Daily at 6PM) Starts the workflow every day at a set time. 🌐 Firecrawl POST Request Sends a custom extraction prompt and schema to Firecrawl, targeting any list of URLs you provide. ⏳ 30 Seconds Wait Waits to give Firecrawl enough time to complete processing. 📥 GET Firecrawl Result Fetches the extraction results using the request ID. 🔁 Loop with IF Node Checks whether data is returned. If not, waits another 15 seconds and retries. 🧹 Format & Clean (Set Node) Prepares and formats the extracted result into a readable message. 📲 Telegram Message Node Delivers the structured data directly to your Telegram channel or group. 🔧 Requirements: ✅ Firecrawl API Key (Header Auth) ✅ Telegram Bot Token & Chat ID 💡 Use Cases: Extract structured data (like product info or events) from niche websites Automate compliance monitoring or intelligence gathering Create market alert bots with real-time info delivery 🛠 Customization Ideas: Swap Telegram with Gmail, Discord, or Slack Expand schema to include more complex nested fields Add a Google Sheet node to log daily scraped data Integrate with a summarizer or language model for intelligent summaries Ready to automate your web intelligence gathering? 🧠 Let Firecrawl do the scraping — and let this workflow do the rest.

How to use Get a .csv file with your contacts (you can download this from any contact manager app) Set API key for Google Drive API, and Notion (you need to create a "connection" in Notion) Create Database for your contacts in Notion Choose which properties to extract from the .csv and pass it in to the Notion database. Right now, it transfer 4 pieces of information: full name, email, phone, and company.

🎨 AI Image Generator with Flux AI Generate realistic, high-quality images from text prompts using the Flux AI Text-to-Image Generator API via RapidAPI, and seamlessly store the results in Google Drive and log them in Google Sheets — all automated using n8n. 🧠 What This Workflow Does This no-code automation enables you to: 🖋️ Enter a custom text prompt using a web form. 🖼️ Generate a photorealistic image using Flux AI’s Text-to-Image Generator via RapidAPI. ☁️ Upload the image to Google Drive. 📊 Log the prompt and result in a Google Sheet. ⚠️ Capture and log errors in a fallback sheet. 💡 Use Case Ideal for: Digital artists and marketers Social media managers Brand mockup creators Rapid concept prototyping All without writing a single line of code. ✅ Benefits No-code automation** for AI-generated images Cloud storage** and structured logging Error handling** built-in Fast content creation** for design, branding, or concept testing Powered by* the Flux AI Text-to-Image Generator API via *RapidAPI** 🧩 Node-by-Node Breakdown 1. 📝 On Form Submission Accepts user input for a creative text prompt. 🔍 Example: “A silver can with vapor and blue lightning background.” 💡 Benefit: No technical knowledge needed. 2. 🌐 HTTP Request — Flux AI API Sends the prompt to the Flux AI Text-to-Image Generator API via RapidAPI. 📦 Returns an image encoded in base64. 💡 Benefit: Seamless integration with cutting-edge image generation. 3. 🧪 Code Node — Base64 Decoder Converts the base64 image to a binary .jpg file. 💡 Benefit: Readies the image for upload/download/sharing. 4. 📁 Google Drive Uploads the generated image to your Google Drive folder. 💡 Benefit: Secure, sharable cloud storage. 5. 📊 Google Sheets — Success Log Appends a row with the original prompt, filename, and generation date. 💡 Benefit: Tracks history of all generated images. 6. ⚠️ IF Node — Error Detection Checks if the image generation failed. 💡 Benefit: Prevents workflow from halting and routes to error logging. 7. 📉 Google Sheets — Error Log Logs failed prompts and error messages. 💡 Benefit: Helps identify what went wrong (e.g. malformed prompt). 🛠️ Challenges Solved | Problem | How This Workflow Fixes It | |--------|-----------------------------| | Manual prompt-based image generation is slow | Fully automated with Flux AI | | No storage pipeline for generated images | Integrated with Google Drive | | No audit trail for prompts/images | Logged into Google Sheets | | Errors go unnoticed in image generation | Built-in error check and logging | | Users lack API access or dev experience | Friendly web form UI | 🔗 API Spotlight This workflow is powered by the Flux AI Text-to-Image Generator API — available exclusively on RapidAPI. Why use this API? Ultra-fast text-to-image rendering High-resolution results Developer-friendly and cost-effective Great for branding, mockups, and visuals We’ve integrated this API to make advanced image generation accessible with just a prompt — no AI or dev experience required.

Triggers every day at 1pm Gets the current content from Hacker News Gets all the different submission items Extracts the rank, title and url Checks if it is a "Show HN" submission Combines the items into a simple email text Sends an email with the email text

This is a workflow where a support channel on Telegram is being used to gather customer feedback. Depending on certain keywords in the customer's message, this workflow creates a ticket with a tag in your Freshdesk instance. The customer is then sent a message on Telegram and an item is created on Monday.com for tracking.

This n8n workflow automates the process of monitoring inventory levels for Shopify products, ensuring timely updates and efficient stock management. It is designed to alert users when inventory levels are low or out of stock, integrating with Shopify's webhook system and providing notifications through Discord (can be changed to any messaging platform) with product images and details. Workflow Overview Webhook Node (Shopify Listener): This node is set up to listen for Shopify's inventory level webhook. It triggers the workflow whenever there is an update in the inventory levels. The webhook is configured in Shopify settings, where the n8n URL is specified to receive inventory level updates. Function Node (Inventory Check): This node processes the data received from the Shopify webhook. It extracts the available inventory and the inventory item ID, and determines whether the inventory is low (less than 4 items) or out of stock. Condition Nodes (Inventory Level Check): Two condition nodes follow the function node. One checks if the inventory is low (low_inventory equals true), and the other checks if the inventory is out of stock (out_of_stock equals true). GraphQL Node (Product Details Retrieval): Connected to the condition nodes, this node fetches detailed information about the product using Shopify's GraphQL API. It retrieves the product variant, title, current inventory quantity, and the first product image. HTTP Node (Discord Notification): The final node in the workflow sends a notification to Discord. It includes an embed with the product title, a warning message ("This product is running out of stock!"), the remaining inventory quantity, product variant details, and the product image. The notification ensures that relevant stakeholders are immediately informed about critical inventory levels.

This workflow demonstrates the use of static data in n8n. The workflow is built on the concept of polling. Cron node: The Cron node triggers the workflow every minute. You can configure the time based on your use-case. HTTP Request node: This node makes an HTTP Request to an API that returns the position of the ISS. Set node: In the Set node we set the information that we need in the workflow. Since we only need the timestamp, latitude, and longitude we set this in the node. If you need other information, you can set them in this node. Function node: The Function node, checks if the incoming data is similar to the data that was returned in the previous execution or not. If the data is different the Function node returns this new node, otherwise, it returns a message 'No New Items'. The data is also stored as static data with the workflow. Based on your use-case, you can build the workflow further. For example, you can use it send updates to Mattermost or Slack