Workflow Templates

Generate AI Ecommerce Ads from Product Page and Images with Claude + NanoBanana 👥 Who is this for? This workflow is designed for ecommerce brands, marketers, agencies, and content teams who want to generate static product ads faster from minimal product input. It works especially well if you already have: a product page URL a logo a product image a need to turn that into a more structured ecommerce ad concept and final creative without building everything manually 🧩 What problem is this workflow solving? / Use case Creating decent ecommerce ad creatives usually takes more than just prompting an image model. You need to: understand what the product actually is extract the real use cases and customer needs identify the most important product features and benefits pull proof points, pricing, or offer context from the page decide what visual direction makes sense for the product then generate the final ad This workflow solves that by automating the full process from product page + brand assets → product insights → ad concept → generated image. ⚙️ What this workflow does Collects a product URL, logo, and product image through a form Analyzes the uploaded product image with Claude to understand what kind of product visual it is Fetches the product page Extracts and cleans product page text into one usable source Builds structured product insights such as: product name product summary product category customer group use cases problems / needs key product features key benefits proof / trust signals offer / pricing brand voice Creates an ecommerce ad concept with Claude Generates a static ecommerce ad creative with NanoBanana through OpenRouter Converts the output into a file and uploads it to Google Drive 🔌 Setup Connect your accounts: Anthropic API** for product insight extraction and ad concept generation OpenRouter** for image analysis and final image generation Google Drive** if you want to store the final output Set your credentials in the respective nodes. Make sure your form accepts: .jpg** .png** .webp** If you do not want file export, disable the Upload file node. 🛠️ How to customize this workflow to your needs Product analysis: Adjust the product insight prompt if you want different fields, such as ingredients, materials, objections, bundle logic, or audience segments. Ad concept style: Edit the concept generation prompt to control tone, structure, and creative direction. Visual output: Update the image generation prompt to make outputs more minimal, more premium, more editorial, more offer-led, or more product-shot focused. Copy structure: Change the allowed copy structures if you want more offer-first, testimonial-first, or badge-led ecommerce ads. Export flow: Replace Google Drive with your own storage, CMS, or downstream creative workflow. 🔍 How it works The workflow starts with a form submission containing a product URL, logo, and optional product image. The uploaded assets are processed first: the logo is prepared for generation, while the product image is analyzed to understand whether it is a product shot, packaging, illustration, object, or another kind of asset. Next, the workflow fetches the product page and converts it into readable text. That content is then cleaned and turned into one usable source. Claude uses it to build structured product insights, including product summary, category, customer group, problems or needs, use cases, features, benefits, trust signals, pricing or offer, and brand voice. Based on that, Claude creates one ecommerce ad concept with the copy structure, main text, optional supporting text, badges or microcopy, CTA, visual direction, layout direction, and style direction. Finally, the concept and uploaded assets are passed to the image model to generate the final ecommerce ad creative, which can then be exported automatically. ✅ Result With this workflow, you go from product page + assets → product insights → ad concept → generated ecommerce creative in one flow, with much less manual prompting and much more structure. This is also close to the idea behind Blumpo: better ads come from better context first, not just better prompting.

Quick Overview This workflow scrapes a Russian joke from anekdot.ru, uses OpenRouter (chat + image) to turn it into a single-panel comic image, posts the image with a caption to Telegram, and tracks state and deduplication in Google Sheets while storing generated images in Google Drive. How it works Starts manually (or on a schedule if you replace the trigger) and searches Google Drive for the history Google Sheets spreadsheet, creating it (plus an images folder) on first run. Loads the last processed page from the spreadsheet’s State tab, builds the anekdot.ru tag URL, downloads the page HTML, and extracts jokes that match the target length. Reads previously used joke hashes from the Used Jokes tab and selects the first unused joke, paging through anekdot.ru (up to 15 pages) until it finds a valid unused candidate. Sends the chosen joke text to an OpenRouter chat model to extract a strict JSON description (scene, characters, and short dialogue), then assembles a safe image prompt with optional speech bubbles. Generates a square comic image via the OpenRouter Images API, and if moderation blocks the request it logs the joke as blocked in Google Sheets and retries with the next unused joke. Converts the returned base64 image to a PNG, uploads it to Google Drive, shares it publicly, and posts it to Telegram with an HTML caption containing the joke text. Appends the sent joke hash, excerpt, timestamp, and Drive image URL to the Used Jokes tab and updates the current page in State if it changed. Setup Add credentials for OpenRouter API, Telegram, Google Sheets OAuth2, and Google Drive OAuth2 (with the Google Sheets API and Drive API enabled). Set the Telegram chat ID in the Telegram “send photo” step to your target channel/chat numeric ID. Ensure the Google Drive search name and the Google Sheets spreadsheet title match exactly (default is “Anekdot Bot — History”), or change both to your preferred name. Optionally change the anekdot.ru tag in the URL-building code (default is “вовочка”) and the Google Drive folder name where images are stored. Select an OpenRouter chat model in the OpenRouter Chat Model node (the workflow ships without a preset model). If you want automatic posting, replace the Manual Trigger with a Schedule Trigger and activate the workflow.

💥 Generate product images with NanoBanana Pro to Veo videos and Blotato Who is this for? This workflow is designed for: Content creators and marketers E-commerce and product-based businesses Agencies producing social media visuals and videos Automation builders looking for AI-powered creative pipelines It is ideal for anyone who wants to automate product image and video creation using AI and publish content without manual work. What problem is this workflow solving? / Use case Creating product visuals and marketing videos usually requires multiple tools, manual prompt writing, and repetitive steps. This workflow solves: Manual image and video creation Inconsistent visual quality across assets Time-consuming prompt iteration Manual video publishing to social platforms The workflow automates the entire process from image generation to video publishing using AI. What this workflow does This workflow provides an end-to-end automation pipeline: Generates high-quality product images using NanoBanana Pro Applies Contact Sheet Prompting to explore multiple visual variations Converts selected images into short marketing videos using Veo 3.1 Automatically publishes the final videos via BLOTATO The result is a fully automated creative workflow that turns AI prompts into ready-to-publish video content. Setup To use this workflow, you need the following services and credentials: OpenAI API** Used for image analysis and prompt generation NanoBanana Pro (fal.ai)** Product image generation API: https://fal.ai/models/fal-ai/nano-banana-pro/edit/api Veo 3.1 (fal.ai)** Video generation API: https://fal.ai/models/fal-ai/veo3.1/first-last-frame-to-video Blotato** Video publishing to social platforms Sign up at BLOTATO All credentials must be added in n8n before running the workflow. How to customize this workflow to your needs You can easily adapt this workflow by: Modifying AI prompts to match your brand style Adjusting image composition and realism parameters in NanoBanana Pro Changing video motion, pacing, and aspect ratio in Veo 3.1 Selecting different social platforms or publishing rules in Blotato Replacing or extending individual steps while keeping the same architecture The workflow is modular and can be reused for multiple products or campaigns. 🎥 Watch This Tutorial 👋 Need help or want to customize this? 📩 Contact: LinkedIn 📺 YouTube: @DRFIRASS 🚀 Workshops: Mes Ateliers n8n 📄 Documentation: Notion Guide Need help customizing? Contact me for consulting and support : Linkedin / Youtube / 🚀 Mes Ateliers n8n

Generate AI ad creatives from website, logo, and product image with Claude + NanoBanana Who is this for? This workflow is designed for marketers, founders, agencies, and content teams who want to generate static ad creatives faster from minimal brand input. It works especially well if you already have: a website a logo a product image, screenshot, or UI visual and want to turn that into a structured ad concept and final creative without building everything manually. What problem is this workflow solving? / Use case Creating decent ad creatives usually takes more than just prompting an image model. You need to: understand what the product actually does pull useful messaging from the website figure out who the product is for write a clear value proposition decide what visual direction makes sense then generate the final ad This workflow solves that by automating the full process from website + brand assets → insights → ad concept → generated image. What this workflow does Collects a website URL, logo, and product image through a form Analyzes the uploaded product image with Claude to understand what kind of visual it is Fetches the homepage and selected internal pages from the website Extracts and cleans website text into one usable source Builds structured brand insights such as: product summary customer group problems key features key benefits brand voice Creates a marketing brief and ad concept with Claude Generates a static ad creative with NanoBanana through OpenRouter Converts the output into a file and uploads it to Google Drive Setup Connect your accounts: Anthropic API** for brand insights and ad concept generation OpenRouter** for image analysis and final image generation Google Drive** if you want to store the final output Set your credentials in the respective nodes. Make sure your form accepts: .jpg** .png** .webp** If you do not want file export, disable the Upload file node. How to customize this workflow to your needs Brand analysis: Adjust the prompt in the brand insight step if you want different fields, such as competitor angles, tone categories, or ICP detail. Page selection: Change the subpage selection prompt if you want to prioritize pages like pricing, testimonials, integrations, or case studies. Ad concept style: Edit the concept generation prompt to control tone, structure, and creative direction. Visual output: Update the image generation prompt to make outputs more minimal, more editorial, more SaaS-like, or more product-focused. Export flow: Replace Google Drive with your own storage, CMS, or downstream creative workflow. How it works The workflow starts with a form submission containing a website, logo, and optional product image. The uploaded assets are processed first: the logo is prepared for generation, while the product image is analyzed to understand whether it is a UI, product shot, illustration, object, or another type of visual. Next, the workflow fetches the homepage, extracts navigation links, and uses Claude to select a few useful internal pages likely to contain stronger marketing input. Those pages are fetched and converted into text. That content is then cleaned and merged into one source. Claude uses it to build structured brand insights and turn them into a full ad concept, including headline, subheadline, CTA, visual direction, and layout direction. Finally, the concept and uploaded assets are passed to the image model to generate the final ad creative, which can then be exported automatically. Result With this workflow, you go from website + assets → brand insights → ad concept → generated creative in one flow, with much less manual prompting and much more structure.

Turn your code commits into engaging social media content automatically. This workflow monitors a GitHub repository, uses AI to write a LinkedIn post about your changes, generates a beautiful "Mac-window" style image of your code, and publishes it all to LinkedIn. How it works GitHub Trigger: Watches for new push events in your selected repository. AI Analysis: Passes the code changes to an LLM (via LangChain) to write a professional LinkedIn post and select the best code snippet. Image Generation: Creates a custom HTML view of your code (with syntax highlighting and window controls) and converts it to an image using the HCTI API. Hosting & Posting: Uploads the generated image back to GitHub for hosting, then combines the text and image to publish a live post on LinkedIn. Set up steps Configure Credentials: You will need credentials for: GitHub (OAuth2 or Access Token) LinkedIn (OAuth2) OpenRouter (or swap the model node for OpenAI/Anthropic) HCTI.io (for the HTML-to-Image conversion) Update GitHub Nodes: In the Trigger node: Set your Owner and Repository. In the File Download node: Set the same Owner and Repository. In the Upload Image node: Set the target repo where you want images stored. Update LinkedIn Node: Add your LinkedIn Person URN in the Person field.

AI Image Remix & Design Bot for Telegram with BrowserAct & Gemini This workflow transforms your Telegram bot into an intelligent creative assistant. It can chat conversationally, fetch trending image prompts from PromptHero for inspiration, or perform a deep "remix" of any photo you upload by analyzing its composition and regenerating it with high-fidelity prompt engineering. Target Audience Digital artists, designers, content creators, and hobbyists looking for AI-assisted inspiration and image generation. How it works Traffic Control: The workflow starts with a Telegram Trigger and immediately splits traffic: new messages go one way, while interactive button clicks (like "Regenerate") go another. Intent Classification: An AI Agent analyzes text inputs to decide if the user wants to "Chat" (small talk) or "Start" a creative session (fetch inspiration). Inspiration Mode: If "Start" is detected, BrowserAct scrapes trending prompts from PromptHero and saves them to a Google Sheet. Visual Forensics: If the user uploads an image, an AI Vision Agent (using OpenRouter/Gemini) analyzes it in extreme detail (lighting, composition, subjects) and saves the description. Master Prompt Engineering: Specialized AI Agents expand these inputs (either scraped prompts or image descriptions) into massive, detailed prompts using the "Rule of Multiplication." Production: Google Gemini generates the new image, which is sent back to Telegram with interactive buttons to "Regenerate" or move to the "Next" idea. ⚠️ Complex Workflow This workflow is complex. Please proceed using the tutorial video. How to set up Configure Credentials: Connect your Telegram, Google Sheets, BrowserAct, Google Gemini, and OpenRouter accounts in n8n. Prepare BrowserAct: Ensure the Image Remix & Design Bot template is saved in your BrowserAct account. Setup Google Sheet: Create a Google Sheet with four tabs: PromptHero, Current State, UserImage, and Current Image. Connect Sheet: Open all Google Sheets nodes in the workflow and paste your spreadsheet ID. Configure Telegram: Ensure your bot is created via BotFather and the API token is added to the Telegram credentials. Activate: Turn on the workflow. Requirements BrowserAct* account with the *Image Remix & Design Bot** template. Telegram** account (Bot Token). Google Sheets** account. Google Gemini** account. OpenRouter** account (or compatible LLM credentials). How to customize the workflow Change Art Style: Modify the system prompt in the Generate Image agents to enforce a specific style (e.g., "Cyberpunk," "Watercolor," or "Photorealistic"). Add More Sources: Update the BrowserAct template to scrape prompts from other sites like Civitai or Midjourney feed. Switch Image Model: Replace the Gemini image generation node with Stable Diffusion or DALL-E 3 if you prefer different aesthetics. Need Help? How to Find Your BrowserAct API Key & Workflow ID How to Connect n8n to BrowserAct How to Use & Customize BrowserAct Templates Workflow Guidance and Showcase Video How To create stateful n8n Workflows | AI Image Remix Bot with n8n & BrowserAct & Telegram 🎨

Automated Meeting Minutes from Video Recordings This workflow automatically transforms video recordings of meetings into structured, professional meeting minutes in Notion. It uses local AI models (Whisper for transcription and Ollama for summarization) to ensure privacy and cost efficiency, while uploading the original video to Google Drive for safekeeping. Ideal for creative teams, production reviews, or any scenario where visual context is as important as the spoken word. 🔄 How It Works Wait & Detect: The workflow monitors a local folder. When a new .mkv video file is added, it waits until the file has finished copying. Prepare Audio: The video is converted into a .wav audio file optimized for transcription (under 25 MB with high clarity). Transcribe Locally: The local Whisper model generates a timestamped text transcript. Generate Smart Minutes: The transcript is sent to a local Ollama LLM, which produces structured, summarized meeting notes. Store & Share: The original video is uploaded to Google Drive, a new page is created in Notion with the notes and a link to the video, and a completion notification is sent via Discord. ⏱️ Setup Steps Estimated Time**: 10–15 minutes (for technically experienced users). Prerequisites**: Install Python, FFmpeg, and required packages (openai-whisper, ffmpeg-python). Run Ollama locally with a compatible model (e.g., gpt-oss:20b, llama3, mistral). Configure n8n credentials for Google Drive, Notion, and Discord. Workflow Configuration**: Update the file paths for the helper scripts (wait-for-file.ps1, create_wav.py, transcribe_return.py) in the respective "Execute Command" nodes. Change the input folder path (G:\OBS\videos) in the "File" node to your own recording directory. Replace the Google Drive folder ID and Notion database/page ID in their respective nodes. > 💡 Note: Detailed instructions for each step, including error handling and variable setup, are documented in the Sticky Notes within the workflow itself. 📁 Helper Scripts Documentation wait-for-file.ps1 A PowerShell script that checks if a file is still being written to (i.e., locked by another process). It returns 0 if the file is free and 1 if it is still locked. Usage: .\wait-for-file.ps1 -FilePath "C:\path\to\your\file.mkv" create_wav.py A Python script that converts a video file into a .wav audio file. It automatically calculates the necessary audio bitrate to keep the output file under 25 MB—a common requirement for many transcription services. Usage: python create_wav.py "C:\path\to\your\file.mkv" transcribe_return.py A Python script that uses a local Whisper model to transcribe an audio file. It can auto-detect the language or use a language code specified in the filename (e.g., meeting.en.mkv for English, meeting.es.mkv for Spanish). The transcript is printed directly to stdout with timestamps, which is then captured by the n8n workflow. Usage: Auto-detect language python transcribe_return.py "C:\path\to\your\file.mkv" Force language via filename python transcribe_return.py "C:\path\to\your\file.es.mkv" `

Book2Audio Pro Workflow brief Book2Audio Pro turns an uploaded book PDF into organized audio files. The workflow starts with a file upload form, extracts the book text, uses AI to detect the chapter structure and generate splitting logic, converts each chunk into audio, and then saves the final MP3 files into a Google Drive folder created for that upload. How it works The user uploads a PDF through the form trigger. The PDF text is extracted from the uploaded binary file. An AI agent analyzes the first part of the book to detect chapter/section patterns and generates JavaScript code for structuring the full text. A code node executes the generated logic to split the book into chapters and smaller sentence-safe chunks. The text chunks are passed to OpenAI audio generation. Each generated audio file is uploaded to a Google Drive folder named after the uploaded book. Quick Setup Guide 👉 Demo & Setup Video 👉 Course Nodes of interest Book Pdf Upload** — Form trigger for uploading the book PDF. Extract Book Content** — Extracts text from the uploaded PDF. AI Agent** — Detects chapter patterns and generates parsing logic. Structured Output Parser** — Enforces a clean AI response format. Structure The Content** — Runs the generated code to split the book into chunks. Generate audio** — Converts text chunks into audio using OpenAI. Create folder** — Creates a Google Drive folder for the book. Loop Over Items** — Processes each chunk one by one. Upload file** — Uploads the final MP3 files to Google Drive. Merge** — Combines the folder metadata with the processed content. What you’ll need Credentials Google Drive OAuth2 credentials** for creating folders and uploading MP3 files. OpenAI API credentials** for: the chat model used by the AI agent audio generation Input requirements A valid PDF book file A book with reasonably detectable chapter or section markers for best results Recommended settings & best practices Keep audio chunks under 3900 characters to avoid request limits and improve generation quality. Split on sentence boundaries to prevent unnatural audio cuts. Use a consistent chapter pattern in source books whenever possible, such as Chapter 1, CHAPTER I, or Part One. Make sure the binary property name matches the uploaded file field exactly. Keep the workflow idempotent by creating a separate Drive folder per upload. Test with a short PDF first to confirm extraction, parsing, and audio output are working correctly. If books have unusual formatting, improve the AI prompt so it can detect more chapter styles reliably. Customization ideas Add voice selection for different narration styles. Add language detection and generate audio in the original language. Add chapter-level naming for cleaner MP3 filenames. Add file naming rules based on book title, chapter number, and part number. Add error handling for scanned PDFs or extraction failures. Add a status notification after upload completion. Save chapter metadata in Google Sheets or a database. Support multiple output formats, such as MP3 and WAV. Tags book-to-audio, pdf-to-speech, openai, google-drive, n8n, text-to-audio, automation, ai-workflow, audiobook, document-processing

Quick overview This workflow receives a blog request via webhook, researches the topic with Tavily, generates a long-form HTML article using Google Gemini, creates two images via the kie.ai API, stores assets in Google Drive, updates a Google Sheets tracker, and notifies a Slack user with links. How it works Receives a POST webhook request containing a Google Sheets row payload with an “AI Blog Title” and related metadata. Searches the web for supporting sources using Tavily and passes the research plus the title to Google Gemini to generate the full article as HTML. Converts the generated content to HTML, creates a temporary HTML file in Google Drive, downloads it to set the correct text/html MIME type, re-uploads it as the final Drive file, and deletes the temporary file. Sends the finished article to OpenAI to generate a short LinkedIn post, then updates the matching row in Google Sheets with a Done flag, the article folder/link value, and the LinkedIn post text. Creates a cover image and an in-article infographic by submitting two text-to-image jobs to the kie.ai API, polling until each job succeeds, downloading each resulting image, and uploading both images to Google Drive. Writes the Google Drive links for both images back to the same Google Sheets row and then fetches the updated row to send a Slack message with quick links to the sheet and the generated assets. Setup Create credentials for Tavily, Google Gemini (PaLM), OpenAI, Google Drive, Google Sheets, and Slack, then select them in the corresponding nodes. Replace the placeholder “Bearer {YOUR API KEY}” headers and callback URL values in the kie.ai HTTP requests with your actual API key and a valid callback URL. Update the Google Sheets document ID and sheet/tab name (and ensure columns like AI Blog Title, row_number, Done, ARTICLE, LN Post, Image 1, and Image 2 exist and match the workflow mappings). Set the target Google Drive folder IDs for saving article HTML files and images, and adjust naming conventions if needed. Set the Slack recipient (user or channel) and edit the message template links to match your Drive folder and Google Sheets dashboard URLs.

N8N UGC Video Generator - Setup Instructions Transform Product Images into Professional UGC Videos with AI This powerful n8n workflow automatically converts product images into professional User-Generated Content (UGC) videos using cutting-edge AI technologies including Gemini 2.5 Flash, Claude 4 Sonnet, and VEO3 Fast. Who's it for Content creators** looking to scale video production E-commerce businesses** needing authentic product videos Marketing agencies** creating UGC campaigns for clients Social media managers** requiring quick video content How it works The workflow operates in 4 distinct phases: Phase 0: Setup - Configure all required API credentials and services Phase 1: Image Enhancement - AI analyzes and optimizes your product image Phase 2: Script Generation - Creates authentic dialogue scripts based on your input Phase 3: Video Production - Generates and merges professional video segments Requirements Essential Services & APIs Telegram Bot Token** (create via @BotFather) OpenRouter API** with Gemini 2.5 Flash access Anthropic API** for Claude 4 Sonnet KIE.AI Account** with VEO3 Fast access N8N Instance** (cloud or self-hosted) Technical Prerequisites Basic understanding of n8n workflows API key management experience Telegram bot creation knowledge How to set up Step 1: Service Configuration Create Telegram Bot Message @BotFather on Telegram Use /newbot command and follow instructions Save the bot token for later use OpenRouter Setup Sign up at openrouter.ai Purchase credits for Gemini 2.5 Flash access Generate and save API key Anthropic Configuration Create account at console.anthropic.com Add credits to your account Generate Claude API key KIE.AI Access Register at kie.ai Subscribe to VEO3 Fast plan Obtain bearer token Step 2: N8N Credential Setup Configure these credentials in your n8n instance: Telegram API Credential Name: telegramApi Bot Token: Your Telegram bot token OpenRouter API Credential Name: openRouterApi API Key: Your OpenRouter key Anthropic API Credential Name: anthropicApi API Key: Your Anthropic key HTTP Bearer Auth Credential Name: httpBearerAuth Token: Your KIE.AI bearer token Step 3: Workflow Configuration Import the Workflow Copy the provided JSON workflow Import into your n8n instance Update Telegram Token Locate the "Edit Fields" node Replace "Your Telegram Token" with your actual bot token Configure Webhook URLs Ensure all Telegram nodes have proper webhook configurations Test webhook connectivity Step 4: Testing & Validation Test Individual Nodes Verify each API connection Check credential configurations Confirm node responses End-to-End Testing Send a test image to your Telegram bot Follow the complete workflow process Verify final video output How to customize the workflow Modify Image Enhancement Prompts Edit the HTTP Request node for Gemini Adjust the prompt text to match your style preferences Test different aspect ratios (current: 1:1 square format) Customize Script Generation Modify the Basic LLM Chain node prompt Adjust video segment duration (current: 7-8 seconds each) Change dialogue style and tone requirements Video Generation Settings Update VEO3 API parameters in HTTP Request1 node Modify aspect ratio (current: 16:9) Adjust model settings and seeds for consistency Output Customization Change final video format in MediaFX node Modify Telegram message templates Add additional processing steps before delivery Workflow Operation Phase 1: Image Reception and Enhancement User sends product image via Telegram System prompts for enhancement instructions Gemini AI analyzes and optimizes image Enhanced square-format image returned Phase 2: Analysis and Script Creation System requests dialogue concept from user AI analyzes image details and environment Claude generates realistic 2-segment script Scripts respect physical constraints of original image Phase 3: Video Generation Two separate videos generated using VEO3 System monitors generation status Videos merged into single flowing sequence Final video delivered via Telegram Troubleshooting Common Issues API Rate Limits**: Implement delays between requests Webhook Failures**: Verify URL configurations and SSL certificates Video Generation Timeouts**: Increase wait node duration Credential Errors**: Double-check all API keys and permissions Error Handling The workflow includes automatic error detection: Failed video generation triggers error message Status checking prevents infinite loops Alternative outputs for different scenarios Advanced Features Batch Processing Modify trigger to handle multiple images Add queue management for high-volume usage Implement user session tracking Custom Branding Add watermarks or logos to generated videos Customize color schemes and styling Include brand-specific dialogue templates Analytics Integration Track usage metrics and success rates Monitor API costs and optimization opportunities Implement user behavior analytics Cost Optimization API Usage Management Monitor token consumption across services Implement caching for repeated requests Use lower-cost models for testing phases Efficiency Improvements Optimize image sizes before processing Implement smart retry mechanisms Use batch processing where possible This workflow transforms static product images into engaging, professional UGC videos automatically, saving hours of manual video creation while maintaining high quality output perfect for social media platforms.

Who this is for Users who frequently receive images or documents via LINE or email Teams needing automatic OCR + AI summarization Anyone who wants hands-free document processing and structured storage How it works Triggers: LINE Webhook and Gmail IMAP Trigger capture incoming messages or emails. Source Tagging: Inputs are tagged as LINE or EMAIL for later branching. File Handling: Files are uploaded to Google Drive and converted for analysis. OCR: An AI vision model extracts all readable text from the document image. AI Summarization: A text model produces a concise summary. Logging: The summary is appended to Google Sheets for record-keeping. Email Drafting: A Gmail Draft is generated containing the OCR text and summary. How to set up Connect your LINE, Gmail, OpenAI, and Google Drive/Sheets credentials. Update folder IDs, sheet names, and authentication fields as needed. Optional: customize summarization instructions. Customization ideas Add translation or classification steps Modify output format for Slack/Notion Store files in date-based Drive folders

Automate your Instagram growth strategy by generating and posting viral Reels using AI and Creatomate. This workflow plans content topics based on trends, generates video assets, and handles the approval and posting process—all without manual video editing. How it works Schedule Trigger: Runs every day at 9:00 AM. Topic Planning: Checks past topics from Google Sheets to avoid duplicates, then uses OpenAI (GPT-4o) to generate a new quiz-style content plan. Video Generation: Uses Creatomate to generate a video based on a template, dynamically inserting the AI-generated text and images. Approval Loop: Sends the generated video to Slack for human review. Posting: Once approved in Slack, the workflow automatically uploads the Reel to Instagram. Logging: Saves the new topic to Google Sheets and notifies Slack upon successful publication. Setup steps Configure Credentials: OpenAI: For generating content plans. Creatomate: For video rendering. Google Sheets: For tracking past topics. Slack: For approval notifications. Facebook Graph API: For Instagram publishing. Google Sheets Setup: Create a Google Sheet with columns: Question, Answer, Title, Date. Update the Get Past Topics and Save New Topic nodes with your Sheet ID. Creatomate Setup: Create a template in Creatomate or use an existing one. Update the Generate Video node with your template_id in the JSON body. Slack Setup: Create a channel for approvals. Update the Slack Approval Request and Slack Notification nodes with your Channel ID. Activate: Turn on the workflow to start automating your content pipeline!