Generate videos from images with Wan 2.2 I2V A14B AI model
Generate Videos from Images with Wan 2.2 I2V A14B AI Model π Overview This workflow connects n8n with Replicateβs Wan-Video model to generate video content from an image + prompt. It handles: π API authentication π€ Sending a generation request β³ Polling until completion π₯ Returning a downloadable video link --- π’ Section 1: Start & Authentication π Nodes: 1οΈβ£ On clicking 'execute' (Manual Trigger) βΆοΈ Starts the workflow manually when you click Execute Workflow. 2οΈβ£ Set API Key π Stores your Replicate API Key securely inside n8n. Value: YOURREPLICATEAPI_KEY π‘ Beginner Benefit: β No need to hardcode API keys in every request β Easy to swap keys for different accounts --- π΅ Section 2: Send Video Generation Request π Nodes: 3οΈβ£ Create Prediction (HTTP Request) π€ Sends a request to Replicate API β /v1/predictions Model: wan-video/wan-2.2-i2v-a14b Input Parameters: π prompt β your text description πΌοΈ image β input video/image URL π² seed β reproducibility ποΈ num_frames β 81 frames β© sample_shift β 5 βοΈ sample_steps β 30 π¬ framespersecond β 16 4οΈβ£ Extract Prediction ID (Code) π Pulls out the prediction ID + status from Replicateβs response. This ID is needed for polling until the video finishes generating. π‘ Beginner Benefit: β Automates the API call to generate video β Extracts ID β avoids manual copy-paste --- π£ Section 3: Polling & Status Check π Nodes: 5οΈβ£ Wait (2 sec) β³ Adds a short delay before checking progress. Prevents API spam 6οΈβ£ Check Prediction Status (HTTP Request) π Calls Replicate API β /v1/predictions/{id} Checks whether the video is still processing or finished 7οΈβ£ Check If Complete (IF Node) β Compares status β succeeded or not β If complete β goes to Process Result β If not β loops back to Wait and tries again π‘ Beginner Benefit: β Automatic re-checking β you donβt need to refresh manually β Works until result is ready --- π‘ Section 4: Process Final Result π Nodes: 8οΈβ£ Process Result (Code) π₯ Once complete, extracts: β Status ποΈ Output video URL π Generation metrics β±οΈ Timestamps (created\at, completed\at) 𧩠Model used Final output = direct video URL you can download/share π₯ --- π Final Overview | Section | What Happens | Why Itβs Useful | | --------- | ------------------------------ | --------------------------------- | | π’ Auth | Manual Trigger + API Key | Secure, easy start | | π΅ Send | Create Prediction + Extract ID | Kicks off video generation | | π£ Poll | Wait + Check Status + IF | Auto-checks progress until done | | π‘ Result | Process Result | Gives final video link + metadata | --- π Why This Workflow Rocks π₯ Video from Image + Prompt β AI-powered video generation in minutes π Fully automated β from request to final video, no manual checks π Secure β API keys handled safely βοΈ Customizable β tweak frames, FPS, prompt, seed --- β¨ With this workflow, youβve got a personal AI video generator inside n8n β all you need to do is provide a prompt + input image/video, and youβll get a fresh AI video link back. ---
By Yaron BeenCreate a two-way WhatsApp + Telegram integration for 10k+ customer support chats
β‘ Next-Gen Customer Support: Two-Way WhatsApp + Telegram Integration for 10k+ Clients ------------------------------------------------------------------------ Who is this workflow for This workflow is designed for customer support teams, e-commerce founders, and operations managers who want to handle thousands of customer queries seamlessly. Instead of building a brand-new chat application, it leverages WhatsApp (where customers already are) and Telegram (where your support team operates) to create a scalable, topic-based support system. If you are a brand handling 1000s of daily WhatsApp customer messages and need a structured way to map each customer into a dedicated support thread without chaos, this workflow is for you. ------------------------------------------------------------------------ What it does / How it works This two-way n8n automation bridges WhatsApp and Telegram by creating one Telegram forum topic per customer and syncing messages both ways: Incoming WhatsApp β Telegram When a new WhatsApp message arrives, the workflow checks if the customer already has a topic in Telegram. If yes β The message is forwarded into that existing topic. If no β A new topic is created automatically, the mapping is saved in the database, and the message is posted there. Result: every customer has a dedicated thread in your Telegram supergroup. Outgoing Telegram β WhatsApp When a support agent replies in a Telegram topic, the workflow looks up the linked WhatsApp number. The reply is sent back to the customer on WhatsApp, preserving context. Result: two-way synced conversations without building a custom app. ------------------------------------------------------------------------ How to set it up Configure WhatsApp Cloud API Create a Meta Developer account and register a WhatsApp Business number. Generate an access token and phone number ID. Configure Telegram Bot Use BotFather to create a bot and enable it in a Telegram Supergroup with Topics. Get the chat_id and allow the bot to create/send messages in topics. Database (Supabase/Postgres) Create a table watgthreads to map phone_e164 β telegramtopicid β supergroup_id. n8n Workflows Workflow A: WhatsApp β Telegram Trigger: WhatsApp Webhook Steps: Lookup customer β If exists send to topic, else create topic β Save mapping β Forward message. Workflow B: Telegram β WhatsApp Trigger: Telegram Webhook Steps: Filter only topic replies β Lookup mapping β Send WhatsApp message. Testing Send a WhatsApp message β Check Telegram topic created. Reply in Telegram topic β Ensure customer receives WhatsApp reply. ------------------------------------------------------------------------ Requirements A free or paid n8n instance (self-hosted or cloud). WhatsApp Cloud API credentials (phone number ID + access token). Telegram Bot token with access to a Supergroup with Topics enabled. A Postgres/Supabase database to store thread mappings. Basic familiarity with editing HTTP Request nodes in n8n. ------------------------------------------------------------------------ How to customize the workflow Brand personalization: Pre-populate first message templates (thank you, order status, delivery updates). Routing rules: Assign specific agents to certain topics by ID ranges. Integrations: Extend to CRMs (HubSpot, Zoho) or support platforms (Freshdesk, Zendesk). Notifications: Push high-priority WhatsApp queries into Slack/Teams for instant alerts. Archival: Auto-close inactive topics after N days and mark customers as dormant. ------------------------------------------------------------------------ Why Telegram instead of building a new App The client's requirement was clear: use an existing, reliable, and scalable chat platform instead of building a new app from scratch. Telegram Supergroups with Topics scale to 100,000+ members and millions of messages, making them ideal for managing 10k+ customer threads. Agents don't need to install or learn a new tool---they continue inside Telegram, which is fast, free, and mobile-friendly. Building a custom chat app would require authentication, push notifications, scaling infra, and UX---all solved instantly by Telegram. This decision saves development cost, accelerates deployment, and provides proven scalability. ------------------------------------------------------------------------ Why this improves support productivity Organized by customer: Each WhatsApp number has its own Telegram topic. No missed messages: Agents can quickly scroll topics without drowning in one endless chat. Two-way sync: Replies flow back to WhatsApp seamlessly. Scales automatically: Handle 10k+ conversations without losing track. Leverages existing tools: WhatsApp (customers) + Telegram (agents). Result: faster responses, better tracking, and zero need to reinvent chat software. ------------------------------------------------------------------------
By RuthwikAppSheet intelligent query orchestrator- query any data!
AppSheet Intelligent Query Orchestrator A friendly, practical tool that makes working with AppSheet data simpler and more efficient. This workflow is your go-to helper for building precise queries without getting lost in a sea of different tables. Background Previously, I built a community node to enable this functionality: Appsheet n8n Community node How It Works This workflow fetches the most up-to-date schema and taxonomy from your Google Sheet mirror and constructs a custom query using key components: TableName: Specifies exactly which table to query. Selector: Uses powerful functions like SELECT(), FILTER(), and CONTAINS() to filter data with precision. Columns Required: Extracts only the essential fields, keeping the payload lean and focused. Natural Language Search Query: Provides a clear, descriptive context that helps refine and re-rank results. Real-World Use Cases This orchestrator is designed for various industries, making data retrieval effortless: π¦ Supply Chain & Manufacturing Find the right product based on specific attributes. Locate suppliers that meet certain quality or pricing criteria. Obtain details about the lowest-priced raw materials. π Retail & E-commerce Match customer queries to the most relevant product listings. Identify inventory levels and stock variations. Compare pricing and product features across vendors. π₯ Healthcare Retrieve patient records based on specific attributes. Track inventory of medical supplies. Schedule and manage appointments dynamically. π Education Monitor student attendance or performance metrics. Allocate resources and track equipment usage. Manage events and class schedules efficiently. π§ Field Services & Maintenance Schedule maintenance tasks by matching service requirements. Track asset conditions and inventory for field equipment. Monitor work orders and dispatch field teams based on real-time data. Examples: Iterative Refinement This workflow operates iteratively, refining the query until it finds the best matchβeven if it takes multiple rounds. This makes it incredibly versatile for complex inventory management, procurement, and precise data retrieval. --- In a Nutshell The AppSheet Intelligent Query Orchestrator is like having a smart assistant that: β Understands your data structure β Builds the perfect query every time β Handles a variety of real-world scenarios with ease π Practical, adaptable, and ready to tackle your toughest data challenges!
By Mohammed RifadSend a message on Mattermost when a lead replies to your Lemlist email
This workflow allows you to send a message on Mattermost when a lead replies to your email. Lemlist Trigger: The Lemlist Trigger node will trigger the workflow when a lead sends a reply to a campaign. Mattermost node: This node will send a message to the Leads channel in Mattermost with the information about the reply. Based on your use-case, you may want to send the message to a different channel. You may even want to use a different service. Replace the node with the service where you want to send a message.
By Harshil Agrawal