Generate ad image variations using GPT-4, Dumpling AI & Google Drive
🧾 What this workflow does This workflow takes a reference ad image and brand website, then uses GPT-4, LangChain, and Dumpling AI to generate 10 high-quality image variations for ad testing. These image variations are visually consistent but subtly different in background, mood, lighting, and tone — perfect for performance testing on platforms like Meta Ads or TikTok. --- 👤 Who is this for DTC marketers and brand designers testing ad creatives Creative teams automating visual experimentation Content agencies using AI for fast ad mockups Performance marketers running multivariate testing --- ⚙️ How to set up ✅ Requirements You’ll need the following tools set up in n8n: Google Drive (OAuth2 credential) Google Sheets (OAuth2 credential) OpenAI API (for GPT-4 or GPT-4o) Dumpling AI API (via HTTP header authentication) --- 🛠️ Steps to configure Google Sheet Setup Create a sheet with one column: Image URL Update the Sheet ID and tab name in the final Google Sheets node. Drive Setup Create a folder in Google Drive for storing the reference image. Replace the folderId in the “Upload Ad Image to Google Drive” node. Dumpling AI API Key Use n8n’s credential manager (HTTP Header Auth) — do not hardcode the key. OpenAI API Key Required for both image description and LangChain agent prompt generation. Form Inputs Required Brand Name Brand Website Ad Image (upload field) --- 🧠 How it works A user submits the brand name, website, and a reference ad image through a form. The image is uploaded to Google Drive. GPT-4o describes the image’s visual style (e.g., mood, lighting, composition). GPT-4 analyzes the brand’s website to define its visual aesthetic. A LangChain agent uses both analyses to create 10 tightly scoped variation prompts. Dumpling AI generates a new image for each prompt using its “FLUX.1-pro” model. Each new image’s link is logged into Google Sheets. --- 🛠️ How to customize 🧪 Change prompt logic to experiment with different variations (e.g., theme, season). 🎨 Switch image model in Dumpling AI to one that supports your desired style. 🔗 Log additional metadata (prompt, timestamp) to Google Sheets. 📤 Connect output images to Airtable, Notion, or a review tool like Figma. 🎯 Modify GPT system message to reflect a different tone or brand strategy. --- This workflow gives creative teams and marketers an instant, AI-powered ad image testing system — built on real brand visuals, not generic stock content.
By YangManage Webflow form submissions in Airtable
What this does This automation will create tables in your Airtable base and send Webflow form submissions as records in those tables. It keeps track of your Webflow forms with a Form Index table to ensure that form content does not get sent to the wrong table if you have Webflow forms with identical names. This is useful for Enhancing your Webflow form submission management. By sending structured data to your Airtable base you can do more with your Webflow forms. Usage guide Full written and video guide This automation is made to be as low effort as possible to start enhancing your Webflow forms. Simply create credentials for Webflow and a Personal Access Token for your Airtable base and connect them to the relevant nodes. The guide demonstrates a realworld example using a Webflow template and breaksdown the flow and logic for all the nodes.
By kreonovoAutomate research-based newsletters with Perplexity, GPT-4, and image generation
This n8n workflow automates the process of creating and sending high-quality newsletters with images generated by a GPT image generator. It is triggered on a schedule. What is included? 1 n8n workflow (json) 1 Setup tutorial doc 1 video guidance on how to connect n8n with all Google products 1 video guidance on how to connect n8n with Google Cloud Storage Who is this for? This template is ideal for: Content creators looking to automate their newsletter process. Marketers seeking to efficiently produce engaging newsletters with AI-generated content and imagery. Anyone wanting to create and send personalized newsletters on a schedule. What problem is this workflow solving? Manually creating and sending newsletters can be time-consuming, especially when including relevant and engaging content and imagery. This workflow automates the content generation (using AI and web search), image creation, and sending process, freeing up time and ensuring consistent communication with clients. What this workflow does: This workflow automates the following steps: Scheduled Trigger: The workflow is triggered automatically on a predefined schedule. Get Newsletter Topic: Retrieves the first unpublished newsletter topic from a Google Sheet titled "Newsletter Topics". It then updates the status of this topic and records the publication date to avoid duplication in future runs. AI Newsletter & Image Generator: This is the core content creation step. It uses an AI agent (configured with OpenAI and Perplexity APIs) to generate an engaging newsletter and a detailed, ultra-realistic image prompt based on the selected topic and real-time web research. GPT Image Generation: Uses the OpenAI API to generate an image based on the detailed image prompt created in the previous step. Get Client List: Retrieves client names and email addresses from a Google Sheet titled "Clients". Send Newsletter: Sends the personalized newsletter via Gmail to each client on the list, including the AI-generated title, content, and the uploaded image. The email body HTML is customizable. Setup: Configure the workflow's run frequency within the "Schedule Trigger" node. Create a Google Sheet named "Newsletter Topics" and "Clients" in your Google Drive. Enter your OpenAI and Perplexity API key in the 'Input' node. Connect your Gmail account to the "SendNewsletter" node. How to customize this workflow: Adjust the prompt for your newsletter style in the "AI Agent" node. Adjust the Email Body HTML for your newsletter style in the "SendNewsletter" node. Optionally, enable the "Tavily WebSearch" node and configure it if you prefer to use Tavily instead of Perplexity for web search. Category: Marketing, Content Creation, Automation
By TianyiAI-powered Zendesk support responses with RAG, OpenAI, and Supabase knowledge base
⚡ How it works This workflow automates first responses to new Zendesk tickets with the help of AI and your internal knowledge base. Webhook trigger fires whenever a new ticket is created in Zendesk. Ticket details (subject, description, requester info) are extracted. Knowledge base retrieval – the workflow searches a Supabase vector store (with OpenAI embeddings) for the most relevant KB articles. AI assistant (RAG agent) drafts a professional reply using the retrieved KB and conversation memory stored in Postgres. Decision logic: If no relevant KB info is found (or if it’s a sensitive query like KYC, refunds, or account deletion), the workflow sends a fallback response and tags the ticket for human review. Otherwise, it posts the AI-generated reply and tags the ticket with ai_reply. Logging & context memory ensure future ticket updates are aware of past interactions. ------ 🔧 Set up steps This workflow takes about 15–30 minutes to set up. Connect credentials for Zendesk, OpenAI, Supabase, and Postgres. Prepare your knowledge base: store support content in Supabase (documents table) and embed it using the provided Embeddings node. Set up Postgres memory table (zendesktickethistories) to store conversation history. Update your Zendesk domain in the HTTP Request nodes (<YOURZENDESKDOMAIN>). Deploy the webhook URL in Zendesk triggers so new tickets flow into n8n. Test by creating a sample ticket and verifying: AI replies appear in Zendesk Correct tags (aireply or humanrequested) are applied Logs are written to Postgres
By Md Sagor KhanGenerate business proposals with Azure GPT-4o & save as Gmail drafts from Sheets
Description: Accelerate your sales cycle with this n8n workflow template that automatically generates professional business proposals and saves them as Gmail drafts—ready to send. No more manual writing or formatting—let AI create polished proposals tailored to each client. This automation pulls client and deal data from Google Sheets, checks if the lead has reached the Proposal stage, and uses AI to draft structured proposals with clear sections like scope, deliverables, pricing, and timelines. The content is automatically formatted into professional HTML, and drafts are saved in Gmail for review and quick sending. What This Template Does: 📊 Retrieves client & lead data from Google Sheets ⚡ Filters deals at the Proposal stage only 🧠 Uses AI to generate client-ready business proposals (subject, scope, deliverables, pricing, etc.) 📝 Cleans and formats AI output into professional HTML proposals 📧 Saves proposals as Gmail drafts for easy review & sending 🌟 100% automated: from deal data to polished draft Built-in Logic Ensures: ✔️ AI proposals always include required sections (scope, deliverables, pricing, timeline, conclusion) ✔️ No extra details are invented—only uses provided client data ✔️ Proposals are styled and formatted for professional email delivery ✔️ Gmail drafts preserve subject + HTML body, ready to send instantly Requirements: Google Sheets with client/deal data (name, email, scope, pricing, stage) Gmail account for draft creation & sending Azure OpenAI (or compatible) account for AI-powered proposal generation n8n instance (self-hosted or cloud) Perfect For: Sales teams preparing client proposals at scale Agencies looking to standardize proposal structure & speed up delivery Startups automating proposal creation from CRM/Sheets Business development teams needing ready-to-send drafts without manual effort
By Rahul JoshiFind the best Roblox server for your game using a webhook and Roblox API
Who For? Gamers who don't like bad and slow preformance playing games and want to find a good preformance based server near them. Setup? None! Modes Available Auto - Optimized (Recommended & Default) Ping - Finds the lowest ping Latency - Lowest ping & highest FPS
By Gwa Shark