Generate & deploy landing pages with GPT, Gemini and Vercel
Needs changesNeeds changes. This template uses 2 thing(s) that n8n 3.0 removes: OpenAI (legacy), Function (legacy). 2 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 20 nodes and runs when a chat message arrives. Along the way it connects Google Gemini and OpenAI. It also calls api.cloudinary.com and api.vercel.com over HTTP.
How it runs
Trigger: When a chat message arrives.
- Get memory for current session (Data table): get
- Prepare Chat Prompt with Memory (Code): runs custom JavaScript code
- Generate Image Prompt (OpenAI): uses OpenAI
- Generate an image (Google Gemini): work with image
- Convert Image to Base (Extract from File): extracts data from a file (binary to propery)
- Format Image as Data URI (Edit Fields (Set)): sets 1 field: file
- Upload Image to Cloudinary (HTTP Request): calls api.cloudinary.com (POST)
- Return Hero Image URL (Code): runs custom JavaScript code
- Generate HTML (OpenAI) (OpenAI): work with chat
- Save HTML to Memory Table (Data table): create or update
…plus 9 more steps. See the full node list below.
Services it uses
HTTP calls to: api.cloudinary.com, api.vercel.com
Before you upgrade to n8n 3.0
2 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- OpenAI (legacy) in Generate HTML (OpenAI): replace with OpenAI node (AI section).
- Function (legacy) in Prepare Vercel Deployment Payload: replace with Code node, mode 'Run Once for All Items'.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| OpenAI (legacy) Generate HTML (OpenAI) | OpenAI node (AI section) |
| Function (legacy) Prepare Vercel Deployment Payload | Code node, mode 'Run Once for All Items' |
Nodes used (11)
- Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - OpenAI
n8n-nodes-base.openAi - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Chat
@n8n/n8n-nodes-langchain.chat - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - Data table
n8n-nodes-base.dataTable - OpenAI
@n8n/n8n-nodes-langchain.openAi - Extract from File
n8n-nodes-base.extractFromFile - Edit Fields (Set)
n8n-nodes-base.set - Function
n8n-nodes-base.function
From the author
Who’s it for This workflow is for: - People who want to quickly launch simple landing pages without paying monthly fees to landing page creators. It’s ideal for rapid prototyping, generation of large amounts of landing pages, testing campaign ideas, or…