Generate marketing images in a webhook image studio with Google Gemini
Ready for 3.0What this workflow does
This AI workflow has 18 nodes and runs when an HTTP GET request hits its webhook URL. Along the way it connects Google Gemini.
How it runs
Trigger: When an HTTP GET request hits its webhook URL.
- Settings (UI) (Edit Fields (Set)): sets 5 fields: ui_title, ui_subtitle, max_images…
- Settings (generator) (Edit Fields (Set)): sets 3 fields: gemini_model, max_images, max_file_mb
- Build studio page (Code): runs custom JavaScript code
- Validate & build prompt (Code): runs custom JavaScript code
- Respond with studio page (Respond to Webhook): sends the response back to the webhook caller
- Request valid? (If): checks a condition and branches into true / false
- How many images? (Switch): routes items into 3 branches
- Respond 400 (bad request) (Respond to Webhook): sends the response back to the webhook caller
- Gemini: text to image (Google Gemini): work with image
- Gemini: edit 1 image (Google Gemini): edit (image)
…plus 7 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (8)
- Webhook
n8n-nodes-base.webhook - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - Respond to Webhook
n8n-nodes-base.respondToWebhook - If
n8n-nodes-base.if - Switch
n8n-nodes-base.switch - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - Merge
n8n-nodes-base.merge
From the author
Quick overview This workflow serves a self-hosted HTML “Image Studio” via webhook and uses Google Gemini to generate or edit images from one or two reference uploads, returning the result as a downloadable data URL with prompt and metadata. How it works 1.…