Easy captioning of photos with Gemini 1.5
Workflow Description
An automation that leverages Gemini 1.5 to intelligently generate and apply captions to images. The workflow analyzes image content, produces descriptive text, and adds the captions automatically, eliminating manual annotation tasks.
How it works
- 1.Trigger the automation manually and upload the target image
- 2.Send the image to Gemini 1.5 for content analysis and caption generation
- 3.Parse and structure the model's response into organized data
- 4.Edit and embed the generated caption directly onto the image
- 5.Merge results and transmit via HTTP request for storage or downstream processing
Use cases
- Batch-process image libraries with automatic, AI-generated captions
- Enhance searchability and discoverability of image collections
- Streamline content workflows for marketing, social media, and digital asset management
Requirements
- Valid Google Cloud API key with Gemini access enabled
- Images in standard formats (JPG, PNG) within model size constraints
- Basic understanding of LLM chain parameters and prompt engineering
Service Value
Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (16)
When clicking ‘Test workflow’
Manual Trigger
Google Gemini Chat Model
Gemini Model
Structured Output Parser
Output Parser Structured
Get Info
Edit Image
Resize For AI
Edit Image
Calculate Positioning
Code
Apply Caption to Image
Edit Image
Sticky Note
Sticky Note
Merge Image & Caption
Merge
Merge Caption & Positions
Merge
Get Image
HTTP Request
Sticky Note1
Sticky Note
Sticky Note2
Sticky Note
Sticky Note3
Sticky Note
Sticky Note4
Sticky Note
Image Captioning Agent
LLM Chain