How to Automate Google Drive Image Keywords?
Description
Tired of untagged photos piling up in Drive? Turn every new image into a searchable asset with automatic keywords written into the file. Ideal for marketing teams, agencies, and ecommerce shops that need fast, consistent tagging.
A Google Drive event watches a chosen folder and picks up each new image. The file is downloaded and converted to base64 so an AI vision model can read it and return a clean, comma separated list of keywords. That output is merged with the file data, and a code step writes the list into XMP dc:subject inside the image. The file is then converted back to binary and the original item in Drive is updated in place. Links and sharing settings stay the same while the content gets smarter.
You only need a Google Drive connection and an AI API key to get started. Expect manual tagging to drop from minutes per file to seconds while search accuracy and reuse improve across your library. Works well for product catalogs, event galleries, brand archives, and social content folders.
Tools Required
What this workflow does?
- Watches a specific Google Drive folder and picks up new files every minute
- Downloads the image and converts it to base64 for AI analysis
- Uses an AI vision model to return a comma separated list of keywords
- Merges AI keywords with the file data for a single clean payload
- Writes keywords into XMP dc:subject using a code step
- Converts the edited base64 back into a binary image file
- Updates the original Google Drive file in place with new metadata
What are the benefits?
- Reduce manual tagging from 2 minutes per image to under 10 seconds
- Automate about 90 percent of repetitive tagging work
- Improve findability and search accuracy by 50 percent
- Handle 10 times more images without extra staff
- Connect Google Drive and OpenAI with no manual exports
- Keep file names and links unchanged while adding metadata
How to set this up?
- Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
- You'll need accounts with Google Drive and OpenAI. See the Tools Required section above for links to create accounts with these services.
- Open the Google Drive Trigger node and in the Credential to connect with field click Create new credential. Follow the on screen steps to sign in with Google and grant Drive access. Name the credential clearly, for example Google Drive Prod.
- In the same trigger node, choose the folder to watch and keep the polling interval at every minute or adjust to your needs.
- Open the Download Image File and Update Image File nodes. Select the same Google Drive credential so both nodes use the correct account and permissions.
- Open the Analyze Image Content node. In Credential to connect with click Create new credential for OpenAI, then paste your API key from your OpenAI account API page. Select the model chatgpt 4o latest if not already set.
- Check the Extract from File node and confirm that the binary is converted to a property named data. Then open the Convert to File node and confirm sourceProperty is set to data.
- Open the Update Image File node and make sure Change File Content is enabled, File ID is mapped from the Download Image File node, and New Updated File Name uses the original name.
- Run a test by adding a small JPEG to the watched Google Drive folder. Wait up to one minute and confirm the file updates. Download it and check the file properties to see the new keywords in the tags field.
- If keywords do not appear, confirm that the Analyze Image Content node returns a content field with comma separated values, check your OpenAI key and usage limits, make sure your image format supports XMP metadata, and review execution logs in n8n for any errors.
Need help or want to customize this?
Ask in the Free Futurise Community.
Similar Templates
Credits: Friedemann Schuetz - these templates were sourced from publicly available materials across the web, including n8n’s official website, YouTube and public GitHub repositories. We have consolidated and categorized them for easy search and filtering, and supplemented them with links to integrations, step-by-step setup instructions, and personalized support in the Futurise community. Content in this library is provided for education, evaluation and internal use. Users are responsible for checking and complying with the license terms with the author of the templates before commercial use or redistribution. If you are the author and would like this template removed from the template library, email us at info@futurise.com and we will remove it promptly.
