A Lightroom Classic plugin to fill keywords, image title, caption and Alt Text by using ChatGPT, Gemini or local Ollama.

Currently Available models

There is a poll at GitHub, on which AI models you prefer most. Please share your likings! :-)

ChatGPT	Gemini	Ollama
gpt-4.1-nano	1.5pro	gemma3
gpt-4.1-mini	2.0-flash	llama3.2-vision
gpt-4.1	2.0-flash-lite	mistral-small3.1
gpt-4o-mini	2.5pro	deepseek-r1
gpt-4o		llava

Privacy

If your concerned about the privacy of your images, using Ollama might be a good idea. This way your images stay on your hardware. Also the use of ChatGPT or Gemini on will generate costs. Depending on your hardware and internet connection either Ollama or Gemini/ChatGPT can be faster.

Download the plugin

Download

Installation

Installation guide

Usage

• Install plugin using Lightroom addon module manager.
• Obtain an API key for the model you want to use or install Ollama:
  • Obtain Google Gemini API key
  • Obtain ChatGPT API key
  • Download and setup Ollama on your local machine
• Configure API key in Lightroom module manager. (Not needed for Ollama.)
• Choose the model you want to use on the Lightroom module manager.
• Go to Library in Lightroom
• Select some photos
• Go to menu -> Library -> Addon Modules -> Analyze photo(s) with AI
• If enabled a preflight dialogs pops up, where the settings for the batch run can be set/verified.
• Also if enabled, a photo context dialog pops up for every photo, with a preview of the image and a text box to enter additional information for the specific image. This drastically improves the results.
• If enabled review before save for title, caption or Alt Text and the field is already filled with data, a review dialog will show up. There is not (yet) a dialog for reviewing keywords.
• Wait it to fill your keywords, caption, title and Alt Text as selected.
• The plugin is designed to stop only on fatal errors.

Troubleshooting

If you run into troubles, best thing to do is check the log file. Easiest way to find the log file, is by opening the Lightroom module manager, navigate to the AI Assitant plugin, and enable debug logging. There’s also a button Show log file. If nothing helps, open an issue over at GitHub.

Notes

• All generated keywords are hierarchically beneath a top keyword “Google Gemini”, “ChatGPT” or “Ollama”. The hierarchy beyond can be edited in “Library -> Addon Modules -> Edit Keyword Categories”. You can easily remove all keywords generated by the plugin, by deleting the top keyword in Lightroom’s keyword list. Additionally you can create smart collections with filters for top keyword to keep track of photos that have or haven’t been analyzed yet.
• Feel free to open issues or discussions. Any feedback is welcome.

Credits

• All contributors
• Guillermo Esteves for his plugin, which gave me the idea for this one, and on which the source code is based on.
• Enrique García Cota for inspect.lua
• Jeffrey Friedl for JSON.lua