Using the new Gemma 3 Model to Generate Photo Captions Locally in Lightroom
Keep it local
Couple of years ago I reviewed a plugin called AnyVision by Jeffrey Friedl that generated all of your photo metadata – captions, titles, keywords, alt-tag – by using Google Gemini. It’s a genuinely useful addition to Lightroom that I used to generate thousands of captions and keywords in my main catalog.
But the problem was that Gemini’s in the cloud and that means sending (a low resolution version of) your photo online for interpretation. Lots of folks are justifiably uneasy about doing that given how the LLMs plundered entire stock photo libraries and any other publicly facing online photographs to train generative imaging models. And while you could get away with generating thousands of captions for nothing under Google’s generative capped system, you still needed an API attached to your credit card in the Google console.
Since then the models have come a long way and it’s now possible to do this sort of automated title and caption generation entirely locally on your machine.
The rest of this one’s for paid subscribers.
Already a paid subscriber or a Patron? Enter the members’ password from your welcome email.
Not a member? Subscribe on Substack or leave a one-off tip.
Also published in RAW & Unfiltered on Substack.
