Docs/Visual Tagging

Visual Tagging

Visual Tagging is an optional add-on that extracts rich, searchable metadata from every photo — scene type, shooting technique, weather conditions, and more. It costs +0.5 tokens per image on top of standard analysis and transforms your archive into a searchable library.

What It Extracts

When Visual Tagging is enabled, the AI analyzes each image and generates structured tags across several dimensions:

🎬 Scene Type

On-track action, pit stop, pit lane, podium, grid walk, press conference, paddock, aerial, technical detail

📸 Technique

Panning shot, static shot, portrait, close-up, wide-angle, overhead, reflection, silhouette

🌦️ Context & Conditions

Rain, sunset, golden hour, night, spray, sparks, smoke, overtake moment, crash/incident, celebration

📍 Location & Subject

Track section, grandstand, garage, tire wall, gravel trap. Also identifies multiple subjects, fans, team personnel

For Photographers

Visual tags make it dramatically easier to find specific shots weeks or months later. Instead of scrolling through thousands of thumbnails, you can search your archive semantically:

  • Find all panning shots for your portfolio
  • Pull every podium celebration for a year-end recap
  • Isolate rain shots across multiple events
  • Locate pit stop sequences for a technical feature
  • Search for sunset/golden hour images for social media

Pro tip: Tags are written into IPTC metadata keywords, so they're searchable in Lightroom, Photo Mechanic, Capture One, and any DAM system that reads IPTC data.

For Social & Marketing Teams

If you deliver photos to social media managers, press offices, or marketing teams, Visual Tagging is a game-changer. Your clients can filter the gallery by exactly what they need:

  • “I need a panning shot of car #33 for Instagram” — search panning + #33
  • “Get me all podium photos for the press release” — filter by podium tag
  • “Find dramatic rain shots for the season review” — filter rain + action

This eliminates the back-and-forth of “can you send me that shot where...” — the tags make the entire archive self-service for your clients and collaborators.

Cost & How to Enable

Visual Tagging adds +0.5 tokens per image to your standard analysis cost. For a typical batch of 500 photos, that's 250 extra tokens.

To enable it, go to the Analysis page and look for the purple Visual Tagging section below the 3-step setup. Toggle the “Enable visual tagging” switch. That's it — tags will be generated alongside your normal race number analysis.

When to enable: Best for events where you'll need to search your archive later, or when delivering to clients/teams who need to self-serve. For quick personal edits where you already know which shots you want, you can skip it to save tokens.