ImageCatty: Photo And Video Cataloging With AI Support

Introduction

ImageCatty is a desktop application for Windows that helps professional photographers and videographers organize archives, fill in metadata, manage stock release workflows, and automate repetitive catalog work with AI support.

The focus is not on a generic gallery. The focus is on a production workflow where large libraries, metadata quality, and review discipline matter every day.

Supported File Formats

ImageCatty works with the file types that usually define real media libraries rather than toy examples. The goal is to let teams review mixed archives without splitting the workflow across separate viewers and metadata tools.

• Photos: JPG, PNG, GIF, BMP, WebP, TIFF, HEIC, HEIF, and AVIF.
• RAW files: NEF, CR2, CR3, ARW, DNG, ORF, RW2, and RAF, with broad camera support out of the box.
• Video: MP4, MOV, WebM, MKV, AVI, and M4V.

Main Window

The interface is split into three working zones so operators can move between folders, gallery review, and metadata editing without losing context.

• Left side: a folder tree for local folders and network resources, with missing disks or unavailable locations marked visually and with context-menu actions for creating, renaming, deleting, dragging, and reindexing folders.
• Center: a file gallery with breadcrumb navigation, direct path entry, sorting, filtering, grouping, and a thumbnail size slider for fast browsing.
• Right side: a metadata panel that can stay docked, collapse, float, or move into a separate window depending on the review setup.

Search

Search opens with Ctrl+F and expands into a live query bar with immediate results. Alongside plain text, the product supports structured filters that let operators narrow down large collections without depending on memory or folder structure alone.

• date:2025-01 for capture month filtering.
• type:raw for RAW-only results.
• release:ready for files with release status already prepared.
• camera:"Canon EOS R6", lens:"24-70", and iso:400 for capture details.
• keywords:beach, path:travel, and filename:IMG for metadata, path, and naming filters.

Metadata Panel

The metadata panel is a full file card editor rather than a passive inspector. Information is split into practical tabs so technical data, editorial metadata, release state, and AI drafts remain understandable.

• EXIF and IPTC: technical capture information plus editable title, description, keywords, and authorship fields with validation during input.
• File: size, resolution, codec, and duration details for video.
• Releases: model and property release state, linked people and objects, and validation status.
• Stocks: upload status by platform with manual status updates.
• AI: draft title, description, categories, and keywords suggested by the model and ready for review.

AI Metadata Generation

ImageCatty can generate metadata automatically for single files or large batch selections. Before running a job, the operator can control the language and tone of the descriptions, target keyword count, mandatory and forbidden terms, scene hints, and a single-word-only mode for stock workflows.

Results are not applied automatically. The application shows drafts, scores their quality, highlights weaker outputs, and explains the reasoning behind the generated metadata so the user can accept, edit, rerun, or reject each result before anything touches the files.

The system supports three AI backend options: a local model that works offline, an external or LAN server, and a cloud option through OpenRouter.

Releases

The releases area is built for stock-oriented workflows where permissions and legal completeness matter as much as descriptive metadata. The library keeps reusable records so operators do not rebuild the same release context for every shoot.

Each release document is validated automatically, and the product flags missing fields or mismatches against the chosen validation profile. Those profiles cover general commercial requirements and guidance aligned with Adobe Stock, Shutterstock, and editorial content workflows.

• People: name, legal status, age category, and guardians when needed.
• Property: owner, location, and release requirements.
• Groups: reusable sets of people for team or multi-subject shoots.
• Bulk assignment: attach release documents to folders or large selections using defined criteria.

Stock Platform Status

Each file keeps a table of upload status by platform. Platforms are configured manually, and ImageCatty does not push directly into stock websites, but it gives the team one control surface for tracking where a file has already been submitted and what still needs attention.

That matters because operational clarity is often more valuable than partial automation when the business process crosses several external systems.

Background Indexing

ImageCatty indexes catalogs automatically in the background while the application is idle. That keeps search fast and metadata availability current without making the operator stop work to maintain the index manually.

Indexing can also be forced, paused, scoped by exclusion rules, or rebuilt from scratch when the dataset changes in a bigger way.

Working With Files

Standard file operations such as copy, cut, paste, rename, delete, and folder creation are available from the context menu and hotkeys, with drag-and-drop supported between folders.

When naming conflicts appear, the application shows a side-by-side visual comparison of the two files and offers practical choices: overwrite, rename the incoming file, or skip it. The same decision can be applied to all conflicts in the batch.

Viewer Mode

If a user opens a photo or video directly from Windows Explorer, ImageCatty can start in a lighter viewer mode without loading the full catalog. That keeps ad hoc viewing fast while leaving the full archive workflow available when it is actually needed.

Conclusion

ImageCatty is designed for media libraries that have already outgrown casual desktop viewers. It brings file browsing, structured search, metadata editing, release management, and AI-assisted enrichment into one local-first workflow.

For teams working with large archives, that combination is what keeps the catalog usable instead of turning it into another slow operational burden.