Image Captioner and Tagger - AI-Powered Visual Analysis Tool
Overview
A web-based application that uses Google Gemini AI to automatically generate descriptive captions and tags for images. Perfect for generation, dataset, and anyone needing quick visual image analysis.
Link -
Key Features
Multiple Generation Types: Create descriptive captions, comma-separated tags, or weighted prompts for AI art generation
Batch Processing: Upload and process multiple images simultaneously with customizable delays
Smart Export Options:
Standard text/JSON output
Auto-rename files for sequential organization
Kohya_SS structure for LoRA training datasets
Advanced Controls:
Adjustable AI creativity levels (precise to creative)
Custom trigger words and prompt enrichment
Word count limits and formatting options
Usage Tracking: Built-in quota monitoring for Google's free tier API limits
Technical Requirements
Google Gemini API key (free tier available)
Modern web browser
No installation required - runs entirely in browser
Transform your visual content workflow with AI-powered automation that saves hours of manual description writing.

