A batch image captioning tool powered by AI vision models. Supports multiple providers including Google Gemini, OpenRouter, and local Ollama models. Drag images and you get captions! Features Multi-provider support: Gemini (Direct), OpenRouter, and Ollama (local) Batch processing: Caption multiple images with configurable concurrency Drag & drop: Drag images directly into the browser Auto-translation: Automatic translation (Chinese/Japanese) Editable captions: Click to edit generated captions and translations Image preview: Click to enlarge images Customizable prompts: Adjust caption style (natural/precise) and length (short/long/very-detailed) Export: Download captions as ZIP file Real-time progress: Track processing with stop/cancel support

Image Captioner Pro

Drag images and you get captions!

Drag images and you get captions!