VisionTagger

VisionTagger delivers comprehensive image metadata generation directly on your Mac, prioritizing privacy and local processing. Key features include: • Generates captions, keywords, and structured metadata • All processing occurs locally; no uploads or subscriptions • Customizable metadata schema with built-in and custom fields • Exports metadata in XMP, JSON, or TXT formats • Direct integration with Photos Library and Finder tags This application revolutionizes how photographers, designers, and content managers handle image organization. It leverages the power of Apple Silicon Macs (macOS 26 Tahoe+) to process images swiftly and securely without relying on cloud services. Users can define exactly what metadata to extract, from basic captions and keywords to highly specific content and style descriptors, ensuring consistency across their entire image library. VisionTagger offers flexibility in model selection, allowing users to download preconfigured vision models or integrate their own GGUF models. Adjustable parameters enable fine-tuning of metadata generation for precise, repeatable results. The tool eliminates concerns about data privacy and recurring costs, making it an ideal choice for professionals and enthusiasts who demand control over their digital assets. A free trial for up to 100 images is available. Designed for individual users and small teams who require robust, local image cataloging. Perfect for those needing meticulous image organization for portfolios, digital archives, or content management systems without external dependencies.