Image Input Node
The Image Input Node enables visual content analysis using computer vision, OCR text extraction, and multi-modal AI understanding.
Vision Capabilities
- Image Analysis: Describe and understand image content
- OCR: Extract text from images and screenshots
- Object Detection: Identify objects, faces, and landmarks
- Visual Q&A: Answer questions about image content
Supported Formats
PNG, JPG, JPEG, WebP, GIF, BMP, SVG