Object detection with Amazon Nova 2 Lite
Amazon Nova 2 Lite enables zero-shot object detection via natural language prompts with no model training required.
“This multimodal foundation model detects objects through natural language prompts with no training required.”
An AWS tutorial demonstrates using Amazon Nova 2 Lite through Bedrock for zero-shot object detection, returning bounding boxes in structured JSON from natural language prompts without training or ML infrastructure. It matters as a sign of foundation models displacing traditional purpose-built computer vision pipelines, lowering the cost and expertise barrier (~$5.69 per 10,000 images), but it is a vendor how-to rather than a major industry announcement.