AWS nova documentation change
Summary
Added documentation for bounding box detection feature in Amazon Nova, including usage instructions and sample prompt format
Security assessment
Change introduces a new feature (bounding box detection) but contains no security-related content or references to vulnerabilities
Diff
diff --git a/nova/latest/userguide/prompting-vision-prompting.md b/nova/latest/userguide/prompting-vision-prompting.md index 4c8d285b5..b80a00d9e 100644 --- a//nova/latest/userguide/prompting-vision-prompting.md +++ b//nova/latest/userguide/prompting-vision-prompting.md @@ -5 +5 @@ -Placement mattersMultiple media filesImproved instruction followingRicher outputs or style +Placement mattersMultiple media filesImproved instruction followingBounding box detectionRicher outputs or style @@ -18,0 +19,2 @@ The following vision prompting techniques will help you create better prompts fo + * Bounding box detection + @@ -103,0 +106,16 @@ The following template can be used to for improved instructions: +## Bounding box detection + +If you need to identify bounding box coordinates for an object, you can utilize the Amazon Nova model to output bounding boxes on a scale of [0, 1000). After you have obtained these coordinates, you can then resize them based on the image dimensions as a post-processing step. For more detailed information on how to accomplish this post-processing step, please refer to the [Amazon Nova Image Grounding notebook](https://github.com/aws-samples/amazon-nova-samples/blob/main/multimodal-understanding/repeatable-patterns/13-image-grounding/image_grounding.ipynb). + +The following is a sample prompt for bounding box detection: + + + Detect bounding box of objects in the image, only detect {item_name} category objects with high confidence, output in a list of bounding box format. + Output example: + [ + {"{item_name}": [x1, y1, x2, y2]}, + ... + ] + + Result: +