AWS Security ChangesHomeSearch

AWS nova documentation change

Service: nova · 2025-04-16 · Documentation low

File: nova/latest/userguide/prompting-vision-prompting.md

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:
+