AWS nova medium security documentation change
Summary
Updated feature descriptions for Amazon Nova Canvas, including additions for content provenance verification and invisible watermarking. Expanded regions list and minor formatting changes.
Security assessment
The addition of 'Watermarking' explicitly addresses security concerns by introducing invisible watermarks to reduce misinformation, protect copyright, and track content usage. The 'Content provenance' section also adds security documentation by enabling verification of image origins. These changes directly relate to security features aimed at content authenticity and misuse prevention.
Diff
diff --git a/nova/latest/userguide/image-generation.md b/nova/latest/userguide/image-generation.md index 48fcb87b5..13e4743d3 100644 --- a//nova/latest/userguide/image-generation.md +++ b//nova/latest/userguide/image-generation.md @@ -5 +5 @@ -# Generating images with Amazon Nova +# Generating images with Amazon Nova Canvas @@ -7 +7 @@ -With the Amazon Nova Canvas model, you can generate realistic, studio-quality images by using text prompts. You can use the Amazon Nova Canvas for text-to-image and imaging editing applications. +With the Amazon Nova Canvas model, you can generate realistic, studio-quality images by using text prompts. You can use Amazon Nova Canvas for text-to-image and imaging editing applications. @@ -9 +9 @@ With the Amazon Nova Canvas model, you can generate realistic, studio-quality im -Amazon Nova canvas supports the following features: +Amazon Nova Canvas supports the following features: @@ -13 +13 @@ Amazon Nova canvas supports the following features: - * Image editing options – include: inpainting, outpainting, generating variations, and automatic editing without an image mask. + * Image conditioning – Uses an input reference image to guide image generation. The model generates output image that aligns with the layout and the composition of the reference image, while still following the textual prompt. @@ -15 +15 @@ Amazon Nova canvas supports the following features: - * Inpainting – Uses an image and a segmentation mask as input (either from the user or estimated by the model) and reconstructs the region within the mask. Use inpainting to remove masked elements and replace them with background pixels. + * Color guided content – You can provide a list of hex color codes along with a prompt. A range of 1 to 10 hex codes can be provided. The image returned will incorporate the color palette provided by the user. @@ -17 +17 @@ Amazon Nova canvas supports the following features: - * Outpainting – Uses an image and a segmentation mask as input (either from the user or estimated by the model) and generates new pixels that seamlessly extend the region. Use precise outpainting to preserve the pixels of the masked image when extending the image to the boundaries. Use default outpainting to extend the pixels of the masked image to the image boundaries based on segmentation settings. + * Image variation – Uses 1 to 5 images and an optional prompt as input. It generates a new image that borrows characteristics from the reference images including style, color palette, and subject. @@ -19 +19 @@ Amazon Nova canvas supports the following features: - * Image variation – Uses 1 to 5 images and an optional prompt as input. It generates a new image that preserves the content of the input images, but varies its style and background. + * Inpainting – Uses an image and a segmentation mask as input (either from the user or estimated by the model) and reconstructs the region defined by the mask. Use inpainting to replace masked pixels with new generated content. @@ -21 +21 @@ Amazon Nova canvas supports the following features: - * Image conditioning – Uses an input reference image to guide image generation. The model generates output image that aligns with the layout and the composition of the reference image, while still following the textual prompt. + * Outpainting – Uses an image and a segmentation mask as input (either from the user or estimated by the model) and generates new content that seamlessly extends the masked region, effectively replacing the image background. @@ -23 +23 @@ Amazon Nova canvas supports the following features: - * Subject consistency – Subject consistency allows users to fine-tune the model with reference images to preserve the chosen subject (for example, pet, shoe, or handbag) in generated images. + * Background removal – Automatically identifies multiple objects in the input image and removes the background. The output image has a transparent background. @@ -25 +25 @@ Amazon Nova canvas supports the following features: - * Color guided content – You can provide a list of hex color codes along with a prompt. A range of 1 to 10 hex codes can be provided. The image returned will incorporate the color palette provided by the user. + * Subject consistency – Subject consistency is achieved by fine-tuning the model with reference images to preserve the chosen subject (for example, pet, shoe, or handbag) in generated images. @@ -27 +27 @@ Amazon Nova canvas supports the following features: - * Background removal – Automatically identifies multiple objects in the input image and removes the background. The output image has a transparent background. + * Content provenance – Use publicly available tools such as [Content Credentials Verify](https://contentcredentials.org/verify) to check if an image was generated by Amazon Nova Canvas. This should indicate the image was generated unless the metadata has been removed. @@ -29 +29 @@ Amazon Nova canvas supports the following features: - * Content provenance – Use sites like [Content Credentials Verify](https://contentcredentials.org/verify) to check if an image was generated by Amazon Nova Canvas. This should indicate the image was generated unless the metadata has been removed. + * Watermarking – Adds an invisible watermark to all generated images to reduce the spread of misinformation, assist with copyright protection, and track content usage. Watermark detection is available to help you confirm whether an image was generated by an Amazon Nova model, which checks for the existence of this watermark. . @@ -36 +35,0 @@ Amazon Nova canvas supports the following features: -Model Characteristics | @@ -51,2 +50 @@ Supported Languages | English -Regions | US East (N. Virginia) -Bedrock Feature Support | +Regions | US East (N. Virginia), Europe (Ireland), and Asia Pacific (Tokyo) @@ -54,2 +52,2 @@ Invoke Model API | Yes -Fine Tuning | Yes -Provisioned Throughput | No +Fine-tuning | Yes +Provisioned throughput | No