Amazon Bedrock Guardrails now supports multimodal toxicity detection with image support (preview)
AWS News Blog
Amazon Bedrock Guardrails has launched a preview feature for multimodal toxicity detection with image support, enhancing content safety for generative AI applications.
- Detects and filters undesirable image content across categories like hate, insults, sexual, and violence
- Allows configuration of toxicity detection thresholds from low to high
- Works with all foundation models in Amazon Bedrock that support image data
- Provides a consistent layer of protection across text and image modalities
- Available in multiple AWS regions during preview
Users can create and test guardrails in the AWS Management Console, configuring content filters for text and image data to build more responsible AI applications.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Dec 4
2024
2024
Amazon Bedrock Guardrails supports multimodal toxicity detection for image content (Preview)
Dec 3
2024
2024
Amazon Bedrock Guardrails now supports Automated Reasoning checks (Preview)
Jul 11
2025
2025
Uphold ethical standards in fashion using multimodal toxicity detection with Amazon Bedrock Guardrails
Apr 23
2024
2024
Guardrails for Amazon Bedrock now available with new safety filters and privacy controls
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.