Amazon Bedrock Guardrails supports multimodal toxicity detection for image content (Preview)
News
Amazon Bedrock Guardrails has introduced a new multimodal toxicity detection feature for image content, now in public preview.
- Enables content filtering for potentially harmful images across multiple industries
- Supports detection of undesirable content in categories like hate, sexual, and violence
- Available with all foundation models supporting images in 11 AWS regions
- Removes manual image evaluation processes for organizations
- Provides configurable content detection thresholds
This capability allows organizations to build more responsible generative AI applications with comprehensive content safeguards for both text and image data.
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 now supports multimodal toxicity detection with image support (preview)
Jul 11
2025
2025
Uphold ethical standards in fashion using multimodal toxicity detection with Amazon Bedrock Guardrails
Mar 28
2025
2025
Amazon Bedrock Guardrails announces the general availability of industry-leading image content filters
Mar 28
2025
2025
Amazon Bedrock Guardrails image content filters provide industry-leading safeguards, helping customer block up to 88% of harmful multimodal content: Generally available today
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.