AWS – Introducing Stable Diffusion 3.5 Large in Amazon Bedrock

Stability AI’s Stable Diffusion 3.5 Large (SD3.5 Large) is now available in Amazon Bedrock. SD3.5 Large is an advanced text-to-image model featuring 8.1 billion parameters. Trained on Amazon SageMaker HyperPod, this powerful model will enable AWS customers to generate high-quality, 1-megapixel images from text descriptions with superior accuracy and creative control.

The model excels at creating diverse, high-quality images across multiple styles, making it valuable for media, gaming, advertising, ecommerce, corporate training, retail, and education industries. Its enhanced capabilities include exceptional photorealism with detailed 3D imagery, superior handling of multiple subjects in complex scenes, and improved human anatomy rendering. The model also generates representative images with diverse skin tones and features without requiring extensive prompting. Today, Stable Image Ultra in Amazon Bedrock has been updated to include Stable Diffusion 3.5 Large in the model’s underlying architecture.

Stable Diffusion 3.5 Large is now available in Amazon Bedrock in the US West (Oregon) AWS region. To learn more read the AWS News Blog or visit the Stability AI in Amazon Bedrock product page, and documentation. To get started with SD3.5 Large, visit the Amazon Bedrock console.

Read More for the details.