As announced during AWS re:Invent 2024, Luma AI’s Ray2 video model is now available in Amazon Bedrock, enabling users to generate high-quality video clips from text prompts. AWS is the first and only cloud provider to offer fully managed models from Luma AI, revolutionizing video generation workflows.
What is Luma Ray2?
On January 16, 2025, Luma AI introduced Luma Ray2, a groundbreaking large-scale video generative model designed to create realistic visuals with smooth, coherent motion. Built on Luma’s advanced multi-modal architecture, Ray2 offers ten times the computing power of its predecessor, Ray1, allowing it to produce stunning 5- to 9-second video clips with resolutions of 540p and 720p.
The model excels at understanding natural language prompts, accurately capturing the interactions between people, animals, and objects to generate consistent, realistic, and physically accurate scenes. With Ray2, users can create high-quality, production-ready videos for applications in content creation, entertainment, advertising, and media.
Features and Use Cases
- Dynamic Camera Movements: Ray2 generates cinematic, lifelike camera angles that convey the desired emotion of a scene.
- Creative Flexibility: Experiment with various styles, perspectives, and animations for industries like architecture, fashion, film, and graphic design.
- Text-to-Video Generation
Examples include:
- A humpback whale swimming through space particles
- A baby cat exploring on the surface of a fingertip
- A massive orb of water floating in a backlit forest
- A macro closeup of a bee pollinating
These capabilities streamline the creative process, from concept to execution, allowing users to produce visually stunning videos in minutes.
Getting Started with Luma Ray2 on Amazon Bedrock
To begin using Luma Ray2:
- Log into the Amazon Bedrock console and request access to the Luma Ray2 model.
- Navigate to the Playgrounds section, select Image/Video, and choose Ray2 under the Luma AI category.
- Ensure you have an Amazon S3 bucket to store the generated videos. Amazon Bedrock will automatically handle the bucket permissions.
- Input your prompt and desired video configuration (e.g., resolution, frames per second, and duration). For instance:
- Prompt: A humpback whale swimming through space particles
- Output: A 5-second 720p video at 24 frames per second in a 16:9 aspect ratio
Generated videos are stored in your S3 bucket, and you can view or download them directly.
API Integration
For developers, the model can be accessed programmatically using the AWS CLI or AWS SDKs. The model ID luma.ray-v2:0 allows seamless integration into applications. Below is a sample AWS CLI command:
aws bedrock-runtime invoke-model \ --model-id luma.ray-v2:0 \ --region us-west-2 \ --body "{\"modelInput\":{\"taskType\":\"TEXT_VIDEO\",\"textToVideoParams\":{\"text\":\"a humpback whale swimming through space particles\"},\"videoGenerationConfig\":{\"seconds\":6,\"fps\":24,\"dimension\":\"1280x720\"}},\"outputDataConfig\":{\"s3OutputDataConfig\":{\"s3Uri\":\"s3://your-bucket-name\"}}}"
You can also use Converse API examples with AWS SDKs to build video-generation applications in various programming languages.
Availability and Pricing
The Luma Ray2 video model is now generally available in the US West (Oregon) AWS Region, with plans to expand to additional regions in the future. Visit the Luma AI on Amazon Bedrock product page and the Amazon Bedrock Pricing page for more details.
Watch the Luma Introduction video here: https://youtu.be/lIKRRRhHN2U
Try It Today
Start using Luma Ray2 in the Amazon Bedrock console today. Share your feedback through AWS re:Post for Amazon Bedrock or contact AWS Support. Explore how Luma Ray2 can bring your creative vision to life with cutting-edge text-to-video generation!