Amazon Enhances Nova Reel AI for Longer Video Generation

Amazon has enhanced its Nova Reel AI model, allowing it to generate videos up to two minutes in length. This update, announced in a company blog post, introduces Nova Reel 1.1, which supports multi-shot videos with consistent style across shots. Users can provide a prompt of up to 4,000 characters to create a video composed of six-second shots.

Nova Reel 1.1 also features a new 'Multishot Manual' mode, enabling users to reference an image along with a prompt for more control over video composition. This mode allows for up to 20 shots per video, using images with a resolution of 1280 x 720. The model is accessible through AWS platforms, including Amazon Bedrock, and requires users to request access, which is automatically approved.

The Nova Reel model is designed to enhance creative productivity by reducing the time and cost of video production. It is available in the US East (N. Virginia) AWS Region and follows a pay-as-you-go pricing model. However, Amazon has not disclosed the source of the training data for Nova Reel, raising questions about the ethical considerations of its development.