- Amazon's Nova Reel 1.1 update enables the creation of AI-generated videos up to two minutes in length.
- The model supports multi-shot videos with a consistent style across sequences.
- Amazon's advancement intensifies competition in the generative video AI sector, challenging OpenAI and Google.
Amazon announced its newest AI generation of foundation model, Amazon Nova Reel 1.1 at Amazon re:Invent 2024.
Nova Reel 1.1 provides quality and latency improvements in 6-second shot video generation, in contrast to Amazon Nova Reel 1.0.
Nova Reel remains exclusive to Amazon Web Services (AWS) platforms, including Amazon Bedrock, the company's AI development suite.
With this update, users can generate multi-shot videos up to 2 minutes in length with consistent style across shots. Users can also input prompts up to 4000 characters and compose videos generated through compiling multiple six-second shots.
"This update lets you generate multi-shot videos up to 2-minutes in length with consistent style across shots," the official blog statement said.
"You can either provide a single prompt for up to a 2-minute video composed of 6-second shots, or design each shot individually with custom prompts. This gives you new ways to create video content through Amazon Bedrock."
By leveraging the usage of generative AI, Amazon is taking on models from Google, OpenAI and many such rivals in a fast-evolved industry.
The standout mode in Nova Reel 1.1, "Multishot Manual" can reference an image along with a prompt to offer more direct control over a video shot's composition. The user can specify a unique prompt for an individual shot.
This mode supports videos containing up to 20 shots when provided with a 1280 x 720-resolution image and a concise prompt.
Designed to enhance creative workflows, employing consistent visuals and timing, using natural language-based controls, Amazon Nova Reel also helps to reduce the time and cost of video production while stepping up video quality.
Edited by Harshajit Sarmah
