Amazon's AI video model now capable to generate minutes-long clips

Users can provide prompt up to 4,000 characters long to generate a two-minute long video

Amazons AI video model now capable to generate minutes-long clips
Amazon's AI video model now capable to generate minutes-long clips

Amazon has updated its artificial intelligence (AI) video model, Nova Reel, with the capability to generate long videos.

Amazon on Monday, April 7, announced that users can now make videos up to two minutes long using Nova Reel.

Amazon-owned AI video model competes with OpenAI, Google, and others in what’s fast becoming a crowded market.

In a blog post, AWS developer advocate Elizabeth Fuentes stated that the latest Nova Reel, Nova Reel 1.1, can generate “multi-shot” videos with “consistent style” across shots.

Related: Amazon launches cutting-edge 'Buy for Me' AI-powered shopping assistant

Users can provide a prompt up to 4,000 characters long to generate up to a two-minute video composed of six-second shots.

Nova Reel 1.1 also introduced a new mode called “Multishot Manual," in which the model can reference an image along with a prompt to offer more control over a video shot’s composition.

According to Fuentes, given a 1280 x 720-resolution image and 512-maximum-character prompt, Multishot Manual can generate videos containing up to 20 shots.

To note, Nova Reel is only available through AWS platforms and services, including Bedrock, Amazon’s AI dev suite, and customers must request access.

It is worth mentioning that Amazon hasn’t announced the source of Reel’s training data, nor has it provided an explicit way for creators possibly feeding the models’ datasets with their videos to opt-out.

Meanwhile, the company has said that it will protect any AWS customers accused of violating copyright with media generated by its models, in keeping with its indemnification policy.

Related: New ARK app introduced to protect artists work from AI-generated content