Skip to main content

Build creative applications with Amazon Nova

High-quality image and video generation models

Amazon Nova Creative Models

Amazon Nova models include Amazon Nova Canvas for image generation and Amazon Nova Reel for video generation. These models are designed to generate high-quality images and videos from text and image inputs, providing unparalleled creative flexibility and scalability. Through seamless integration with AWS services such as Amazon S3 and simple pay-as-you-go pricing, Amazon Nova Canvas and Nova Reel allow developers to build creative applications without complex infrastructure management.

Text on a dark background reads "Type it." and "Amazon Nova Canvas," with a beige box displaying "A running sneaker sitting on a city street" and a pink "Generate" button.

Key capabilities

With Amazon Nova Canvas, customers can fine-tune the model on their proprietary data to generate fully customized images that align with to specific requirements and style guidelines.
Amazon Nova Canvas allows precise image editing operations where you can replace objects or backgrounds in an input image using text prompts. You can also easily remove a background with the background removal feature, leaving the subject of the image unchanged.

Virtual try-on creates immersive shopping and visualization experiences. Users can easily upload two images - one showing a person or living space, and another showing the product - to see realistic results of the product intelligently placed while preserving important details.

With Amazon Nova Reel 1.1, users can generate multi-shot videos up to 2-minutes in length and style consistency across shots. Multi-shot videos offer two modes: automated mode (single prompt and specifying total video duration) and manual mode (multiple prompts and an optional image for each 6-second shot).
Amazon Nova Reel and Amazon Nova Canvas have built-in controls for the safe and responsible use of AI. These include watermarking for traceability, content moderation, and indemnification.

Amazon Nova Canvas

Amazon Nova Canvas is a high-quality image generation model that offers broad customization and control features for builders in advertising, marketing, entertainment, and retail industries. As one of the most cost-effective image generation models with fine-tuning to generate fully customized and consistent images, it excels in generating images for ads, marketing assets, stock images, social media, and e-commerce content. Amazon Nova Canvas is ideal for B2C use cases with its core strengths in cost, quality, and responsible use of AI.

Example images generated by Amazon Nova Canvas

A cartoon-style cactus with large, expressive eyes holding a lit sparkler in a desert setting.

A cactus with googly eyes holding a magic wand emitting sparks

A futuristic robot with glowing blue eyes standing in a sleek, minimalistic cityscape.

Hand drawn pencil illustrated character design of a shape shifting robot in a sci-fi city

Pink hot air balloon floating above a grassy field with rolling hills in the background at sunset.

A pink hot air balloon

An octopus underwater wearing a colorful polka-dotted party hat.

An octopus at the bottom of the ocean wearing a party hat

A vibrant blue running shoe with glowing neon orange and pink accents, set against a blurred urban night background with warm lights.

A bright running shoe

Two cartoon puppies, one black-and-white and the other orange-and-white, hugging each other with happy expressions.

Two cartoon dogs hugging each other

A small, colorful dinosaur sitting inside a floral teacup on a saucer.

A dinosaur sitting in a teacup

Elegant restaurant interior with ornate decor, large windows, round tables set with white linens, and a stocked bar.

A very fancy French restaurant

A close-up of a person's ear and tousled hair in grayscale.

Black-and-white photo, character study, multi-angle

Introducing Amazon Nova Reel 1.1

Amazon Nova Reel 1.1 extends the generation of multi-shot videos up to 2-minutes in length and style consistency across shots. In addition, Amazon Nova Reel 1.1 introduces quality and safety improvements to the automated prompt-based video generation experience over Nova Reel 1.0.

Missing alt text value

Introducing virtual try-on in Amazon Nova Canvas

Amazon Nova Canvas now offers a virtual try-on capability that creates immersive shopping and visualization experiences. Whether it's clothing naturally draped on a shopper or furniture intelligently placed in a room, Amazon Nova Canvas creates realistic visualizations while preserving important details.

Missing alt text value

Videos generated by Amazon Nova Reel 1.1

Underwater Raccoon

This video was generated with Amazon Nova Reel 1.1 in automated mode, with a single, simple prompt: “A cute raccoon playing guitar underwater.”

A curious raccoon underwater, looking directly at the camera with a vibrant blue background.

Color Burst

Using automated mode, this video was generated with details to provide guidance and control. The prompt included "explosion of colored powder against black background. Start with slow-motion closeup of single purple powder burst. Dolly out revealing multiple powder clouds in vibrant hues colliding mid-air."

A curious raccoon underwater, looking directly at the camera with a vibrant blue background.

Above Zero

Using manual mode, this video used individual images per shot generated by Amazon Nova Canvas. The images helped to refined thematic set of prompts and consistency. The prompts included "dramatic overcast day at a massive glacier terminus, moody cinematic."

A curious raccoon underwater, looking directly at the camera with a vibrant blue background.

Animal Sanctuary

Using manual mode, this video included 10 specific shots across an animal santuary. The prompt for the first shot is, "Silhouette of woman with dark curly hair reflected in glass elevator, breathing exercise, slight fog on glass surface, cool ambient lighting"

A curious raccoon underwater, looking directly at the camera with a vibrant blue background.

Lone Wolf

Using automated mode, this video captures character consistency of a wolf, with distinctive features: silver-tipped charcoal fur, piercing amber eyes, and a small white patch on its chest. The prompts provided recommended minimal movement, focusing on composition and atmosphere.

A curious raccoon underwater, looking directly at the camera with a vibrant blue background.