The Gen AI Cube
at re:Invent 2024

The Gen AI Cube is an interactive art installation designed for the annual AWS re:Invent conference in Las Vegas. Powered by real-time AI-generated imagery, it recognizes human forms and reflects body movements in four unique visual languages: Explorer, Millennium, Flair, and Botanical. As guests step into the installation, their poses change instantly, inspiring both play and spectatorship.

Category One: Explorer

Attendee interactions shaped natural scenery such as mountains, glaciers, buildings, or foreign planets with their movements, merging both organic and synthetic structural elements.

The sun is setting over a mountain lake.

Mountains

A city street filled with lots of neon signs.

Tokyo Lights

A group of icebergs floating on top of a body of water.

Glacier

Building

Category Two: Flair

In this concept, attendees created their own abstract expressionist art. The human form itself transforms into a tool for creation, or a moving hand becomes a tool like a paintbrush.

A red vase sitting on top of a table next to other items.

Bodegón

A red, yellow, and orange paint splattered on a black background.

Color Splatter

A painting of a city skyline at night.

Skyline

A purple flower with a gold center on a black background.

Gaudí

A multicolored piece of art on a black background.

Kadinsky

Category Three: Millenium

With abstract and tactile direction, the forms generated in Millennium invited playful interactions which inspired very sensory-specific shapes and materials.

A group of colorful sticks sticking out of the side of a blue wall.

Plastic Tubes

A blue sculpture on a white table.

Rubber Tires

Bronze

A colorful sculpture on a yellow background.

Ceramic

A green object with a black background.

Shag Carpet

Category Four: Botanical

Participants' movements generated digital flora, where gestures grew intricate bonsais, unfurled bulbous structures, and coaxed liquid flowers and flowing orchids into bloom, creating an ever-evolving botanical garden responsive to human interaction.

A flower that is in a vase on a table.

Petalwires

A pink flower with green leaves on a black background.

Orchid

A pink flower is hanging from a stem.

Bulbous

A bonsai tree in a pot on a black background.

Bonsai

A green glass sculpture with a black background.

Liquid Flowers

How It Looked at re:Invent

A room with a large display of a woman in motion.A group of people standing in a room.A large display of a flower in a building.A man standing in front of a large screen with icebergs on it.A group of people standing in front of a large screen.A man taking a picture of a large sculpture.A man and a little girl standing in front of a tv.A woman standing in front of a large screen.A group of people standing around a yellow box.A group of people dancing in a room.A picture of a large object on display in a room.A man standing in front of a crowd of people.

How the Cube Works

We used an infrared sensor to capture participants' body movements by extracting skeleton data and a depth image from the infrared sensor. The skeleton data then tracked key joint movements, while the depth image provided information on the participant's distance from the screen. This data drove the Generative AI visuals, with movements influencing the creation of dynamic imagery in real-time. Powered by fine-tuned AI image models, the system generated an impressive 15 high-quality images per second.

A close up of a computer screen with a blurry background.A computer screen with a bunch of buttons on it.A blurry image of a person standing in front of a microwave.

Our custom development inside TouchDesigner allowed us to control human silhouettes, depth images, and skeletons, applying various effects and color palettes to create rich variations in the output. Gestures shaped the visuals, while proximity added layers of interactivity, allowing participants to control the evolution of the digital artwork through their body movements.

A.I. Photo Moments

A more lightweight version of the Gen AI Cube, this adaptation took personalization to the next level. Using real-time face tracking and custom AI models, this installation instantly transformed participants into over 25 artistic styles, from Renaissance portraits to surrealist interpretations, creating unforgettable digital masterpieces.

A large screen with a blue man's face on it.A group of people standing in front of a large screen.A large group of people in a room.A group of people standing in front of a crowd.A group of people standing in front of a large screen.A large screen with a picture of a man's head made out of vegetables.
A painting of a man's face is shown.A painting of a man's face is shown.A woman with her eyes closed wearing a hoodie.A drawing of a man with his hands on his face.A woman's face with a red and blue stripe on it.A painting of a man wearing glasses and a red shirt.A sculpture of a man's face made out of wires.A painting of a person with a blue face.A painting of a man's face made up of different colored objects.A computer generated image of a human's brain.A man's face is made up of flowers and vines.A digital painting of a man's face and brain.

Special thanks to dot simulate for creating the streamdiffusion TouchDesigner module which we used for the installation.

Notice at Collection