PORTAL

An art installation that enables the real-time generation of a continuous video from written or spoken words.

The Technology

Developed in house, our technology combines real-time AI generation, signal optimization, and artistic expertise to create interactive visual experiences that generate emotion.

System

System

Modalities

Moderation

Moderation

Control

Style

Style

Aesthetics

System

Mode 01 • System

Speech to video

We turn spoken sentences into evolving visuals in real-time, collected using a microphone.

Discover the setup

Mode 02 • System

Text to video

We generate a continuous video from queued text prompts written by the audience.

Discover the setup

Mode 01 • Speech to video

Speech to video

Our speech to video setup lets people command an AI algorithm by speaking inside a microphone.

Once a sentence is spoken, the video immediately transitions into a visual interpretation of it, then continues in constant motion until a new sentence is voiced.

  • The experience can be presented on any type of screen or projection.
  • An automated moderation allows for content safety.
  • The installation only requires an internet connection.

Mode 02 • Text to video

Text to video

Our text to video system is accessible through a web app, with no download required. Users submit text descriptions that directly steer the AI in real time.

Prompts are queued, enabling large scale participation. Each participant can track their position in the queue and see which prompt is currently shaping the video.

  • The experience can be presented on any type of screen or projection.
  • Automated and manual moderation keep the content safe.
  • The installation only requires an internet connection.

Moderation

The installation comes with three levels of moderation.

Moderation layer

Natural moderation

The algorithms used for visual creation are trained on a curated dataset, allowing objectionable content to be excluded without removing creative range.

Moderation layer

Automatic moderation

A ban list can be configured with forbidden words or phrases. Refused prompts are rejected immediately and the participant can submit a new one.

Moderation layer

Human moderation

A live interface allows manual approval, rejection, prioritization, and timing control for each prompt when an event requires tighter supervision.

Style

We can adapt the visual generation to your artistic direction, from color palette to motifs and overall atmosphere. A small set of inspiration references is enough to shape a dedicated style.

Contact

Want to design your own live experience?

The interactive project brief loads on demand. You can already reach the team directly by email if you want to discuss a live activation now.

Email Obvious

About Us

We are Obvious, a French trio of artists and researchers working with artificial intelligence to create art. Inspired by Renaissance workshops, we operate at the crossroads of academic research and artistic production.

Our research lab at Sorbonne University, funded by the French National Research Agency, develops image, video, and sound generation systems. We were behind the first AI-created artwork to go through Christie’s in 2018.

Visit our main website
Obvious team