Arter
An AI-powered storyboarding tool that lets you use language and the power of machine learning to illustrate your ideas.
Arter - is an AI-powered storyboarding tool. The AI agent, Art, works by listening for a user's input and, through NLP (Natural Language Processing), parses each word into an image object using image association analysis.
All work put forth in this case study was realized over ten weeks, for our senior Interaction Design Studio exploring machine learning and agentive technology @ ArtCenter College of Design — advised through lead faculty: Jenny Rodenhouse and Todd Masilko.
The goal for this class was to gain a deeper understanding of machine learning by exploring its associated technologies. And through that, let our discovery and insights drive our conceptualization/area of focus.
We gained more in-depth theoretical knowledge about how machines learn through various papers and articles. Two publications that stood out, in particular, was the "AI-EDAM" paper published by Cambridge.
"Designing Agentive Technology" by Christopher Noessel which helped us better understand how to design for machine learning and the role artificial intelligence plays in our lives.
Another big initial driver for us was taking inspiration from Code2Pix, which is a deep learning compiler for generating Graphical User Interfaces GUI from images.
Our vision is to have a platform that enables people to ideate visually and work together without having any barriers to language and skills.
Short-term
At Arter, we are looking forward to providing a touch-based app that allows users to create storyboards, vision boards/mood boards, narratives for their more significant projects, and collaborate with their teammates. Users will be able to art-direct their ideas on Arter by giving simple text-based or voice-based instructions, translating them into meaningful artwork generated by the Machine Learning model running in the background.
Long-term
Arter's machine learning model will learn from the different modifications and content generated by the active users and create a much more robust dataset. We envision Arter will be able to become an integral part of people's productivity workflow and establish some form of strategic partnerships, B2B offerings and integrations with existing applications that are an essential part of their workflow.
