Computer science student creates new tool to make AI-generated art more sustainable


AI image of a golden apple.

Computer science doctoral student Maitreya Patel is working with Yezhou “YZ” Yang, an associate professor in the School of Computing and Augmented Intelligence, part of the Ira A. Fulton Schools of Engineering at Arizona State University, on a new, more sustainable artificial intelligence image creation tool. Image generated by Eclipse/ASU Active Perception Group

|

Tech experts say that users produce more than 34 million images per day using artificial intelligence, or AI, tools such as Midjourney and DALL-E 2. The results are often inventive and astonishing.

While people might find making AI-generated art a relaxing, creative outlet, these images come at a cost. Server farms, giant data centers full of computers, will consume more energy each year processing AI art than the entire country of Argentina. In 2023, Google used 5.6 billion gallons of water just cooling its servers.

The challenge of how to make these artistic tools available to those who want to use them while keeping an eye on sustainability is a problem that computer science doctoral student Maitreya Patel is keen to solve.

Patel has been working under the supervision of Yezhou “YZ” Yang, an associate professor of computer science and engineering in the School of Computing and Augmented Intelligence, part of the Ira A. Fulton Schools of Engineering at Arizona State University. Yang heads the Active Perception Group, a lab that studies computer vision and image generative AI.

Yang oversees several projects funded by grants from the National Science Foundation dedicated to researching computer visual recognition tools. Some of the novel work being done there seeks to make a system that can create an image, check out what it has produced and learn from the comparison. The computer might draw a dog, scan the image, ask itself if the picture looks like a dog and then update its programming based on the results.

As part of his doctoral research, Patel has created Eclipse, a resource-efficient tool that takes in text prompts and then produces images. He made a demonstration website where a user can type in a short description of what they would like to see, and the AI tool will generate a picture.

An apple tree in a garden
Eclipse, the AI image tool developed by ASU engineering doctoral student Maitreya Patel, can potentially be trained in a matter of days using a small number of processors. Image generated by Eclipse/ASU Active Perception Group

A model of more sustainable artificial intelligence

The work deals with the central problem of training a model.

Today, most AI solutions have been created by feeding large sets of data into networks of computers and “training” models — tweaking the algorithms, or sets of instructions, that the computers use to do their work. The software engineer supplies a computer with thousands of pictures of dogs and then tasks it with generating its own dog images.

But Patel and Yang believe there are better ways of harnessing the power of AI than simply using more and more computers to process more and more data.

“We have created a new model pipeline,” Patel says. “Our model will use a small number of processing units, and it can be trained in one to two days.”

The team’s work is concerned with three basic issues: creating an image-generating model that requires less time and computational resources to train; producing a good open-source system that can be reused; and, finally, making software that users can train exclusively with their own images.

With the help of tools and technical expertise provided by ASU Research Computing, the team set out to make a more efficient image-generation model. They have a few new ideas. One is using a training strategy called contrastive learning, or teaching the computer what information is not relevant to get the right result.

Patel and Yang are also using adversarial training, a programming technique that deliberately attacks the image model and tries to get it to fail.

“The advantage to this type of training is that we can discover the shortcomings of the current model, deal with its disadvantages and improve the system based on attacking the results,” Yang says.

A dog rests under an apple tree
ASU engineering doctoral student Maitreya Patel and Associate Professor Yezhou "YZ" Yang see Eclipse as a potential solution for businesses that want to train their own resource-efficient AI art models. Image generated by Eclipse/ASU Active Perception Group

Users can use their own images

Patel and Yang are concerned about matters of privacy and ethics. Many AI image tools are rife with controversy about the provenance of the art that was used to train their models.

The Eclipse team — which also includes computer science doctoral students Sheng Cheng and Sangmin Jung, computer engineering doctoral student Changhoon Kim and Chitta Baral, a professor of computer science and engineering, who is serving in an advising role — has a plan that could enable businesses to deploy their own versions of the Eclipse model and train it using only images owned by that enterprise. Concerns about lawsuits or image sources would be eliminated.

These are ideas that are interesting to artists working in the AI space. Erika Gronek, a Fulton Schools photographer, has used AI art tools and even written a book on AI art called "Uncanny: AI Speaks for Itself."

Strange unicorn eating a meatball sandwich
Artists can use AI art tools to jump-start their creativity, using humorous or whimsical prompts to generate unique results. Image generated by Erika Gronek using Eclipse/ASU Active Perception Group

“AI isn’t going away,” Gronek says. “It has its critics, and rightly so, but it can also be viewed as another tool in the toolbox for an artist. At the very least, it should be wielded ethically by using proper datasets and sustainably because it can require such immense computing power.”

In June, Yang and the research team will present their work at the prestigious IEEE/CVF Conference on Computer Vision and Pattern Recognition in Seattle. They are also on the lookout for enterprise partners who might want to back further development of their technology.

“We’re trying to figure out the sweet spot where vision and language meet to make critical improvements to the efficiencies of these models,” Yang says.

He also hopes the project will inspire more doctoral and master’s thesis students like Patel.

“Exciting work in AI is being done here at the School of Computing and Augmented Intelligence,” Yang says. “We want to attract and inspire new doctoral and master’s thesis students, help them develop professionally and showcase their efforts.”

More Science and technology

 

Isabella Faris works on a laptop

Cracking the code of online computer science clubs

Experts believe that involvement in college clubs and organizations increases student retention and helps learners build valuable social relationships. There are tons of such clubs on ASU's campuses…

Jack Stilgoe, seated, speaks to an unseen audience

Consortium for Science, Policy & Outcomes celebrates 25 years

For Arizona State University's Consortium for Science, Policy & Outcomes (CSPO), recognizing the past is just as important as designing the future. The consortium marked 25 years in Washington, D…

Portrait of Christopher Langenderfer.

Hacking satellites to fix our oceans and shoot for the stars

By Preesha KumarFrom memory foam mattresses to the camera and GPS navigation on our phones, technology that was developed for space applications enhances our everyday lives on Earth. In fact, Chris…