Art

Stable Attribution Identifies the Art Behind AI Images

Published

1 year ago

April 27, 2023

Shortly after their first releases to the public, text-to-image artificial intelligence models like Stable Diffusion and Midjourney also became the focal points in debates around the ethics of their usage. Anton Troynikov is a cofounder of Chroma, a startup working to improve AI interpretability—that is, making what goes on under the hood of AI systems a little less mysterious. With AI art generators, Troynikov and others at Chroma saw an opportunity to build a tool that would make it easier to address some of the thorny attribution issues that have emerged. Troynikov answered five quick questions on the project—called Stable Attribution—and how he thinks artists and AI engineers can stop talking past each other on the topic of AI-generated art.

What were your first impressions of AI art generators when they were released?

Anton Troynikov: I started paying attention to the AI art discourse after Stable Diffusion was released and a lot more people got access to the model. And I started to realize pretty quickly that people on both sides of the conversation were talking past each other. I wanted to see if there was a technical solution to the problem of making sure that technologists and creatives were not antagonists to one another.

What’s your goal with Stable Attribution?

Troynikov: I wanted to demonstrate that this problem is not technically infeasible to tackle. After talking to a bunch of people, especially on the creative side, but also on the technology and research side, we felt it was the right thing to just go ahead and see what kind of reaction we’d get when we launched it.

What’s the short version for how Stable Attribution works?

Troynikov: Stable Diffusion is in a class of models called latent diffusion models. Latent diffusion models encode images and their text captions into vectors (basically a unique numerical representation for each image). During training time, the model adds random values (noise) to the vectors. And then you train a model to go from a slightly more noisy vector to a slightly less noisy vector. In other words, the model tries to reproduce the original numerical representation of every image in its training set, based on that image’s accompanying text caption.

The thinking was, because these numerical representations come from these pretrained models that turn images into vectors and back, the idea is basically, “Okay, it’s trying to reproduce images as similarly as possible.” So a generated image wants to be similar to the images that most influenced it, by having a similar numerical representation. That’s the very short explanation.

How do you make that final step and determine who the artists and creators are?

Troynikov: We would really like to be able to attribute directly back to the human who created the source images. What we have—and what’s available in the public training data set of Stable Diffusion—are URLs for images, and those URLs often come from a CDN [content delivery network]. The owners of the sites where those images appear and the owners and operators of those CDNs could make that connection.

We do have a little submission form on the site. If people recognize who the creator is, they can submit it to us, and we’ll try to link it back.

How do you see generative AI like this—alongside the ability to attribute source images to their creators—affecting artistic creation?

Troynikov: I think there’s two things you could do. One is, by being able to do attribution, you can then proportionately compensate the contributors to your training set based on their contribution to any given generation. The other really interesting thing is, if you have attribution in generative models, it turns them from just a generator into a search engine. You can iteratively find that aesthetic that you like and then link back to the things that are contributing to the generation of that image.

Anton Troynikov is the cofounder of Chroma, an AI company focused on understanding the behavior of AI through data. Previously, Troynikov worked on robotics with a focus on 3D computer vision. He does not believe AI is going to kill us all.

From Your Site Articles

Source link

Art

Ukrainian sells art in Essex while stuck in a warzone – BBC.com

Published

1 week ago

September 2, 2024

Harry Miller

[unable to retrieve full-text content]

Ukrainian sells art in Essex while stuck in a warzone BBC.com

Source link

Art

Somerset House Fire: Courtauld Gallery Reopens, Rest of Landmark Closed

Published

4 weeks ago

August 18, 2024

Harry Miller

The Courtauld Gallery at Somerset House has reopened its doors to the public after a fire swept through the historic building in central London. While the gallery has resumed operations, the rest of the iconic site remains closed “until further notice.”

On Saturday, approximately 125 firefighters were called to the scene to battle the blaze, which sent smoke billowing across the city. Fortunately, the fire occurred in a part of the building not housing valuable artworks, and no injuries were reported. Authorities are still investigating the cause of the fire.

Despite the disruption, art lovers queued outside the gallery before it reopened at 10:00 BST on Sunday. One visitor expressed his relief, saying, “I was sad to see the fire, but I’m relieved the art is safe.”

The Clark family, visiting London from Washington state, USA, had a unique perspective on the incident. While sightseeing on the London Eye, they watched as firefighters tackled the flames. Paul Clark, accompanied by his wife Jiorgia and their four children, shared their concern for the safety of the artwork inside Somerset House. “It was sad to see,” Mr. Clark told the BBC. As a fan of Vincent Van Gogh, he was particularly relieved to learn that the painter’s famous Self-Portrait with Bandaged Ear had not been affected by the fire.

Blaze in the West Wing

The fire broke out around midday on Saturday in the west wing of Somerset House, a section of the building primarily used for offices and storage. Jonathan Reekie, director of Somerset House Trust, assured the public that “no valuable artefacts or artworks” were located in that part of the building. By Sunday, fire engines were still stationed outside as investigations into the fire’s origin continued.

About Somerset House

Located on the Strand in central London, Somerset House is a prominent arts venue with a rich history dating back to the Georgian era. Built on the site of a former Tudor palace, the complex is known for its iconic courtyard and is home to the Courtauld Gallery. The gallery houses a prestigious collection from the Samuel Courtauld Trust, showcasing masterpieces from the Middle Ages to the 20th century. Among the notable works are pieces by impressionist legends such as Edouard Manet, Claude Monet, Paul Cézanne, and Vincent Van Gogh.

Somerset House regularly hosts cultural exhibitions and public events, including its popular winter ice skating sessions in the courtyard. However, for now, the venue remains partially closed as authorities ensure the safety of the site following the fire.

Art lovers and the Somerset House community can take solace in knowing that the invaluable collection remains unharmed, and the Courtauld Gallery continues to welcome visitors, offering a reprieve amid the disruption.

Source link

Art

Sudbury art, music festival celebrating milestone

Published

4 weeks ago

August 15, 2024

Harry Miller

Sudbury’s annual art and music festival is marking a significant milestone this year, celebrating its long-standing impact on the local cultural scene. The festival, which has grown from a small community event to a major celebration of creativity, brings together artists, musicians, and visitors from across the region for a weekend of vibrant performances and exhibitions.

The event features a diverse range of activities, from live music performances to art installations, workshops, and interactive exhibits that highlight both emerging and established talent. This year’s milestone celebration will also honor the festival’s history by showcasing some of the artists and performers who have contributed to its success over the years.

Organizers are excited to see how the festival has evolved, becoming a cornerstone of Sudbury’s cultural landscape. “This festival is a celebration of creativity, community, and the incredible talent we have here in Sudbury,” said one of the event’s coordinators. “It’s amazing to see how it has grown and the impact it continues to have on the arts community.”

With this year’s milestone celebration, the festival promises to be bigger and better than ever, with a full lineup of exciting events, workshops, and performances that will inspire and engage attendees of all ages.

The festival’s milestone is not just a reflection of its past success but a celebration of the continued vibrancy of Sudbury’s arts scene.

Source link