Find the Real AI Artists with This Powerful New Tool 

Stable Attribution deconstructs an AI image to reveal source images. To address artist copyrighting issues.
Listen to this story

With text-to-image AI tools such as DALL.E 2 and Stable Diffusion, images are scraped off the internet and used without proper attribution. The artist’s information is unavailable and the process largely remains shrouded in anonymity. This has led to artists accusing these platforms of stealing their artwork

Enter Stable Attribution, which looks to address this by backtracking the human element to the AI created art. It works on reverse engineering principles to extract the images that were used to create an AI image. The platform also allows attribution to the artists whose images were used for the creation. Stemming from the policies of infringement and copyrighting, the tool helps safeguard the rights of the owner and at the same time, build a repository of artists’ works. 

Chroma, a startup trained to make AI solutions from machine learning, created Stable Attribution. The application was predominantly built by Jeffrey Huber, alongside Anton Troynikov and others. In Stable Attribution, if you post an AI image from an AI-generative application, say, Stable Diffusion, the source images that were used to generate the AI image will pop up. 

AIM Daily XO

Join our editors every weekday evening as they steer you through the most significant news of the day, introduce you to fresh perspectives, and provide unexpected moments of joy
Your newsletter subscriptions are subject to AIM Privacy Policy and Terms and Conditions.

In the below example, Stable Diffusion created the AI image from the text prompt, “Stormtroopers having ice cream in Central Park”. Upon uploading that image in Stable Attribution, the source images used for creating it appears. There is an option to attribute each picture with the artist’s link.  

Screenshot of Stable Attribution tool with source images

Stable Attribution works on models such as LAION and Stable Diffusion where the datasets are available. However, a tool like Dall-E 2 by OpenAI does not have its training dataset exposed, which blocks Stable Attribution from crawling. The application is still learning from the datasets it has. The algorithm of Version 1 of Stable Attribution deconstructs an AI image by matching with the most similar images from the dataset it has.

Download our Mobile App

As it is still learning, the repository is limited and the images it pulls out are the most influential and visually matching. Apart from addressing an artist’s copyright issues, this application has limited use in the current version. Unless they add new features, Stable Attribution is a mere image deconstruction tool. 

Sign up for The Deep Learning Podcast

by Vijayalakshmi Anandan

The Deep Learning Curve is a technology-based podcast hosted by Vijayalakshmi Anandan - Video Presenter and Podcaster at Analytics India Magazine. This podcast is the narrator's journey of curiosity and discovery in the world of technology.

Vandana Nair
As a rare breed of engineering, MBA, and journalism graduate, I bring a unique combination of technical know-how, business acumen, and storytelling skills to the table. My insatiable curiosity for all things startups, businesses, and AI technologies ensure that I'll always bring a fresh and insightful perspective to my reporting.

Our Upcoming Events

24th Mar, 2023 | Webinar
Women-in-Tech: Are you ready for the Techade

27-28th Apr, 2023 I Bangalore
Data Engineering Summit (DES) 2023

23 Jun, 2023 | Bangalore
MachineCon India 2023 [AI100 Awards]

21 Jul, 2023 | New York
MachineCon USA 2023 [AI100 Awards]

3 Ways to Join our Community

Telegram group

Discover special offers, top stories, upcoming events, and more.

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Subscribe to our Daily newsletter

Get our daily awesome stories & videos in your inbox

Council Post: The Rise of Generative AI and Living Content

In this era of content, the use of technology, such as AI and data analytics, is becoming increasingly important as it can help content creators personalise their content, improve its quality, and reach their target audience with greater efficacy. AI writing has arrived and is here to stay. Once we overcome the initial need to cling to our conventional methods, we can begin to be more receptive to the tremendous opportunities that these technologies present.