AI

Meta's AI image generator can't seem to grasp the idea that interracial couples exist

Meta Imagine
Meta's AI image generator struggled with a straightforward prompt. Meta Imagine
Read in app

Meta's AI image-generation tool is struggling to understand the concept of interracial couples.

The tool failed to correctly generate a Black man with a white wife when prompted by Business Insider. Instead, delivering images of a Black couple.

The same happened when BI asked it to produce an image of an Asian man with a white wife — only pictures of Asian couples were shown. However, the generator was able to successfully depict an interracial couple with a Black woman and a white husband.

AI-generated photo of interracial couple
Meta's Imagine tool was able to generate pictures of a Black woman and white man embracing.  Meta Imagine

Meta launched the standalone AI-powered image generator — Imagine with Meta — late last year. The tool is free to use and similar to OpenAI's DALL-E, Midjourney, and Stable Diffusion.

The Verge first reported the issue on Wednesday, with reporter Mia Sato claiming she "tried dozens of times" to create images of Asian men and women with white partners and friends. Sato said the image generator was only able to return one accurate image of the races specified in her prompts.

Representatives for Meta did not immediately respond to a request for comment from BI, made outside normal working hours.

AI image generators have struggled to accurately present people of different races in the past.

Google's Gemini image generator provoked a firestorm of backlash after users found it was creating historically inaccurate images. Google paused the Gemini's image-generating capacity after users accused it of being overly "woke."

High-profile figures, including Elon Musk, used the incident as an example of what they saw as Google's leftwing culture and employees.

Google CEO Sundar Pichai later said the company got it wrong on Gemini and that the flagship AI system had "offended our users and shown bias."

Read next

Beatrice Nolan was a tech reporter on the business news team in the UK. She joined Insider in January 2022 as a fellow on Business Insider's careers desk. Beatrice covered tech and the future of work, with a focus on artificial intelligence. Some of her stories and early experiments with ChatGPT are widely cited. Beatrice has also discussed her work covering AI trends on panels and radio shows, including NPR.She was based in Business Insider's London office and graduated from the University of  York with a bachelor's degree in English.Featured Articles:Artists say AI image generators are copying their style to make thousands of new images — and it's completely out of their control.ChatGPT was a black swan eventFinland is the world's happiest country, but Finns say we're confusing happiness for something elseThe world is splitting between those who use ChatGPT to get better, smarter, richer — and everyone elseThis man used AI to write and illustrate a children's book in one weekend. He wasn't prepared for the backlash.ChatGPT has only been around for 2 months and is causing untold chaosTwo professors who say they caught students cheating on essays with ChatGPT explain why AI plagiarism can be hard to proveChatGPT wrote college application essays. Admissions professionals said they passed for essays written by students but wouldn't have a chance at any top colleges.College professors are considering creative ways to stop students from using AI to cheatChatGPT wrote my cover letters. Here's how recruiters responded.
Jordan Hart's face on a gray background.
Jordan Hart