MITB Banner

Balenciaga Goes Gaga Over AI

Even with powerful tools like Midjourney, the creator believes that AI still can't generate “a good aesthetic judgement” on its own.

Share

Listen to this story

The biggest Balenciaga moment isn’t even its own doing. Last month, demonflyingfox uploaded a video on YouTube titled “Harry Potter by Balenciaga.” The hilarious video leverages the uncanny valley phenomenon resulting in a masterpiece that has netted nearly five million views in a mere three weeks. The popularity of the original led to a sequel released last week. 

The video showcases beloved Harry Potter characters in a highly unconventional fashion. The characters, presented as models with razor-sharp cheekbones, were outfitted in gothic capes and leather jackets, set against the backdrop of Thip Trong’s electronica beat “Lightvessel.” The characters’ lines from the books were remixed with fashion references, providing a twist to the original story. In one scene, Hagrid announces “You are Balenciaga, Harry,” instead of breaking the news that Potter is a wizard. 

A video tutorial by PromptJungle shows the exact process. There are “Star Wars”, “The Office” and the latest “Breaking Bad” by Balenciaga too!

Pop-culture remix

The YouTube creator, Alexander Niklass, a Berlin-based photographer told The New Yorker, the video shows AI’s newfound ability to “create filmlike moments.”

The production process began with Midjourney to generate the basic static images of the Harry Potter characters and their fashion outfits using text prompts such as “male model, grotesque, balenciaga commercial.” Next, ElevenLabs, a voice cloning tool came into play to generate models of the actors’ voices by analysing previously recorded audio.

Finally, the images were fed into D-ID, a service that specialises in “avatar videos.” The tool subtly animated the portraits to create lip syncs and head nods reminiscent of fashion models tilting their chins and posing for the cameras. 

Despite being a combination of a child-friendly film and containing a notable fashion brand, Niklass insisted that the project was meant solely for entertainment and was quite meaningless. “The nonsense is the point”, he said.  

AI tools may have been able to replicate actors’ faces and generate fashionable outfits, but Niklass was the creative brain behind the project. Even with powerful tools like Midjourney, Niklass believes that AI still can’t generate “a good aesthetic judgement” on its own. While the tools can make things look great, it can’t match humans in creating truly inspired content. The explosion of copycats on YouTube only confirms that unique and creative ideas still come from human minds, not just machines.

In a 2022 interview, David Holz, founder of Midjourney, used the term “aesthetic accelerationism” to describe how AI can quickly and easily generate an abundance of images and ideas. It seems AI has solved some formulas for attention. “They’re new, interesting, human aesthetics that I think will spill out into the world,” Holz added. These creations don’t always have to be super artistic – they can be bizarre but just need to catch people’s attention just like the ‘Harry Potter by Balenciaga’ video. 

Generated Reality

While no one would mistake the Harry Potter videos for real footage—maybe an advertising campaign—another AI-generated image recently made news headlines because so many thought it was real. 

It was, or appeared to be, a photo of Pope Francis walking on the street wearing a silken white puffer jacket with a to-go coffee. The details and texture of the image made it appear incredibly lifelike. The image quickly gained traction online, prompting several news outlets to decry the incident as “one of the first instances of wide-scale misinformation stemming from artificial intelligence.”

The creator, Pablo Xavier from Chicago told the Chicago Tribune he used prompts with phrases such as “Catholic Pope Francis. Balenciaga puffer coat. Streets of Paris.” He told Buzzfeed, “I just thought it was funny to see the Pope in a funny jacket”. It seems AI hobbyists will not rest until everyone has been filtered through the cold lens of Balenciaga; from Potter to the Pope.

Share
Picture of Tasmia Ansari

Tasmia Ansari

Tasmia is a tech journalist at AIM, looking to bring a fresh perspective to emerging technologies and trends in data science, analytics, and artificial intelligence.
Related Posts

CORPORATE TRAINING PROGRAMS ON GENERATIVE AI

Generative AI Skilling for Enterprises

Our customized corporate training program on Generative AI provides a unique opportunity to empower, retain, and advance your talent.

Upcoming Large format Conference

May 30 and 31, 2024 | 📍 Bangalore, India

Download the easiest way to
stay informed

Subscribe to The Belamy: Our Weekly Newsletter

Biggest AI stories, delivered to your inbox every week.

AI Courses & Careers

Become a Certified Generative AI Engineer

AI Forum for India

Our Discord Community for AI Ecosystem, In collaboration with NVIDIA. 

Flagship Events

Rising 2024 | DE&I in Tech Summit

April 4 and 5, 2024 | 📍 Hilton Convention Center, Manyata Tech Park, Bangalore

MachineCon GCC Summit 2024

June 28 2024 | 📍Bangalore, India

MachineCon USA 2024

26 July 2024 | 583 Park Avenue, New York

Cypher India 2024

September 25-27, 2024 | 📍Bangalore, India

Cypher USA 2024

Nov 21-22 2024 | 📍Santa Clara Convention Center, California, USA

Data Engineering Summit 2024

May 30 and 31, 2024 | 📍 Bangalore, India

Subscribe to Our Newsletter

The Belamy, our weekly Newsletter is a rage. Just enter your email below.