Harry Styles - Watermelon Sugar (AI)
It's not the first time an Artist used AI to recreate Harry Styles' 'Watermelon Sugar' music video, and we can't wait to see more…
Christian Nielsen worked on getting the AI to transform everyone into Harry Styles and add more watermelon, and we like it!
When the world was starved for human contact in the early days of the pandemic, Harry Styles dropped the “Watermelon Sugar” music video with a cheeky message: “This video is dedicated to touching.”
Released on 18 May 2020, directed by Bradley & Pablo and filmed in Malibu, California, it features Styles alongside
The video oozes the song’s warm, seductive, and playful vibe. Styles is surrounded by a plethora of people on the beach, surrounded by enough watermelon to feed a small army.
Despite the video’s saucy undertones, the intimacy between Styles and the actors held a special place in our hearts in 2020. The hand-holding, hair-stroking, and strawberry-feeding depicted in the video became the stuff of dreams for those starved for physical affection during the quarantine era. Styles’ original video served up a delicious, juicy taste of these longed-for sensations, reminding us all of the sheer joy of human touch during a time when it was most scarce.
If you have not seen the original video, check it out!
It’s not the first time an Artist used AI to recreate Harry Styles’ ‘Watermelon Sugar’ music video, and we can’t wait to see more AI-generated videos of Watermelon Sugar!
André Röhrig used AI to recreate Styles’ song using footage from the Reagan Presidential Library.
Röhrig said he got the idea for the project when he noticed that AI and machine learning often fail in interesting ways. Artist Mario Klingemann is also an inspiration, he said.
The original music videos for both Watermelon Sugar and Video Games are nostalgia trips that copy the aesthetic style of the 1960s. According to André Röhrig, this was important to help his AI-he designed and trained himself-understand how to make its music video.
“There are certain parameters like hard cuts and short scenes that are important for the process not to fail,” he said. “And the video footage the AI tries to replicate must be represented to a certain extent within the distribution of the archival footage. Otherwise, the results are not very satisfying. This is the case for these retro style videos I’ve used here; the ‘real’ Lana Del Rey video even uses lots of archival footage.”
According to Röhrig, creating the AI took about two weeks. Why the Reagan Library, though? After all, there are plenty of other sources of workable video, including the libraries of other American presidents. Röhrig said that it produced the best results.
“Initially, I was looking for footage in the public domain for practical reasons, so the videos don’t get blocked because of copyright claims,” he said. “This is the case for these public domain presidential video collections. I’ve tried other collections (Trump, Obama) and also other sources like old educational films produced by the U.S. Government. Still, I’ve had the best results with the Reagan Library footage. The more recent presidential videos have much better production videos and more editing. In contrast, the Reagan videos are often just someone filming random people at campaign rallies for hours, which is great for a diverse data set vs. just lots of shots of the president.”
Other videos on Röhrig’s channel show an AI trained to make abstract art using a Generative Adversarial Network (GAN), a common technique for creating artificial images.
“This animation of abstract images was created by an AI that was trained without any training data,” Röhrig said in the video’s description. “Instead, an adversarial training process of different deep convolutional neural networks against each other was used to create ‘pure’ abstract visuals.
Originally published at codame.com