Why it's important: The advent of AI-based technology has put artists, musicians, and other entertainers in a difficult position in recent years. While some fear that new AI-based tools will erode jobs and opportunities across the entertainment industry, others embrace AI for its ability to push the boundaries of what is achievable. Chillwave music artist Washed His Out recently decided to explore the limits of possibility by releasing a new music video. All of this video was created using OpenAI's new text-to-video technology.
The four-minute music video features a series of scenes depicting the dating life of an anonymous red-haired woman and a dark-haired man. The main character in this video progresses from her teenage years to adulthood, and is depicted at various stages of her life, from her teenage years on the school bus to her adult life where she is married and has a family. .
The video, directed by Paul Trillo, may seem like a pretty typical depiction of a song about love, loss, and relationships. However, there is one major difference from other videos. It's that none of the actors are real. All scenes and characters were generated using Sora, OpenAI's text-to-video service.
According to the LA Times, Washed Out (real name Ernest Green) and Trillo originally planned to shoot a traditional video with live locations, sets, and dancers. However, due to time and budget constraints, the pair were unable to implement Green's vision. Future releases. Fortunately for Trillo, he was one of the few creative professionals granted early access to OpenAI's Sora service.
Using detailed text prompts to generate video sequences, the pair created scenes depicting the lives and locations of a fictional couple over several decades. Once generated, Trillo culled his 700+ clips that her Sora had generated to assemble the final product.
The result is a trippy, high-speed, dream-like journey through the lives of two people building a life together. However, this video is far from perfect and, like many AI-generated videos, contains a lot of extra body parts.
OpenAI introduced Sora's new Text-to-Video capabilities earlier this year. The tool can generate complex video scenes with specific characters, locations, characteristics, movements, and actions from only detailed text prompts. Additionally, you can use existing videos and still images to create longer videos or fill in missing frames.
Trillo emphasized the importance of responsible tool use, saying that technologies like Sora should be considered “tools in your toolbelt” rather than your primary content creation method. While some may see this as a threat, Trillo and Green see these advances as valuable steps forward for creators with ambitious ideas but limited budgets.
Sora is still being tested and refined by OpenAI and selected creators who received access. There is no official release date at this time.
