A group of artists who say they received early access to OpenAI’s Sora video generation model released a version of the tool to the public.
For a brief moment on Tuesday, a group of angry artists shared a tool that allowed anyone to use OpenAI’s officially unreleased Sora AI model, which takes text prompts and turns them into videos.
in a open letter Titled “Dear Corporate Lords of AI,” accompanied by illustrations of figures attacking their middle fingers, the artists wrote that they had been offered early access to Sora to test the product and be creative partners. Instead, they believe OpenAI wanted to use hundreds of unpaid AI artists like themselves in order to “art launder” in an exploitative business model.
“Hundreds of artists provide unpaid work through bug testing, feedback, and experimental work for a $150 billion company’s program,” the group wrote on AI model hosting platform Hugging Face. “While hundreds contribute for free, a select few will be chosen through a competition to have their Sora-created films screened, offering minimal compensation that pales in comparison to the significant PR and marketing value OpenAI receives” .
The letter was written by 16 artists who said they were not opposed to the use of AI as an artistic tool; In fact, many of them are early adopters of AI in their work, but felt the need to protest against early access. program that seemed to be a public relations strategy rather than an opportunity to freely experiment and critique the tool. They said that any video they created using the tool had to be approved by OpenAI before being shared.
“What we disagree with is how this artist program has been implemented and how the tool is being outlined ahead of a potential public release,” the group wrote. “We share this with the world in the hope that OpenAI will become more open, more artist-friendly, and support the arts beyond PR stunts.”
The tool published in hugging face It no longer works and a note added to the top of the letter says that OpenAI has temporarily closed Sora’s early access program for artists.
OpenAI mocked Sora on February 15 with a Web page with videos generated by the model and in a series of tweets from CEO Sam Altman, who posted videos about X that the model generated based on crowdsourced cues. Altman called it a “remarkable moment,” but Sora has yet to be released for use beyond a small group of early testers, some of whom were clearly not enthusiastic about how OpenAI wanted to use their work.
In their letter, the artist group urged their peers to use open source video generation tools and encouraged AI companies to “listen and provide a path to true expression for artists, with fair compensation for the artists”.