Why Tyler Perry Puts $800M Studio Expansion on hold after seeing OpenAI’s Sora

Over the past four years, Tyler Perry has been planning an $800 million expansion of his studio in Atlanta, which would have added 12 soundstages to the 330-acre property. Now, however, those ambitions are on hold—thanks to the rapid developments he’s seeing in the realm of artificial intelligence, including OpenAI’s text-to-video model Sora. 

According to a report in The Hollywood Reporter, Perry has reportedly put his ambitious $800 million studio expansion plan on hold after seeing Sora’s capabilities. The filmmaker also raised alarm about the potential impact of the technology.

“Being told that it can do all of these things is one thing, but seeing the capabilities, it was mind-blowing,” he said in an interview, noting that his productions might not have to travel to locations or build sets with the assistance of the technology.

According to a report, Perry has reportedly put his ambitious $800 million studio expansion plan on hold after seeing Sora’s capabilities. The filmmaker also raised alarm about the potential impact of the technology.

Also Read: How is OpenAI’s Sora impacting Artificial Intelligence (AI) Tokens?

The OpenAI model is capable of churning out trailer-quality videos with just a few words as prompts. While this may be seen as a threat, there are many filmmakers and members of the AI community who see Sora as a huge leap forward and a significant step for generative Artificial Intelligence. Videos generated by Sora are consistent with characters, backgrounds, and motions, with detailed settings and multiple cameras.

Why Tyler Perry Pauses $800M Studio Expansion Due to OpenAI’s Sora Advancements

AI Impact: Tyler Perry, the renowned actor and filmmaker, has put a significant $800 million expansion of his Atlanta studio on hold. The decision comes after witnessing the capabilities of OpenAI’s text-to-video model, Sora.

Technological Shock: Perry expressed his astonishment at Sora’s ability to generate realistic video outputs from text descriptions. This advancement could potentially eliminate the need for location shoots or set construction, revolutionizing the film production process.

Labor Concerns: The introduction of AI technologies like Sora raises concerns about the future of various job roles in the entertainment industry. Perry is worried about the potential impact on employment, from actors to construction workers.

Industry Response: Urging for a unified approach, Perry calls for industry-wide collaboration and government intervention to establish regulations that protect jobs against the rapid development of AI.

Personal Use: Despite his concerns, Perry has already implemented AI in two upcoming films, which allowed him to avoid lengthy makeup sessions.

What is OpenAI Sora and How Does It Help in Film Making?

Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world.

According to an OpenAI research paper, Sora works on a video compression network that takes raw video as input and outputs a latent representation that is compressed both temporally and spatially. Sora is trained on and subsequently generates videos within this compressed latent space. 

The compressed input video extracts a sequence of spacetime patches that act as transformer tokens. This scheme works for images too since images are just videos with a single frame. The patch-based representation enables Sora to train on videos and images of variable resolutions, durations, and aspect ratios. At inference time, users can control the size of generated videos by arranging randomly initialized patches in an appropriately sized grid.

Sora is also capable of generating images. We do this by arranging patches of Gaussian noise in a spatial grid with a temporal extent of one frame. The model can generate images of variable sizes—up to 2048×2048 resolution. video models exhibit a number of interesting emergent capabilities when trained at scale. 

These capabilities enable Sora to simulate some aspects of people, animals, and environments from the physical world. These properties emerge without any explicit inductive biases for 3D, objects, etc.—they are purely phenomena of scale.

Also Read: Text-to-Video AI Tool: Open AI Sora vs Canva and Other Video Generators