James Cameron’s films have long pushed the boundaries of visual effects—most notably the Avatar series, which brought the heroic blue Na’vi characters to life through performance capture technology.

However, that doesn’t mean Cameron is a fan of generative AI.

In an interview with CBS’s Sunday Morning tied to the upcoming release of Avatar: Fire and Ash, the director acknowledged that performance capture—where actors’ performances are recorded and used as a reference for digital artists—might sound similar to generative AI. But he insisted it’s “exactly the opposite.”

“For years, people have thought, ‘Oh, they’re doing something weird with computers—they’re replacing actors,’” Cameron said. “But in reality, once you really dig in and see what we’re doing, it’s a celebration of the actor and the director’s moment.”

Indeed, the CBS segment showed Avatar cast members performing underwater scenes inside a 250,000-gallon tank.

“On the other end of the spectrum, you’ve got generative AI, where they can create a character, an actor, or even a performance from a text prompt,” Cameron added. “No—that’s terrifying… That’s exactly what we don’t want to do.”