Sora Not Ready for Hollywood Work: Former Pixar Animator

Sora Not Ready for Hollywood Work: Former Pixar Animator

AI video generating tool like Sora has been described as “impressive” and impactful in the film industry, but former Pixar animator has reservations and thinks it’s not ready for serious Hollywood business.

Craig Good is not fully convinced that a tool like OpenAI’s Sora will survive in Hollywood and be as useful until they allow directors to make some small changes that bring life to their stories.

Also read: New Chinese AI Robot Can Fold Clothes and Make a Sandwich

It’s frustrating

Good, who has worked on several animations like “Toy Story” and “Nemo” thinks there is a big problem with AI video software that will immediately frustrate anyone working on a movie. He believes it is “impossible, at this point, to make small changes using nothing but AI.”

Tools like OpenAI’s Sora enables users to create content straight from nothing but a simple prompt, which experts say is “impressive.”

However, the same tools do not allow users to make “some kind of iterative changes that are necessary when making a movie.”

Good, who is also an assistant professor and California College of Arts spoke in a video recorded by one of his students, where they discussed videos posted publicly and made using Sora.

“If I’m trying to use this in a production context, my first question is going to be, how do I revise this?” asked Good.

“Like if I say, I hate whatever’s going on with the background, can we do exactly this again, but with a locked-off background or a different one?” Good says in the video.

According to Quartz, there isn’t much that is known yet about Sora, but already there isn’t any indication to show the tool can enable smaller changes, which makes Good’s opinion valid.

So far, its known capabilities are examples from artists who have gained access to the tool, as OpenAI is yet to release it to the public.

Not all doom and gloom but still no iteration

However, not everything is bad about the tool. Good had some praises for one of the videos he reviewed with his student. The video features a fuzzy monster who seem smitten by a candle.

Good however pointed out that the framing was a “little tight and the flame is not really doing anything there.”

The challenge now is what it would take “to get the exact same scene with the camera pulled back and more flicker from the candle.”

“Making a movie is all about iterating. It’s iteration. And if you can’t iterate on one of these, I don’t know how you would possibly use it in production,” says Good.

“I mean, I spent decades at Pixar making tiny tweaks to shots. The director is going to give some fairly specific notes that the animator, the artist is going to have to interpret and then show that revised work the next day and then get further notes on it,” he continued.

“I don’t know how you would use it in production if you can’t iterate in a controlled way.”

But Good also thinks there is room for improvement with the AI video generating tools, comparing Sora to the first computer animation demonstrations in the early 1980s.

“This reminds me of the early days at SIGGRAPH where we would see, you know, a movie with, you know, a walking mechanical ant. And we all went nuts over it. Because, wow, we’re seeing a walking mechanical ant, right? A big robot ant, you know, in 1984,”he said.

How do others feel about Sora?

It seems Good is not the only one with reservations. A recent post on X platform from an art director at some major studio raised the same concerns. According to the post, the studio brought AI people to work on a production but it did not work out well.

The videos, according to the director were not bad, but each time they asked for changes, for instance a different color, they couldn’t, and “they get angry about being asked to change things because that’s not how it works.”

“The one that can actually use Photoshop hasn’t developed the eye to see mistakes, ends up getting angry at me for not understanding he can’t make specific changes,” read the post.

“The girl whose background was a little photography has given me 40 progressively worse images with wilder mistakes every time. This is 4 days into the project.”

Image credits: Shutterstock, CC images, Midjourney, Unsplash.