What is Sora Turbo and is it a game changer for artificial intelligence? | Explanatory news

Sora, an artificial intelligence (AI) video generating program created by startup OpenAI in 2021, is making waves as it has now come out of the research phase and officially launched to the public under the new name Sora Turbo.

The launch has sparked an online frenzy among users, causing the company to temporarily halt creating new accounts after being overwhelmed by a flood of traffic.

Sora uses text prompts to create content, similar to other content creation programs like ChatGPT. Unlike traditional AI programs that produce written responses, Sora creates high-quality videos based on the user’s text input.

Sora is disgustingly hot, gj. @The same

Adding it to @everartai as soon as possible so you can bring your images to life pic.twitter.com/wMehxOc8cm

—Jay A (@jay_azhang) December 9, 2024

According to a statement from OpenAI that accompanied the launch on December 9, Sora Turbo is an improvement over the original Sora program, enabling faster video creation, higher quality videos, and a host of video editing features that They allow users to trim and create videos. sequences and change elements in a video while preserving other parts of the video.

So what exactly is Sora Turbo and how is it changing the video creation industry?

How does Sora Turbo work?

The power of Sora, and many other AI video generators, is its ability to replicate what humans can do with high-quality filmmaking equipment, but in an extremely short time.

Users can tell the program not only what to include in the video, but also what type of camera they want to use, lens selection, lighting settings, visual aesthetics, composition, and storyboards.

An example message that uses some of these details might look like this:

“Use a medium telephoto lens (85mm) to capture an intimate portrait of a street vendor working at night. Illuminate the scene with a combination of the warm, bright lights of the vendor booths and the cooler ambient lights of the city in the background. Focus on the details of the seller’s hands as they prepare food or products, balancing the frame with their expressive face. The image should evoke hard work and pride in your craft.”

How good is Sora Turbo?

It’s not perfect.

Users type a text message about what type of video they would like to generate and Sora creates the video. There are limitations in the current version. The video quality is up to 1080p at 30 frames per second and can only last 20 seconds.

This is an example of a Sora Turbo video by Emi Kusana, multimedia artist and lead singer of Satellite Young, a musical group inspired by J-pop and sci-fi themes from the 80s, using songs from Takenoko-zoku, a 1980s fashion group. Although there is a 20-second limit, the Sora Storyboard feature allows users to stitch together multiple AI-generated videos and arrange them sequentially, as shown in the video below.

Obvious errors also appear in some videos. For example, in the video above, at the 36-second mark, one of the dancers does a 180-degree neck turn, which of course is not humanly possible, and continues the dance routine. The company will have to work harder to resolve errors like this, he said.

In an example video of a woman cooking, posted in February by Sam Altman, founder of OpenAI, viewers will notice that the spoon in the woman’s right hand disappears when she stops mixing.

https://t.co/rmk9zI0oqO pic.twitter.com/WanFKOzdIw

—Sam Altman (@sama) February 15, 2024

How has Sora Turbo been received within the industry?

Some industry experts and creative directors are concerned about how Sora may disrupt the film industry, particularly Hollywood.

In March, a Hollywood executive told Al Jazeera on condition of anonymity: “I don’t see it so much as a threat to production but more to the way production is done as we currently know it.”

He referred to changes in the way post-production was done in the past, such as when people started editing videos on laptops instead of paying post-production companies to do the work.

“Many people were eliminated in that transition, while others were suddenly able to afford a proper editor without the overhead that a post office requires,” he said.

Is Sora the only AI video generator?

No, it’s not. The market for AI video generators is growing day by day. However, a clear differentiator between Sora and other competitors is the unmatched video quality and realism that Sora is capable of producing.

Additionally, the new version, Sora Turbo, comes with a number of advanced video editing features that users can find in Adobe Premiere Pro or Final Cut Pro, two very popular video editing software programs used in film, television and online content creation.

In addition, Sora has the financial backing of the mega software company Microsoft. To date, Microsoft has invested nearly $14 billion with the latest cash injection of $10 billion on January 23. According to CNBC in October, OpenAI now has a $4 billion revolving credit facility, bringing its total liquidity to more than $10 billion. That amount of investment provides Sora with a level of leverage that many other competitors don’t have.

What other video generators are available?

There are several other top-notch AI video generators, including:

Gen 3 Track

Runway, founded in 2018, has raised a total of $237 million in funding and is reportedly in talks with venture capital firm General Atlantic to raise $450 million in new funding, according to The Information, a publication covering the technology industry and the venture capital industry. The free version of Runway Gen 3 can output 10-second video clips at 720p resolution and 30 frames per second. For paid subscribers, video clips can be set to 1440p or 2160p.

Like Sora, it can create a video based on a text message, but it relies heavily on social media creators and marketers who use it to create advertising due to its high speed and efficiency in video projects. short format.

One of the challenges with AI-generated long-form videos is consistency between multiple generated videos. Longer videos require interactive refinement so that all videos look and feel the same.

Leaf AI

Kuaishou-backed Kling, also known internationally as Kwai, is a major Chinese technology company based in Beijing, China. Kling was introduced in June 2024 and is positioning itself as a competitor to platforms like OpenAI’s Sora. Kling can output videos up to two minutes long at 1080p resolution at 30 frames per second.

minimax

MiniMax, a Chinese AI startup, is backed by Alibaba Group Holding, a multinational company specializing in e-commerce, Internet services and technology services based in China and whose most recent financing round was $600 million in March . MiniMax was founded in 2021 by former employees of SenseTime, a leading artificial intelligence company based in Shatin, Hong Kong.

Minimax can output six-second video clips at 720p resolution and 25 frames per second.