wordpress blog stats
Connect with us

Hi, what are you looking for?

OpenAI introduces new text-to-video AI generator called Sora

access to Sora is currently limited to researchers to assess critical areas for harm or risks, and a select group of creative professionals.

Image Source: Screenshot from example video shared by OpenAI

OpenAI on February 16 introduced Sora, the company’s new text-to-video AI generator that can generate videos up to a minute long based on user prompts. The company shared some examples of videos created with Sora that, despite some obvious signs of being AI-generated, are impressive. However, access to the tool is currently limited to researchers to assess critical areas for harm or risks and a select group of creative professionals to gain feedback on advancing the model, OpenAI informed.

 

OpenAI CEO Sam Altman also took a few prompts from users on X, which you can find here, here, here here, and here.

“In addition to being able to generate a video solely from text instructions, the model is able to take an existing still image and generate a video from it, animating the image’s contents with accuracy and attention to small detail. The model can also take an existing video and extend it or fill in missing frames,” OpenAI said.

As you might guess, along with the myriad of positive use cases, the potential for misuse of this technology is also high. OpenAI has tried to calm fears by noting that Sora will reject prompts that violate OpenAI’s usage policies, like those that request extreme violence, sexual content, hateful imagery, celebrity likeness, or the intellectual property of others. The company has also said it will take several other important safety steps ahead of making Sora available in OpenAI’s products and that it is working with red teamers  in areas like misinformation, hateful content, and bias , who will be adversarially testing the model.

Also, the model does have some glaring weaknesses. “It may struggle with accurately simulating the physics of a complex scene, and may not understand specific instances of cause and effect. For example, a person might take a bite out of a cookie, but afterward, the cookie may not have a bite mark. The model may also confuse spatial details of a prompt, for example, mixing up left and right, and may struggle with precise descriptions of events that take place over time, like following a specific camera trajectory,” OpenAI warned.

But these weaknesses could be useful in the fight to detect AI-generated content:

OpenAI has also said that it will build tools that can tell when a video was generated by Sora and such videos will also include C2PA metadata, the same kind it is embedding in images generated by Dall.E.

There are also emerging concerns on what data was Sora trained on and what does it mean for the creators of those content:

For more about Sora and example footage, here is the research from OpenAI.

Also Read

 


STAY ON TOP OF TECH NEWS: Our daily newsletter with the top story of the day from MediaNama, delivered to your inbox before 9 AM. Click here to sign up today!


 

Written By

Free Reads

News

The ‘Reforming Intelligence and Securing America Act’ (RISAA) is a legislation to reauthorize Section 702 of the Foreign Intelligence Surveillance Act (FISA).

News

In its submission, the Interior Ministry said the decision to impose a ban was "made in the interest of upholding national security, maintaining public...

News

Among other things, the security requirements include data encryption and regular review and updated access permissions to reflect personnel changes.

MediaNama’s mission is to help build a digital ecosystem which is open, fair, global and competitive.

Views

News

NPCI CEO Dilip Asbe recently said that what is not written in regulations is a no-go for fintech entities. But following this advice could...

News

Notably, Indus Appstore will allow app developers to use third-party billing systems for in-app billing without having to pay any commission to Indus, a...

News

The existing commission-based model, which companies like Uber and Ola have used for a long time and still stick to, has received criticism from...

News

Factors like Indus not charging developers any commission for in-app payments and antitrust orders issued by India's competition regulator against Google could contribute to...

News

Is open-sourcing of AI, and the use cases that come with it, a good starting point to discuss the responsibility and liability of AI?...

You May Also Like

News

Google has released a Google Travel Trends Report which states that branded budget hotel search queries grew 179% year over year (YOY) in India, in...

Advert

135 job openings in over 60 companies are listed at our free Digital and Mobile Job Board: If you’re looking for a job, or...

News

By Aroon Deep and Aditya Chunduru You’re reading it here first: Twitter has complied with government requests to censor 52 tweets that mostly criticised...

News

Rajesh Kumar* doesn’t have many enemies in life. But, Uber, for which he drives a cab everyday, is starting to look like one, he...

MediaNama is the premier source of information and analysis on Technology Policy in India. More about MediaNama, and contact information, here.

© 2008-2021 Mixed Bag Media Pvt. Ltd. Developed By PixelVJ

Subscribe to our daily newsletter
Name:*
Your email address:*
*
Please enter all required fields Click to hide
Correct invalid entries Click to hide

© 2008-2021 Mixed Bag Media Pvt. Ltd. Developed By PixelVJ