Categories
Life Style

How OpenAI’s text-to-video tool Sora could change science – and society

[ad_1]

An animated sequence from a video generated by OpenAI's Sora of a young man reading a book while sitting on a cloud.

Sora is one of several AI tools that generates video from text promptsCredit: OpenAI

The release of OpenAI’s Sora text-to-video AI tool last month was met with a mix of trepidation and excitement from researchers who are concerned about misuse of the technology. The California-based company showcased Sora’s ability to create photorealistic videos from a few short text prompts, with examples including clips of a woman walking down a neon-lit street in Tokyo and a dog jumping between two windowsills.

Tracy Harwood, a digital-culture specialist at De Montfort University in Leicester, UK, says she is “shocked” by the speed at which text-to-video artificial intelligence (AI) has developed. A year ago, people were laughing at an AI-produced video of the US actor Will Smith eating spaghetti. Now some researchers are worried that the technology could upend global politics in 2024.

OpenAI, which also developed ChatGPT and the text-to-image technology DALL·E, debuted Sora on 15 February, announcing that it was making the technology “available to red teamers to assess critical areas for harms or risks”. ‘Red teaming’ refers to the process of conducting simulated attacks or exploitation of a technology to see how it would cope with nefarious activity, such as the creation of misinformation and hateful content, in the real world.

Sora isn’t the first example of text-to-video technology; others include Gen-2, produced by Runway in New York City and released last year, and the Google-led Lumiere, announced in January. Harwood says she has been “underwhelmed” by some of these other offerings. “They are becoming more and more vanilla in what they present to you,” she says, adding that the programs require very specific prompts to get them to produce compelling content.

Misinformation is a major challenge for these text-to-video technologies, Harwood adds. “We’re going to very quickly reach a point in which we are swamped with a barrage of really compelling-looking information. That’s really worrying.”

Election fears

That poses particular problems with upcoming elections, including the US presidential election in November and an impending general election in the United Kingdom. “There will be colossal numbers of fake videos and fake audio circulating,” says Dominic Lees, who researches generative AI and filmmaking at the University of Reading, UK. Fake audio of the leader of the UK Labour Party, Keir Starmer, was released in October 2023, and fake audio of US President Joe Biden encouraging Democrats not to vote circulated in January.

One solution might be to require text-to-video AI to use watermarks, either in the form of a visible mark on the video, labelling it as AI, or as a telltale artificial signature in the video’s metadata, but Lees isn’t sure this will be successful. “At the moment watermarks can be removed,” he says, and the inclusion of a watermark in a video’s metadata relies on people actively researching whether a video they’ve watched is real or not. “I don’t think we can honestly ask audiences across the world to do that on every video they’re looking at,” says Lees.

There are potential benefits to the technology, too. Harwood suggests it could be used to present difficult text, such as an academic paper, in a format that is easier to understand. “One of the biggest things it could be used for is to communicate findings to a lay audience,” she says. “It can visualize pretty complex concepts.”

Another potential use might be in health care, with text-to-video AI able to talk to patients in place of a human doctor. “Some people might find it disconcerting,” says Claire Malone, a consultant science communicator in the United Kingdom. “Others might find it extremely convenient if they want to ask a medical professional questions multiple times a day.”

Data management

Text-to-video AI tools such as Sora could help researchers to wade through huge data sets, such as those produced by the European particle-physics laboratory CERN near Geneva in Switzerland and other large scientific projects, says Malone. Generative AI could “sift out code and do the mundane tasks of research”, she adds, but also do “much more sophisticated work [such as] giving it data and asking it to make predictions”.

Concerns have also been raised by people working in creative industries. The US actor Tom Hanks suggested last year that AI could enable him to continue appearing in films “from now until kingdom come” after his death. “If you were a young ambitious actor thinking about their future, and you were told ‘I’m sorry, Tom Hanks is always going to play the leading roles’, would you plan a future in that?” says Lees.

Text-to-video AI will throw up broad issues for society to face. “We’re going to have to learn to evaluate the content we see in ways we haven’t in the past,” says Harwood. “These tools put the opportunity to be a media content creator in the hands of everybody,” she says. “We’re going to be dealing with the consequences of that. It’s a fundamental shift in the way material will be consumed.”

[ad_2]

Source Article Link

Categories
News

How to access OpenAI Sora text-to-video AI video generator

How to access OpenAI Sora text-to-video AI model

OpenAI has released details on how to access its new and highly anticipated Sora text-to-video AI model, capable of generating amazing  animations and videos from text prompts. Initially OpenAI is making Sora available to red teamers to assess critical areas for harms or risks. OpenAI is being very careful about who gets to use Sora. They’re only letting a few professionals and their own team try it out. Why? Because they want to make sure it’s used responsibly. They’re worried about the wrong people using it for the wrong reasons, so they’re taking their time to think about the best way to introduce Sora to the world.

Even though Sora isn’t out for everyone yet, it’s already causing a lot of talk about where video technology is headed. It’s so good at making videos from text that some people are comparing it to deepfake technology. You know, the kind that can make fake videos that look real. That’s why there’s a bit of worry about how this kind of tech could be misused and what that could mean for everyone.

How To Access Sora

Sora is becoming available to red teamers to assess critical areas for harms or risks. OpenAI are also granting access to a number of visual artists, designers, and filmmakers to gain feedback on how to advance the model to be most helpful for creative professionals. For more examples of what has already been created using the Sora AI video generator jump over to the official OpenAI website.

Here are some other articles you may find of interest on the subject of OpenAI :

OpenAI Availability Announcement

“Introducing Sora, our text-to-video model. Sora is an AI model that can create realistic and imaginative scenes from text instructions. Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt.

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.

Categories
News

Runway AI text-to-video Ambient Motion Control feature demo

New Runway AI text-to-video Ambient Motion Control feature demonstrated

Runway the text-to-video AI service is transforming the way we create videos and animations with a powerful new feature that allows users to add motion to static images with incredible precision. This ambient control setting is a breakthrough for those who use the platform, offering a sophisticated method to animate AI-generated content. Whether you’re looking to add a gentle sway to trees in a landscape or subtle expressions to a character’s face, this tool makes it possible.

The Ambient Motion Control feature is a leap forward for Runway text-to-video users, providing a refined way to animate AI-generated content. Imagine wanting to capture the subtle rustle of leaves or the nuanced expressions in a portrait that make it appear almost alive. With the ambient slider, you can adjust the intensity of the motion, customizing the animation to fit your vision. This user-friendly feature allows for the quick creation of different clips for comparison.

Runway text to video AI

Features of Runway

  • Pre-trained AI models: These models cover a variety of tasks, like generating photorealistic images or videos from text prompts, manipulating existing media like changing the style of a video or adding special effects, and analyzing content to identify objects or people.
  • Image of RunwayML AI model generating video from text prompt
  • No coding required: RunwayML’s interface is designed to be user-friendly and intuitive, even for those with no coding experience. You can access and use the various AI models with simple clicks and drags.
  • Customizable tools: The platform also allows users to train their own AI models and import models from other sources, giving them even more control over their creative process.
  • Community-driven: RunwayML has a thriving community of creators who share their work and collaborate on projects. This fosters a sense of inspiration and learning for everyone involved.

When you adjust the ambient settings, the impact on your videos is clear. A slight tweak can add a gentle movement to foliage, while a stronger setting can create the illusion of a windy day. For portraits, the technology can mimic realistic movements, such as hair fluttering in the breeze or the natural blink of an eye, giving your animations a sense of authenticity and life.

But the ambient control is just one part of what Runway text-to-video AI service offers. Others include camera controls and text prompts, which help direct the viewer’s attention and add narrative to your animation. To further enhance your work, you can use post-processing techniques with tools like Adobe After Effects to achieve a professional finish.

RunwayML text-to-video

  • AI Magic Tools: These are pre-trained models that let you perform various tasks with just a few clicks, such as generating different artistic styles for an image, changing the lighting or weather in a video, or adding facial expressions to a still image.
  • AI Training: This feature allows you to train your own custom AI models using RunwayML’s platform. This is helpful if you need a model that performs a specific task that is not already available in the pre-trained model library.
  • Video Editor: RunwayML also includes a full-featured video editor that you can use to edit your videos and add special effects.
  • Community: The RunwayML community is a great place to find inspiration, learn new things, and share your work with others.

By mastering the ambient controls and incorporating camera movements, you can produce animations that not only draw the viewer in but also fully immerse them in the story you want to tell. These creations go beyond simple videos; they are experiences that draw audiences into the worlds you create.

RunwayML’s ambient control setting within the motion brush feature opens up new possibilities for creativity. By experimenting with different images, artistic styles, and additional tools like camera controls and Adobe After Effects, you can create animations that are visually and emotionally compelling. As you become more skilled with these features, your work will stand out in the world of AI-generated content, captivating viewers with every frame. RunwayML is a powerful and versatile AI text to video platform that can be used to create all sorts of amazing things give it a try for yourself a free.

Image Credit :  RunwayML

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.