Meta presented the AI ​​video generator Movie Gen: it creates 16-second videos with sound and can insert real people into them

Meta✴ introduced an artificial intelligence-based video generator, Movie Gen, which allows you to create or edit videos using a simple text request – the company is becoming an increasingly serious competitor to OpenAI and Google in the field of AI, writes Bloomberg.

Image source: Gerd Altmann / pixabay.com

Based on text queries, Movie Gen creates new videos up to 16 seconds long. The same queries can be used to generate audio for existing videos, to edit finished videos, or to create a video featuring a real person based on a given photograph. For now, only some of the company’s employees, as well as its partners, including some directors, can use Movie Gen; and next year Meta✴ intends to add neural network support to its popular applications.

The company is still discussing how best to implement this integration, but Movie Gen’s goal is to encourage social media users to actively create or edit video posts, said Connor Hayes, Meta✴ vice president of generative AI. . “The tool will be easy to use, useful for bloggers, good for general in-app experiences, but at this point we don’t have a specific product plan for what it will look like,” Hayes said.

Meta✴ has large amounts of data, which is enough to train AI capable of generating text, sound or video. The company has invested several billion dollars in this area and has built a Meta✴ AI chatbot into most of its applications, capable of answering user questions and maintaining a conversation. Other large companies also have their own video generators – for example, OpenAI Sora and Google Veo.

The company is in no hurry to launch Movie Gen: currently creating a video based on a text request takes “several tens of minutes,” and it is unlikely that the average social network user will use such a tool on their phone. Meta✴ also has to address several important issues “related to safety and liability”: for example, it should not be possible for one person to create a video of inappropriate content involving another; The company also intends to label AI-generated videos so people know their source—an important lesson learned from the deepfake stories.

Now the AI ​​direction is a priority for Meta✴ – AI, its head Mark Zuckerberg is sure, can become a factor in the growth of both the user base of the company’s services and its income. In addition, AI will play a growing role in both Meta✴’s applications and the future devices it produces or intends to produce, including smart glasses. AI featured prominently at the presentation of the prototype Orion holographic augmented reality glasses that Meta✴ unveiled last week.

admin

Share
Published by
admin

Recent Posts

Nissan Leaf EV to Become NACS-Ported Compact Crossover in Third Generation

Nissan Leaf can rightfully be considered a long-liver of the electric car market, since the…

2 days ago

OpenAI expects to more than triple its revenue this year and then double it next year.

OpenAI, the market leader in generative artificial intelligence systems, remains nominally a startup, its financial…

2 days ago

OpenAI Decides to Hold 4o Image Generation Launch for Free Users

OpenAI has been forced to delay the release of ChatGPT's built-in image generator for free…

2 days ago

1440p and 240Hz for just $200: Xiaomi updates the 27-inch Redmi G27Q gaming monitor

Xiaomi continues to update its Redmi G27Q gaming monitor every year. The model was first…

2 days ago

Beware, Android is shutting down: OS development will cease to be public, but there is no reason to panic

Android device makers can significantly customize the look and feel of the operating system, but…

2 days ago

Fake GeForce RTX 4090s with RTX 3090 chips have started popping up in China — craftsmen are even changing the GPU markings

In China, scammers have started selling GeForce RTX 3090 graphics cards, passing them off as…

2 days ago