Goal has presented a set of foundational models that it collects under the name Movie Gen, with which it offers creators tools to generate, customize and edit hyper-realistic videos even with audio through text descriptions. In this way, Zuckerberg joins other companies in creating artificial intelligence (AI) tools to generate videos, as OpenAI did with Sora last February.
This new tool, in Meta’s wordsis aimed at content creators and filmmakers, with the goal that it helps “boost their creativity, rather than replace it.” Movie Gen has two functional models, one aimed at video (Movie Gen Video), with 30,000 million parameters, and another focused on generating sounds (Movie Gen Audio), with 13,000 million parameters.
Zuckerberg puts it to the test
As Meta explains, the way Movie Gen works is quite similar to other utilities of this type. With just a text description it is possible to create a video between 4 and 16 seconds long, at 16 frames per second. AI also allows you to edit existing clips using different text descriptions, or even create custom videos uploading a photo of the user. Although the company says that the material is hyperrealistic and has full HD quality, it is striking that Meta has opted to make them with 16 FPS and not a style of 24 frames per second, as is done in the film industry.
Zuckerberg himself provided a first look at Meta Movie Gen’s capabilities through a post on Instagram. In it you can see him exercising, while different elements of the background, his clothes or the devices change according to what is asked of the artificial intelligence.
Ability to generate audio
One of the main differentiating elements of Movie Gen is its ability to generate sounds for the videos in question. Let’s keep in mind that tools like Sora, for example, do not offer this possibility. According to its creators, the 13 billion parameter model can use a video and a text description to generate an audio track that matches what is happening in the image.
Among the examples that Meta shared, a quad is seen accelerating and jumping, with the noise of the engine heard in the background along with music. You can also see a snake moving among the vegetation, with the noise of leaves and the corresponding musical accompaniment also created with AI. On this occasion, the audio allows a duration of up to 45 seconds, and can achieve everything from ambient sounds to instrumental music. However, it does not allow generating voices or dialogues, probably to avoid the generation of deepfakes.
#Meta #rivals #Sora #Movie #Gen #videogenerating
