Meta, challenging OpenAI, announces new AI model that can generate video with sound.
Facebook owner Meta has announced the development of a new AI model called Movie Gen, which can create realistic-seeming video and audio clips in response to user prompts. This move positions Meta as a challenger to OpenAI, a leading player in the generative AI space. Movie Gen is designed to rival tools from other media generation startups like ElevenLabs.
According to Meta, Movie Gen can generate videos up to 16 seconds long at 16 frames per second. It also includes capabilities for personalized video generation, precise video editing, and audio generation. The model can ingest a video and text prompt to produce high-quality and high-fidelity audio files, including ambient sound, sound effects, and instrumental background music — all synced to the video content.
Meta has shared samples of Movie Gen’s creations, which include videos of animals swimming and surfing, as well as videos using people’s real photos to depict them performing actions like painting on a canvas. The tool can also edit existing videos by specifying elements within the video using a text prompt.
In a blog post and a research paper about the tool, Meta revealed that it used a mix of licensed and publicly available datasets to build Movie Gen. The company is unlikely to release Movie Gen for open use by developers, as it has with its Llama series of large-language models, citing individual risk assessments for each model. Instead, Meta is working directly with the entertainment community and other content creators on uses of Movie Gen and plans to incorporate it into Meta’s own products sometime next year.
This announcement comes as Hollywood grapples with how to harness generative AI video technology. OpenAI has been meeting with Hollywood executives and agents to discuss possible partnerships involving its Sora model, although no deals have been reported yet. Anxieties over OpenAI’s approach increased in May when actor Scarlett Johansson accused the company of imitating her voice without permission for its chatbot.
The introduction of Movie Gen by Meta underscores the growing competition in the AI video generation space, with various companies vying to enhance and expedite filmmaking processes. However, concerns about copyright infringement and the use of AI-generated fakes, or deep fakes, in elections around the world remain a significant issue. Lawmakers have highlighted these concerns, particularly in the US, Pakistan, India, and Indonesia.
source:https://www.reuters.com/technology/artificial-intelligence/meta-challenging-openai-announces-new-ai-model-that-can-generate-video-with-2024-10-04/
