OpenAI, the company behind AI -powered chatbot ChatGPT and image generation tool Dall-E, is expanding its offering with software that allows users to generate multi-second videos through text descriptions. Dubbed Sora , OpenAI’s tool aims to conquer the AI-generated video space.
This model, which is initially available to a limited number of users, allows users to generate realistic videos and creative scenes from prompts . As OpenAI points out: “Sora can generate videos up to one minute long while maintaining visual quality and compliance with user prompts.”
The company led by Sam Altman highlighted in a statement that Sora is currently available to members of the "red team," who will be responsible for evaluating critical areas for damage or risks to the tool. In addition, OpenAI has given access to visual artists, designers, and filmmakers to develop the capabilities of this AI model "to make it more useful for creative professionals." Currently, the company highlights that Sora may have difficulty accurately simulating the physics of a complex scene and may not understand specific cases.
OpenAI demonstrates the power of Sora, its new video generation tool
After presenting Sora, Sam Altman , CEO of OpenAI, published a post on his X profile where he invited his followers to propose text descriptions to demonstrate the capabilities of the new tool, capable of creating both realistic and animated images with good resolution.
Among the user suggestions that Altman responded to, Sora was able to generate futuristic cities with a "cyberpunk" aesthetic, or a funny video where a hamster flies on a dragon.
text generation with ChatGPT, OpenAI could revolutionize text-based canada whatsapp data video production with this new tool.
Google is also betting on video generation with Gemini
Google , in its bid to stay in the battle to conquer artificial intelligence, has introduced Gemini 1.5 Pro, a new model that is capable of processing 1 hour of video, 11 hours of audio, 30,000 lines of code or more than 700,000 words. This new generation of Google's AI model, which can evaluate videos and longer texts, will initially be available only to developers and business customers.
Google and Alphabet CEO Sundar Pichai said in a statement that “this new generation also offers a major advance in understanding context.” He highlights that the amount of information that the models can process has increased significantly, being able to execute up to 1 million tokens constantly “and achieve the longest context window of any large-scale basic model to date,” the professional says.
If you cannot view the video correctly, click here.
Newsletter
Subscribe to our newslett
Just as it did with AI-powered
-
tasnimsanika00
- Posts: 39
- Joined: Sat Dec 28, 2024 3:09 am
