CNN Indonesia
Friday, 16 Feb 2024 19:34 IWST
AI video maker from OpenAI, Sora, shows off even though it hasn’t been officially released yet. (OpenAI)
Jakarta, CNN Indonesia —
Even though OpenAI hasn’t officially released yet, Soraan artificial intelligence (AI) video creation platform, has been revealed to be capable of making videos that are truly realistic like recordings camera.
“Meet Sora, our text-to-video model. Sora can create videos up to 60 seconds long featuring highly detailed scenes, complex camera movements, and many characters with vivid emotions,” tweeted OpenAI, an artificial intelligence company led by Sam Altman, on its Twitter account.
In the upload, OpenAI shows a video of Tokyo, Japan, in the middle of snow and filled with cherry blossoms. The appearance is very realistic, like recording using a drone camera with high resolution.
It is acknowledged that the video was created using just a paragraph command (prompt).
“The beautiful and snowy city of Tokyo is bustling. The camera moves through the busy city streets, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Beautiful cherry blossom petals flutter in the wind with snowflakes,” the video prompt reads.
In the upload at his blog on Wednesday (14/2), OpenAI said Sora was able to produce videos up to 60 seconds long from text instructions, with the ability to present scenes with multiple characters, certain types of movement, and detailed background details.
“The model (Sora) understands not only what the user is asking for promptbut also how they exist in the physical world,” according to the company.
OpenAI said it intends to train AI models so they can “help people solve problems that require real-world interactions.”
Sora is the latest effort from the company that owns the viral ChatGPT chatbot to continue to push forward the progress of generative AI.
Although ‘multi-modal models’ are nothing new and other text-to-video models have existed before, Reece Hayden, senior analyst at market research firm ABI Research, reported CNNadmitted that Sora has advantages in the form of duration and accuracy.
Hayden said this kind of AI model could have a major impact on the digital entertainment market with new, personalized content streamed across channels.
“One obvious use case is in TV; creating short scenes to support a narrative,” he explains, “The model is still limited, but it shows where the market is headed.”
OpenAI acknowledged Sora is still a work in progress with clear “weaknesses,” particularly in terms of the spatial details of a prompt. Namely, mixing left and right prompts, as well as cause and effect.
For example, a video of someone biting into a cake but there is no bite mark afterwards.
For now, OpenAI remains focused on security issues. The company plans to work with a team of experts to test the latest model and look closely at areas including misinformation, hate content and bias.
OpenAI is also building tools to help detect misleading information.
While there is no official public release date yet, Sora will first be available to cybersecurity professors, so-called “red teamers,” who can assess the dangers or risks of a product.
It also gives access to a range of visual artists, designers and filmmakers to gather input on how creative professionals can use it.
The latest update comes as OpenAI continues to advance ChatGPT. Earlier this week, the company said it was testing a feature where users could control ChatGPT memory.
This allows them to ask the platform to remember the chat to make future conversations more personal or tell it to forget what was previously discussed.
(team/arh)
2024-02-16 12:34:37
#OpenAI #shows #Sora #realistic #artificial #intelligence #video #creator
