OpenAI recently unveiled its text-to-video model ‘Sora’.
The moment Sora was unveiled it caught everyone’s attention from its capabilities.
The videos generated by Sora look so real that they make people both amazed and worried.
OpenAI recently unveiled its text-to-video model ‘Sora’. According to the company, Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt. The moment Sora was unveiled it caught everyone’s attention from its capabilities.
The videos generated by Sora look so real that they make people both amazed and worried. They seem almost like videos made by humans, with characters that look alive and move smoothly.
Also read: OpenAI releases Sora – All you need to know about this latest video generation AI model
Prompt: “A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. she wears a black leather jacket, a long red dress, and black boots, and carries a black purse. she wears sunglasses and red lipstick. she walks confidently and casually.… pic.twitter.com/cjIdgYFaWq
— OpenAI (@OpenAI) February 15, 2024
Whether it’s scenes of nature or made-up characters, Sora’s videos have lots of detail and look really lifelike. Because they look so real, people are talking a lot about whether it’s okay to make videos like this and what might happen if we do.
Also read: AI sound generator: ElevenLabs will enhance your Sora AI videos
Prompt: “Several giant wooly mammoths approach treading through a snowy meadow, their long wooly fur lightly blows in the wind as they walk, snow covered trees and dramatic snow capped mountains in the distance, mid afternoon light with wispy clouds and a sun high in the distance… pic.twitter.com/Um5CWI18nS
— OpenAI (@OpenAI) February 15, 2024
While it’s natural to feel scared about what AI can do, it’s important to remember that this is just the beginning. AI tools like Sora are only going to get better and more advanced over time.
What we’re seeing now is just a small part of what’s possible. So, while it’s good to be cautious, it’s also important to think about how we can use this technology in positive ways and how we can make sure it’s used responsibly.
— Sam Altman (@sama) February 15, 2024
Campaign India talked to AI ad experts about the creative possibilities presented by Sora and the challenges it could pose from a copyright and quality-of-work perspective.
“All of the existing text-to-video and image-to-video models struggle with common things like framerate and people walking realistically. Sora looks like it’s solved all of that, but also added a level of realism that we’ve never seen before,” Jason Zada, founder of Secret Level, said.
“We’ve been preaching ethically-conscious AI, which includes using actors for performance capture with voice and image. Once we get to a point where we can prompt two generative AI actors to act in a scene, we will move into a dangerous area that threatens the entire filmmaking process, “ Zada added.
“There are also a lot of questions — an entire world of questions regarding misinformation warfare. OpenAI can monitor for this, but if the technology is around, how long before it is replicated? How long before we have AI-generated videos that relay hatred and surgically sway elections?” Henry Daubrez, CEO and chief creative officer at Dogstudio/Dept, said.
Talking about copyright, Henry Cowling– chief innovation officer at MediaMonks– said: When it comes to copyright, we have copyright-protected models to address these challenges. It’s true that how brands choose to engage with technology is an important expression of their values. But the genie is out of the bottle. There’s no going back to a world before LLMs because of copyright alone.
Follow Us
Ayushi Jain
Tech news writer by day, BGMI player by night. Combining my passion for tech and gaming to bring you the latest in both worlds. View Full Profile
