OpenAI Sora is a New AI Mode l Generate One-Minute videos from Text Prompts
OpenAI, creators of ChatGPT, have introduced their latest AI “Sora” capable to produce realistic-looking one-minute videos solely from text prompts.
IN SHORT:
- The developers behind ChatGPT have introduced a fresh AI model named Sora.
- This innovative AI utilizes basic text prompts to craft concise one-minute videos.
- Presently, Sora is exclusively accessible to internal testers, as well as select artists and designers.
The developers behind ChatGPT, OpenAI, have introduced a new AI model named Sora. This model is capable of generating an entire one-minute video based solely on text inputs. “We’re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction,” the OpenAI Sora blog reads.
OpenAI CEO Sam Altman also showed the tool through updates on his X account. “We’d like to show you what sora can do, please reply with captions for videos you’d like to see, and we’ll start making some!!” Altman expressed in his post. Many users on the platform submitted prompts, and the outcomes he shared exhibit striking realism.
Another OpenAI member has shared a Sora-generated video and it is a little hard to believe how real it looks.
OpenAI reports that Sora has the ability to create elaborate scenes with multiple characters, intricate movements, and elaborate backgrounds. The model not only understands the user’s instructions but also interprets how these components translate into real-world contexts. “The model has a deep understanding of language, enabling it to accurately interpret prompts and generate compelling characters that express vibrant emotions. Sora can also create multiple shots within a single generated video that accurately persist characters and visual style,” says OpenAI.
While the OpenAI Sora model has added a lot of excitement to the internet this morning, popular YouTuber Marques Brownlee aka MKBHD has rightly pointed out the possible concerns around the model. “Every single one of these videos is AI-generated, and if this doesn’t concern you at least a little bit, nothing will,” he wrote in his post.
The potential of the OpenAI Sora model undeniably showcases impressive capabilities presently. Yet, exercising caution regarding a model capable of effortlessly producing a one-minute video from basic text prompts is imperative, considering its susceptibility to misuse. Reflecting on the AI-generated video of Will Smith consuming spaghetti that gained viral attention in early 2023, one can appreciate the substantial leap that Sora signifies from that. Another notable instance featured Scarlett Johansson consuming a meal. Sora illustrates a significant advancement with its remarkably realistic looking videos.
OpenAI, however, is not avoiding the safety discourse. The company asserts that, before integrating Sora into OpenAI’s offerings, they will enact several vital safety measures. These encompass engaging with red teamers, experts proficient in misinformation, hateful content, and bias domains. They will rigorously assess the model to pinpoint potential vulnerabilities. Furthermore, OpenAI will devise tools to spot deceptive content, like a detection classifier proficient in identifying Sora-generated videos.
OpenAI will also harness existing safety protocols developed for its DALL·E 3-based products, which are pertinent to Sora. For instance, within an OpenAI product, the company’s text classifier will scrutinize and reject input prompts violating usage policies, such as those soliciting extreme violence, sexual content, hateful imagery, or celebrity resemblance. The company emphasizes establishing robust image classifiers to scrutinize every frame of produced videos, ensuring compliance with usage policies prior to user access.
OpenAI also emphasizes its active engagement with policymakers, educators, and artists worldwide to address concerns and explore the positive applications of this groundbreaking technology. “We’ll be engaging policymakers, educators, and artists around the world to understand their concerns and to identify positive use cases for this new technology. Despite extensive research and testing, we cannot predict all of the beneficial ways people will use our technology, nor all the ways people will abuse it. That’s why we believe that learning from real-world use is a critical component of creating and releasing increasingly safe AI systems over time,” says OpenAI.
At present, Sora is exclusively accessible to red teamers to check out the important areas. OpenAI is also extending access to visual artists, filmmakers, and designers to collect input on enhancing the model.
(source:Indiatoday)