Latin America. The company OpenAI, creator of Chat GPT, announced the creation of a new artificial intelligence aimed at creating videos from texts called Sora.
Sora is capable of generating complex scenes with multiple characters, specific types of movement, and precise details of the subject and background. The model understands not only what the user has asked for in the message, but also how those things exist in the physical world.
The model has a deep understanding of language, allowing it to interpret prompts accurately and generate compelling characters that express vibrant emotions. Sora can also create multiple shots within a single generated video that accurately persist the characters and visual style.
In addition to being able to generate a video solely from text instructions, the model can take an existing still image and generate a video from it, animating the content of the image with precision and attention to small detail. The model can also take an existing video and zoom in or fill in the missing frames. Learn more in our white paper.
He highlighted that it is a development that is in the works, which is why they are granting access to a number of visual artists, designers and filmmakers to get feedback on how to move the model forward to make it more useful for creative professionals.
"We're sharing the progress of our research early on to get work and feedback from people outside of OpenAI and to give the public a sense of the AI capabilities that are on the horizon," he said.
Trial version
OpenAI reported that the current model has weaknesses. These include difficulties accurately simulating the physics of a complex scene and may not understand specific cases of cause and effect. For example, a person may take a bite of a cookie, but afterward, the cookie may not have the bite mark.
The model can also confuse the spatial details of a message, for example, by mixing left and right, and may struggle with accurate descriptions of events that take place over time, such as following a specific camera path.
Focus on security
The company announced that it will take several important security measures before Sora is available in OpenAI's products. They seek to avoid misinformation, hateful content, and prejudice.
They're also building tools to help detect misleading content, such as a detection classifier that can indicate when Sora generated a video. They plan to include C2PA metadata in the future if they implement the model in an OpenAI product.
"Our text classifier will check and reject text entry requests that violate our usage policies, such as those that request extreme violence, sexual content, hateful images, images of celebrities, or the IP of others. We've also developed robust image classifiers that are used to review the frames of each generated video to help ensure it complies with our usage policies, before showing it to the user."
