OpenAI, the makers of ChatGPT, has recently revealed their proprietary text-to-video generator called Sora. The AI model can create 1 minute long videos “while maintaining visual quality and adherence to the user’s prompt”.
“Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background”, the company stated in a blog post. The company added several videos produced by Sora. It includes videos of “photorealistic close-ups of two pirate ships”, “a young man in his 20s is sitting on a piece of cloud in the sky”, and many more.
See Related: OpenAI Launches ChatGPT Plus Subscription In India; Includes GPT-4
Sora AI And OpenAI Past Research
Sora is a diffusion model that builds on OpenAI’s past research on DALL-E and GPT models. It can either generate the entire video all at once or extend a generated video and make it longer. It can produce a full video from a still image in the same style.
The company has iterated its intent on ensuring the safety of Sora before introducing it in other OpenAi products. It is working with several red teamers to test the integrity of the model, in areas like misinformation, hateful content, and bias. Additionally, they have pledged to work with artists and policymakers “to understand their concerns and to identify positive use cases for this new technology”.
This technology will not be available for quite some time as it is still under development. Addressing the decision to reveal the model early, OpenAI stated, “We’re sharing our research progress early to start working with and getting feedback from people outside of OpenAI and to give the public a sense of what AI capabilities are on the horizon”.