OpenAI launches Sora: How AI can create videos from a text prompt

Contact Counsellor

Last Updated18/02/2024

Recently, OpenAI introduced Sora, a new generative artificial intelligence (GenAI) model capable of converting text prompts into videos.
This marks a significant advancement in the field of AI, addressing previous inconsistencies in text-to-video conversion.

It can create full videos in one go or add more to already created videos to make them longer.
It can generate videos up to a minute long while maintaining visual quality and adhering to the user's prompt.
It can also animate a static image, transforming it into a dynamic video presentation.
It is capable of creating complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background.

OpenAI has developed safety protocols to detect and prevent misuse of Sora. This includes
- A text classifier to reject prompts violating usage policies
- Image classifiers to review generated videos for compliance.
The company plans to engage with policymakers, educators, and artists to understand concerns and identify positive use cases for the technology.
The company will also work with visual artists, designers, and filmmakers to gather feedback for further improvements.

Struggles with accurately simulating complex scenes' physics
Understanding specific instances of cause and effect.
- For example, a person might take a bite out of a cookie, but afterward, the cookie may not have a bite mark.
It may also confuse spatial details and struggle with precise descriptions of events that unfold over time.