OpenAI’s text-to-video generator “Sora” now proves that AIs are becoming smarter. The tool creates almost perfect realistic scenes from text prompts.
Those: Sora/OpenAI
The Sora text-to-video generator has the ability to create and visualize both realistic and imaginary scenes. Sora is part of an OpenAI research project that aims to give artificial intelligence the ability to understand and recreate movements in the real world. The model is intended to generate high-quality videos of up to one minute in length and precisely take user input into account. For example, Sora is able to create complex scenes with multiple people and characters, specific types of movement, and precise subject and background details.
The videos that OpenAI presents on its website to introduce the tool are diverse: everything from scenes from the animal kingdom, everyday scenes with several people to cute animated characters. The results are definitely impressive.
Please accept YouTube cookies to play this video. If you accept this, you will access content from YouTube, a service provided by an external third party.
YouTube privacy policy
If you accept this notice, your choice will be saved and the page will be updated.
View YouTube content
Of course, the tool also has some weaknesses. For example, it often cannot understand cause and effect, such as when a person bites into something and the piece bitten off is not missing. For this reason, OpenAI decided to publish the tool in an early development phase in order to incorporate user feedback into the development to improve the tool.
Who can use the tool and what measures are there?
The tool is currently not available to the general public. In order to improve and expand the tool, access was initially only made available to certain groups. This includes people from creative fields as well as security assessment experts to test and further develop the model in different contexts. OpenAI writes on the website: “We are also developing tools to detect misleading content, such as a detection classifier that can determine whether a video was generated by Sora.” This is to prevent the tool from being used for improper purposes. With “Sora”, OpenAI presents another important step in the development of artificial intelligence.