OpenAI unveils state-of-the-art text-to-video generator tool Sora

The new ground-breaking AI video generator model Sora can generate 60 seconds of motion picture with just a text prompt.

Artificial Intelligence (AI) startup OpenAI unveiled the ground-breaking video generator tool Sora.

The new state-of-the-art AI video generator model Sora generates 60 seconds of motion picture with just a text prompt.

"Sora is a diffusion model, which generates a video by starting with one that looks like a static noise and gradually transforms it by removing the noise over many steps. Sora is capable of generating entire videos all at once or extending generated videos to make them longer. By giving the model foresight of many frames at a time, we’ve solved the challenging problem of making sure a subject stays the same even when it goes out of view temporarily. Similar to GPT models, Sora uses a transformer architecture, unlocking superior scaling performance," the company said.

The sample videos shared by OpenAI look very genuine with realistic human faces.

For instance, the video generated with the test prompt--"A young man in his 20s is sitting on a piece of cloud in the sky, reading a book' looks amazingly great, way better than what we have seen in fictional movies, where gods speak amidst the clouds.

A screen-grab of video generated by Sora AI text-to-video generator tool. 

The Tokyo video with a woman walking in the damp street laced with neon lights beaming from shops around is too good. The human face of the woman looks real with natural skin tone and wrinkles.

However, there are anomalies such as mismatches in the movement of shadows of the people in a scene, but very few can spot them.

A screen-grab of video generated by Sora AI text-to-video generator tool. 

Microsoft-backed OpenAI will first offer Sora to select a team of registered developers for more testing and seek feedback. It aims to ensure Sara is free from misinformation, hateful content, and bias before making it available to the public.

"Sora is becoming available to red teamers to assess critical areas for harms or risks. We are also granting access to several visual artists, designers, and filmmakers to gain feedback on how to advance the model to be most helpful for creative professionals," the company said.

CEO Sam Altman asked his followers to come up with creative text prompts to show how great Sora works. You can check out the sample videos below:

Get the latest news on new launches, gadget reviews, apps, cybersecurity, and more on personal technology only on DH Tech.