OpenAI, the developer of ChatGPT, has added a new one to the artificial intelligence models that are taking the world by storm today. “soraThe model called ” can create video from text. From the sample images shared by the company, the model is frighteningly good.

Sora is currently being tested by people who are experts in issues such as disinformation, hate content and bias. The company indicates that it wants to take the necessary security measures before the model is put into use.

Sora can create realistic 60-second videos with text commands

“The beautiful, snowy and lively city of Tokyo. The camera moves through the busy city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Beautiful sakura petals fly with snowflakes in the wind.”

*If you can’t watch the video, click the link here.

As we said at the beginning, Sora is a text-to-video creation model. In other words, it can turn a text command you type into a video. OpenAI, Sora 60 seconds, He explained that he can make videos of up to one minute.

of these videos the visual quality remains high, is highly detailed, involves complex movements and has multiple characters with vivid emotions It was said he could accommodate. Looking at the videos, we see that it is terrifyingly realistic. OpenAI’s statement reads as follows:

Sora is open to people such as artists, filmmakers and designers, as well as security testers. These people will provide feedback using the artificial intelligence tool and contribute to the further development of the model.

It can also create videos from images

*If you can’t watch the video, click the link here.

In addition, OpenAI added that it can create videos not only from text, but also from images. According to the company’s statement, it can take an existing image and turn it into a video. He also pays attention to small details and details in this video.

It is not without some weaknesses

Because the model is still in the testing phase, it obviously also has weaknesses. OpenAI also recognizes this. The company sometimes analyzes the physics of complex scenes. may have difficulty simulating it accurately. And may not understand cause-and-effect examples say.

For example, in a video we can see that someone bites into a cookie, but afterwards there is no bite mark on this cookie. It is also said that it can confuse details such as left and right and have difficulty explaining events that may occur over time, such as tracking the movement of the camera. You can see examples of these errors above.

However, if we look at the sample videos in general, we can see what great potential Sora has. Clearly it has the potential to revolutionize artificial intelligence models. We’ll see what he can do when he visits everyone.

Other video examples produced with Sora

*If you can’t watch the video, click the link here.

*If you can’t watch the video, click the link here.