Home » OpenaAI showed how ChatGpt can be used to create videos identical to real ones

OpenaAI showed how ChatGpt can be used to create videos identical to real ones

by admin
OpenaAI showed how ChatGpt can be used to create videos identical to real ones

OpenAI just unveiled Soraits first AI model capable of generate videos starting from text.

The image quality, as well as the fluidity of subject and camera movements, are impressive.

And impressive is the fact that you can get – it seems – clips that can last up to a minute.

OpenAI has released some examples of content generated by Sora, such as that of a girl walking in the night, in Tokyo, and which was obtained by typing this prompt:

“A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. she wears a black leather jacket, a long red dress, and black boots, and carries a black purse. she wears sunglasses and red lipstick. she walks confidently and casually. the street is damp and reflective, creating a mirror effect of the colorful lights. many pedestrians walk about”.

They already exist Sora-like toolsand also open to the public, but none of these – think of Runway for example – they are able to produce minute-long clips like those released by OpenAI.

On its official blog, OpenAI writes that “Sora is capable of generating complex scenes with multiple characters, specific types of movement, and accurate subject and background details. The model includes not only what the user asked for in the prompt, but also how different elements coexist in the real world.”

Sora is not currently open to the public. In short, it cannot be proved. OpenAI has made this new model available to “red teams” who identify any AI security flaws and a small group of visual artists and filmmakers who were asked to provide “feedback”.

See also  With 3 seconds of our voice the AI ​​will make us say things we never said

Various fears are associated with the amazement at the perfect images created from a simple text. There is a risk, for example, that such technology make it even easier to produce deepfakes. And then there is the environmental issue: generating a simple image with AI has a significant impact on the planet’s resources. To create a 60-second video you will need even more computing power and therefore even more energy.

prompt: “Several giant wooly mammoths approach treading through a snowy meadow, their long wooly fur lightly blows in the wind as they walk, snow covered trees and dramatic snow capped mountains in the distance, mid afternoon light with wispy clouds and a sun high in the distance creates a warm glow, the low camera view is stunning capturing the large furry mammal with beautiful photography, depth of field”

OpenAI has highlighted for now current technical defects:

“The current model has weaknesses. It may have difficulty accurately simulating the movements of a complex scene and may not understand specific instances of cause and effect. For example, a person might take a bite of a cookie, but then the cookie may not leave a bite mark.”

“The model can also confuse the spatial details of a prompt, such as confusing left and right, and may have difficulty with precise descriptions of events that occur over time, such as following a specific camera trajectory.”

See also  Stephen Fry: Greek Mythology, Singularity and the EU AI Act

You may also like

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More

Privacy & Cookies Policy