Should You Be Scared? OpenAI Introduces Sora ‘Text-To-Video’ AI That Absolutely Stuns Social Media With Mind-Bending PhotoReality.

OpenAI is launching a new video-generation model, and it’s called Sora. The AI company says Sora ‘can create realistic and imaginative scenes from text instructions.’

Social media right now is on fire, in a total state of shock over the new hyper-realistic videos created in under 30 second by an AI program called Sora from OpenAI.

It is the most-realistic AI video you’ve ever seen, and text-to-video technology is still very much in it’s infancy.

For a comparison, think of how different things had been if the first plane successfully flown at Kitty Hawk would have done 60 miles-per-hour instead of the 6.8 MPH it actually did. That would have made for a completely different development curve.

That’s Sora, and she’s here to blow your mind.

“But thou, O Daniel, shut up the words, and seal the book, even to the time of the end: many shall run to and fro, and knowledge shall be increased.” Daniel 12:4 (KJB)

We are right now in a period of time where AI programs like Sora can be given a text prompt like “show me two kittens eating tacos in a snowstorm in August”, and in under 30 seconds you are looking at that video.

What does that mean? It means that from this moment on, no photo can be trusted, no video believed, there is zero guarantee that anything we are shown from this point on is actually real.

These text-to-video creations are starting hyper-realistic, but in a few months to a year they will be indistinguishable from an actual video or movie.

AI is like that old movie ‘The Blob’ with Steve McQueen in the 1950’s. It’s oozing out of every crack and crevice, and there is no where to go to get away from it.

AI is of the Devil, and it’s here to prepare the world for the arrival of Antichrist.

Now, the really mind-blowing part of all this is that the videos are created from words, spoken or typed, and the AI ‘gives birth’ to the video. God created everything using words. AI so very much has the fingerprint of the Devil all over it. Avoid it for as long as you can, but fair warning, soon it will be impossible to avoid.

OpenAI introduces Sora, its text-to-video AI model

FROM THE VERGE: Sora is capable of creating “complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background,” according to OpenAI’s introductory blog post. The text-to-video model allows users to create photorealistic videos up to a minute long — all based on prompts they’ve written.

The company also notes that the model can understand how objects “exist in the physical world,” as well as “accurately interpret props and generate compelling characters that express vibrant emotions.”

The model can also generate a video based on a still image, as well as fill in missing frames on an existing video or extend it. The Sora-generated demos included in OpenAI’s blog post include an aerial scene of California during the gold rush, a video that looks as if it were shot from the inside of a Tokyo train, and others.

Many have some telltale signs of AI — like a suspiciously moving floor in a video of a museum — and OpenAI says the model “may struggle with accurately simulating the physics of a complex scene,” but the results are overall pretty impressive.

A couple of years ago, it was text-to-image generators like Midjourney that were at the forefront of models’ ability to turn words into images. But recently, video has begun to improve at a remarkable pace: companies like Runway and Pika have shown impressive text-to-video models of their own, and Google’s Lumiere figures to be one of OpenAI’s primary competitors in this space, too.

Similar to Sora, Lumiere gives users text-to-video tools and also lets them create videos from a still image.

None of this is real either

Sora is currently only available to “red teamers” who are assessing the model for potential harms and risks.

OpenAI is also offering access to some visual artists, designers, and filmmakers to get feedback. It notes that the existing model might not accurately simulate the physics of a complex scene and may not properly interpret certain instances of cause and effect. READ MORE

Source