AI video is freaky and weird right now. But where are they going?

AI Video & Visuals


Short videos give the impression of flipbooks, swaying from one surreal frame to the next. These are the result of Internet meme creators playing around with the first widely available text-to-video AI generators, and they’re the result of Dwayne “The Rock” Johnson eating rocks and nasty things like the President of France. I am envisioning a possible scenario. Emmanuel Macron Sift through the trash, chew, and distort the mundane like Paris Hilton taking a selfie.

This new wave of AI-generated videos has a distinct echo of the Dall-E that took the internet by storm last summer, performing the same trick with still images. Less than a year later, these shaky Dall-E images are almost indistinguishable from reality, begging two questions. Will AI-generated video advance this fast?

ModelScope, a video generator hosted by AI company Hugging Face, allows people to type just a few words and receive amazingly shaky videos. His AI company, Runway, which co-developed the image generator Stable Diffusion, announced the text-to-video generator in late March, but hasn’t made it widely available to the public. Both Google and Meta have announced that they are working on text-to-video technology in the fall of 2022.

see more

Now it’s either a jarring celebrity video or a teddy bear drawing a self-portrait. But in the future, AI’s role in cinema could evolve beyond viral memes, with technology helping film casting, modeling scenes before shooting, and even swapping actors in and out of scenes. It may become possible. The technology is advancing rapidly, and it will likely be many years before such a generator can produce an entire short film based on a prompt. Still, the potential for AI in entertainment is immense.

“Just as Netflix has disrupted how and where content is viewed, I think AI will create even greater disruption to the actual creation of that content itself,” says Sinead Bovell, futurist and founder of tech education firm WAYE. says.

But that doesn’t mean AI will completely replace writers, directors, and actors anytime soon. And some considerable technical hurdles remain. The AI ​​model still can’t maintain perfect frame-to-frame consistency, which is necessary for smooth visuals, so the video looks choppy. It takes more computer power and more data to create compelling, grotesque, and consistent content that lasts longer than a few seconds. In other words, a large investment in technology development is required. “You can’t easily scale up these image models,” says Bharath Hariharan, a professor of computer science at Cornell University.

But even as rudimentary as it seems, progress on these generators is progressing “really, really fast,” says Jiasen Lu, a research scientist at the Allen Institute for Artificial Intelligence.

The speed of progress is the result of new developments that have enhanced the generator. Like an image generator, ModelScope is trained with text and image data, and is also fed a video showing the model in action. should do it Look, says Apolinário Passos, machine learning art engineer at Hugging Face. It’s a tactic used in the meta. The burden of annotating videos and labeling them with text descriptors was removed, simplifying the process and allowing rapid advancement of the technology.

But this generative video technology is unlikely to eliminate humans from the film process. Wonder Dynamics, a company that enables filmmakers to drag and drop computer-generated characters into their videos, uses AI to provide an inexpensive way to bring visual effects into movies. The goal is not only to add generated humans instead of real people, but also imaginative characters such as aliens and robots to complement the process and make VFX more accessible. When movies become dehumanized, the “magic of cinema” can disappear, says Wonder Dynamics co-founder Nikola Todorovich. “What is the point of a movie if there are no humans involved in making it?”

The success of AI in cinema depends on its ability to recreate its magic. Previous attempts have been interesting, but ultimately disappointing or even harmful. can engineer content does not mean that should do it“Nothing, Forever,” a take on the never-ending streaming AI parody my neighbor seinfeld, lead character “Larry Feinberg” was briefly banned from Twitch in February after he made a transphobic joke. After the clip to put in went viral last week, it was immediately deemed “diabolical” and “terrifying.” As Jason Parham wrote on his WIRED earlier this week, AI has “turned fantasies into terrible bards.” Creating AI like this can strip you of control over your own image and demean it. “They are visceral and the distortion is like a dagger,” Parham writes.

There is certainly room for improvement. “I think in the future it will be possible to generate credible and good content, and it could evoke human emotions, but it could be done by AI actors,” he said. says Mr. She thinks it could happen in the next decade. But even if it were possible, the question remains whether it’s what viewers want. “Society may decide something isn’t right about it,” she says.

Videos also raise other ethical concerns. Now text-to-video clips are almost unbelievable. But as technology advances, it may become easier for anyone to create compelling deepfakes with just a few lines of text. And like any image generator, using images you don’t own can subject you to copyright lawsuits.

Creating a complete movie or show with just one generator and a few lines of text is a daunting task, but a combination of various AI tools makes it possible, Passos said. ChatGPT writes the script, the voice generator reads it, the videohe generator creates the visuals and all the pieces can be edited together. “These building blocks are already there,” says Passos. “He does it all and he might take one model leap. But those leaps could come in a matter of weeks.”





Source link

Leave a Reply

Your email address will not be published. Required fields are marked *