Toggle light / dark theme

Meta unveiled its Make-a-Scene text-to-image generation AI in July, which like Dall-E and Midjourney, utilizes machine learning algorithms (and massive databases of scraped online artwork) to create fantastical depictions of written prompts. On Thursday, Meta CEO Mark Zuckerberg revealed Make-a-Scene’s more animated contemporary, Make-a-Video.

As its name implies, Make-a-Video is, “a new AI system that lets people turn text prompts into brief, high-quality video clips,” Zuckerberg wrote in a Meta blog Thursday. Functionally, Video works the same way that Scene does — relying on a mix of natural language processing and generative neural networks to convert non-visual prompts into images — it’s just pulling content in a different format.

“Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage,” a team of Meta researchers wrote in a research paper published Thursday morning. Doing so enabled the team to reduce the amount of time needed to train the Video model and eliminate the need for paired text-video data, while preserving “the vastness (diversity in aesthetic, fantastical depictions, etc.) of today’s image generation models.”

Sometimes, it can be hard to follow dietary recommendations despite new dieting ideas and trends.

Everyone’s dietary needs are different, which means that diets often need to be diverse and tailored based on individual needs and health risks.

A recent study published in Gastroenterology looked at diets high in fermentable fiber in mice and their associated risk for developing liver cancer.

CAPE CANAVERAL, Fla. (AP) — The world now has stunning new photos of this week’s asteroid strike, the first planetary defense test of its kind.

NASA on Thursday released pictures of the dramatic event taken by the Hubble and Webb space telescopes.

A few hours later, SpaceX joined NASA in announcing that they’re studying the feasibility of sending a private mission to Hubble, potentially led by a billionaire, to raise the aging telescope’s orbit and extend its life.

Regent has released video of its remarkable Seaglider prototype in flight testing. The first machine to combine the efficiency advantages of ground effect and hydrofoiling in a single design, it promises revolutionary speed and range in coastal areas.

Wing-in-ground effect (WIG) aircraft such as the Soviet-era Ekranoplan have shown promise in the past, but they’re yet to take off, so to speak, as a mainstream form of transport. These low-flying birds ride on a cushion of air between their wings and the surface, which gives them a significant lift and efficiency boost over regular planes flying higher in the air – as long as they stay within their own wingspan of the surface beneath. This extreme altitude restriction means that while ground-effect aircraft could fly over land, it’s too dangerous for regular operations, and they typically stay over water.

The numbers haven’t been attractive enough to date, but the era of electrification brings a set of new incentives to the game. Electric boats are struggling to prove their worth; batteries simply don’t hold enough energy to push through the tough medium of water for long distances. Early electric aircraft struggle to deliver useful range with a decent number of passengers on board, too. Regent looked at this, and saw a situation where the efficiency of the old ground-effect vehicle could give it a genuine commercial advantage, if paired with another, more recent technology.

Few human injuries are as catastrophic as those to the spine. An accident, disease or act of violence affecting the spine can result in poor function – even paralysis – almost anywhere in the body.

The spinal column is enormously complex, with limited capacity for regeneration and any health implications are usually long-term and chronic.

While there is no known way to repair a spinal cord injury (SCI), scientists may be on the cusp of some important breakthroughs. New approaches are being taken to reverse the nerve damage, with some researchers attempting to reshape the architecture of the spinal cord using materials engineered in the laboratory.

The existing jacket can perform one logical operation per second, compared to the more than a billion operations per second typical of a home computer, says Preston. In practice, this means the jacket can only execute short command sequences. Due to the speed of the logic, along with some other engineering challenges, Zhang says he thinks it’ll take five to 10 years for these textile-based robots to reach commercial maturity.

In the future, Preston’s team plans to do away with the carbon dioxide canister, which is impractical. (You have to refill it like you would a SodaStream.) Instead, his team wants to just use ambient air to pump up the jacket. As a separate project, the team has already developed a foam insole for a shoe that pumps the surrounding air into a bladder worn around the waist when the wearer takes a step. They plan to integrate a similar design into the jacket.

Preston also envisions clothing that senses and responds to the wearer’s needs. For example, a sensor on a future garment could detect when the wearer is beginning to lift their arm and inflate without any button-pressing. “Based on some stimulus from the environment and the current state, the logic system can allow the wearable robot to choose what to do,” he says. We’ll be waiting for this fashion trend to blow up.