Apple’s latest Vision Pro update improves the look of ‘Persona’ avatars

A key feature of Apple’s Vision Pro VR, er, spatial computing headset is Personas that that lets people see a digital version of themselves during calls, Zoom meetings, etc. At launch, they looked a bit creepy, but Apple has improved them considerably in the latest release, according to posts on X spotted by MacRumors. They’re now more realistic, so users look less like impressionist paintings and more like humans. 

Once the visionOS 1.1 update is installed, you’ll be prompted to recapture your Persona to get the “latest appearance updates” — this is apparently done in part with the headset off and pointing at your face. Most users feel the updated Personas are better, and visually, they look less blurry and a touch more realistic, plus the proportions seem better.

So, maybe it’s just me, but I feel like the visionOS 1.1 beta vastly improves the Persona feature.

Is it still uncanny and creepy? Yeah, but I don’t look like Stalin anymore. pic.twitter.com/uYGUugHFSl

— Snazzy Labs (@SnazzyLabs) February 6, 2024

As a reminder, Personas are a digital representing of the users created by data from the headset’s sensors and a new machine learning algorithm. They’re designed to be an “authentic spatial representation” of someone that shows their facial expressions and hand movements — so you won’t be a dork in a mask on group calls.

If you need to do that, though, a similar feature called EyeSight shows other people a digital version of your eyes when you’re wearing the Vision Pro. Apple still calls Personas a beta feature and provides detailed instructions to get the best results.

This article originally appeared on Engadget at https://www.engadget.com/apples-latest-vision-pro-update-improves-the-look-of-persona-avatars-100558320.html?src=rss 

Toyota announces a three-row electric SUV for US customers

While Toyota helped lead the hybrid charge with its Prius, the company has been less active in EV production. But that might be in the past, as Toyota has announced another $1.3 billion for its Kentucky facility, with a focus on EVs. In particular, the company is building a new three-row electric SUV that will be available for US customers. 

Toyota’s Kentucky operation is its flagship facility, with nearly 9,400 employees. “Today’s announcement reflects our commitment to vehicle electrification and further reinvesting in our US operations,” Kerry Creech, president of Toyota Kentucky, said in a release. “Generations of our team members helped prepare for this opportunity, and we will continue leading the charge into the future by remaining true to who we are as a company and putting our people first for generations to come.”

Little is known so far about the three-row electric SUV, as Toyota only mentions it briefly in relation to the investment. However, it follows the company’s prior announcement of its Urban SUV concept slated to launch in Europe this year. 

The $1.3 billion investment will also go towards creating a battery pack assembly line at its Kentucky factory (a separate manufacturing plant in North Carolina produces the batteries). Toyota has big plans for its battery production, previously announcing three battery ranges focused on higher performance and low cost slated for 2026 and onward. The company is also working on its first solid-state batteries, which have the potential to charge an EV from 10 to 80 percent in 10 minutes. Toyota’s bZ4X EV currently takes 32 minutes to do so. 

This article originally appeared on Engadget at https://www.engadget.com/toyota-announces-a-three-row-electric-suv-for-us-customers-092545458.html?src=rss 

Apple releases an AI model that can edit images based on text-based commands

Apple isn’t one of the top players in the AI game today, but the company’s new open source AI model for image editing shows what it’s capable of contributing to the space. The model called MLLM-Guided Image Editing (MGIE), which uses multimodal large language models (MLLMs) to interpret text-based commands when manipulating images. In other words, the tool has the ability to edit photos based on the text the user types in. While it’s not the first tool that can do so, “human instructions are sometimes too brief for current methods to capture and follow,” the project’s paper (PDF) reads. 

The company developed MGIE with researchers from the University of California, Santa Barbara. MLLMs have the power to transform simple or ambiguous text prompts into more detailed and clear instructions the photo editor itself can follow. For instance, if a user wants to edit a photo of a pepperoni pizza to “make it more healthy,” MLLMs can interpret it as “add vegetable toppings” and edit the photo as such.

Apple

In addition to changing making major changes to images, MGIE can also crop, resize and rotate photos, as well as improve its brightness, contrast and color balance, all through text prompts. It can also edit specific areas of a photo and can, for instance, modify the hair, eyes and clothes of a person in it, or remove elements in the background. 

As VentureBeat notes, Apple released the model through GitHub, but those interested can also try out a demo that’s currently hosted on Hugging Face Spaces. Apple has yet to say whether it plans to use what it learns from this project into a tool or a feature that it can incorporate into any of its products.  

This article originally appeared on Engadget at https://www.engadget.com/apple-releases-an-ai-model-that-can-edit-images-based-on-text-based-commands-081646262.html?src=rss 

Ben Affleck’s Child Seraphina, 15, Debuts Dramatic New Buzzcut While Hugging Mom Jennifer Garner in Sweet New Photos

The ‘Gone Girl’ star and his ex-wife’s middle child sported a fresh new haircut while waiting for the school bus in Los Angeles on February 6.

The ‘Gone Girl’ star and his ex-wife’s middle child sported a fresh new haircut while waiting for the school bus in Los Angeles on February 6. 

Taylor Swift Expertly Handles Near On-Stage Fall While Dancing on Chair During ‘Eras’ Show: Watch

The singer was performing her sexy song ‘Vigilante Sh*t’ when she seemed to slip during the epic Tokyo concert.

The singer was performing her sexy song ‘Vigilante Sh*t’ when she seemed to slip during the epic Tokyo concert. 

Bluesky has added almost a million users one day after opening to the public

Bluesky, the open source Twitter alternative, has seen a surge in new users just one day after opening its platform up to the public. The service has gained more than 850,000 users bringing its total sign-ups to just over 4 million.

The service had been in an invitation-only beta for about a year and had grown to just over 3 million users when it officially opened to the public. It currently has close to 4.1 million sign-ups, according to an online tracker. “Things are rolling over here,” Bluesky CEO Jay Graber wrote in a post on X.

The surge in new users suggests that there is still ample curiosity about the Jack Dorsey-backed platform that began as an internal project at Twitter in 2019. It also indicated that Meta hasn’t entirely cornered the market for a text-based Twitter alternative. The company’s Threads app has grown to 130 million monthly users, Meta announced last week.

Graber has said that Bluesky intended to grow at a slower pace so that it could build it the platform, and the underlying protocol, without the added pressure sudden surges in growth can cause. Some of those concerns were borne out over the last day as the spike in activity led to some technical issues on the site, including problems with the app’s custom feeds and a brief outage overnight. The outage was resolved within a couple hours, according to the company.

Much of Bluesky’s future success will hinge on whether it can maintain new growth and keep the interest of all its new users. Threads also saw an initial spike in new users, only for it to drop-off before eventually rebounding.

Though Bluesky may look a bit like Threads or X, it’s a fundamentally different kind of platform and part of the growing movement for decentralized social media. Its open-source protocol functions like a “permanently open” API, according to Graber, and the site already has dozens of developers building their own experiences. Bluesky also offers more customization features for users, with features like custom algorithms and the ability to choose your own content moderation settings.

This article originally appeared on Engadget at https://www.engadget.com/bluesky-has-added-almost-a-million-users-one-day-after-opening-to-the-public-004854186.html?src=rss 

Morgan Wade Breaks Her Silence on Rumored Feud With Kyle Richards in Rare Statement

Less than one week after the Bravo personality shared an update about her friendship with Morgan, the singer took to social media to clarify where they stand.

Less than one week after the Bravo personality shared an update about her friendship with Morgan, the singer took to social media to clarify where they stand. 

Generated by Feedzy
Exit mobile version