Tuesday, February 7, 2023
HomeUS NewsWhat is it? Is it free?

What is it? Is it free?

  • Social media users have been having fun with an app called Lensa and its latest “magic avatar” feature.
  • The app lets people upload photos of themselves, which are then turned into magical, whimsical AI images.
  • Some social media users have cautioned against the apps, claiming they rob artists and pose a safety threat to those who upload their photos to the app.
- Advertisement -

You could look like a warrior, gearing up for battle. Or maybe you’d like to be surrounded by flowers, donned in a bridal gown. Better yet, how about a goddess?

These depictions, called magic avatars, are images made by an app called Lensa. Owned by Prisma Labs, Lensa allows users to upload photos of themselves, pay a fee, and within minutes, download photos of themselves in all kinds of whimsical settings.

The avatars have quickly gained popularity among social media users and celebrities, including Chance the Rapper, Michaela Jaé Rodriguez and Taraji P. Henson.

But while the AI-generated photos have been a hit among some, there have been claims that apps of this sort are stealing from real artists. Others say they produce racist depictions of users who upload their photos.

Here’s what to know about these magic avatars and how the company has responded to warnings against them.

Deepfakes:What is a deepfake? This video technology is spooking some politicians

No, Paris Hilton and Tom Cruise aren’t dating:A TikTok video with impersonator confuses fans

Two original images and two AI-generated images created by Lensa.

What are ‘magic avatars’ from the Lensa AI app? How are they created?

This latest fad started with Stability AI, the company that created a network model called stable diffusion. The model uses internet data to generate images from text.

Lensa uses a copy of the stable diffusion model, allowing users to upload their own photos and wait as the app creates personalized images, the company said on its website. The model was trained using LAION 5B, a large dataset with image-text pairs. 

Story Credit: usatoday.com

- Advertisment -

Most Popular