The tech giant said that it would provide researchers with access to components of a new ‘human-like’ artificial intelligence model (Picture: AFP/GETTY IMAGES)

Meta, the parent company of Facebook and Instagram, has released a new artificial intelligence (AI) model that can create human-like images from incomplete sketches.

The model, called I-JEPA, uses ‘knowledge-guided generation’ to fill in the missing details of an image using its knowledge of the world.

On Tuesday, the tech giant said it would provide researchers with access to components of a new ‘human-like’ artificial intelligence model.

The new AI model can analyze and complete unfinished images more accurately than existing models as it uses background knowledge about the world to fill in missing pieces of images, rather than looking only at nearby pixels like other generative AI models, the company said.

Developed by Meta’s top AI scientist, Yann LeCun, the model was trained on a massive dataset of images and text, which allowed it to learn the relationships between different objects and scenes.

This could help solve common errors in AI-generated images, like hands with extra fingers.

Lecun, considered one of the ‘godfathers of AI’, has railed against ‘AI doomerism’ and argued in favour of building safety checks into AI systems.

How does it work?

Meta has released I-JEPA as an open-source project, which means that it is freely available for use by other researchers and developers (Picture: Bloomberg via Getty Images)

To create an image, I-JEPA first analyzes a user-provided sketch. It then uses its knowledge of the world to fill in the missing details, such as the colour of objects, the lighting conditions, and the background. The result is a realistic image that is indistinguishable from a human-created image.

I-JEPA is still under development, but it has the potential to be used in a variety of applications, such as creating realistic avatars for virtual reality (VR) and augmented reality (AR) experiences, generating realistic images for marketing and advertising campaigns, and creating new forms of art and entertainment.

Meta has released I-JEPA as an open-source project, which means that it is freely available for use by other researchers and developers. This will help accelerate the development of new AI image-creation technology applications.

The company’s CEO Mark Zuckerberg, has said that sharing models developed by Meta’s researchers can help the company by spurring innovation, spotting safety gaps and lowering costs.

‘For us, it’s way better if the industry standardizes on the basic tools that we’re using and therefore we can benefit from the improvements that others make,’ he told investors in April.

The company’s executives have dismissed warnings from others in the industry about the potential dangers of the technology, declining to sign a statement last month backed by top executives from OpenAI, DeepMind, Microsoft and Google that equated its risks with pandemics and wars.

Meta is also starting to incorporate generative AI features into its consumer products, like ad tools that can create image backgrounds and an Instagram product that can modify user photos, both based on text prompts.

What could go wrong?