Meta has introduced a new image generation feature called Imagine that allows users to create images in real time with the help of its AI model. This feature is currently in beta and is available to users on WhatsApp and the Meta AI website. Users can generate images by typing the prompt “Imagine” followed by a description of the image they want to create. The image will change as users continue to type.
This new feature utilizes Meta’s latest open-source large language model, Llama 3, to generate sharper and higher quality images. It also has a better ability to include text in images. Once an image is created, users have the option to animate it, iterate on it in a new style, or turn it into a GIF.
Meta’s AI assistant has undergone several updates recently, allowing users to receive specific recommendations and assistance, such as restaurant recommendations with “sunset views” or “vegan options,” interior decor inspiration, or help with studying difficult concepts. CEO Mark Zuckerberg has referred to this as “pretty wild” news, but Meta is still working to catch up to competitors like OpenAI and Anthropic.
The company is continuing to train larger models like Llama 3 and is expected to release them soon. These models are likely to be on par with OpenAI’s GPT-4 and Anthropic’s Claude 3 Opus, which were both recently released. Overall, Meta’s Imagine feature and AI advancements demonstrate the company’s commitment to innovation and providing users with unique and versatile tools.