Meta (formerly known as Facebook) has rolled out a new "Imagine with Meta" which is a standalone AI-powered image generator. The new tool is powered by artificial intelligence and it enables the users to create images by describing them in natural language.
The image generator was first previewed at the Connect event which took place in November 2023 and it has been available as a part of Meta’s AI chatbot.
About Imagine with Meta
'Imagine with Meta' is powered by the company's existing Emu image generation model. This model creates high-resolution images from text prompts received from the users. At present, the tool is free to use by any user in the United States and generates four images on every prompt.
In an official Blogspot, Meta stated, "Today, we’re expanding access to imagine outside of chats, making it available in the US to start at imagine.meta.com. This standalone experience for creative hobbyists lets you create images with technology from Emu, our image foundation model.”
It further added, "While our messaging experience is designed for more playful, back-and-forth interactions, you can now create free images on the web, too.”
Creating images via AI will leave a visible watermark in the lower left corner which will indicate that they were created with Meta AI. It also reduces the chance of people mistaking them for human-generated content.
Meta said that it will add invisible watermarking to the Imagine with Meta AI experience which will help in increasing transparency and traceability in the coming weeks (timeline not specified, by the time of writing). The invisible watermark will be applied with a deep learning model.
Meta said, "While it’s imperceptible to the human eye, the invisible watermark can be detected with a corresponding model. It’s resilient to common image manipulations like cropping, colour change (brightness, contrast, etc.), screenshots and more. We aim to bring invisible watermarking to many of our products with AI-generated images in the future.”
Inputs from IANS