Standalone Image Generator Is Among New AI Tools by Meta

Meta Platforms is moving Imagine with Meta from its test bed as a generative AI experience in chats to a standalone experience on the Web that allows users to create high-resolution images using natural language text prompts. That is one of more than 20 generative AI features Meta is deploying to create new business opportunities globally leveraging AI across search, ads, business messaging and more. While most will wind up on Facebook, Instagram, Messenger and WhatsApp, some say Meta’s popular Facebook and Instagram platforms have plateaued at 2 to 3 billion users per month, circumscribing ad growth.

“Meta is facing stiff competition from TikTok, whose U.S. users spend almost double the average time on the short-form video platform as on Meta’s apps. Meanwhile, Snap Inc. and Adobe Inc., the maker of Photoshop, have introduced chatbots, image editors and video creators that are infused with generative AI,” Bloomberg writes.

Noting that Meta has spent “billions on the infrastructure, talent and development needed to keep up in the nascent AI arms race,” Bloomberg points out that the fruit of such efforts has largely been “out of the view of the general public,” as Meta focused on “things like building expensive data centers and releasing open-source versions of the Llama large language model that powers chatbots.”

Imagine with Meta emerges as a new consumer product that, while free to U.S. users at launch, the company will presumably, at some point, try to monetize. Imagine with Meta generates four images per prompt.

Powered by Meta’s own image model Emu, the new platform will compete with Midjourney, OpenAI’s DALL-E and Stability AI’s Stable Diffusion, all of which offer some form of paid subscription.

In the coming weeks, Meta plans to roll out “invisible watermarking” to “increase transparency and traceability” for AI-generated images.

The new invisible watermarks are “resilient to common image manipulations like cropping, resizing, color change (brightness, contrast, etc.), screen shots, image compression, noise, sticker overlays and more,” Meta notes in a blog post, adding that “we aim to bring invisible watermarking to many of our products with AI-generated images in the future.”

According to TechCrunch, interest has increased in watermarking and other means by which GenAI images can be identified. French startup Imatag provides watermarking tech, as does newcomer Steg.AI, while established players like Microsoft, Google, Shutterstock and Midjourney have embraced watermarking guidelines and standards for AI.

Next year, Meta AI plans add features that include “a virtual assistant that can answer questions and generate photorealistic images,” says Bloomberg, noting that “the tool can be used in one-on-one and group chats, as well as in Meta’s augmented reality glasses.”

No Comments Yet

You can be the first to comment!

Leave a comment

You must be logged in to post a comment.