Taylor Swift deepfakes be damned, Google is releasing a brand new AI-powered tool, ImageFX, for image creation.
Underpinned by Imagen 2, a GenAI image model developed by Google’s DeepMind team, ImageFX offers a prompt-based UI to create and edit images. That’s no different than tools like OpenAI’s DALL-E 3, Midjourney, Meta’s Imagine with Meta AI and Microsoft Designer. But ImageFX’s unique twist is “expressive chips” — mainly a listing of keyword suggestions that permit users experiment with “adjoining dimensions” of their creations and concepts.
“Designed for experimentation and creativity, ImageFX enables you to create images with an easy text prompt, then easily modify them with a brand new tackle prompting using expressive chips,” Google writes in a blog post.
But what of the potential for abuse — especially in light of recent events?
Image Credits: Google
Google claims that it’s taken steps to make sure that ImageFX can’t be utilized in ways in which it wasn’t intended, for instance by adding “technical safeguards” to limit “problematic outputs” like violent, offensive and sexually explicit content. ImageFX also has a prompt-level filter for “named people,” presumably public figures — although Google wasn’t especially clear on that time in its press materials.
“We invested in the security of coaching data from the outset,” Google said. “Consistent with our AI principles, we also conducted extensive adversarial testing and red teaming to discover and mitigate potential harmful and problematic content.”
As a further preventive measure, Google’s tagging images produced using ImageFX with SynthID, a digital watermark that’s allegedly robust against image edits and crops.
A picture sample from Imagen 2. Image Credits: Google
“SynthID watermarks are imperceptible to the human eye but detectable for identification,” Google continues within the blog post. “With added insights in ‘About this image,’ you’ll know if a picture could have been generated with Google’s AI tools while you come across it in Google Search or Chrome.”
You’ll find ImageFX in AI Test Kitchen, Google’s web app for experimental AI projects.
Imagen 2 expanded
In related news today, Google said that it’s bringing Imagen 2 to more of its services and products starting this week, including to its next-gen AI search experience and family of managed AI services Vertex AI.
Imagen 2 — which also now powers text-to-image capabilities in Google Ads and Duet AI in Workspace, Google’s GenAI suite of products for productivity — has made its way into Google’s SGE (Search Generative Experience). SGE, which began surfacing image generation tools for users in Google Image Search last October, now taps Imagen 2 for generating images. Users can enter a prompt specifying what type of image they need and SGE will return 4 results directly within the SGE conversational experience.
One other sample from Imagen 2. Image Credits: Google
In Vertex AI, Imagen 2 is obtainable through an API to Google Cloud customers. Elsewhere, Imagen 2 is now invokable through Bard, Google’s AI-driven chatbot.
“With Imagen 2, Bard understands easy or complex prompts so you could generate a variety of high-quality images,” Google explains. “Just type in an outline — like ‘create a picture of a dog riding a surfboard’ — and Bard will generate custom, wide-ranging visuals to assist bring your idea to life.”
Google still hasn’t revealed the information it used to coach Imagen 2, which — while disappointing — doesn’t exactly come as a surprise. It’s an open legal query as as to if GenAI vendors like Google can train a model on publicly available — even copyrighted — data after which turn around and commercialize that model.
Image Credits: Google
Relevant lawsuits are working their way through the courts, with vendors arguing that they’re protected by fair use doctrine. However it’ll be a while before the dust settles.
Within the meantime, Google’s playing it protected by keeping quiet on the matter.
