Google Bard is the internet search giant’s contribution to the recent generative AI craze. Though oddly, its image generation capabilities are getting a new addition, via the recently announced ImageFX. The latter is also available as a standalone tool for those who are only interested in that aspect of generative AI.
For the most part, this new tool is used like any other text-to-image generator out there – you enter your prompt, and the tool generates an image based on what was provided. Google says that what makes ImageFX different is the inclusion of “expressive chips” as part of the prompt to help further tweak or narrow down the style of the image.
Introducing #ImageFX ✨ a new image generation tool powered by Imagen 2, Google's most advanced text-to-image model. We’re excited to add this to our suite of generative AI tools at Labs, and to help bring your most creative ideas to life. Try it out: https://t.co/e07Zz3Pdx4 pic.twitter.com/MVXEEt9c2b
— labs.google (@labsdotgoogle) February 1, 2024
Naturally, the ImageFX tool comes with the usual safeguards that you see with most image generators today. This includes IPTC metadata showing that images are generated, as well as the SynthID digital watermark. Then there are other guardrails to “limit problematic outputs” of the violent, offensive and sexually explicit variety. A natural inclusion, considering what happened last week.
Unfortunately, this is not something that’s widely available just yet. In fact, extremely limited is about as accurate a phrase as it gets when describing who gets access. Google says that ImageFX is now available in US, New Zealand, Australia and Kenya. No word on when this list will be expanded just yet.
(Source: Google)
