"Google is not just blowing smoke-the new image generator is much better. Its grasp of the world and the nuance of language is apparent, producing much more realistic results. Even before this, AI images were getting so good that it could be hard to spot them at a glance. Gone are the days when you could just count fingers to identify AI. Google is making an effort to help identify AI content, though."
"Images generated with Nano Banana Pro continue to have embedded SynthID watermarks that Google's tools can detect. The company is also adding more C2PA metadata to further label AI images. The Gemini app is part of this effort, too. Starting now, you can upload an image and ask something like "Is this AI?" The app won't detect just any old AI image, but it will tell you if it's a product of Google AI by checking for SynthID."
"At the same time, Google is making it slightly harder for flesh and blood humans to know an image was generated with AI. Operating with the knowledge that professionals may want to generate images with Nano Banana Pro, Google has removed the visible watermark from images for AI Ultra subscribers. These images still have SynthID, but only the lower tiers have the Gemini twinkle in the corner."
Google's Nano Banana Pro significantly improves AI image realism, making generated images harder to spot. Images from Nano Banana Pro embed SynthID watermarks that Google's tools can detect, and the company is adding C2PA metadata to label AI images. The Gemini app can check uploaded images for Google-origin SynthID and report whether an image is a product of Google AI. Google removed the visible watermark for AI Ultra subscribers while retaining SynthID, leaving only lower-tier images with the Gemini visible marker. Access limits vary by tier: AI Ultra receives the highest usage, Gemini Pro receives less, and free users have the most restricted access.
Read at Ars Technica
Unable to calculate read time
Collection
[
|
...
]