-
NYT ‘Connections’ October 28: Clues and Answers for Game #505 - 12 mins ago
-
Trump headlines Madison Square Garden rally after vulgar, racist remarks from allies - 13 mins ago
-
WNBA coaching changes for the 2025 season - 15 mins ago
-
Vinicius Junior Favourite For Ballon d’Or In Post-Lionel Messi/Cristiano Ronaldo Era - 29 mins ago
-
China’s industrial profits plunge at fastest pace since the pandemic - 43 mins ago
-
Aaron Rodgers, Jets coach riff on ‘darkness’ after upset loss to Patriots - 44 mins ago
-
Beef not behind McDonald’s E. coli; Quarter Pounders back this week - 57 mins ago
-
Timothée Chalamet crashes his own look-alike contest after police shut down crowded event – National - about 1 hour ago
-
Norman-Era Hoard of Silver Coins Becomes Britain’s Most Valuable Treasure - about 1 hour ago
-
Oil slides over 4% as Israel’s attack on Iran unlikely to disrupt supplies - about 1 hour ago
Google Gemini will again support AI image generation of people
The Deepmind logo is being displayed on a smartphone with the Google Gemini logo in the background in this photo illustration in Brussels, Belgium, on February 8, 2024.
Jonathan Raa | Nurphoto | Getty Images
Google said it will soon allow users to create images of people using its Gemini artificial intelligence tool, after pulling the AI image generation option in February.
In a blog post Wednesday, Dave Citron, a senior director of product on Gemini, wrote that early access to Google’s new Imagen 3 generator will be available to Gemini Advanced, Business and Enterprise users starting in English in the coming days.
“We’ve worked to make technical improvements to the product, as well as improved evaluation sets, red-teaming exercises and clear product principles,” Citron wrote. Red-teaming refers to a practice companies use to test products for vulnerabilities.
Google paused its image generation feature earlier this year after saying it was offering “inaccuracies” in historical pictures. Embarrassing examples spread across social media.
One user asked the tool to generate an image of a German soldier in 1943, and it created a racially diverse set of soldiers wearing German military uniforms. Another query for a historical depiction of a medieval British king also generated a racially diverse set of images, including a woman ruler.
Citron said Imagen 3 doesn’t support photorealistic identifiable individuals, depictions of minors or excessively gory, violent or sexual scenes.
“Of course, as with any generative AI tool, not every image Gemini creates will be perfect, but we’ll continue to listen to feedback from early users as we keep improving,” Citron wrote. “We’ll gradually roll this out, aiming to bring it to more users and languages soon.”
Source link