Google Relaunches AI Image Generation Tool with Enhanced Accuracy and Diversity

Google to relaunch controversial tool for creating AI images after inaccuracies

Google said it will soon allow users to create images of people using its Gemini artificial intelligence tool, after pulling the AI image-generation tool in February. In a blog post on 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."

Google to relaunch tool for creating AI-generated images of people after pulling service due to inaccuracies

Google said it will soon allow users to create images of people using its Gemini artificial intelligence tool, after pulling the AI image-generation tool in February. In a blog post on 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."

Google relaunching problematic tool for AI-generated images

Aug. 28 (UPI) --Google has retooled its controversial Gemini artificial intelligence tool for generating images of people and made it customizable and available for use within days. Google launched the Gemini AI image-generation program earlier this year but pulled it after it produced controversial images that led to many accusing the program of having an inherent bias. Among images that produced controversy and claims of bias were those that depicted a Black viking, an Asian Nazi soldier and a female pope. Google officials apologized for the controversial images and said they were due to the program being designed to ensure diversity in its images but without considering cases in which AI-generated images would be specific to particular types of people. The retooled AI image-generator called Imagen 3 enables users to customize the AI tool by creating custom "Gems" that act as personalized "AI experts" for any topic. Users can refine the Gems to achieve specific outcomes, write instructions for the Gem and chat with it to obtain the desired results. Google is including several Gems with the new Imagen 3 AI tool. Those Gems include a learning coach, inspirational brainstormer, writing editor, coding partner and a career guide. Google is launching its retooled Imagen 3 for Gemini subscribers this week.

Months after controversy, Google AI can generate images of humans again

Ars testing shows some historical prompts no longer generate artificially diverse scenes. Further ReadingGoogle's Gemini AI model is once again able to generate images of humans after that function was "paused" in February following outcry over historically inaccurate racial depictions in many results. Further ReadingIn a blog post, Google said that its Imagen 3 model -- which was first announced back in May -- will "start to roll out the generation of images of people" to Gemini Advanced, Business, and Enterprise users in the "coming days." But a version of that Imagen model -- complete with human image-generation capabilities -- was recently made available to the public via the Gemini Labs test environment without a paid subscription (though a Google account is needed to log in). That new model comes with some safeguards to try to avoid the creation of controversial images, of course. Google writes in its announcement that it doesn't support "the generation of photorealistic, identifiable individuals, depictions of minors or excessively gory, violent or sexual scenes." In an FAQ, Google clarifies that the prohibition on "identifiable individuals" includes "certain queries that could lead to outputs of prominent people." In Ars' testing, that meant a query like "President Biden playing basketball" would be refused, while a more generic request for "a US president playing basketball" would generate multiple options. In some quick tests of the new Imagen 3 system, Ars found that it avoided many of the widely shared "historically inaccurate" racial pitfalls that led Google to pause Gemini's generation of human images in the first place. Asking Imagen 3 for a "historically accurate depiction of a British king," for instance, now generates a set of bearded white guys in red robes, rather than the racially diverse mix of warriors from the pre-pause Gemini model. More before/after examples of the old Gemini and the new Imagen 3 can be found in the gallery below. Some attempts to depict generic historical scenes seem to fall afoul of Google's AI rules, though. Asking for illustrations of "a 1943 German soldier" -- which Gemini previously answered with Asian and Black people in nazi-esque uniforms -- now tells users to "try a different prompt and check out our content policies." Requests for images of "ancient chinese philosophers," "a woman's suffrage leader giving a speech," and "a group of nonviolent protesters" also led to the same error message in Ars' testing. "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," the company writes on its blog. "We'll gradually roll this out, aiming to bring it to more users and languages soon." Listing image by Google / Ars Technica