Google's Gemini chatbot gets improved image-creation tools: Here's what is new

Google has announced new enchantments to the image generation capabilities of its chatbot — Gemini. The company has revealed that the upgrades tools are being rolled out on May 1 and promise to offer a more control over the images produced using Google Gemini . “We’re rolling out the ability to easily modify both your AI creations and images you upload from your phone or computer. You can change the background, replace objects, add elements, and more. For example, you can upload a personal photo and prompt Gemini to generate an image of what you’d look like with different hair colours,” Google said in an official blog post.

While details on the specifics of the upgrades are still emerging, Google has indicated that the enhancements will allow for more detailed prompts, resulting in more accurate and visually compelling image outputs. Users can likely expect greater control over aspects like artistic style, specific object details, and the overall composition of the generated images.

The company has also revealed that Gemini has now got multi-step editing capability which means users can get richer, more contextual responses to their prompts with text and images integrated.

“Consistent with all AI-generated images with Gemini, images created or edited with native image generation will include the invisible SynthID digital watermark. We're also currently experimenting with adding a visible watermark on all images generated by Gemini. Native image editing in Gemini will start rolling out gradually today, expanding to more people in over 45 languages and most countries in the coming weeks,” added the company.

The rollout will likely occur in phases, with users gaining access to the new features progressively. Google is expected to provide more comprehensive documentation and examples of the upgraded capabilities in the coming days.