Gemini in Google Docs Gets In-Line Image Generation Feature
In a blog post, the tech large detailed the brand new function. With Gemini in Google Docs, customers can generate in-line photos utilizing textual content prompts. The function is powered by the corporate’s newest picture era mannequin Imagen 3, which might create photos of individuals, landscapes, objects and extra throughout a variety of kinds.
AI-powered in-line picture era function in Google Docs
Photo Credit: Google
Users can activate the function by clicking on the ‘Insert’ menu and navigating to ‘Help me create a picture’ throughout the ‘Images’ choice. This will open the Gemini facet panel. The identical Insert menu additionally has a ‘Cover photos’ choice, utilizing which customers can generate AI-powered cowl photos.
To generate an in-line picture, customers can kind a textual content immediate detailing what they need after which choose from three side ratios — sq., huge, and tall. Additionally, customers also can select between totally different kinds together with pictures, vector artwork, sketch, watercolour, cyberpunk, and extra.
After clicking on the ‘Create’ button, the function will generate 4 totally different photos. Users can both choose one in every of them or click on on ‘View extra’ to see extra choices. Once chosen, the picture is added to the doc and will be adjusted on the web page manually.
Notably, the function is being rolled out to Google Workspace customers with Gemini Business, Gemini Enterprise, Gemini Education, Gemini Education Premium, or the Google One AI Premium add-on. Currently, the function is just out there on the Web. While the function has already been rolled out to eligible customers, it’d take as much as 15 days earlier than it’s seen in Docs.
