Google Docs Gets Upgraded With Gemini-Powered Text-to-Image Generation Feature

In-line image generation capability in Google Docs is being powered by the Imagen 3 AI model.

Written by Akash Dutta, Edited by Manas Mitul | Updated: 18 November 2024 14:24 IST

Google Docs Gets Upgraded With Gemini-Powered Text-to-Image Generation Feature

Photo Credit: Google

The Google Docs feature is available only to Workspace users with a Gemini add-on

Highlights

The AI feature lets users choose from multiple aspect ratios
Google Docs’ image generation feature also offers multiple styles
Earlier, Google released an AI cover image feature for Docs

Google Docs is getting a new artificial intelligence (AI) feature that will allow users to generate in-line images. Announced on Friday, the feature will be available via Gemini to Google Workspace users. The text-to-image generator is powered by the Mountain View, California-based tech giant's Imagen 3 AI model and can generate high-resolution images that can be added to the document. Users can also pick between different aspect ratios and image styles. Earlier this year, the tech giant added an AI-powered cover image feature to Google Docs.

Gemini in Google Docs Gets In-Line Image Generation Feature

In a blog post, the tech giant detailed the new feature. With Gemini in Google Docs, users can generate in-line images using text prompts. The feature is powered by the company's latest image generation model Imagen 3, which can create images of people, landscapes, objects and more across a wide range of styles.

AI-powered in-line image generation feature in Google Docs
Photo Credit: Google

Users can activate the feature by clicking on the ‘Insert' menu and navigating to ‘Help me create an image' within the ‘Images' option. This will open the Gemini side panel. The same Insert menu also has a ‘Cover images' option, using which users can generate AI-powered cover images.

To generate an in-line image, users can type a text prompt detailing what they want and then pick from three aspect ratios — square, wide, and tall. Additionally, users can also choose between different styles including photography, vector art, sketch, watercolour, cyberpunk, and more.

After clicking on the ‘Create' button, the feature will generate four different images. Users can either pick one of them or click on ‘View more' to see more options. Once selected, the image is added to the document and can be adjusted on the page manually.

Notably, the feature is being rolled out to Google Workspace users with Gemini Business, Gemini Enterprise, Gemini Education, Gemini Education Premium, or the Google One AI Premium add-on. Currently, the feature is only available on the Web. While the feature has already been rolled out to eligible users, it might take up to 15 days before it is visible in Docs.

Comments

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who'sThat360 on Instagram and YouTube.

Further reading: Google Docs, Gemini, Imagen 3, AI, Artificial Intelligence

Akash Dutta Email Akash Dutta

Akash Dutta is a Senior Sub Editor at Gadgets 360. He is particularly interested in the social impact of technological developments and loves reading about emerging fields such as AI, metaverse, and fediverse. In his free time, he can be seen supporting his favourite football club - Chelsea, watching movies and anime, and sharing passionate opinions on food. More