Google Unveils Novel AI-Powered Image Generation Tool: Exploring Boundless Creative Possibilities

Google Experiments with New Image Generator That Remixes Three Images into One Creation

In a recent experiment, Google’s research arm, Google Labs, has been testing a novel AI-powered image generation tool called Whisk. This innovative technology allows users to input multiple images and create a brand new visual masterpiece by merging the subject, scene, and style of each photo.

Whisk uses Google’s state-of-the-art image generation model, Imagen 3, which can combine three distinct images to produce a unique output. Users can upload their preferred images as prompts, selecting one for the subject, another for the scene, and a third for the style. This versatile tool has far-reaching implications for creative professionals, artists, and even everyday users looking for new ways to express themselves.

The process of creating an image with Whisk is straightforward. First, you can upload your preferred images as prompts. For instance, you could use a photo of yourself as the subject, a futuristic landscape as the scene, and an anime style for the final look. Once you’ve uploaded your images, you can input detailed text prompts to further refine the desired outcome. These prompts can include elaborate descriptions like “Subject is riding a flying bike.”

While Whisk offers immense creative freedom, Google warns that the results may not always align with users’ expectations. The generated subject could vary in height, weight, hairstyle, or skin tone, for instance. Users will also have access to view and edit the underlying prompts at any time.

It’s worth noting that this experiment is currently only available to users based in the United States and can be accessed through labs.google/whisk.

Source: techcrunch.com