news 
Google Experiments with a New Image Generator That Remixes Three Images Into One Creation
TechCrunch has learned that Google’s experimental arm, Google Labs, is testing a novel AI-powered image generation tool called Whisk. This innovative technology allows users to create unique images by combining the subject, scene, and style of three different photos.
Whisk employs Google’s advanced image generation model, Imagen 3, to merge the inputted images into one cohesive creation. To get started with this feature, users can upload their own photos or select from a curated library provided by Google.
The tool’s capabilities are quite impressive, as it enables users to manipulate various aspects of the final product, including the subject’s appearance, the environment they inhabit, and the visual style used in the image. For instance, an individual could input a photo of themselves, a futuristic landscape, and anime-inspired visuals, resulting in a customized image that effectively combines these different elements.
Google stresses that the AI model may not always produce the desired output, as it only focuses on specific aspects of each uploaded image. This means that users should be prepared for some variations in height, weight, hairstyle, or skin tone within the generated subject, according to the company.
It’s important to note that users have the ability to view and edit the underlying prompts at any time during the creative process.
Source: techcrunch.com
