Google has launched a new AI tool, “Whisk,” which allows users to upload images and generate a combined AI image without needing to input text. The tool lets users mix elements like subjects, settings, and styles to create new images, with the option to add text for specific details, though it’s not required.
Described as a “creative tool” rather than a professional image editor, Whisk aims to inspire quick, exploratory visuals rather than perfect, polished designs. It uses Google’s Gemini AI platform and Imagen 3, a text-to-image generator developed by DeepMind, to remix and reinterpret the uploaded images.
Currently available on Google Labs for U.S. users, Whisk is in its early stages. Google’s move comes as competition heats up in the AI space, with OpenAI also releasing new tools like Sora, a text-to-video generator. According to Dan Ives, managing director at Wedbush Securities, Whisk is a key step in Google’s push to lead the AI race.
Related topics:
Alessandra Alessio Joins StackAdapt as APAC Marketing Director
Brussels Investigates Google and Meta Over Secret Ad Deal Targeting Teens
Google DeepMind Unveils Veo 2: The Next-Generation AI for Video Generation