Google has introduced a new artificial intelligence tool called 'Whisk,' which allows users to upload photos and receive a combined, AI-generated image without the need for text input. This innovative tool enables users to input images depicting subjects, setting, and style, which Whisk then combines into a single image.
Described as a 'creative tool' by Google, Whisk is designed for quick inspiration rather than professional editing. It serves as a fun AI feature that aims to provide users with a unique visual exploration experience.
Whisk is part of the growing trend of AI-generated artwork, following the success of OpenAI's text-to-image creation tool, Dall-E. By leveraging generative AI technology developed by DeepMind, Whisk utilizes Google's Gemini and Imagen 3 to generate images based on user inputs.
Users can 'remix' the final image by editing their inputs and mixing categories to create variations like plushie toys, enamel pins, or stickers. While users can add text to direct specific details, it is not necessary for image creation.
Despite its early stages of development, Whisk has already garnered attention for its unique approach to image generation. Google's focus on AI products, including Whisk, underscores the company's commitment to innovation in the tech industry.
OpenAI's recent release of a text-to-video generator called Sora further highlights the competition in the consumer AI product market. Industry analysts view Whisk as another significant milestone for Google in the AI and tech race, showcasing the capabilities of DeepMind as a key asset for the company.
As Google continues to expand its product offerings in 2025, including a new Android operating system developed in collaboration with Samsung and Qualcomm, Whisk represents a glimpse into the future of AI-driven creativity and innovation.
