Anúncios
The new Google AI tool called “Whisk” is revolutionizing the way users interact with technology by allowing them to utilize picture instructions instead of words. This innovative product is designed to merge photographs into a single, AI-generated image without the need for any typing.
With Whisk, users can simply upload photographs of subjects, settings, and styles to create unique and creative images. This process eliminates the need for traditional image editing tools and allows for a more intuitive and streamlined experience. Google has described Whisk as a “creative tool” that is meant to inspire rapid visual exploration rather than pixel-perfect editing.
Whisk builds on the success of other AI-generated artwork tools, such as OpenAI’s Dall-E, which was introduced in 2021. The use of AI technology in art and design has become increasingly popular, with the proliferation of AI-generated images on social media and consumer products.
Anúncios
One of the key features of Whisk is its ability to mix categories and alter inputs to create a wide range of products, such as plushies, enamel pins, and stickers. Users can experiment with different combinations of subjects, scenes, and styles to create unique and visually striking images. While words can be used to provide direction, the focus of Whisk is on creating visually appealing and innovative images.
Google Labs director of product management, Thomas Iljic, emphasized that Whisk is designed to offer users a new and creative way to explore visual concepts. The tool allows for rapid experimentation and exploration, rather than focusing on precise editing and manipulation of images.
Anúncios
Whisk utilizes Google’s AI service, Gemini, which was introduced in December 2023. It also incorporates Imagen 3, DeepMind’s latest text-to-image generator, to capture the essence of the input photographs and create a merged final image. This process allows for a high degree of creativity and flexibility in generating unique and unexpected results.
Despite its early success, Google has faced challenges with the accuracy of its AI-generated images. In February, the company received criticism for producing historically inaccurate images with Gemini’s text-to-image converter. However, Google continues to innovate and develop new AI tools, such as Whisk, to push the boundaries of technology and creativity.
Whisk is currently available as a US-only website and is still in the early stages of development, according to Google. The company is also working on other AI products, such as Sora, a text-to-video generator, to meet the growing demand for innovative and intelligent consumer products.
Industry analysts, like Dan Ives from Wedbush Securities, view Whisk as a significant milestone for Google in the AI and tech space. Ives described Whisk as a “flex the muscles moment” for Google, highlighting the company’s commitment to pushing the boundaries of technology and innovation.
Overall, Whisk represents a new era in AI technology, where users can interact with machines in a more intuitive and visual way. With its ability to merge photographs and create unique images, Whisk is setting the stage for a future where creativity and innovation are at the forefront of human-machine interaction.
