Google to launch gen AI experiment ’Whisk’ today: ’Now prompt with images’ | Mint

Google to launch gen AI experiment ’Whisk’ today: ’Now prompt with images’ | Mint

Source: Live Mint

Google is all set to launch “Whisk,” a new generative AI tool designed for creative professionals and artists. Whisk enables users to create and modify images using visual prompts, instead of depending entirely on detailed text descriptions.

In a post on X, Google said on Tuesday, “Today, we’re launching our newest gen AI experiment in @labsdotgoogle : Whisk. Instead of generating images with long, detailed text prompts, Whisk lets you prompt with images. Simply drag in images, and start creating.”

In a blog post, Google said that Whisk lets users input images for the subject, one for the scene, and another for the style. “Then, you can remix them to create something uniquely your own, from a digital plushie to an enamel pin or sticker,” it added.

Also Read: Weekly Tech Recap: Apple rolls out iOS 18.2 update, Google unveils Gemini 2.0, OpenAI hits back at Elon Musk and more

Know behind the scenes

Google explained in the blog post that behind the scenes, the Gemini model automatically writes detailed captions for your images. “It then feeds those descriptions into Google’s latest image generation model, Imagen 3. This process captures your subject’s essence, not an exact replica,” it added.

Thus, one can easily remix subjects, scenes and styles in novel ways.

Google explained that since Whisk only extracts a few key features from the input image, it may produce results that differ from what users expect. For example, the generated image could have variations in height, weight, hairstyle, or skin tone. Recognizing that these details may be important for a project, Google allows users to view and edit the underlying prompts at any time.

During early testing with artists and creatives, Whisk has been described as a new kind of creative tool, rather than a traditional image editor. Google designed it for fast visual exploration, not for precise pixel-level edits. The goal is to enable users to explore ideas innovatively, allowing them to experiment with numerous options and download the ones they find most appealing, said the blog.

(This is a developing story)



Read Full Article

Leave a Reply

Your email address will not be published. Required fields are marked *