Google’s AI image generation experiment, Whisk, is going global.
After debuting in the United States last December, the Google Labs experiment is expanding to over 100 countries, offering creative minds worldwide the chance to visualize and remix ideas using AI.
Whisk boasts a distinct approach where instead of inputting detailed text prompts, users can drag and drop images as prompts, focusing on subjects, scenes, and styles to generate unique digital art with Google’s latest image generation model, Imagen 3.
Users can explore concepts rapidly by leveraging Gemini, which crafts detailed captions from the provided images, subsequently translating these visual ideas into imaginative creations via Imagen 3.
This AI-driven tool aims not just at image generation, but at facilitating fast-paced visual ideation, allowing users to experiment with concepts without needing to master the intricacies of prompt crafting.
For example, I tried it out with an image of Nvidia CEO Jensen Huang from the featured image of our prior article on him getting a precision medicine Luminary award and below was the result.
The feature does not always produce expected results and the generated image often vary in attributes like height or skin tone, or at times more.
There are editing options for underlying prompt built into Whisk though to give users some control over the outcome.
As Google Labs expands Whisk’s accessibility, it joins a portfolio of experiments that test new generative AI features like those using Veo and Gemini.
Google also recently made Gemini 2.0 Flash model available for production apps and has been showing its AI overviews in Google Search to more and more users as Perplexity and OpenAI heat up competition in Search.
Do you want to plan your financial future? Fire Fast by Dzambhala is the right tool for you.
Join the vibrant privacy-ensured Dzambhala community on
Want to give feedback on this story? Write to us.