Google announced the launch of ImageFX , an innovative text-to-image conversion tool that will revolutionize the way we create and share visual content. This new tool is part of a series of updates in the field of generative artificial intelligence, which also include improvements to MusicFX and TextFX.
ImageFX stands out for its interface featuring “expressive chips,” designed to allow users to quickly explore different creative dimensions and ideas. With this feature, Google aims to give users a smoother and more intuitive experience in creating images from text.
In addition to ImageFX, Google announced significant improvements to MusicFX and TextFX. With MusicFX, users can now generate songs up to 70 seconds faster and with higher audio quality. TextFX, on the other hand, has received usability updates to improve navigation and the overall user experience when creating text-based content.
A key element of ImageFX and MusicFX is the introduction of SynthID, a digital watermark that identifies images and audio generated using artificial intelligence. This will help ensure transparency and correct attribution of works created with these tools, especially when shared on platforms like Search or Chrome.
The new features are currently available in the US, Kenya, New Zealand and Australia, with support for English only. However, Google said it is committed to expanding availability globally.
At the heart of ImageFX is the Imagen 2 model, the same technology that powers projects like Bard, Search, Ads, and other Google AI projects. This model ensures the highest quality in AI-generated images, keeping them free from artifacts and improving generation areas.
Furthermore, Google announced that the Gemini Pro model, previously available only in some regions, will now also be available in 230 other countries, including Italy. This means that Bard, Google’s search engine, will be powered by Gemini Pro rather than PalM2, opening up new possibilities and potential for Italian users.
In summary, ImageFX represents a step forward in the evolution of text-based image generation, offering users an innovative and intuitive way to express their ideas and visual creations.