Google Unveils New Text-to-Image Tool ImageFX and Upgrades to MusicFX and TextFX

Google, the multinational technology company, has recently announced a series of updates to its generative AI offerings. Among these updates is the introduction of a new text-to-image tool, ImageFX, which features expressive chips to help users experiment with their creations and ideas.

Google’s new text-to-image tool, ImageFX, is designed to provide users with a more interactive and expressive experience. The tool’s expressive chips allow users to quickly explore different dimensions of their ideas and creations. This new feature is expected to enhance the overall user experience and make it easier for users to generate high-quality images using AI technology.

In addition to the debut of ImageFX, Google has also made improvements to its existing generative AI tools, MusicFX and TextFX. The company has upgraded the MusicLM model, which powers MusicFX, to deliver faster generation of music and higher-quality audio. Users can now generate songs that last up to 70 seconds, providing them with more flexibility and creativity.

TextFX, another popular generative AI tool from Google, has received usability updates aimed at improving navigation and overall user experience. These improvements are expected to make it easier for users to generate text using AI technology and to explore different text-generation options.

Google’s new and revamped generative AI tools, including ImageFX, MusicFX, and TextFX, are now available in the AI Test Kitchen for users in the US, Kenya, New Zealand, and Australia. These tools are only available in English for now, but Google plans to expand availability to other languages and regions in the future.

The Imagen 2 model is powering the new image generation features of ImageFX. This model is also responsible for driving new generative AI options in Bard, Search, Ads, Duet AI in Workspace, and Vertex AI. Google claims that Imagen 2 helps deliver its highest-quality AI-generated images yet, with improvements in areas such as clarity and reduction of artifacts.

Google has made significant investments in Imagen 2 training data safety and added guardrails to limit problematic outputs like violent, offensive, or sexually explicit content. The company also applies filters to reduce the risk of generating images of named individuals. These upgrades are due to Imagen 2’s ability to generate photorealistic images, which requires additional safeguards to prevent the generation of harmful or inappropriate content.

Google also announced that Gemini Pro in Bard is now more broadly available, with support for more than 40 languages and availability in over 230 countries and territories. Additionally, users in most countries can now generate images in Bard for free, with SynthID watermarks included to indicate that the images were generated using AI technology.

In conclusion, Google’s latest updates to its generative AI offerings, including the new text-to-image tool ImageFX and improvements to MusicFX and TextFX, represent a significant step forward in the field of AI-generated content. These tools offer users more flexibility, creativity, and control over their creations, while also providing improved safety and quality features to prevent the generation of harmful or inappropriate content. With these updates, Google continues to push the boundaries of what is possible with AI technology and to provide users with innovative and powerful tools for generating text and images.