Google has recently announced the launch of ImageFX, an innovative AI-powered tool for image creation. This new tool is underpinned by Imagen 2, a GenAI image model developed by Google’s DeepMind team. ImageFX offers a prompt-based user interface that allows users to create and edit images using a simple text prompt, along with the unique feature of “expressive chips” for experimenting with different dimensions of their creations and ideas.
Key Takeaway
Google’s ImageFX, powered by Imagen 2, introduces a new AI-driven approach to image creation, accompanied by measures to prevent misuse. The expansion of Imagen 2 across various Google products and services signifies a significant advancement in AI integration.
Addressing Potential Misuse
Google has taken steps to address potential misuse of ImageFX by implementing technical safeguards to limit problematic outputs such as violent, offensive, and sexually explicit content. The tool also includes a prompt-level filter for “named people,” and images produced using ImageFX are tagged with SynthID, a digital watermark that provides identification insights and is robust against image edits and crops.
Expansion of Imagen 2
In addition to the launch of ImageFX, Google has announced the expansion of Imagen 2 to more of its products and services. Imagen 2 will be integrated into Google’s next-gen AI search experience, family of managed AI services Vertex AI, Google Ads, Duet AI in Workspace, and SGE (Search Generative Experience) which now taps Imagen 2 for generating images. Moreover, Imagen 2 will be available through an API to Google Cloud customers and can be accessed through Bard, Google’s AI-driven chatbot.
