Google introduces ImageFX, a cutting-edge tool in Labs, revolutionizing image creation with simple text prompts. Featuring an innovative prompt interface with “expressive chips,” sparking limitless creative exploration.
New Delhi, February 03, 2024: In a move that adds another layer to the ever-evolving landscape of artificial intelligence, Google has launched ImageFX, an innovative AI-powered image generator. The tool is set to join the ranks of other creative platforms like OpenAI’s DALL-E 3, Meta’s Imagine with Meta AI, and Microsoft Designer, but with its own distinctive feature – “expressive chips.”
Developed by Google’s DeepMind team using the Imagen 2 GenAI image model, ImageFX provides a user-friendly, prompt-based interface for creating and editing images. The standout feature, “expressive chips,” functions as a list of keyword suggestions, allowing users to explore different dimensions of their creations and ideas.
“Designed for experimentation and creativity, ImageFX lets you create images with a simple text prompt, then easily modify them with a new take on prompting using expressive chips,” explains Google in a blog post. To ensure responsible use, Google has implemented “technical safeguards” to prevent the generation of problematic outputs, such as violent, offensive, and sexually explicit content. Additionally, ImageFX includes a prompt-level filter for “named people,” possibly targeting public figures, although Google’s press materials leave some ambiguity on this point.
Google emphasizes its commitment to safety, stating, “We invested in the safety of training data from the outset” and conducted extensive testing to identify and mitigate potential harmful and problematic content.
In parallel news, Google announces the expansion of Imagen 2 across its products and services, starting this week. Imagen 2, already powering text-to-image capabilities in Google Ads and Duet AI in Workspace, is set to enhance Google’s next-gen AI search experience and the family of managed AI services, Vertex AI.
The Imagen 2 integration extends to Google’s Search Generative Experience (SGE), which began offering image generation tools in Google Image Search last October. Now, users can enter a prompt specifying the desired image, and SGE, utilizing Imagen 2, will return four results directly within the conversational experience. This move marks Google’s continued investment in AI capabilities across various applications, pushing the boundaries of what is possible in the realm of artificial intelligence.