What you need to know
Google is reportedly developing an innovative “annotation” feature for its Gemini platform, aimed at enhancing user interaction with generated images. This feature, which has surfaced through leaks from TestingCatalog on X, promises to empower users by allowing them to write or draw directly on images before downloading them. According to the information shared, users may soon have the ability to annotate their images with text and drawings, providing a more personalized touch to the AI-generated visuals.
In addition to the annotation capabilities, there are whispers of a “resubmission” option that could further streamline the user experience. One user noted that they could annotate an image—circling, adding arrows, and including text instructions—before resubmitting it with a new prompt. This functionality would enable users to make specific adjustments to the AI’s output without needing to rephrase their requests entirely, potentially making the creative process more intuitive.
As Google continues to refine its Gemini platform, the introduction of this annotation feature marks a significant step toward fostering a more interactive relationship between users and AI. Currently, there is no official timeline for when this feature will be available, leaving enthusiasts eagerly anticipating its release.
Mark it up, make the change
Google is working on an image annotation feature for Gemini. Users will be able to draw and add text to generated images before downloading them. “Generate me a coloring page” 🍌 pic.twitter.com/mknesNVwrp
Earlier this year, Google began integrating native image editing capabilities into Gemini, allowing users to modify both AI-generated images and their own photographs. This includes changing backgrounds, adding or removing objects, and blending various images together. Users can even narrate a story, prompting the AI to create visuals that align with their narrative.
The anticipated annotation feature appears to enhance this existing functionality by allowing users to engage more directly with the AI’s outputs. Instead of starting from scratch, users will have the opportunity to fine-tune the results, bridging the gap between human creativity and artificial intelligence.
In tandem with these developments, Google recently unveiled the Nano Banana Pro model, which boasts improved accuracy and richer content in image generation. This upgrade also enhances text legibility, suggesting that it may be a precursor to the forthcoming annotation capabilities. As the Gemini platform evolves, users can look forward to a more dynamic and personalized creative experience.
