Google has launched a built-in AI image editor in its Gemini app, allowing users to edit their own photos as well as AI-generated images directly within the app. This new feature, rolling out now, lets users swap backgrounds, add or remove objects, and blend images using AI capabilities. The editor is designed not only for transforming AI-created visuals but also for tweaking personal photos uploaded from devices.
Users can seamlessly communicate their editing wishes to Gemini, which ensures that changes maintain a cohesive look throughout the image. This update represents a significant upgrade for the Gemini app, enhancing its functionality from simple chatting to detailed image editing. Gemini introduces a step-by-step editing flow that aims to deliver richer, context-aware outcomes by integrating text and visuals.
For instance, if a user requests a story about a dragon at night, Gemini can generate a narrative alongside unique visuals to enrich the storytelling experience. The rollout of the image editing feature is anticipated to expand to over 45 languages and a wide range of countries in the coming weeks. Additionally, edited images will include a SynthID digital watermark, a discreet identifier implemented by Google to denote AI-generated content.
The company is contemplating applying this watermark to all images created with Gemini, not limited to edited ones. This development follows Google’s earlier testing of AI image editing capabilities in AI Studio, which garnered attention primarily for its ability to remove watermarks. The positive response to that initial test has paved the way for these advanced editing tools to be integrated into the Gemini app.