Google Gemini Enhances AI Image Editing Capabilities
Google has upgraded its Gemini chatbot app with powerful new image editing tools. Users can now modify both AI-generated images and uploaded photos directly within the app.
This new functionality, announced by Google, is rolling out gradually and will be available to most users in over 45 languages and countries in the coming weeks. This update builds upon Google's previous AI image editing model piloted in AI Studio.
Edit Images Directly Within Gemini
Similar to ChatGPT's enhanced image editing feature, Gemini's new native image editor offers a multi-step editing flow. This provides richer, more contextual responses to prompts, integrating text and images seamlessly. Users can perform various edits, including:
- Changing image backgrounds
- Replacing objects
- Adding new elements
This enhanced functionality allows for greater creative control and more complex image manipulations within the Gemini platform.
Google provides examples of potential use cases. Users can upload a personal photo and experiment with different hair colors using Gemini's AI. Alternatively, they can create a bedtime story about dragons and generate accompanying images.
Addressing Deepfake Concerns
To address potential deepfake concerns, Google is implementing safeguards. Images created or edited with Gemini will include an invisible watermark. Furthermore, Google is experimenting with visible watermarks on all Gemini-generated images.
This update positions Gemini as a more versatile and powerful AI tool, combining chatbot functionality with advanced image editing capabilities.
