Google Gemini Introduces Advanced AI Image Editing Tools
Google's Gemini chatbot app has been enhanced with new image creation tools, allowing users to modify both AI-generated images and images uploaded from their devices. This latest update brings native image editing capabilities directly to the Gemini platform, eliminating the need for external photo editing software.
Enhanced Image Editing Functionality
The new image editing tools in Gemini offer a "multi-step" editing flow that provides richer and more contextual responses to user prompts. Users can change backgrounds, replace objects, add elements, and more within the Gemini platform. This allows for a seamless and intuitive editing experience, all through simple text prompts.
For instance, users can upload a personal photo and instruct Gemini to generate an image showing how they would look with different hair colors. Additionally, users can request Gemini to create visual content based on specific prompts, such as generating images for a bedtime story about dragons.
Watermarking and Safety Measures
To address concerns related to deepfake risks, Google has implemented measures to ensure the authenticity of edited images. All images created or modified using Gemini will include an invisible SynthID digital watermark. While there are currently no visible watermarks on the generated images, Google is exploring the option of adding them in the future.
These advanced image editing features are gradually being rolled out to users, with availability in over 45 languages and most countries expected in the coming weeks. The integration of AI-powered image editing tools within the Gemini app represents a significant step towards enhancing user creativity and engagement.
For more information, you can check out the original articles on TechCrunch, Google's official blog, and other relevant sources.
