Google has announced an update for its Gemini chatbot that includes new image editing capabilities, allowing users to manipulate visual content more effectively.
Google Gemini: Enhanced Visual Capabilities
The Gemini chatbot is receiving a significant update that improves its image editing capabilities. Users can now not only generate images from text prompts but also edit existing photos. The update will be available in over 45 languages in the coming weeks.
AI Image Editing: What Can You Do?
The new image editing features in Gemini include:
* Background changes. * Object replacement within images. * Adding new elements to images. * Modifying features (such as hair color).
Users can upload images or work with AI-generated ones and refine them using text instructions in the Gemini interface.
Generative AI: Powering Creative Workflows
The technology supporting these new features is Generative AI. It allows users to interact with visual content and text in a single flow, facilitating the creation of complex projects. Google provided examples demonstrating how to generate images for stories or change colors in personal photos.
The Google Gemini update with image editing capabilities represents a significant advancement for AI chatbots. It not only expands users' creative possibilities but also raises important issues regarding responsible use and the potential for fraud in the context of image manipulation.
