Google has enhanced the capabilities of their chatbot Gemini to edit images according to specified prompts. This feature supports images generated from AI as well as images uploaded by users. Google tested this feature previously in the AI Studio platform for developers.
Users can input commands such as deleting or changing backgrounds, adding objects to images, or other components they desire. This feature will gradually update for Gemini users starting today. It will support over 45 languages and in many countries worldwide in the coming weeks.
Google states that the image editing capability works incrementally, allowing for detailed adjustments. All generated images will have a watermark SynthID embedded following AI-generated image standards.
TLDR: Google’s chatbot Gemini can now edit images based on prompts, supporting both AI-generated and user-uploaded images in over 45 languages worldwide.
Leave a Comment