Rahul Somvanshi
Google has added powerful AI image editing to its Gemini app, letting users modify photos with simple text commands instead of complex editing tools.
Photo Source: Sheetal. Sammy Fans
Representative Image.
Users can now change backgrounds, add objects, or alter specific elements in photos by typing natural instructions like "change the background to a beach."
Photo Source: Jibin Joseph. PG MAG
Representative Image.
Photo Source: ElisaRiva
The new feature works on both AI-generated images and personal photos uploaded from phones or computers, making advanced editing accessible to everyone.
Photo Source: ElisaRiva
Representative Image.
Gemini remembers context throughout editing sessions, allowing users to refine their images with follow-up prompts until they achieve the perfect result.
Photo Source: Oksana Pysarenko. Rbc Ukraine
Representative Image.
Google is tackling potential misuse by adding invisible SynthID watermarks to all AI-edited images and is testing visible watermarks for extra transparency.
Photo Source: Robby Payne. Chrome Unboxed
Representative Image.
This upgrade follows successful testing in Google's AI Studio and will roll out in over 45 languages across most countries in the coming weeks.
1. Photo Source: Index Box
Representative Image.
The integration lets users create content like bedtime stories with matching illustrations all in one conversation, putting Google in direct competition with ChatGPT's image tools.
Photo Source: Jibin Joseph. PG MAG
These accessible editing capabilities open new creative possibilities for content creators, small business owners, and casual users without specialized design skills.
Photo Source: User199 (CC BY 2.5)
Representative Image.