Google is extending its native AI image editing technology to the Gemini app, allowing users to seamlessly modify both AI-generated images and personal photos uploaded from their devices. This expansion follows the successful introduction of similar capabilities in AI Studio earlier this year.
The new functionality enables users to transform images in multiple ways—changing backgrounds, replacing objects, adding elements, and more. For example, users can now upload a personal photo and ask Gemini to generate variations showing different hair colors or styles.
“This intuitive, multi-step editing capability means users can get richer, more contextual responses to their prompts with text and images integrated,” according to Google’s announcement. The technology opens up creative possibilities such as asking Gemini to draft a bedtime story about dragons complete with accompanying illustrations.
Google maintains its commitment to responsible AI by including the invisible SynthID digital watermark on all AI-generated or edited images. The company is also testing visible watermarks as an additional transparency measure.
The feature begins rolling out today and will expand to users in over 45 languages across most countries in the coming weeks.
This development represents a significant step in making sophisticated AI image manipulation tools accessible to everyday users, continuing Google’s efforts to bring advanced AI capabilities directly to consumers through the Gemini platform.
Read more on Google’s blog: https://blog.google/products/gemini/image-editing/?utm_source=newsletter.theresanaiforthat.com&utm_medium=newsletter&utm_campaign=2025-prompt-engineering-guide&_bhlid=d623ab617e25d7c645227bf7d7544982ab120eda
