Image editing in Gemini just got a major upgrade

Details

Google DeepMind expanded Gemini's image editing capabilities, building on the model family's multimodal foundation. The update enables more fine-grained control over image modifications, letting users target specific elements within an image rather than regenerating the whole image from scratch. The upgrade positions Gemini more directly against Adobe Firefly and OpenAI's GPT-4o image generation, both of which have been investing heavily in precise in-image editing. For consumers, this lowers the barrier to quick photo corrections; for creative workflows, it adds flexibility without requiring a dedicated design app. Google has been steadily expanding Gemini from a text assistant toward a full multimodal platform. Image editing is a natural extension of that roadmap and signals continued investment in competing with specialized creative AI tools. Note: Source content was unavailable for this article. This summary is reconstructed from the title and source name only. Specific feature names, benchmarks, or model versions are not confirmed.