Googleās new AI image editing and generation model integrated into Gemini
Nano Banana (officially Gemini 2.5 Flash Image) is Google DeepMindās state-of-the-art image generation and editing model. Launched in August 2025, it supports both text-to-image and image editing capabilities. It excels at character consistency, scene blending, and precise, localized edits from natural-language prompts. It is accessible via the Gemini app, Google AI Studio, and APIs.
Text-to-image generation and image editing in one model
Maintain consistent appearance of characters across edits
Scene fusion and multi-image blending
World-knowledge aware edits (contextual understanding)
Uses invisible SynthID watermarking in outputs
Refining or transforming existing photos via text prompts
Swapping backgrounds, adjusting angles, or combining images
Creating highly realistic composite images
Brand content production with consistent characters/subjects
Rapid prototyping of visual ideas with tight control
More precise, believable edits with fewer iterations
Better consistency and identity preservation across edits
Seamless blending of new elements into existing scenes
Join thousands of users already leveraging Nano Banana (Gemini 2.5 Flash Image) to transform their workflow
Access Nano Banana (Gemini 2.5 Flash Image)