Google announced the launch of Gemini 2.5 Flash Image, the company’s latest advancement in image generation and editing technology. Developed by the Gemini team, this new model significantly enhances creative control, visual consistency, and efficiency in AI-powered workflows. The model is available now via the Gemini API, Google AI Studio, and Vertex AI.
Gemini 2.5 Flash Image, also referred to by its codename “nano-banana,” empowers users with a rich set of capabilities:
-
It enables blending multiple input images into one seamless visual.
-
It ensures consistent appearance of characters or objects across multiple prompts and edits.
-
It supports targeted transformations through simple natural language commands.
-
It leverages Gemini’s extensive world knowledge to produce semantically intelligent edits and creations.
Also Read: Meta Strikes Licensing Deal with Midjourney to Advance AI Image and Video Tools
As part of the developer experience enhancements, Google has upgraded AI Studio’s “Build Mode.” Developers can now prototype, remix, or deploy custom AI-powered image apps such as filters or image editing workflows with minimal friction Google Developers Blog. Google is enabling partnerships with OpenRouter.ai and fal.ai to bring Gemini 2.5 Flash Image access to millions of developers beyond its own platforms Google Developers Blog. Additionally, all images generated or edited by Gemini 2.5 Flash Image include an invisible SynthID digital watermark for transparent attribution to AI-generated content.
Vertex AI now offers Gemini 2.5 Flash Image in preview with built-in watermarking and support for responsible deployments. The model supports multi-image fusion and maintains brand or subject consistency across variations. The incorporation of SynthID watermark ensures clear identification of AI-generated imagery Google Cloud.
