Available via the Gemini API and Google AI Studio, as well as Vertex AI for enterprise, the image generation and editing tool leverages generative AI capabilities.
Google has introduced Gemini 2.5 Flash Image, an image generation and editing model enabling capabilities including the blending of multiple images into a single image. Developers can use the model for multimodal creativity for visual apps.
Introduced August 26 and also identified as “Nano Banana,” Gemini 2.5 Flash Image enables developers to maintain character for consistency, make targeted transformations using natural language, and use Gemini knowledge to generate and edit images. The model is available via the Gemini API and Google AI Studio for developers and Vertex AI for enterprise. To assist with building with Gemini 2.5 Flash Image, Google has made updates to Google AI Studio’s build mode. Developers can quickly test the model’s capabilities with custom AI-powered apps and remix them or bring ideas to life with a single prompt, according to Google. Apps can be shared from Google AI studio or code saved to GitHub.
Gemini 2.5 Flash Image enables targeted transformation and precise local edits with natural language, Google said. For example, the model can blur the background of an image, remove a stain in a t-shirt, remove an entire person from a photo, alter a subject’s pose, add color to a black and white photo, all with a simple prompt. Key features of the model include:
- The ability to maintain the appearance of a character or object across multiple images and scenes, a significant challenge in generative AI.
- Users can make targeted edits to images.
- The model can blend multiple source images to create a single, photorealistic fused image.
- Leveraging the Gemini AI assistant, the model understands and incorporates real-world context and detail into image generation and editing tasks.
