Gemini 2.5 Flash Image is available via the Gemini API and Google AI Studio for developers, and Vertex AI for enterprise. The model is designed to make building with it easier, with significant updates to Google AI Studio's 'build mode'. Users can quickly test the model's capabilities with custom AI-powered apps, remix them, or bring ideas to life with just a single prompt. When ready, users can deploy their app directly from Google AI Studio or save the code to GitHub. The model is in preview, but will be stable in the coming weeks.
Gemini 2.5 Flash Image has several key capabilities, including maintaining character consistency, prompt-based image editing, native world knowledge, and multi-image fusion. The model can place the same character into different environments, showcase a single product from multiple angles in new settings, or generate consistent brand assets, all while preserving the subject. It can also blur the background of an image, remove a stain in a t-shirt, or alter a subject's pose, among other capabilities. Additionally, the model benefits from Gemini's world knowledge, which unlocks new use cases, such as reading and understanding hand-drawn diagrams, helping with real-world questions, and following complex editing instructions.
