Google Unveils Gemini 2.5 Flash Image for Advanced AI Generation
Google launches Gemini 2.5 Flash Image, a powerful new model that enables developers to generate, edit, and blend images with enhanced character consistency. The model is available immediately through the Gemini API and Google AI Studio.
Google introduces Gemini 2.5 Flash Image, a state-of-the-art model designed for high-quality image generation and editing. This new tool allows developers to blend multiple images together, make targeted edits using natural language, and leverage Gemini's world knowledge to create visuals. The release addresses user feedback requesting greater creative control and higher quality outputs compared to the previous Gemini 2.0 Flash model.
The model excels at maintaining character consistency across different prompts and environments, solving a fundamental challenge in AI image generation. Developers use this feature to place the same character in various settings, showcase products from multiple angles, and generate unified brand assets. Users access these capabilities immediately through the Gemini API, Google AI Studio, and Vertex AI.
Pricing for the new model sits at $30.00 per one million output tokens, which translates to roughly $0.039 per individual image. To accompany the launch, Google updates the build mode in Google AI Studio so developers can quickly test, remix, and deploy custom image editing applications. Users try preset templates or write simple prompts to build free apps and push their code directly to GitHub.