Experiment with Gemini 2.0 Flash native image generation

In December, we first introduced native image output in Gemini 2.0 Flash to trusted testers. Today, we’re making it available for developer experimentation across all regions currently supported by Google AI Studio. You can now test this new capability using an experimental version of Gemini 2.0 Flash (gemini-2.0-flash-exp) in Google AI Studio and via the Gemini API. Gemini 2.0 Flash combines multimodal input, enhanced reasoning, and natural language understanding to create images. It enables you to add text and image generation with just a single model for creating visuals like illustrated interactive stories or brainstorming visual ideas in conversation. Inspire your audience and provide them with a more engaging experience through this new capability. Given below is an example of how 2.0 Flash creates images using natural language prompts. In this case, the user provides a simple prompt like “Create a photo of your favorite plant.” The model learns from this prompt and generates a visually appealing image with consistent style throughout. “` Given prompt: Create a photo of your favorite plant Explanation: Use Gemini 2.0 Flash to tell a story and it will illustrate it with pictures, keeping the characters and settings consistent throughout. Give it feedback and the model will retell the story or change the style of its drawings. Sorry, your browser doesn’t support playback for this video Unlike many other image generation models, Gemini 2.0 Flash leverages world knowledge and enhanced reasoning to create the right image. This makes it perfect for creating detailed imagery that is realistic, not absolute or complete. While it strives for accuracy, like all languaine models, its knowledge is broad and general, not absolute or complete. Sorry, your browser doesn’t support playback for this video Most image generation models struggle to accurately render long sequences of text, often resulting in poorly formatted or illlegible characters, or misspellings. International benchmarks show that 2.0 Flash has stronger rendering compared to leading competitive models and can create visuals with great consistency and accuracy. Get ready for Google I/O: Program lineup revealed Start building with Gemini 2.5 Flash and achieve real-time interaction by building with the Live API.