Experiment with Gemini 2.0 Flash native image generation
Gemini 2.0 Flash just got native image generation. Developers can start building with it today.

Why it matters
Google is expanding Gemini 2.0 Flash's capabilities to include native image output, lowering friction for developers building multimodal applications and competing directly with OpenAI's GPT-4V and Claude's vision features.
The key facts
5 to knowNative image generation now available in Gemini 2.0 Flash
Accessible via Google AI Studio and Gemini API
Published March 12, 2025 — recent product availability
Multimodal capability expansion for existing model
Developer-first rollout (not public consumer feature yet)
Go to the source
Google DeepMind Blogdeepmind.google
Publisher excerpt: Native image output is available in Gemini 2.0 Flash for developers to experiment with in Google AI Studio and the Gemini API.