Google’s Developer Blog announced the availability of native image generation with Gemini 2.0 Flash for experimentation.
Key features of Gemini 2.0 Flash include multimodal input, enhanced reasoning, and natural language understanding for generating images.
- It allows creating illustrated stories, conversational image editing, generating realistic and detailed imagery, and rendering long sequences of text accurately.
- Developers can access this feature through the Gemini API using the “gemini-2.0-flash-exp” model in Google AI Studio.
- The blog encourages developers to explore the capabilities and provide feedback to improve the production-ready version.
https://deepmind.google/discover/blog/experiment-with-gemini-20-flash-native-image-generation/