Google has launched native image generation in Gemini 2.0 Flash, now available for developers worldwide. This feature, which integrates multimodal input and natural language processing, allows for text and image generation, conversational image editing, and realistic illustrations. Unlike OpenAI’s GPT-4o, which announced a similar feature but hasn’t released it, Gemini is fully native. Google encourages developers to experiment with this model and provide feedback for future improvements.
