Google is announcing significant updates to its generative media models available on Vertex AI. Nano Banana, previously known as Gemini 2.5 Flash Image, is now generally available and production-ready. This model allows for iterative image refinement and context-aware conversational editing. Veo 3, a video generation model, now supports vertical formats for social media and offers precise duration control. Imagen 4, a text-to-image model, is also generally available, delivering photorealistic images with sharp clarity and accurate text rendering. Gemini 2.5 Text-to-Speech (TTS) models are now GA, offering studio-quality dialogue and advanced style and tone control in over 70 languages. These updates empower enterprises to create and refine high-quality media across various formats faster and with greater control. Gemini 2.5 Flash Image is ideal for iterative editing and adapting existing visuals. Veo 3 suits dynamic video creation with granular control. Imagen 4 excels in generating new images from text with speed and high resolution. Gemini 2.5 TTS is perfect for creating lifelike voice applications and narration. All these models are now accessible through Vertex AI for enterprise-grade creativity.