Google Launches Imagen 4 and Imagen 4 Ultra in Gemini API
Google brings Imagen 4, its most advanced text-to-image model, to the Gemini API and Google AI Studio. The new model family features significantly improved text rendering and prompt alignment.
Google releases Imagen 4, its latest and most capable text-to-image model, as a paid preview in the Gemini API and for limited free testing in Google AI Studio. This new model family represents a significant leap forward in image generation quality, with a particular emphasis on highly accurate text rendering compared to previous iterations like Imagen 3.
The Imagen 4 family consists of two distinct models designed for different creative needs. The standard Imagen 4 serves as the flagship model for general image generation tasks at a cost of $0.04 per image, while Imagen 4 Ultra focuses on strict prompt adherence for users who require precise control over their outputs at $0.06 per image.
Developers can currently experiment with these models through Google AI Studio or integrate them directly into their applications via the Gemini API. Google plans to introduce additional billing tiers in the coming weeks, and interested users have the option to request higher rate limits to accommodate larger workloads.