Google has released its Imagen 4 family of text-to-image models, making them generally available in the Gemini API and Google AI Studio. According to a post on the Google Developers blog, the release includes the new Imagen 4 Fast model, which is optimized for speed and high-volume tasks. This model is priced at $0.02 per output image. The family also features the flagship Imagen 4 model and Imagen 4 Ultra for maximum detail and prompt adherence. Google states that the models show significant improvements in rendering text within images. Additionally, both Imagen 4 and Imagen 4 Ultra now support image generation up to 2K resolution. All images created with the models are imperceptibly watermarked with Google’s SynthID technology.