Google launches Imagen 3 API, priced at $0.03 per picture

Recently, Google officially launched its latest image generation model - Imagen3, which is now available to developers on the Gemini API. The model is visually excellent and can generate high-quality images in a variety of styles, including surreal works, impressionist landscapes, abstract works, and anime characters. Imagen3 not only improves the clarity and composition of images, but also helps users to convert their creativity into images more easily through simplified text prompts.

In the early stage, Imagen3 will only be open to paid users and is expected to be gradually launched to free users soon . According to the official introduction, users can enjoy the powerful features of Imagen3 only by paying $0.03 per image. At the same time, when generating images, users can freely control the aspect ratio of the image and the number of generated options to meet different needs.

To combat false information and misattribute, all images generated by Imagen3 carry an invisible digital watermark SynthID, which recognizes works generated by the image as an artificial intelligence. In addition, developers can easily achieve image generation through Python code, and specific code examples have also been provided in the official documentation. Users can generate the image they want by simply setting the API key and entering the prompt word, experiencing the convenience of this new technology.

In order to give users a better understanding of Imagen3's capabilities, the official also showed a series of generated image samples covering a variety of styles and themes. With the continuous advancement of technology, Google plans to integrate more generative media models into the Gemini API in the near future, further promoting the combination of generative media and language models, and helping developers create more interesting applications.

Blog: https://developers.googleblog.com/en/imagen-3-arrives-in-the-gemini-api/