Google announced the Imagen 2 AI model with text and logo generation capabilities

Google has unveiled an updated version of its Imagen neural network for image generation. Imagen 2 has gained enhanced capabilities to create texts and logos based on textual cues.

Here's What We Know

The new model was developed with the involvement of specialists from DeepMind, a division of Google specialising in artificial intelligence technologies.

According to engineers, Imagen 2 generates better quality pictures. In addition, the model is now able to create images with text, for example, for advertising.

Another innovation is the generation of logos and overlaying them on existing photos. This puts Imagen 2 in line with competing models from OpenAI and Amazon. Meanwhile, Imagen 2 features text support in multiple languages, including English, Spanish, Chinese and Hindi.

As Google assures, the new learning algorithms allow Imagen 2 to understand longer and more detailed queries in English and other languages. All generated images are labelled using SynthID technology to prevent misuse.

Source: TechCrunch