Google Cloud announces Imagen 2 text-to-image generator

Google Cloud announces Imagen 2 text-to-image generator

Google Cloud has introduced Imagen 2, the latest upgrade to its text-to-image capabilities.

Google Cloud has introduced Imagen 2, the latest enhancement to its text-to-image capabilities. Exclusive to Vertex AI customers on the allowlist, Imagen 2 empowers users to create and deploy lifelike images through user-friendly tools and fully-managed infrastructure.

Leveraging Google DeepMind technology, Imagen 2 delivers enhanced image quality and a suite of functions tailored for specific applications.

Key features of Imagen 2 include:

  • Varied image generation: Imagen 2 excels in producing high-resolution images from natural language prompts, catering to diverse user needs.
  • Text rendering in multiple languages: Overcoming common challenges, Imagen 2 accurately renders text in various languages.
  • Logo creation: Businesses can utilise Imagen 2 to craft realistic logos and overlay them on products, attire, business cards, and more.
  • Captions and question-answering: Imagen 2’s advanced image comprehension enables descriptive captions and detailed answers about image elements.
  • Multi-language support: Imagen 2 introduces support for six additional languages in preview, with plans for more in early 2024. This includes translation between prompts and output.
  • Safety measures: Imagen 2 incorporates inherent safety features, aligning with Google’s Responsible AI principles. It includes safety filters and integrates with a digital watermarking service for responsible usage.

Enterprise-ready Capabilities

Imagen 2 on Vertex AI meets enterprise standards, ensuring reliability and governance like its predecessor. With enhanced features such as high-quality image rendering, improved text handling, logo creation, and safety measures, Imagen 2 aims to offer organisations a comprehensive tool for creative image production.

Leading companies like Snap, Shutterstock, and Canva have already embraced Imagen for creative purposes.

Chris Loy, Director of AI Services at Shutterstock, remarked: “Our mission is to empower individuals globally to share their narratives by bridging the conceptualization and execution divide.

Diversity is pivotal in the creative journey, which is why we continuously integrate the newest technology into our image generator and editing features, provided it is built on responsibly sourced data.

Danny Wu, Head of AI at Canva, added: “We’re persistently employing generative AI to revolutionise the design process and amplify creativity.

Through Imagen, our 170M+ monthly users can benefit from the enhancements in image quality to elevate their scalable content creation.

As Imagen 2 gains traction in the creative sector, organisations are encouraged to explore its potential. Google Cloud anticipates users leveraging these new features to enhance their creative pursuits, building upon the success attained with Imagen.