Google has announced the general availability of Imagen 2, Google Cloud's text-to-image technology, on Vertex AI for approved customers. This AI-powered tool allows developers to create photorealistic images from text prompts. The tool competes with other leading image-generating models, like OpenAI’s DALL-E 3 and Amazon’s recently launched Titan Image Generator. Imagen 2 renders support in multiple languages: Chinese, Hindi, Japanese, Korean, Portuguese, English and Spanish.
“Imagen 2 is our most advanced text-to-image diffusion technology, delivering high-quality, photorealistic outputs that are closely aligned and consistent with the user’s prompt. It can generate more lifelike images by using the natural distribution of its training data, instead of adopting a pre-programmed style,” the company says about the technology.
Google asserts that Imagen 2 enhances the capabilities of Imagen by providing superior image quality, improved accuracy, and heightened photorealism. This is achieved through innovative training techniques and an advanced understanding of text-to-image relationships. Additionally, Imagen 2 is proficient in generating various elements such as brand and messaging logos, emblems, lettermarks, abstract logos, and overlaying them onto products and marketing materials.
In terms of safety features, Google highlights the integration of Imagen 2 with Google DeepMind's SynthID, which facilitates the publication of invisible watermarks for image verification. The platform also incorporates comprehensive safety filters designed to prevent the generation of harmful content.
See What’s Next in Tech With the Fast Forward Newsletter
Tweets From @varindiamag
Nothing to see here - yet
When they Tweet, their Tweets will show up here.
