Google has announced its access opened for the Imagen 3, a model used for generating images from text prompts. The report was published by Google in a research paper regarding the launch of Imagen 3 in the US. the company shows the potential of its Imagen generation through AI models.
Google describes, “We introduced Imagen 3, a latent diffusion model that generates high-quality images from text prompts. We describe our quality and responsibility evaluations, Imagen 3 is preferred over the state-of-the-art (SOTA) models at the time of evaluation. In addition, we discuss the issues around safety and representation, as well as methods we used to minimize the potential harm of our models”.
Moreover, it mainly focuses on the “safety and representation” that manifests itself through Google’s image generator may deny some prompts. This stated that the emergence comes from Elon Musk’s xAI has launched image generation with Grok-2, which is completely unrestricted and has also seen the countless controversial images created and shared across social media that have the summarisation of detailed points.
In May at Google I/Oit was announced the Imagen 3 is the “highest quality” Image generator to date, it has also come with improvements to how it renders text as well as limiting visual artifacts that are common among AI-generated images, Google also announced the “Veo” at I/O, a generative AI video tool that has probably yet to launch publicly. Users can access Imagen 3 through ImageFX now.