Oct. 10 (Portaltic/EP) –
Image 3, Google’s basic image generation model, is now available globally to all users, who will be able to use this tool to generate photorealistic images.
Google unveiled Image 3 in May, during its annual developer conference. It then indicated that it would be released in preview for a selection of Vertex AI customers. It includes multilingual support, built-in security features such as Google DeepMind’s SynthID digital watermark, and support for multiple aspect ratios.
Now, it is available to all users globally within the Gemini application, as reported by the company through the X profile. Image 3 generates photorealistic-looking images from a text description, using voice or an image.
Add Comment