Google Revives AI-Powered Person Image Generation
Google has announced the reinstatement of its AI-powered image generation model on its Gemini app, following a months-long hiatus.
The American tech giant had previously disabled this feature earlier in the year due to reports of creating inaccurate historical images.
In a statement, Google revealed that it would be transitioning to its most advanced AI image generation model, Imagen 3, which was first unveiled at the developer conference in May. Image generation commands on Gemini will now be executed through this newer model.
The company clarified that this upgrade would restore the ability to generate images of real people using AI, a feature that had been previously suspended. They highlighted that the updated version is capable of creating realistic landscapes and oil paintings based on simple text descriptions of just a few words.
Google indicated that a beta version of this feature would be rolled out in the coming days for paid Gemini subscribers, initially in the English language.
