Google makes its Imagen 3 image AI available to all Gemini users

Google is rolling out its latest image generation AI, Imagen 3, to all Gemini users worldwide, including free accounts. The company claims that Imagen 3 is its most powerful image model yet, outperforming competitors such as DALL-E 3, Midjourney v6, and Stable Diffusion 3 in internal testing. Imagen 3 is said to excel at following detailed text prompts and producing highly photorealistic images. Google says the model produces fewer distracting artifacts than previous versions, but still struggles with tasks that require numerical or spatial reasoning, as well as complex language prompts. To combat potential misuse, Google has implemented safety filters and digital watermarking. Google took down an earlier version because people were using it to generate Black people in Nazi uniforms.

Video: Google