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
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe nowRead on for the full picture.
Subscribe for hype-free coverage.
- Full access to every article on THE DECODER
- No ads
- Join the comments and community discussions
- A weekly AI news recap via mail
- 6x/year: "AI Radar" — deep dives on the AI topics that matter most
- Daily AI news, always up to date
- Our full ten-year archive
- Covered by a team with 10+ years in AI