Google has introduced a new AI image generator called Imagen 4, which the company claims produces higher-quality results compared to its predecessor, Imagen 3. Unveiled at Google I/O 2025, Imagen 4 is capable of rendering fine details such as fabrics, water droplets, and animal fur in both photorealistic and abstract styles. The model can create images in a variety of aspect ratios and up to 2K resolution.
Quality Improvements and Features
Josh Woodward, head of Google’s Labs group, highlighted Imagen 4’s significant quality improvements during a press briefing. The model has undergone enhancements in generating text and typography, making it ideal for creating presentations, invitations, and other materials that blend imagery and text seamlessly.
What Sets Imagen 4 Apart
Despite the abundance of AI image generators like ChatGPT and Midjourney’s V7, Google positions Imagen 4 as a standout tool. The model’s speed distinguishes it from the competition, being faster than Imagen 3. Additionally, Google plans to release a faster variant of Imagen 4 in the future, promising speeds up to 10 times quicker than its predecessor.
Availability and Platforms
Imagen 4 is now available in the Gemini app, Google’s Whisk and Vertex AI platforms, as well as integrated across various Google Workspace applications such as Google Slides, Vids, and Docs. With its enhanced capabilities and speed, Imagen 4 aims to revolutionize AI image generation for various creative purposes.
