![[The AI Show Episode 148]: Microsoft’s Quiet AI Layoffs, US Copyright Office’s Bombshell AI Guidance, 2025 State of Marketing AI Report, and OpenAI Codex](https://www.marketingaiinstitute.com/hubfs/ep%20148%20cover%20%281%29.png)
![[The AI Show Episode 146]: Rise of “AI-First” Companies, AI Job Disruption, GPT-4o Update Gets Rolled Back, How Big Consulting Firms Use AI, and Meta AI App](https://www.marketingaiinstitute.com/hubfs/ep%20146%20cover.png)
.jpg?#)
_Prostock-studio_Alamy.jpg?width=1280&auto=webp&quality=80&disable=upscale#)
Google’s upgraded image generator finally spells things right and doesn’t mess up fur
Imagen 4 can also handle a range of aspect ratios, and can go up to 2K resolution.
Credit: Google
- Google has launched Imagen 4 at Google I/O 2025, offering improved photorealistic quality, better details, and support for resolutions up to 2K.
- The new image generator model version excels in fine textures like fur, fabric, and water droplets, and spelling accuracy for designs featuring text.
- Imagen 4 is available today across Gemini apps and Workspace tools like Slides and Docs.
At Google I/O last year, Google introduced Imagen 3, its highest-quality text-to-image generator. Imagen 3-generated pictures offer better detail, richer lighting, and fewer artifacts. The model also powers the Pixel Studio app on the Pixel 9 series. Today, at this year’s Google I/O, Google is announcing an upgrade to its Imagen model in Imagen 4, alongside a fast variant that is “coming soon.”
Google says Imagen 4 combines speed with precision. It boasts clarity in fine details like intricate fabrics, water droplets, and animal fur, as seen in the example images below. The new model is said to excel in both photorealistic and abstract styles.
