- Imagen 4 is now available to all Gemini users
- 2K -pictures with more details and better typography
- Google claims you can now use it to create greeting cards
Google’s AI image generation is leveled just with a new version of Imagen 4, which brings a bunch of big upgrades including a higher resolution and better text management.
The upgrade was announced on Google I/O 2025 today and should noticeably improve Gemini’s image capacities, which already competed with chatgpt.
Taking over from the previous version 3 has image 4 “remarkable clarity in fine details such as complicated fabrics, water drops and animal fur, and excels in both photorealistic and abstract styles”, according to Google. You can see the new detail level in the preview images above and below.
Imagen 4 is also the first version of Google’s AI image generator that can go up to 2K resolution, which means you will be able to create larger images for presentations and images that look even better when printed.
A real challenge for AI image generators in the past (other than creating realistic fingers) has represented text in a way that makes sense and is readable.
While image 3 made significant interventions to present typography in a better way, Imagen 4 promises to take text to the next level.
Google claims that image 4 will be “significantly better for spelling and typography, making it easier to create your own greeting cards, posters and even comics”.
Use limits
When it comes to use limits for image 4, we do not expect the situation to be radically different from them with image 3, but will update this post if we hear something else.
Currently, if you use image 3 through Gemini Chatbot, daily limits vary depending on whether you are a free gemini user or a Gemini -Advanced Subscriber.
Free users can expect about 10-20 image generations a day, depending on how strong the service is used. Gemini Advanced subscribers can expect higher limits of up to 100-150 daily image generations.
As with image 3, there are content restrictions on image 4, especially about generating images of real individuals. However, image 4 has no trouble generating images of generic people.
Available today across Google Apps
Imagen 4 is also not only available in Gemini; From today you can use it across whisk, peak AI, slides, vids, documents and more in the work area.
And there is also more to come. Google says it will “soon” launch a super -fast variant of image 4, up to 10x faster than image 3 by generating images.
