All Gemini Users Get Access To Advanced Imagen 3 Model With a Major Caveat

Why Trust Techopedia
Key Takeaways

  • Imagen 3 is Google’s most advanced image-generation model.
  • It can now be accessed by free and paid Gemini users.
  • The feature previously faced backlash over highly irrelevant results.

Gemini users across the world can now generate AI images with Imagen 3 after Google extended use of the image generation tool to free users.

The text-to-image model was announced at this year’s annual I/O developer conference with plans to make it available worldwide in August. The updated Imagen 3 is Google’s most advanced model with better results and reduced flaws compared to earlier versions. 

Imagen 3 is capable of creating high-quality images with crisp details, vivid colors, and less imperfections. It can create photorealistic landscapes, textured oil paintings, or modern digital art. Users just need to add a prompt with words like ‘draw’, ‘generate’, or ’create’ and Gemini will generate the image. Adding more details to the prompt will deliver a better final result. Users can also make changes to the prompt if the result is unsatisfactory. The images are generated in a 2048 x 2048 resolution. 

Google has already updated Gemini with Imagen 3. Hence the image-generation model can be accessed directly on the Gemini app and website. It has now been rolled out to both free and paid Gemini subscribers. A major drawback is that generating images that feature people is only limited to the paid tier. That includes advanced, business, and enterprise subscribers. 

The image-generation model for all users comes after Google last week made Gemini Live available for free for all Android phones.