×
Google’s Gemini AI to receive major image generation upgrade
Written by
Published on
Join our daily newsletter for breaking news, product launches and deals, research breakdowns, and other industry-leading AI coverage
Join Now

Google Gemini’s image generation set for a major upgrade: Google is working on improving its Gemini AI’s image generation capabilities, addressing a key limitation in the current system.

  • Gemini’s image generation, powered by Imagen 3, currently only produces square images with a 1:1 aspect ratio.
  • Users have expressed frustration with the lack of flexibility in image dimensions, as cropping is the only available option to alter image sizes.

Upcoming feature revealed in beta code: Android Authority has uncovered evidence of new image resizing options in a recent Google app beta.

  • Code from the 15.41.34.29.arm64 beta version of the Google app suggests that users will soon be able to select from various image sizes.
  • The new feature is expected to include common aspect ratios such as 16:9, providing greater versatility in image creation.

Advanced resizing capabilities: The planned update goes beyond simple cropping, offering a more sophisticated approach to image manipulation.

  • When resizing an image, Gemini will reportedly generate additional content to fill the new space rather than merely stretching or cropping the existing image.
  • Users will have the ability to resize images multiple times while maintaining the expanded environment, with only the main subject being adjusted in size.

Current limitations and premium features: Gemini’s image generation capabilities come with some restrictions and premium options.

  • The basic version of Imagen, available for free with Google Gemini, cannot create images of humans, portraits, or faces.
  • Users seeking these advanced features need to subscribe to Gemini Advanced, which offers a one-month free trial.
  • Gemini saves generated images in JPG format, distinguishing it from competitors like ChatGPT.

Recent developments in Gemini ecosystem: Google has been actively expanding and refining its Gemini AI offerings.

  • Gemini Live, a feature enabling continuous conversations with users, has been rolled out to compatible Android devices.
  • The Gemini app has undergone a visual overhaul, resulting in a more streamlined user experience.

Implications for user experience: The addition of flexible image sizing options is expected to significantly enhance Gemini’s appeal and functionality.

  • This update addresses a major pain point for users, potentially making Gemini a more competitive option in the AI image generation market.
  • The improvement aligns with Google’s efforts to create a more versatile and user-friendly AI assistant, particularly for Android device users.

Looking ahead: While the discovered code suggests these features are in development, it’s important to note that their final implementation and release date remain uncertain.

  • The ability to generate images in various aspect ratios could make Gemini more attractive for content creators and marketers who require specific image dimensions for different platforms.
  • This update may also signal Google’s commitment to continually improving its AI offerings to stay competitive in the rapidly evolving field of generative AI.
Gemini image generation just tipped for a major upgrade

Recent News

Is Tim cooked? Apple faces critical crossroads in 2025 with leadership changes and AI strategy shifts

Leadership transitions, software modernization, and AI implementation delays converge in 2025, testing Apple's ability to maintain its competitive edge amid rapid industry transformation.

Studio Ghibli may sue OpenAI over viral AI-generated art mimicking its style

Studio Ghibli could pursue legal action against OpenAI over AI-generated art that mimics its distinctive visual style, potentially establishing new precedents for whether artistic aesthetics qualify as protected intellectual property.

One step back, two steps forward: Retraining requirements will slow, not prevent, the AI intelligence explosion

Even with the need to retrain models from scratch, mathematical models predict AI could still achieve explosive progress over a 7-10 month period, merely extending the timeline by 20%.