×
Gemini will let users make precise edits to generated images
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 AI Image Generator Upgrade: Google is enhancing Gemini’s AI image generation capabilities in the latest Android beta, introducing new features that allow users to make precise edits to generated images.

  • The upgrade was first reported by Android Authority in the Android beta version 15.40.31.29.
  • The new feature enables users to make small tweaks to images generated by Gemini, such as changing specific elements of the image.
  • In a demonstration, a user was able to generate an image of a dog wearing a hat and sunglasses, then successfully request to change the hat to a birthday hat.

Competitive landscape: While fine-tuning capabilities are not new in the AI image generation field, this update positions Google to better compete with other leading AI platforms.

  • The addition of these features brings Gemini closer to the capabilities of ChatGPT’s DALL-E.
  • With Apple’s Image Playground expected to launch soon, Google’s enhancements to Gemini could make it an attractive alternative for iPhone users seeking third-party image generation options.

Current limitations: The precise image-editing tools in Gemini are still in the beta phase and have some limitations.

  • According to Android Authority’s testing, the edits are not always precise or reliable.
  • The demonstration video was edited to remove wait times, suggesting that the actual process may be slower than depicted.

Rapid advancement in AI image generation: The improvements to Gemini reflect the broader trend of rapid progress in AI image generation technology.

  • AI image generators have made significant strides in a relatively short period.
  • Midjourney, currently considered one of the best AI image generators, faces increasing competition as new tools and updates are introduced frequently.

Looking ahead: While the upcoming update to Google Gemini shows promise, its full capabilities and performance will only be known upon official release.

  • The official launch will provide an opportunity for thorough testing and evaluation of the new features.
  • The integration of more advanced image generation tools in mainstream platforms like Google Gemini could potentially democratize access to sophisticated AI imaging capabilities.

Broader implications: The continuous improvement of AI image generators raises questions about the future of visual content creation and its impact on various industries.

  • As these tools become more sophisticated and accessible, they could potentially transform fields such as graphic design, advertising, and digital art.
  • The ease of creating and manipulating realistic images also brings ethical considerations regarding image authenticity and potential misuse.
Google Gemini could soon get a big AI image generator upgrade to match ChatGPT's DALL-E

Recent News

Databricks founder offers $1M to solve AI coding challenges

New competition offers $1 million prize for developing efficient, open-source AI coding models that can match human programmers' problem-solving capabilities.

ChatGPT is now on WhatsApp — here’s how to access it

OpenAI's latest WhatsApp integration brings basic AI assistance to billions of users in regions with limited internet access, running on a simplified version of GPT-4.

AI filmmakers can now find work on Runway’s new talent platform

As AI video tools become more sophisticated, production companies seek specialists who can blend creative vision with technical proficiency to deliver professional results.