Google Gemini 2.0 improves AI image generation and is available for free

Google Gemini 2.0 improves AI image generation and is available for free

Google has rolled out a major update for its AI image generation tool, now operated by the Gemini 2.0 flash model. The company confirmed that Gemini’s advanced image generation and editing equipment are now available in preview.

Listen to the story

Advertisement
Google Gemini 2.0 improves AI image generation and is available for free

Google has rolled out a major update for its AI image generation tool, now operated by the Gemini 2.0 flash model. The company confirmed that Gemini’s advanced image generation and editing equipment are now available in preview. Users can use these features through the Gemini app and developers can use a new model called “Genini-2.0-Flash-Preview-Image-Generation” through Google AI Studio and Wartex AI.

Advertisement

The new version image quality and lesson rendering brings noticeable improvement in accuracy, while the images are several times blocked due to the material filter. Unlike earlier versions, users no longer need to start from scratches for each editing. Now, Gemini allows you to make specific changes – such as changing the background, modifying hair color, or adding objects – retaining the rest of the image.

Google has also introduced the ability to upload individual photos and edit them using simple signals. This involves generating completely new elements based on the reference to the changing styles, colors, or even uploaded image. According to the company, this multi-step editing feature enables more liquid conversations, where users can add lessons and image signals to the same workflow.

For example, anyone can create a story of children with both the story and picture generated together. Or, an individual photo can be modified to show different hair color, allowing users to find a fun, interactive way to detect visual ideas, a report of 9to5MAC.

Advertisement

To help clearly mark the AI-related material, Google has added two layers of watermarking. A visible “AI” symbol now appears in the corner of images, while an invisible syntid watermark is digitally embedded to help identify synthetic materials.

While the full rollout currently focuses on the US, both free and paid users may appear new abilities in their Gemini apps. Developers, meanwhile, can begin to test image generations and editing features with high use limits, allowing them a head start in integrating Gemini in creative workflows or applications.

To reach the updated tool, users can only log in to their Gemini account and choose the Gemini 2.5 Pro model from the dropdown menu.

Share This Article
Leave a Comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Exit mobile version